test(opencode): avoid forced tool choice in live replay

oxlint flagged the [...candidates] spread as an unnecessary array copy. Use an explicit baseCount loop bound instead so we still iterate the original entries while pushing tier-stripped variants onto the same array.

Co-authored-by: Cursor <cursoragent@cursor.com>

.agents/skills/agent-transcript/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: agent-transcript
+description: "Add a redacted agent transcript section to GitHub PR or issue bodies during OpenClaw agent-created PR/issue workflows."
+---
+
+# Agent Transcript
+
+Best-effort local-only provenance for OpenClaw PR/issue bodies. Use during agent-created GitHub PR or issue workflows before creating/updating the body.
+
+## Contract
+
+- Never use network. Session discovery reads local agent logs only.
+- Never upload raw logs. Render sanitized Markdown first.
+- Always ask the user before adding transcript logs to a GitHub PR/issue body.
+- Tell the user sanitized session logs help reviewers and can make PRs easier to prioritize.
+- Offer a local HTML preview before insertion. If the user wants preview, open it and wait for confirmation before adding the section.
+- Fail closed on unresolved secrets, private keys, browser/session/cookie details, or auth URLs.
+- Drop system/developer prompts, raw tool outputs, reasoning, env, cookies, tokens, and broad local paths.
+- Keep user prompts, assistant visible decisions, terse tool summaries, and test/proof outcomes.
+- Remove session turns unrelated to the PR/issue work. Use the PR/issue title, branch name, changed files, and stated goal as scope; omit earlier/later unrelated tasks even when they are in the same session log.
+- Best effort only: PR/issue creation must continue if no safe transcript is found.
+- Add the `## Agent Transcript` section only when inserting a real transcript. Never add a placeholder transcript heading or text such as "A sanitized local transcript preview was generated but not included."
+- Use a collapsed `<details>` section and update existing markers instead of duplicating sections.
+
+## Helper
+
+```bash
+.agents/skills/agent-transcript/scripts/agent-transcript --help
+```
+
+Find a likely local session:
+
+```bash
+.agents/skills/agent-transcript/scripts/agent-transcript find \
+  --query "$PR_TITLE $BRANCH_OR_PR_URL" \
+  --cwd "$PWD" \
+  --since-days 14
+```
+
+`find` scans the newest 400 matching local JSONL logs by default across Codex, Claude, Pi, and OpenClaw agent sessions. Use `--max-files N` for a wider local search.
+
+Render a PR/issue body section:
+
+```bash
+.agents/skills/agent-transcript/scripts/agent-transcript render \
+  --session "$SESSION_JSONL" \
+  --out /tmp/agent-transcript.md
+```
+
+Preview one candidate session locally:
+
+```bash
+.agents/skills/agent-transcript/scripts/agent-transcript preview \
+  --session "$SESSION_JSONL" \
+  --out /tmp/agent-transcript-preview.html
+open /tmp/agent-transcript-preview.html
+```
+
+Append/update a body file before `gh pr create --body-file` or connector PR creation:
+
+```bash
+.agents/skills/agent-transcript/scripts/agent-transcript append-body \
+  --body /tmp/pr-body.md \
+  --session "$SESSION_JSONL" \
+  --out /tmp/pr-body.with-transcript.md
+```
+
+## PR/Issue Workflow
+
+1. Draft the normal PR/issue body first.
+2. Run `find` with title, branch, PR URL/number if known, and cwd.
+3. If a high-confidence session is found, ask:
+   `Include a redacted agent transcript? It helps reviewers and can make the PR easier to prioritize. I can open a local preview first.`
+4. If the user wants preview, run `preview`, open the HTML with `open`, and wait for confirmation.
+5. Before insertion, trim unrelated session turns from the generated section. Keep only turns that explain this PR/issue's goal, implementation choices, files, tests, proof, blockers, and final outcome.
+6. If the user approves, run `append-body`.
+7. Use the enriched body file for creation/update.
+8. If no safe session is found, say nothing and continue without transcript. If the user declines, continue without transcript and do not add any transcript placeholder section.
+
+## Review Artifacts
+
+For manual audits across many PR/session candidates, create a local HTML preview from a local JSON file. This is for maintainers only and is not part of the PR/issue workflow:
+
+```bash
+.agents/skills/agent-transcript/scripts/agent-transcript html \
+  --prs /tmp/recent-prs.json \
+  --out /tmp/agent-transcript-preview.html
+```

.agents/skills/agent-transcript/scripts/agent-transcript

@@ -0,0 +1,683 @@
+#!/usr/bin/env node
+import fs from "node:fs";
+import os from "node:os";
+import path from "node:path";
+import process from "node:process";
+
+const MARKER_START = "<!-- agent-transcript:start -->";
+const MARKER_END = "<!-- agent-transcript:end -->";
+const DEFAULT_MAX_CHARS = 50000;
+const DEFAULT_ENTRY_MAX_CHARS = 6000;
+
+function usage() {
+  console.log(`Usage:
+  agent-transcript find --query TEXT [--cwd PATH] [--since-days N] [--max-files N] [--root PATH...]
+  agent-transcript render --session FILE [--out FILE] [--max-chars N] [--entry-max-chars N] [--title TEXT] [--url URL]
+  agent-transcript preview --session FILE [--out FILE] [--max-chars N] [--entry-max-chars N] [--title TEXT] [--url URL]
+  agent-transcript append-body --body FILE --session FILE [--out FILE] [--max-chars N] [--entry-max-chars N]
+  agent-transcript html --prs FILE [--out FILE] [--since-days N] [--min-score N] [--root PATH...] [--exclude-session FILE...]
+
+Local-only. No network calls.`);
+}
+
+function parseArgs(argv) {
+  const args = { _: [] };
+  for (let i = 0; i < argv.length; i++) {
+    const arg = argv[i];
+    if (!arg.startsWith("--")) {
+      args._.push(arg);
+      continue;
+    }
+    const key = arg.slice(2);
+    const next = argv[i + 1];
+    if (next == null || next.startsWith("--")) {
+      args[key] = true;
+      continue;
+    }
+    i++;
+    if (args[key] == null) args[key] = next;
+    else if (Array.isArray(args[key])) args[key].push(next);
+    else args[key] = [args[key], next];
+  }
+  return args;
+}
+
+function asArray(value) {
+  if (value == null) return [];
+  return Array.isArray(value) ? value : [value];
+}
+
+function homePath(...parts) {
+  return path.join(os.homedir(), ...parts);
+}
+
+function openClawSessionRoots() {
+  const stateDir = process.env.OPENCLAW_STATE_DIR || homePath(".openclaw");
+  const agentsDir = path.join(stateDir, "agents");
+  if (!fs.existsSync(agentsDir)) return [];
+  try {
+    const roots = fs
+      .readdirSync(agentsDir, { withFileTypes: true })
+      .filter((entry) => entry.isDirectory())
+      .flatMap((entry) => {
+        const agentDir = path.join(agentsDir, entry.name);
+        return [
+          path.join(agentDir, "sessions"),
+          path.join(agentDir, "agent", "sessions"),
+          path.join(agentDir, "agent", "codex-home", "sessions"),
+        ];
+      })
+      .filter((root) => fs.existsSync(root));
+    return [...new Set(roots)];
+  } catch {
+    return [];
+  }
+}
+
+function defaultRoots() {
+  return [
+    homePath(".codex", "sessions"),
+    homePath(".claude", "projects"),
+    homePath(".pi", "agent", "sessions"),
+    ...openClawSessionRoots(),
+  ];
+}
+
+function walkJsonl(root, sinceMs, out = []) {
+  if (!root || !fs.existsSync(root)) return out;
+  const stat = fs.statSync(root);
+  if (stat.isFile()) {
+    if (root.endsWith(".jsonl") && stat.mtimeMs >= sinceMs) out.push(root);
+    return out;
+  }
+  for (const entry of fs.readdirSync(root, { withFileTypes: true })) {
+    if (entry.name === "node_modules" || entry.name === ".git") continue;
+    const file = path.join(root, entry.name);
+    if (entry.isDirectory()) walkJsonl(file, sinceMs, out);
+    else if (entry.isFile() && entry.name.endsWith(".jsonl")) {
+      const entryStat = fs.statSync(file);
+      if (entryStat.mtimeMs >= sinceMs) out.push(file);
+    }
+  }
+  return out;
+}
+
+function readJsonl(file, maxLines = 12000) {
+  const text = fs.readFileSync(file, "utf8");
+  const lines = text.split(/\n+/).filter(Boolean).slice(0, maxLines);
+  const rows = [];
+  for (const line of lines) {
+    try {
+      rows.push(JSON.parse(line));
+    } catch {
+      rows.push({ type: "unparsed", text: line });
+    }
+  }
+  return rows;
+}
+
+function stringContent(value) {
+  if (value == null) return "";
+  if (typeof value === "string") return value;
+  if (Array.isArray(value)) return value.map(stringContent).filter(Boolean).join("\n");
+  if (typeof value === "object") {
+    if (typeof value.text === "string") return value.text;
+    if (typeof value.content === "string") return value.content;
+    if (typeof value.message === "string") return value.message;
+    if (Array.isArray(value.content)) return stringContent(value.content);
+    if (value.type === "text" && value.text) return String(value.text);
+  }
+  return "";
+}
+
+function detectAgent(file, rows) {
+  if (file.includes(`${path.sep}.codex${path.sep}`)) return "codex";
+  if (file.includes(`${path.sep}.claude${path.sep}`)) return "claude";
+  if (file.includes(`${path.sep}.pi${path.sep}`)) return "pi";
+  if (
+    file.includes(`${path.sep}.openclaw${path.sep}`) ||
+    (file.includes(`${path.sep}agents${path.sep}`) && file.includes(`${path.sep}sessions${path.sep}`))
+  ) {
+    return "openclaw";
+  }
+  if (rows.some((row) => row?.type === "session_meta" || row?.type === "response_item")) return "codex";
+  if (rows.some((row) => row?.sessionId && row?.userType)) return "claude";
+  return "agent";
+}
+
+function eventText(row) {
+  if (row?.type === "event_msg") {
+    const payload = row.payload || {};
+    return stringContent(payload.message || payload.text_elements || payload.content);
+  }
+  if (row?.type === "response_item") {
+    const payload = row.payload || {};
+    return stringContent(payload.content || payload.summary || payload.arguments || payload.output);
+  }
+  if (row?.message) return stringContent(row.message);
+  if (row?.content) return stringContent(row.content);
+  if (row?.text) return stringContent(row.text);
+  return "";
+}
+
+function eventRole(row) {
+  if (row?.type === "event_msg") {
+    const type = row.payload?.type;
+    if (type === "user_message") return "user";
+    if (type === "agent_message") return "assistant";
+    if (type === "token_count" || type === "task_started" || type === "task_complete") return null;
+    if (type === "web_search_end") return "web";
+  }
+  if (row?.type === "response_item") {
+    const payload = row.payload || {};
+    if (payload.type === "function_call") return "tool";
+    if (payload.type === "function_call_output") return "tool_output";
+    if (payload.type === "reasoning") return null;
+    if (payload.type === "web_search_call") return "web";
+    if (payload.role === "user") return "user";
+    if (payload.role === "assistant") return "assistant";
+  }
+  if (row?.type === "user") return "user";
+  if (row?.type === "assistant") return "assistant";
+  if (row?.message?.role === "user") return "user";
+  if (row?.message?.role === "assistant") return "assistant";
+  if (row?.type === "tool_result" || row?.type === "tool_use") return "tool";
+  return null;
+}
+
+function hasSetupBlob(text) {
+  return (
+    text.includes("<INSTRUCTIONS>") ||
+    text.includes("# AGENTS.MD") ||
+    text.includes("Knowledge cutoff:") ||
+    text.includes("You are Codex") ||
+    /\byour instructions\b/i.test(text) ||
+    /\binstructions absorbed\b/i.test(text) ||
+    /\bAGENTS\.md\b/i.test(text)
+  );
+}
+
+function redact(input, stats) {
+  let s = String(input ?? "");
+  const rules = [
+    [/-----BEGIN [A-Z ]*PRIVATE KEY-----[\s\S]*?-----END [A-Z ]*PRIVATE KEY-----/g, "[REDACTED_PRIVATE_KEY]"],
+    [/sk-[A-Za-z0-9_-]{20,}/g, "[REDACTED_OPENAI_KEY]"],
+    [/(gh[pousr]_[A-Za-z0-9_]{20,})/g, "[REDACTED_GITHUB_TOKEN]"],
+    [/(AKIA[0-9A-Z]{16})/g, "[REDACTED_AWS_KEY]"],
+    [/eyJ[A-Za-z0-9_-]{20,}\.[A-Za-z0-9_-]{20,}\.[A-Za-z0-9_-]{10,}/g, "[REDACTED_JWT]"],
+    [/\b(?:Bearer|Basic)\s+[A-Za-z0-9._~+/=-]{16,}/gi, "[REDACTED_AUTH_HEADER]"],
+    [/[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}/gi, "[REDACTED_EMAIL]"],
+    [/\b(?:\+?\d[\d .()-]{7,}\d)\b/g, "[REDACTED_PHONE]"],
+    [/\/Users\/[^\s`"'>)]+/g, "[LOCAL_PATH]"],
+    [/~\/[^\s`"'>)]+/g, "[HOME_PATH]"],
+    [/([?&](?:token|key|secret|signature|sig|access_token|auth)=)[^\s`"'>&]+/gi, "$1[REDACTED]"],
+  ];
+  for (const [re, repl] of rules) {
+    const before = s;
+    s = s.replace(re, repl);
+    if (s !== before) stats.redactions++;
+  }
+  return s;
+}
+
+function unsafe(text) {
+  const patterns = [
+    /-----BEGIN [A-Z ]*PRIVATE KEY-----/,
+    /\b(?:Bearer|Basic)\s+[A-Za-z0-9._~+/=-]{16,}/i,
+    /\b(?:user_session|_gh_sess|__Host-user_session_same_site|GH_SESSION_TOKEN)\b/i,
+    /\b(?:GITHUB_TOKEN|GH_TOKEN|OPENAI_API_KEY|ANTHROPIC_API_KEY)\b/,
+    /\/upload\/policies\/assets|uploadToken|authenticity_token/i,
+  ];
+  return patterns.filter((pattern) => pattern.test(text)).map((pattern) => String(pattern));
+}
+
+function normalizeEntry(role, text, stats, options = {}) {
+  let t = redact(text, stats).replace(/\n{3,}/g, "\n\n").trim();
+  if (!t) return null;
+  if (hasSetupBlob(t)) t = "[instructions recap omitted; policy/config text, not task dialogue]";
+  if (unsafe(t).length) t = "[omitted: browser/session/auth internals; not useful for public PR transcript]";
+  const entryMaxChars = Number(options.entryMaxChars || options["entry-max-chars"] || DEFAULT_ENTRY_MAX_CHARS);
+  if (t.length > entryMaxChars) {
+    t = `${t.slice(0, entryMaxChars).trimEnd()}\n...[truncated ${t.length - entryMaxChars} chars]`;
+  }
+  return `[${role}]\n${t}`;
+}
+
+function entryRole(entry) {
+  const match = entry.match(/^\[([^\]]+)\]\n/);
+  return match ? match[1] : null;
+}
+
+function entryBody(entry) {
+  return entry.replace(/^\[[^\]]+\]\n/, "");
+}
+
+function coalesceEntries(entries) {
+  const coalesced = [];
+  for (const entry of entries) {
+    const role = entryRole(entry);
+    const body = entryBody(entry);
+    const last = coalesced[coalesced.length - 1];
+    if (!last || !role || entryRole(last) !== role || role === "tool summary") {
+      coalesced.push(entry);
+      continue;
+    }
+    const lastBody = entryBody(last);
+    if (lastBody === body || lastBody.includes(body)) continue;
+    if (body.includes(lastBody)) {
+      coalesced[coalesced.length - 1] = `[${role}]\n${body}`;
+      continue;
+    }
+    coalesced[coalesced.length - 1] = `[${role}]\n${lastBody}\n\n${body}`;
+  }
+  return coalesced;
+}
+
+function toolFamily(name) {
+  const normalized = String(name).toLowerCase();
+  if (
+    /(read|fetch|open|list|find|search|grep|rg|sed|cat|head|tail|jq|wc|status|diff|show|view|snapshot|screenshot)/.test(
+      normalized,
+    )
+  ) {
+    return "read";
+  }
+  if (/(write|edit|patch|apply|create|update|append|save|comment|fill|click|type|navigate|upload)/.test(normalized)) {
+    return "write";
+  }
+  if (/(exec|command|shell|run|test|build|lint|format|install|pnpm|npm|node|git|gh|ssh)/.test(normalized)) {
+    return "execute";
+  }
+  if (/(web|http|fetch|browser|chrome|github|dropbox|notion|gmail|calendar)/.test(normalized)) {
+    return "network";
+  }
+  return "other";
+}
+
+function shellFamily(command) {
+  const cmd = String(command || "").trim();
+  if (!cmd) return "execute";
+  if (
+    /^(rg|grep|sed|cat|head|tail|jq|wc|ls|find|pwd|git (status|diff|show|log|blame)|gh (pr|issue|api|run|repo|auth) (view|list|status)|test |stat |ps |which |command -v )\b/.test(
+      cmd,
+    )
+  ) {
+    return "read";
+  }
+  if (/^(open |chmod |mkdir |touch |cp |mv |kill |git add|git commit|git push|gh pr create|gh issue create)\b/.test(cmd)) {
+    return "write";
+  }
+  if (/^(node|npm|pnpm|bun|python|python3|ruby|tsx|tsgo|make|cargo|go test|swift|xcodebuild)\b/.test(cmd)) {
+    return "execute";
+  }
+  if (/^(ssh|curl|wget|tailscale|nc )\b/.test(cmd)) return "network";
+  return "execute";
+}
+
+function toolCallFamily(row) {
+  const name = row.payload?.name || row.name || row.message?.name || row.type || "tool";
+  if (name === "exec_command") {
+    try {
+      const args = JSON.parse(row.payload?.arguments || "{}");
+      return shellFamily(args.cmd);
+    } catch {
+      return "execute";
+    }
+  }
+  if (name === "apply_patch") return "write";
+  if (name === "write_stdin") return "execute";
+  return toolFamily(name);
+}
+
+function compactToolSummary(familyCounts, dropped) {
+  const families = new Map();
+  for (const [family, count] of familyCounts.entries()) {
+    families.set(family, (families.get(family) || 0) + count);
+  }
+  const ordered = ["read", "write", "execute", "network", "other"]
+    .map((family) => [family, families.get(family) || 0])
+    .filter(([, count]) => count > 0)
+    .map(([family, count]) => `${count} ${family}`);
+  const calls = ordered.length ? ordered.join(", ") : "0 tool";
+  return `${calls}; raw tool outputs dropped: ${dropped}`;
+}
+
+function recountEntries(stats, entries) {
+  stats.rawEntries = stats.entries;
+  stats.entries = entries.length;
+  stats.user = entries.filter((entry) => entry.startsWith("[user]\n")).length;
+  stats.assistant = entries.filter((entry) => entry.startsWith("[assistant]\n")).length;
+}
+
+function renderSession(file, options = {}) {
+  const rows = readJsonl(file);
+  const agent = detectAgent(file, rows);
+  const stats = {
+    agent,
+    entries: 0,
+    user: 0,
+    assistant: 0,
+    toolCalls: 0,
+    toolOutputsDropped: 0,
+    web: 0,
+    redactions: 0,
+    omittedUnsafe: 0,
+  };
+  const toolCounts = new Map();
+  const items = [];
+  const seenEntries = new Set();
+  const hasEventDialogue = rows.some((row) => {
+    const type = row?.type === "event_msg" ? row.payload?.type : null;
+    return type === "user_message" || type === "agent_message";
+  });
+  for (const row of rows) {
+    const role = eventRole(row);
+    if (!role) continue;
+    if (hasEventDialogue && row.type === "response_item" && (role === "user" || role === "assistant")) {
+      continue;
+    }
+    if (role === "tool_output") {
+      stats.toolOutputsDropped++;
+      continue;
+    }
+    if (role === "tool") {
+      const family = toolCallFamily(row);
+      toolCounts.set(family, (toolCounts.get(family) || 0) + 1);
+      stats.toolCalls++;
+      continue;
+    }
+    if (role === "web") {
+      stats.web++;
+      continue;
+    }
+    const before = eventText(row);
+    const entry = normalizeEntry(role, before, stats, options);
+    if (!entry) continue;
+    const dedupeKey = entry.replace(/\s+/g, " ").trim();
+    if (seenEntries.has(dedupeKey)) continue;
+    seenEntries.add(dedupeKey);
+    if (entry.includes("[omitted: browser/session/auth internals")) stats.omittedUnsafe++;
+    items.push(entry);
+    stats.entries++;
+    if (role === "user") stats.user++;
+    if (role === "assistant") stats.assistant++;
+  }
+  if (toolCounts.size) {
+    items.push(`[tool summary]\n${compactToolSummary(toolCounts, stats.toolOutputsDropped)}`);
+    stats.entries++;
+  }
+  const renderedItems = coalesceEntries(items);
+  recountEntries(stats, renderedItems);
+  const maxChars = Number(options.maxChars || DEFAULT_MAX_CHARS);
+  let joined = renderedItems.join("\n\n");
+  if (joined.length > maxChars) joined = `${joined.slice(0, maxChars).trimEnd()}\n\n...[transcript truncated to ${maxChars} chars]`;
+  const headerBits = [options.title, options.url].filter(Boolean).join(" | ");
+  const unsafeAfter = unsafe(joined);
+  const safe = unsafeAfter.length === 0;
+  const markdown = `${MARKER_START}
+## Agent Transcript
+
+<details>
+<summary>Redacted ${agent} session transcript${headerBits ? `: ${redact(headerBits, stats)}` : ""}</summary>
+
+\`\`\`\`text
+source: [LOCAL_SESSION]
+redaction: local paths, emails, phone-shaped strings, token-shaped strings, auth headers, auth query params
+omitted: raw tool outputs, system/developer prompts, local paths, secrets, browser/session/auth details
+stats: ${JSON.stringify(stats)}
+
+${joined}
+\`\`\`\`
+
+</details>
+${MARKER_END}
+`;
+  return { file, agent, safe, unsafeAfter, stats, markdown };
+}
+
+function readBoundedText(file, maxBytes = 220000) {
+  const fd = fs.openSync(file, "r");
+  try {
+    const stat = fs.fstatSync(fd);
+    if (stat.size <= maxBytes) {
+      const buffer = Buffer.alloc(stat.size);
+      fs.readSync(fd, buffer, 0, stat.size, 0);
+      return buffer.toString("utf8");
+    }
+    const half = Math.floor(maxBytes / 2);
+    const head = Buffer.alloc(half);
+    const tail = Buffer.alloc(half);
+    fs.readSync(fd, head, 0, half, 0);
+    fs.readSync(fd, tail, 0, half, Math.max(0, stat.size - half));
+    return `${head.toString("utf8")}\n[...middle omitted for scan...]\n${tail.toString("utf8")}`;
+  } finally {
+    fs.closeSync(fd);
+  }
+}
+
+function sessionScanRecord(file, maxBytes) {
+  const stat = fs.statSync(file);
+  const agent = detectAgent(file, []);
+  return {
+    file,
+    agent,
+    mtime: new Date(stat.mtimeMs).toISOString(),
+    haystack: `${file}\n${readBoundedText(file, maxBytes)}`.toLowerCase(),
+  };
+}
+
+function scoreScanRecord(record, terms, cwd) {
+  const haystack = record.haystack;
+  let score = 0;
+  const reasons = [];
+  for (const term of terms) {
+    const normalized = term.toLowerCase().trim();
+    if (normalized.length < 3) continue;
+    if (haystack.includes(normalized)) {
+      score += Math.min(20, Math.max(3, Math.floor(normalized.length / 3)));
+      reasons.push(normalized.slice(0, 80));
+    }
+  }
+  if (cwd) {
+    const cwdLower = cwd.toLowerCase();
+    if (haystack.includes(cwdLower) || record.file.toLowerCase().includes(cwdLower.replaceAll("/", "-"))) {
+      score += 8;
+      reasons.push("cwd");
+    }
+  }
+  return { file: record.file, score, reasons, mtime: record.mtime, agent: record.agent };
+}
+
+function recentFiles(files, maxFiles) {
+  return files
+    .map((file) => {
+      try {
+        return { file, mtimeMs: fs.statSync(file).mtimeMs };
+      } catch {
+        return null;
+      }
+    })
+    .filter(Boolean)
+    .sort((a, b) => b.mtimeMs - a.mtimeMs)
+    .slice(0, maxFiles)
+    .map((entry) => entry.file);
+}
+
+function candidateFiles(roots, terms, sinceMs, options = {}) {
+  return recentFiles(roots.flatMap((root) => walkJsonl(root, sinceMs)), Number(options["max-files"] || 400));
+}
+
+function findSessions(options) {
+  const sinceDays = Number(options["since-days"] || 14);
+  const sinceMs = Date.now() - sinceDays * 24 * 60 * 60 * 1000;
+  const roots = asArray(options.root).length ? asArray(options.root) : defaultRoots();
+  const query = String(options.query || "");
+  const terms = query
+    .split(/\s+/)
+    .concat(query.match(/https?:\/\/\S+/g) || [])
+    .filter(Boolean);
+  const files = candidateFiles(roots, terms, sinceMs, options);
+  const scanBytes = Number(options["scan-bytes"] || 60000);
+  const results = files
+    .map((file) => scoreScanRecord(sessionScanRecord(file, scanBytes), terms, options.cwd))
+    .filter((result) => result.score > 0)
+    .sort((a, b) => b.score - a.score || b.mtime.localeCompare(a.mtime))
+    .slice(0, Number(options.limit || 10));
+  return results;
+}
+
+function sessionScanRecords(options) {
+  const sinceDays = Number(options["since-days"] || 14);
+  const sinceMs = Date.now() - sinceDays * 24 * 60 * 60 * 1000;
+  const roots = asArray(options.root).length ? asArray(options.root) : defaultRoots();
+  const excluded = new Set(asArray(options["exclude-session"]).map((file) => path.resolve(file)));
+  return roots
+    .flatMap((root) => walkJsonl(root, sinceMs))
+    .filter((file) => !excluded.has(path.resolve(file)))
+    .map((file) => sessionScanRecord(file, Number(options["scan-bytes"] || 90000)));
+}
+
+function replaceSection(body, section) {
+  const start = body.indexOf(MARKER_START);
+  const end = body.indexOf(MARKER_END);
+  if (start !== -1 && end !== -1 && end > start) {
+    return `${body.slice(0, start).trimEnd()}\n\n${section.trim()}\n\n${body.slice(end + MARKER_END.length).trimStart()}`;
+  }
+  return `${body.trimEnd()}\n\n${section.trim()}\n`;
+}
+
+function escapeHtml(text) {
+  return String(text)
+    .replaceAll("&", "&amp;")
+    .replaceAll("<", "&lt;")
+    .replaceAll(">", "&gt;")
+    .replaceAll('"', "&quot;");
+}
+
+function htmlDocument(records) {
+  const rows = records
+    .map((record) => `<section>
+<h2><a href="${escapeHtml(record.url || "")}">${escapeHtml(record.title || record.url || "PR")}</a></h2>
+<p><code>${escapeHtml(record.session ? "[LOCAL_SESSION]" : "no session")}</code> score: ${escapeHtml(record.score ?? "")} safe: ${escapeHtml(record.safe ?? "")}</p>
+<pre>${escapeHtml(record.markdown || record.error || "")}</pre>
+</section>`)
+    .join("\n");
+  return `<!doctype html>
+<meta charset="utf-8">
+<title>Agent Transcript Preview</title>
+<style>
+body{font:14px/1.45 system-ui,-apple-system,BlinkMacSystemFont,"Segoe UI",sans-serif;margin:32px;color:#1f2328;background:#fff}
+section{border-top:1px solid #d0d7de;padding:24px 0}
+h1,h2{line-height:1.2}
+pre{white-space:pre-wrap;background:#f6f8fa;border:1px solid #d0d7de;border-radius:6px;padding:16px;overflow:auto}
+code{background:#f6f8fa;padding:2px 4px;border-radius:4px}
+a{color:#0969da}
+</style>
+<h1>Agent Transcript Preview</h1>
+${rows}
+`;
+}
+
+function singlePreviewDocument(record) {
+  return htmlDocument([record]);
+}
+
+function readPrs(file) {
+  const raw = fs.readFileSync(file, "utf8");
+  const parsed = JSON.parse(raw);
+  return Array.isArray(parsed) ? parsed : parsed.items || parsed.prs || [];
+}
+
+function main() {
+  const [command, ...rest] = process.argv.slice(2);
+  const args = parseArgs(rest);
+  if (!command || command === "--help" || command === "-h" || args.help) {
+    usage();
+    return;
+  }
+  if (command === "find") {
+    console.log(JSON.stringify(findSessions(args), null, 2));
+    return;
+  }
+  if (command === "render") {
+    if (!args.session) throw new Error("--session is required");
+    const rendered = renderSession(args.session, args);
+    if (!rendered.safe) throw new Error(`unsafe transcript after redaction: ${rendered.unsafeAfter.join(", ")}`);
+    if (args.out) fs.writeFileSync(args.out, rendered.markdown);
+    else process.stdout.write(rendered.markdown);
+    return;
+  }
+  if (command === "preview") {
+    if (!args.session) throw new Error("--session is required");
+    const rendered = renderSession(args.session, args);
+    if (!rendered.safe) throw new Error(`unsafe transcript after redaction: ${rendered.unsafeAfter.join(", ")}`);
+    const output = singlePreviewDocument({
+      title: args.title || "Agent Transcript Preview",
+      url: args.url || "",
+      session: args.session,
+      safe: rendered.safe,
+      markdown: rendered.markdown,
+    });
+    if (args.out) fs.writeFileSync(args.out, output);
+    else process.stdout.write(output);
+    return;
+  }
+  if (command === "append-body") {
+    if (!args.body || !args.session) throw new Error("--body and --session are required");
+    const rendered = renderSession(args.session, args);
+    if (!rendered.safe) throw new Error(`unsafe transcript after redaction: ${rendered.unsafeAfter.join(", ")}`);
+    const body = fs.readFileSync(args.body, "utf8");
+    const next = replaceSection(body, rendered.markdown);
+    if (args.out) fs.writeFileSync(args.out, next);
+    else process.stdout.write(next);
+    return;
+  }
+  if (command === "html") {
+    if (!args.prs) throw new Error("--prs is required");
+    const records = [];
+    const scanRecords = sessionScanRecords(args);
+    const minScore = Number(args["min-score"] || 50);
+    for (const pr of readPrs(args.prs)) {
+      const query = [pr.url, pr.number ? `#${pr.number}` : "", pr.number, pr.title, pr.headRefName, pr.headRefName || pr.branch]
+        .filter(Boolean)
+        .join(" ");
+      const terms = query
+        .split(/\s+/)
+        .concat(query.match(/https?:\/\/\S+/g) || [])
+        .filter(Boolean);
+      const [candidate] = scanRecords
+        .map((record) => scoreScanRecord(record, terms, args.cwd))
+        .filter((result) => result.score >= minScore)
+        .sort((a, b) => b.score - a.score || b.mtime.localeCompare(a.mtime));
+      if (!candidate) {
+        records.push({ ...pr, error: "No local session match found." });
+        continue;
+      }
+      try {
+        const rendered = renderSession(candidate.file, { ...args, title: pr.title, url: pr.url });
+        records.push({
+          ...pr,
+          session: candidate.file,
+          score: candidate.score,
+          safe: rendered.safe,
+          markdown: rendered.markdown,
+        });
+      } catch (error) {
+        records.push({ ...pr, session: candidate.file, score: candidate.score, error: String(error) });
+      }
+    }
+    const output = htmlDocument(records);
+    if (args.out) fs.writeFileSync(args.out, output);
+    else process.stdout.write(output);
+    return;
+  }
+  usage();
+  process.exitCode = 2;
+}
+
+try {
+  main();
+} catch (error) {
+  console.error(error instanceof Error ? error.message : String(error));
+  process.exit(1);
+}

.agents/skills/autoreview/SKILL.md

@@ -26,8 +26,12 @@ Use when:
 - If a review-triggered fix changes code, rerun focused tests and rerun the structured review helper.
 - For security-audit suppression changes, verify accepted findings remain auditable: suppressed findings stay in structured output, active output keeps an unsuppressible suppression notice, and aggregate findings cannot hide unrelated active risk.
 - Never switch or override the requested review engine/model. If the review hits model capacity, retry the same command a few times with the same engine/model.
+- Be patient with large bundles. Structured review can take up to 30 minutes while the model call is active, especially with Codex tools or web search.
+- Treat heartbeat lines like `review still running: ... elapsed=... pid=...` as healthy progress, not a hang. Let the helper continue while heartbeats are advancing. Pass `--stream-engine-output` when live engine text is useful; Codex and Claude filter tool/file chatter, other engines pass raw output through.
+- Do not kill a review just because it has been quiet for 2-5 minutes, or because it is still running under the 30-minute window. Inspect the process only after missing multiple expected heartbeats, after 30 minutes, or after an obviously failed subprocess; prefer letting the same helper command finish.
 - Tools are useful in review mode. The helper allows read-only inspection tools and web search by default so reviewers can check dependency contracts, upstream docs, and current behavior.
 - Security perspective is always included, but it should not cripple legitimate functionality. Report security findings only when the change creates a concrete, actionable risk or removes an important safety check.
+- For regression provenance, if no blamed PR is traceable, use the blamed commit as the provenance: commit SHA, date, and author username. Do not guess a merger or frame missing PR metadata as a separate finding.
 - Do not invoke built-in `codex review`, nested reviewers, or reviewer panels from inside the review. The helper builds one bundle, calls one selected engine, validates one structured result, and stops.
 - Stop as soon as the helper exits 0 with no accepted/actionable findings. Do not run an extra review just to get a nicer "clean" line, a second opinion, or clearer closeout wording.
 - Treat the helper's successful exit plus absence of actionable findings as the clean review result, even if the underlying Codex CLI output is terse.
@@ -46,8 +50,9 @@ Dirty local work:
 ```
 
 Use this only when the patch is actually unstaged/staged/untracked in the
-current checkout. For committed, pushed, or PR work, point the helper at the commit
-or branch diff instead; do not force `--mode local` / `--uncommitted` just
+current checkout. `--mode uncommitted` is accepted as an alias for `--mode local`.
+For committed, pushed, or PR work, point the helper at the commit
+or branch diff instead; do not force dirty modes just
 because the helper docs mention dirty work first. A clean local review
 only proves there is no local patch.
 
@@ -160,15 +165,18 @@ If installed from `agent-scripts`, path is:
 The helper:
 
 - chooses dirty local changes first
+- accepts `--mode uncommitted` as an alias for `--mode local`
 - otherwise uses current PR base if `gh pr view` works
 - otherwise uses `origin/main` for non-main branches
 - supports `--engine codex`, `claude`, `droid`, and `copilot`; default is `AUTOREVIEW_ENGINE` or `codex`; Codex should remain the default when nothing is set
 - use `--mode commit --commit <ref>` for already-committed work, especially clean `main` after landing
 - should be left in `--mode auto` or forced to `--mode branch` for PR/branch work; do not force `--mode local` after committing
-- writes only to stdout unless `--output` or `--json-output` is set
+- writes only to stdout unless `--output`, `--json-output`, or live streamed engine stderr is set
 - supports `--dry-run`, `--parallel-tests`, `--prompt`, `--prompt-file`, `--dataset`, `--no-tools`, `--no-web-search`, and commit refs
+- supports `--stream-engine-output` or `AUTOREVIEW_STREAM_ENGINE_OUTPUT=1` for live engine text while preserving structured validation; Codex and Claude hide tool/file event details, emit compact activity summaries, and report usage at turn completion
 - supports opt-in review panels with `--panel` / `--reviewers`, plus per-engine `--model` and `--thinking`
 - allows read-only tools and web search by default where the selected CLI supports them; forbids nested review in the prompt; Codex is run through `codex exec` with read-only sandbox and structured output
+- prints `review still running: <engine> elapsed=<seconds>s pid=<pid>` to stderr at long-running intervals while waiting for the selected review engine, unless streamed output or compact Codex activity has been visible recently
 - prints `autoreview clean: no accepted/actionable findings reported` when the selected review command exits 0
 - exits nonzero when accepted/actionable findings are present
 

.agents/skills/autoreview/scripts/autoreview

@@ -6,13 +6,15 @@ import concurrent.futures
 import copy
 import json
 import os
+import queue
 import subprocess
 import sys
 import tempfile
 import textwrap
+import threading
 import time
 from pathlib import Path
-from typing import Any
+from typing import Any, Callable
 
 
 ENGINES = ("codex", "claude", "droid", "copilot")
@@ -93,6 +95,124 @@ def run(args: list[str], cwd: Path, *, input_text: str | None = None, check: boo
     return result
 
 
+def run_with_heartbeat(
+    args: list[str],
+    cwd: Path,
+    *,
+    input_text: str | None = None,
+    label: str,
+    heartbeat_seconds: int = 60,
+    stream_output: bool = False,
+    stream_display: Callable[[str, str], str | None] | None = None,
+) -> subprocess.CompletedProcess[str]:
+    if stream_output:
+        return run_with_stream(
+            args,
+            cwd,
+            input_text=input_text,
+            label=label,
+            heartbeat_seconds=heartbeat_seconds,
+            stream_display=stream_display,
+        )
+    started = time.monotonic()
+    proc = subprocess.Popen(
+        args,
+        cwd=cwd,
+        stdin=subprocess.PIPE if input_text is not None else None,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        text=True,
+    )
+    first_communicate = True
+    while True:
+        try:
+            stdout, stderr = proc.communicate(
+                input=input_text if first_communicate else None,
+                timeout=heartbeat_seconds,
+            )
+            return subprocess.CompletedProcess(args, int(proc.returncode or 0), stdout, stderr)
+        except subprocess.TimeoutExpired:
+            first_communicate = False
+            elapsed = int(time.monotonic() - started)
+            print(f"review still running: {label} elapsed={elapsed}s pid={proc.pid}", file=sys.stderr, flush=True)
+
+
+def run_with_stream(
+    args: list[str],
+    cwd: Path,
+    *,
+    input_text: str | None,
+    label: str,
+    heartbeat_seconds: int,
+    stream_display: Callable[[str, str], str | None] | None,
+) -> subprocess.CompletedProcess[str]:
+    started = time.monotonic()
+    proc = subprocess.Popen(
+        args,
+        cwd=cwd,
+        stdin=subprocess.PIPE if input_text is not None else None,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        text=True,
+        bufsize=1,
+    )
+    events: queue.Queue[tuple[str, str | None]] = queue.Queue()
+    stdout_parts: list[str] = []
+    stderr_parts: list[str] = []
+
+    def read_stream(name: str, stream: Any) -> None:
+        try:
+            for line in iter(stream.readline, ""):
+                events.put((name, line))
+        finally:
+            events.put((name, None))
+
+    def write_stdin() -> None:
+        if proc.stdin is None or input_text is None:
+            return
+        try:
+            proc.stdin.write(input_text)
+            proc.stdin.close()
+        except BrokenPipeError:
+            return
+
+    threads = [
+        threading.Thread(target=read_stream, args=("stdout", proc.stdout), daemon=True),
+        threading.Thread(target=read_stream, args=("stderr", proc.stderr), daemon=True),
+    ]
+    for thread in threads:
+        thread.start()
+    stdin_thread = threading.Thread(target=write_stdin, daemon=True)
+    stdin_thread.start()
+
+    open_streams = 2
+    while open_streams:
+        try:
+            name, line = events.get(timeout=heartbeat_seconds)
+        except queue.Empty:
+            elapsed = int(time.monotonic() - started)
+            print(f"review still running: {label} elapsed={elapsed}s pid={proc.pid}", file=sys.stderr, flush=True)
+            continue
+        if line is None:
+            open_streams -= 1
+            continue
+        if name == "stdout":
+            stdout_parts.append(line)
+        else:
+            stderr_parts.append(line)
+        display = stream_display(name, line) if stream_display else line
+        if display:
+            target = sys.stdout if name == "stdout" else sys.stderr
+            target.write(display)
+            target.flush()
+
+    for thread in threads:
+        thread.join()
+    stdin_thread.join(timeout=1)
+    returncode = proc.wait()
+    return subprocess.CompletedProcess(args, returncode, "".join(stdout_parts), "".join(stderr_parts))
+
+
 def git(repo: Path, *args: str, check: bool = True) -> str:
     return run(["git", *args], repo, check=check).stdout
 
@@ -118,6 +238,7 @@ def is_dirty(repo: Path) -> bool:
 
 
 def choose_target(repo: Path, mode: str, base_ref: str | None) -> tuple[str, str | None]:
+    mode = "local" if mode == "uncommitted" else mode
     branch = current_branch(repo)
     if mode == "local" or (mode == "auto" and is_dirty(repo)):
         return "local", None
@@ -305,9 +426,11 @@ def run_codex(args: argparse.Namespace, repo: Path, prompt: str) -> str:
         cmd.extend(["--model", args.model])
     if args.thinking:
         cmd.extend(["-c", f'model_reasoning_effort="{args.thinking}"'])
+    cmd.append("exec")
+    if args.stream_engine_output:
+        cmd.append("--json")
     cmd.extend(
         [
-            "exec",
             "--ephemeral",
             "-C",
             str(repo),
@@ -320,7 +443,14 @@ def run_codex(args: argparse.Namespace, repo: Path, prompt: str) -> str:
             "-",
         ]
     )
-    result = run(cmd, repo, input_text=prompt, check=False)
+    result = run_with_heartbeat(
+        cmd,
+        repo,
+        input_text=prompt,
+        label="codex",
+        stream_output=args.stream_engine_output,
+        stream_display=CodexStreamDisplay() if args.stream_engine_output else None,
+    )
     try:
         output = output_path.read_text()
     finally:
@@ -337,7 +467,7 @@ def run_claude(args: argparse.Namespace, repo: Path, prompt: str) -> str:
         "--print",
         "--no-session-persistence",
         "--output-format",
-        "json",
+        "stream-json" if args.stream_engine_output else "json",
         "--json-schema",
         json.dumps(SCHEMA),
     ]
@@ -345,11 +475,20 @@ def run_claude(args: argparse.Namespace, repo: Path, prompt: str) -> str:
         cmd.extend(["--allowedTools", claude_allowed_tools(args)])
     else:
         cmd.extend(["--tools", ""])
+    if args.stream_engine_output:
+        cmd.append("--verbose")
     if args.model:
         cmd.extend(["--model", args.model])
     if args.thinking:
         cmd.extend(["--effort", args.thinking])
-    result = run(cmd, repo, input_text=prompt, check=False)
+    result = run_with_heartbeat(
+        cmd,
+        repo,
+        input_text=prompt,
+        label="claude",
+        stream_output=args.stream_engine_output,
+        stream_display=ClaudeStreamDisplay() if args.stream_engine_output else None,
+    )
     if result.returncode != 0:
         raise SystemExit(f"claude engine failed ({result.returncode})\n{result.stderr or result.stdout}")
     return result.stdout
@@ -374,7 +513,7 @@ def run_droid(args: argparse.Namespace, repo: Path, prompt: str) -> str:
         cmd.extend(["--model", args.model])
     if not args.tools:
         cmd.extend(["--disabled-tools", "*"])
-    result = run(cmd, repo, check=False)
+    result = run_with_heartbeat(cmd, repo, label="droid", stream_output=args.stream_engine_output)
     prompt_path.unlink(missing_ok=True)
     if result.returncode != 0:
         raise SystemExit(f"droid engine failed ({result.returncode})\n{result.stderr or result.stdout}")
@@ -399,7 +538,7 @@ def run_copilot(args: argparse.Namespace, repo: Path, prompt: str) -> str:
             "--output-format",
             "json",
             "--stream",
-            "off",
+            "on" if args.stream_engine_output else "off",
             "--no-ask-user",
             "--disable-builtin-mcps",
         ]
@@ -416,12 +555,142 @@ def run_copilot(args: argparse.Namespace, repo: Path, prompt: str) -> str:
         )
         if args.web_search:
             cmd.append("--allow-all-urls")
-        result = run(cmd, Path(tempdir), check=False)
+        result = run_with_heartbeat(cmd, Path(tempdir), label="copilot", stream_output=args.stream_engine_output)
     if result.returncode != 0:
         raise SystemExit(f"copilot engine failed ({result.returncode})\n{result.stderr or result.stdout}")
     return result.stdout
 
 
+class CodexStreamDisplay:
+    def __init__(self, *, activity_seconds: int = 20) -> None:
+        self.activity_seconds = activity_seconds
+        self.hidden_events = 0
+        self.last_visible = time.monotonic()
+
+    def __call__(self, name: str, line: str) -> str | None:
+        if name != "stdout":
+            return line
+        try:
+            event = json.loads(line)
+        except json.JSONDecodeError:
+            return self.visible(line)
+        event_type = event.get("type")
+        if event_type == "thread.started":
+            return self.visible(f"codex thread: {event.get('thread_id', '<unknown>')}\n")
+        if event_type == "turn.started":
+            return self.visible("codex turn started\n")
+        if event_type == "turn.completed":
+            usage = event.get("usage")
+            message = format_codex_usage(usage) + "\n" if isinstance(usage, dict) else "codex turn completed\n"
+            return self.visible(self.flush_hidden() + message)
+        item = event.get("item")
+        if isinstance(item, dict) and item.get("type") == "agent_message" and isinstance(item.get("text"), str):
+            return self.visible(self.flush_hidden() + item["text"].rstrip() + "\n")
+        return self.hidden_activity()
+
+    def hidden_activity(self) -> str | None:
+        self.hidden_events += 1
+        if time.monotonic() - self.last_visible < self.activity_seconds:
+            return None
+        return self.visible(self.flush_hidden())
+
+    def flush_hidden(self) -> str:
+        if not self.hidden_events:
+            return ""
+        count = self.hidden_events
+        self.hidden_events = 0
+        return f"codex activity: {count} hidden tool/status events\n"
+
+    def visible(self, text: str) -> str:
+        self.last_visible = time.monotonic()
+        return text
+
+
+class ClaudeStreamDisplay:
+    def __init__(self, *, activity_seconds: int = 20) -> None:
+        self.activity_seconds = activity_seconds
+        self.hidden_events = 0
+        self.last_visible = time.monotonic()
+        self.started = False
+
+    def __call__(self, name: str, line: str) -> str | None:
+        if name != "stdout":
+            return line
+        try:
+            event = json.loads(line)
+        except json.JSONDecodeError:
+            return self.visible(line)
+        event_type = event.get("type")
+        if event_type == "system" and not self.started:
+            self.started = True
+            return self.visible("claude turn started\n")
+        if event_type == "assistant":
+            return self.assistant_message(event)
+        if event_type == "result":
+            return self.visible(self.flush_hidden() + self.result_summary(event))
+        return self.hidden_activity()
+
+    def assistant_message(self, event: dict[str, Any]) -> str | None:
+        message = event.get("message")
+        if not isinstance(message, dict):
+            return self.hidden_activity()
+        chunks: list[str] = []
+        for item in message.get("content", []):
+            if not isinstance(item, dict):
+                continue
+            if item.get("type") == "text" and isinstance(item.get("text"), str):
+                chunks.append(item["text"].rstrip())
+        if chunks:
+            return self.visible(self.flush_hidden() + "\n".join(chunks) + "\n")
+        return self.hidden_activity()
+
+    def result_summary(self, event: dict[str, Any]) -> str:
+        usage = event.get("usage")
+        fields: list[str] = []
+        if isinstance(usage, dict):
+            for key in (
+                "input_tokens",
+                "cache_read_input_tokens",
+                "cache_creation_input_tokens",
+                "output_tokens",
+            ):
+                value = usage.get(key)
+                if isinstance(value, int):
+                    fields.append(f"{key}={value}")
+        cost = event.get("total_cost_usd")
+        if isinstance(cost, (int, float)) and not isinstance(cost, bool):
+            fields.append(f"cost_usd={cost:.6f}")
+        return "claude usage: " + " ".join(fields) + "\n" if fields else "claude turn completed\n"
+
+    def hidden_activity(self) -> str | None:
+        self.hidden_events += 1
+        if time.monotonic() - self.last_visible < self.activity_seconds:
+            return None
+        return self.visible(self.flush_hidden())
+
+    def flush_hidden(self) -> str:
+        if not self.hidden_events:
+            return ""
+        count = self.hidden_events
+        self.hidden_events = 0
+        return f"claude activity: {count} hidden tool/status events\n"
+
+    def visible(self, text: str) -> str:
+        self.last_visible = time.monotonic()
+        return text
+
+
+def format_codex_usage(usage: dict[str, Any]) -> str:
+    fields = [
+        "input_tokens",
+        "cached_input_tokens",
+        "output_tokens",
+        "reasoning_output_tokens",
+    ]
+    parts = [f"{field}={usage[field]}" for field in fields if isinstance(usage.get(field), int)]
+    return "codex usage: " + " ".join(parts) if parts else "codex usage: unavailable"
+
+
 def claude_allowed_tools(args: argparse.Namespace) -> str:
     tools = [tool.strip() for tool in args.claude_allowed_tools.split(",") if tool.strip()]
     if not args.web_search:
@@ -459,7 +728,7 @@ def extract_json(text: str) -> dict[str, Any]:
 
 
 def extract_json_from_jsonl(text: str) -> dict[str, Any] | None:
-    candidates: list[str] = []
+    candidates: list[str | dict[str, Any]] = []
     for line in text.splitlines():
         line = line.strip()
         if not line:
@@ -478,7 +747,13 @@ def extract_json_from_jsonl(text: str) -> dict[str, Any] | None:
             candidates.append(data["content"])
         if isinstance(event.get("result"), str):
             candidates.append(event["result"])
+        if isinstance(event.get("structured_output"), dict):
+            candidates.append(event["structured_output"])
     for candidate in reversed(candidates):
+        if isinstance(candidate, dict):
+            if "findings" in candidate:
+                return candidate
+            continue
         parsed = parse_json_candidate(candidate)
         if isinstance(parsed, dict) and "findings" in parsed:
             return parsed
@@ -615,7 +890,7 @@ def finish_parallel_tests(proc: subprocess.Popen, started: float) -> int:
 
 def parse_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(description="Bundle-driven AI code review.")
-    parser.add_argument("--mode", choices=["auto", "local", "branch", "commit"], default="auto")
+    parser.add_argument("--mode", choices=["auto", "local", "uncommitted", "branch", "commit"], default="auto")
     parser.add_argument("--base")
     parser.add_argument("--commit", default="HEAD")
     parser.add_argument("--engine", choices=ENGINES, default=os.environ.get("AUTOREVIEW_ENGINE", "codex"))
@@ -642,6 +917,12 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--dataset", action="append", help="Extra evidence file to include in the review bundle.")
     parser.add_argument("--output", help="Write human output to a file as well as stdout.")
     parser.add_argument("--json-output", help="Write validated structured review JSON.")
+    parser.add_argument(
+        "--stream-engine-output",
+        action="store_true",
+        default=os.environ.get("AUTOREVIEW_STREAM_ENGINE_OUTPUT") == "1",
+        help="Stream review engine output while preserving buffered output for validation. Codex output is filtered to hide tool/file chatter.",
+    )
     parser.add_argument("--parallel-tests", help="Run a test command concurrently with review; failure fails the helper.")
     parser.add_argument("--require-finding", action="append", default=[], help="Require finding text to contain this substring.")
     parser.add_argument("--expect-findings", action="store_true", help="Treat findings as success; for harness acceptance tests.")

.agents/skills/clawdtributor/SKILL.md

@@ -98,7 +98,7 @@ Do not close from title alone. If closing as done on main or nonsensical, prove
 
 When asked for `5 new`, exclude refs already surfaced in the session and refill from the archive until there are 5 live-open candidates. If fewer than 5 remain open, list all open ones and say how many short.
 
-When asked to `update`, `refresh`, `recheck`, `check again`, or similar, return an updated live-open candidate list. Do not fill the main list with items that merely merged/closed since the last pass; put those numbers in a short bottom line.
+When asked to `update`, `refresh`, `recheck`, `check again`, or similar, return an updated live-open candidate list. Sort by maintainer importance, not recency: high-impact ready fixes first, then useful-but-review-first, then open/not-ready items. Do not include a "changed since last pass" section or bottom-line merged/closed summary unless the user explicitly asks for churn.
 
 Prefer:
 
@@ -142,18 +142,20 @@ No Markdown tables. Compact bullets. Use color/risk markers:
 Required line shape:
 
 ```markdown
-- **PR #81244** `@whatsskill.` `+118/-1` `bug` 🟢 verifiable: yes. This prevents chat action buttons from overlapping short assistant replies. Blast: web chat rendering, low.
-- **Issue #81245** `@alice` `LOC n/a` `bug` 🟡 verifiable: partial. This reports duplicate Telegram replies when reconnecting after gateway restart. Blast: Telegram channel runtime, medium.
+- **PR #81244** `@whatsskill.` `+118/-1` `bug` 🟢 https://github.com/openclaw/openclaw/pull/81244 - Prevents chat action buttons from overlapping short assistant replies. Verifiable: yes. Blast: web chat rendering, low.
+- **Issue #81245** `@alice` `LOC n/a` `bug` 🟡 https://github.com/openclaw/openclaw/issues/81245 - Reports duplicate Telegram replies when reconnecting after gateway restart. Verifiable: partial. Blast: Telegram channel runtime, medium.
 ```
 
 Rules:
 
 - Bold the `PR #n` or `Issue #n` marker.
 - Use `@handle`, not author bio text.
+- Always include the full GitHub URL.
+- Include a one-line description after the URL, separated with `-`.
 - PR LOC is `+additions/-deletions`; issue LOC is `LOC n/a`.
 - Type: `bug`, `feature`, `perf`, `security`, `docs`, `test`, `chore`, or `refactor`.
 - Write a full sentence for what it does.
 - Always include blast radius in one phrase.
 - Always include `verifiable: yes|partial|no` plus the shortest proof hint when helpful.
 - If status is not open, still show it only when the user asked for all surfaced refs; use ✅ or ⚪ and state merged/closed.
-- For refresh-style asks, bottom line: `Merged/closed since last pass: #81016 merged, #81026 closed.` Omit if none.
+- For refresh-style asks, prefer section order: `Best Open Now`, `Useful But Review First`, `Still Open / Not Ready`. Omit merged/closed churn by default.

.agents/skills/crabbox/SKILL.md

@@ -44,7 +44,9 @@ pnpm crabbox:run -- --help | sed -n '1,120p'
 - OpenClaw scripts prefer `../crabbox/bin/crabbox` when present. The user PATH
   shim can be stale.
 - Check `.crabbox.yaml` for direct-provider defaults. Omitting `--provider`
-  means brokered AWS today.
+  means brokered AWS for normal Linux/macOS paths; the wrapper selects Azure
+  for unqualified Windows/WSL2 runs when the local Crabbox binary advertises
+  Azure.
 - The brokered AWS default is a Linux developer image in `eu-west-1`; the repo
   config pins hot `eu-west-1a/b/c` placement so Fast Snapshot Restore can apply.
   If warmup drifts well past the minute-scale path, verify image promotion,
@@ -82,18 +84,16 @@ Use these only when the task needs an existing non-Linux host. OpenClaw broad
 Linux validation uses the repo Crabbox config unless a provider is explicitly
 requested.
 
-Native brokered Windows is available for Windows-specific proof. Use the AWS
-developer image in `us-west-2` on demand; it has the expected OpenClaw developer
-toolchain and Docker image cache. Keep broad Linux gates on Linux/Testbox unless
-the bug is Windows-specific:
+Native brokered Windows is available for Windows-specific proof. Prefer Azure
+for Windows/WSL2 when the subscription has quota or credits and the local
+Crabbox binary advertises Azure. Keep broad Linux gates on Linux/Testbox unless
+the bug is Windows-specific, and only force AWS when the operator asks for the
+older AWS developer image/cache path or Azure is unavailable:
 
 ```sh
-../crabbox/bin/crabbox warmup \
-  --provider aws \
+pnpm crabbox:warmup -- \
   --target windows \
-  --windows-mode normal \
-  --region us-west-2 \
-  --market on-demand \
+  --windows-mode wsl2 \
   --timing-json
 ```
 
@@ -149,7 +149,7 @@ pnpm crabbox:run -- \
   --ttl 240m \
   --timing-json \
   --shell -- \
-  "env CI=1 NODE_OPTIONS=--max-old-space-size=4096 OPENCLAW_TEST_PROJECTS_PARALLEL=6 OPENCLAW_VITEST_MAX_WORKERS=1 OPENCLAW_VITEST_NO_OUTPUT_TIMEOUT_MS=900000 pnpm test:changed"
+  "pnpm test:changed"
 ```
 
 Full suite:
@@ -160,9 +160,14 @@ pnpm crabbox:run -- \
   --ttl 240m \
   --timing-json \
   --shell -- \
-  "env CI=1 NODE_OPTIONS=--max-old-space-size=4096 OPENCLAW_TEST_PROJECTS_PARALLEL=6 OPENCLAW_VITEST_MAX_WORKERS=1 OPENCLAW_VITEST_NO_OUTPUT_TIMEOUT_MS=900000 pnpm test"
+  "pnpm verify"
 ```
 
+Use `pnpm verify` when you need check plus full Vitest proof. It emits
+`CRABBOX_PHASE:check` and `CRABBOX_PHASE:test`, making Crabbox summaries show
+which stage failed. Use plain `pnpm test` only when check proof is already
+covered or intentionally skipped.
+
 Focused rerun:
 
 ```sh
@@ -171,7 +176,7 @@ pnpm crabbox:run -- \
   --ttl 240m \
   --timing-json \
   --shell -- \
-  "env CI=1 NODE_OPTIONS=--max-old-space-size=4096 OPENCLAW_VITEST_MAX_WORKERS=1 OPENCLAW_VITEST_NO_OUTPUT_TIMEOUT_MS=900000 pnpm test <path-or-filter>"
+  "pnpm test <path-or-filter>"
 ```
 
 Read the JSON summary. Useful fields:
@@ -206,7 +211,7 @@ node scripts/crabbox-wrapper.mjs run \
   --ttl 240m \
   --timing-json \
   -- \
-  CI=1 NODE_OPTIONS=--max-old-space-size=4096 OPENCLAW_TEST_PROJECTS_PARALLEL=6 OPENCLAW_VITEST_MAX_WORKERS=1 OPENCLAW_VITEST_NO_OUTPUT_TIMEOUT_MS=900000 OPENCLAW_TESTBOX=1 OPENCLAW_TESTBOX_REMOTE_RUN=1 pnpm check:changed
+  corepack pnpm check:changed
 ```
 
 Read the JSON summary and the Testbox line. Useful fields:
@@ -544,14 +549,14 @@ If brokered AWS cannot dispatch, sync, attach, or stop, retry once with
 
 ```sh
 pnpm crabbox:run -- --debug --timing-json -- \
-  CI=1 NODE_OPTIONS=--max-old-space-size=4096 OPENCLAW_TEST_PROJECTS_PARALLEL=6 OPENCLAW_VITEST_MAX_WORKERS=1 OPENCLAW_VITEST_NO_OUTPUT_TIMEOUT_MS=900000 pnpm test:changed
+  pnpm test:changed
 ```
 
 Full suite:
 
 ```sh
 pnpm crabbox:run -- --debug --timing-json -- \
-  CI=1 NODE_OPTIONS=--max-old-space-size=4096 OPENCLAW_TEST_PROJECTS_PARALLEL=6 OPENCLAW_VITEST_MAX_WORKERS=1 OPENCLAW_VITEST_NO_OUTPUT_TIMEOUT_MS=900000 pnpm test
+  pnpm test
 ```
 
 Auth fallback, only when `blacksmith` says auth is missing:
@@ -591,7 +596,7 @@ Minimal Blacksmith-backed Crabbox run, from repo root:
 
 ```sh
 pnpm crabbox:run -- --provider blacksmith-testbox --timing-json -- \
-  CI=1 NODE_OPTIONS=--max-old-space-size=4096 OPENCLAW_TEST_PROJECTS_PARALLEL=6 OPENCLAW_VITEST_MAX_WORKERS=1 pnpm test:changed
+  corepack pnpm test:changed
 ```
 
 Use direct Blacksmith only when Crabbox is the broken layer and you are
@@ -617,7 +622,7 @@ provider deliberately.
 ```sh
 pnpm crabbox:warmup -- --class beast --market on-demand --idle-timeout 90m
 pnpm crabbox:hydrate -- --id <cbx_id-or-slug>
-pnpm crabbox:run -- --id <cbx_id-or-slug> --timing-json --shell -- "env NODE_OPTIONS=--max-old-space-size=4096 OPENCLAW_TEST_PROJECTS_PARALLEL=6 OPENCLAW_VITEST_MAX_WORKERS=1 OPENCLAW_VITEST_NO_OUTPUT_TIMEOUT_MS=900000 pnpm test:changed"
+pnpm crabbox:run -- --id <cbx_id-or-slug> --timing-json --shell -- "pnpm test:changed"
 pnpm crabbox:stop -- <cbx_id-or-slug>
 ```
 

.agents/skills/openclaw-changelog-update/SKILL.md

@@ -0,0 +1,89 @@
+---
+name: openclaw-changelog-update
+description: Regenerate OpenClaw release changelog sections from git history before beta or stable releases.
+---
+
+# OpenClaw Changelog Update
+
+Use this for release changelog rewrites and GitHub release-note source text.
+Use it with `release-openclaw-maintainer`; this skill owns changelog content,
+ordering, and audit discipline.
+
+## Goal
+
+Rewrite the target `CHANGELOG.md` version section from history, not from stale
+draft notes. Produce user-facing release notes sorted by user interest while
+preserving issue/PR refs and thanks.
+
+## Inputs
+
+- Target base version: `YYYY.M.D`, without beta suffix.
+- Base tag: last reachable shipped release tag, usually the previous stable or
+  the previous beta train requested by the operator.
+- Target ref: exact branch/SHA being released.
+
+## Workflow
+
+1. Start on `main` before branching when possible:
+   - `git fetch --tags origin`
+   - `git pull --ff-only`
+   - confirm clean `git status -sb`
+2. Audit history, including direct commits:
+   - `git log --first-parent --date=iso-strict --pretty=format:'%h%x09%ad%x09%s' <base-tag>..<target-ref>`
+   - `git log --first-parent --grep='(#' --date=short --pretty=format:'%h%x09%ad%x09%s' <base-tag>..<target-ref>`
+   - also inspect `--since='24 hours ago'` when main moved during the release.
+3. Read linked PRs/issues or diffs for ambiguous commits. Direct commits matter;
+   infer notes from subject, body, touched files, tests, and nearby commits.
+4. Rewrite one stable-base section only:
+   - use `## YYYY.M.D`
+   - do not create beta-specific headings
+   - do not leave a stale `## Unreleased` section above the target release
+   - if `Unreleased` contains release-bound notes, fold them into the target
+     section instead of deleting them
+5. Section shape:
+   - `### Highlights`: 5-8 bullets, broad user wins first
+   - `### Changes`: new capabilities and behavior changes
+   - `### Fixes`: user-facing fixes first, grouped by impact and surface
+6. Preserve attribution:
+   - keep `#issue`, `(#PR)`, `Fixes #...`, and `Thanks @...`
+   - every human-authored merged PR represented by a user-facing entry needs
+     its PR ref and `Thanks @author`, even when the PR had no linked issue
+   - do not add GHSA references, advisory IDs, or security advisory slugs to
+     changelog entries or GitHub release-note text unless explicitly requested
+   - never thank bots, `@openclaw`, `@clawsweeper`, or `@steipete`
+   - if grouping multiple entries, carry all relevant refs and thanks into the
+     grouped bullet
+7. Sorting preference:
+   - security/data-loss and content-boundary fixes
+   - transcript/replay/reply delivery correctness
+   - channels and mobile integrations
+   - providers/Codex/local model reliability
+   - install/update/release path reliability
+   - performance and observability
+   - docs and contributor-only/internal details last or omitted
+8. Keep bullets single-line unless existing file style forces otherwise. Avoid
+   internal release-process noise unless it changes user install/update safety.
+9. Check release-note side conditions:
+   - inspect `src/plugins/compat/registry.ts`
+   - inspect `src/commands/doctor/shared/deprecation-compat.ts`
+   - if any compatibility `removeAfter` is on/before release date, resolve it
+     or explicitly record the blocker before shipping
+10. Validate and ship:
+   - `git diff --check`
+   - for docs/changelog-only changes, no broad tests are required
+   - commit with `scripts/committer "docs(changelog): refresh YYYY.M.D notes" CHANGELOG.md`
+   - push, pull/rebase if needed, then branch/rebase release from latest `main`
+
+## Quota / API Outage Rule
+
+If GitHub API quota is exhausted, do not idle. Continue work that does not need
+GitHub API:
+
+- local changelog rewrite and release-note extraction
+- local pretag checks and package/build sanity
+- git push/tag checks over git protocol
+- npm registry `npm view` checks
+- exact workflow-dispatch command preparation
+
+Only GitHub Release creation, workflow dispatch, run polling, artifact download,
+and issue/PR mutation need API quota.

.agents/skills/openclaw-docs/SKILL.md

@@ -1,238 +0,0 @@
----
-name: openclaw-docs
-description: Write or review high-quality OpenClaw developer documentation.
-dependencies: []
----
-
-# OpenClaw Docs
-
-## Overview
-
-Use this skill when writing, editing, or reviewing OpenClaw developer documentation for APIs, SDKs, CLI tools, integrations, quickstarts, platform guides, or technical product docs.
-
-Write documentation that is concise, helpful, and comprehensive: fast for first success, precise for production, and easy to scan when debugging.
-
-## Core Model
-
-Use an OpenClaw documentation model, strengthened by Write the Docs principles:
-
-- Lead with what the developer is trying to do.
-- Give one recommended path before alternatives.
-- Make examples runnable and realistic.
-- Keep guides task-oriented and references exhaustive.
-- Explain production risks exactly where developers can make mistakes.
-- Link concepts, guides, API references, SDKs, testing, and troubleshooting so readers can move between them without rereading.
-- Treat docs as part of the product lifecycle: draft them before or alongside implementation, review them with code, and keep them current.
-- Make each page discoverable, addressable, cumulative, complete within its stated scope, and easy to skim.
-
-## Structure
-
-Choose the page type before writing:
-
-- Overview: route readers to the right product, integration path, or guide.
-- Quickstart: get a new user to a working result with the fewest safe steps.
-- Topic page: give an end-to-end overview of a major domain entity, with setup,
-  key subtopics, troubleshooting, and links to deeper references.
-- Guide: explain one workflow from prerequisites to production readiness.
-- API reference: define every object, endpoint, parameter, enum, response, error, and version rule.
-- SDK or CLI reference: document install, auth, commands or methods, options, examples, and failure modes.
-- Testing guide: show sandbox setup, fixtures, test data, simulated failures, and live-mode differences.
-- Troubleshooting guide: map symptoms to checks, causes, and fixes.
-
-Use this default topic page structure:
-
-1. Title: name the major entity or surface.
-2. Opening overview: start with a few unheaded sentences that explain what it
-   is, what it owns, and what it does not own. Do not add a `## Overview`
-   heading unless the page is itself an overview index.
-3. Requirements: include only when setup needs specific accounts, versions,
-   permissions, plugins, operating systems, or credentials.
-4. Quickstart: show the recommended setup path and smallest reliable verification.
-5. Configuration: show the minimum configuration needed to use the surface,
-   common variants users must choose between, and where each option is set:
-   CLI, config file, environment variable, plugin manifest, dashboard, or API.
-6. Major subtopics: organize the entity's major concepts, workflows, and
-   decisions by reader intent. Put each major subtopic under its own heading;
-   do not wrap them in a generic `## Subtopics` section.
-7. Troubleshooting: diagnose common observable failures under an explicit
-   `## Troubleshooting` heading.
-8. Related: link to guides, references, commands, concepts, and adjacent topics.
-
-Topic pages may be longer than quickstarts, but they should not become exhaustive
-references. Move field tables, API contracts, narrow internals, legacy details,
-and rare debugging workflows to linked reference or troubleshooting pages when
-they interrupt the end-to-end overview.
-
-For configuration, keep task-critical options inline. Link to reference docs for
-full option lists, defaults, enums, generated schemas, and advanced settings. Do
-not duplicate exhaustive config reference tables in topic pages unless the topic
-page is itself the reference.
-
-Use this default guide structure:
-
-1. Title: name the outcome, not the implementation detail.
-2. Opening: state what the reader can accomplish in one or two sentences.
-3. Before you begin: list accounts, keys, permissions, versions, tools, and assumptions.
-4. Choose a path: compare options only when the reader must decide.
-5. Steps: use verb-led headings with code, expected output, and checks.
-6. Test: show the smallest reliable proof that the integration works.
-7. Production readiness: cover security, idempotency, retries, limits, observability, migrations, and cleanup.
-8. Troubleshooting: include common errors near the workflow that causes them.
-9. See also: link to concepts, API references, SDK docs, and adjacent guides.
-
-Keep navigation user-intent based. Do not force readers to understand internal product taxonomy before they can pick a task.
-
-## Documentation Lifecycle
-
-Write and maintain docs with the same discipline as code:
-
-- Draft docs early enough to expose unclear product, API, CLI, or config design.
-- Keep docs source near the code, config, command, plugin, or protocol it describes when the repo layout allows it.
-- Avoid duplicate truth. If the same contract appears in multiple places, pick the canonical page and link to it.
-- Update docs in the same change as behavior, config, API, CLI, plugin, or troubleshooting changes.
-- Remove, redirect, or clearly mark stale docs. Incorrect docs are worse than missing docs.
-- Involve the right reviewers: code owners for behavior, support or QA for user failure modes, and docs maintainers for structure and style.
-- Preserve older-version guidance only when users need it; otherwise document the current supported behavior.
-
-Do not use FAQs as a dumping ground for unrelated material. Promote recurring questions into task, concept, troubleshooting, or reference pages.
-
-## Writing Style
-
-Write in a direct, practical voice:
-
-- Use present tense and active voice.
-- Address the reader as "you" when giving instructions.
-- Prefer short paragraphs and scannable lists.
-- Use concrete nouns: "agent profile", "Gateway webhook", "plugin manifest", "session state".
-- Put caveats exactly where they affect the step.
-- Avoid marketing language, hype, generic benefits, and vague claims.
-- Avoid long conceptual lead-ins before the first actionable step.
-- Do not over-explain common developer concepts unless the product has a nonstandard contract.
-- Define OpenClaw-specific jargon and abbreviations before first use.
-- Use sentence case for headings unless an OpenClaw product name, command, or identifier requires capitalization.
-- Use descriptive link text that names the destination or action; avoid vague links such as "this page" or "click here".
-- Avoid culturally specific idioms, violent idioms, and jokes that make docs harder to translate or scan.
-- Write accessible prose: do not rely on color, screenshots, or visual position as the only way to understand an instruction.
-
-Use headings that describe actions or reference surfaces:
-
-- Good: "Create an agent", "Configure a Slack channel", "Repair plugin installation"
-- Avoid: "How it works", "Under the hood", "Important notes" unless the section truly needs that shape
-
-Use precise modal language:
-
-- Use "must" for required behavior.
-- Use "can" for optional capability.
-- Use "recommended" for the default path.
-- Use "avoid" for known footguns.
-- Explain "why" only when it changes a developer decision.
-
-## Detail Level
-
-Vary detail by page type:
-
-- Overview pages: be brief; help readers choose.
-- Quickstarts: be procedural; include only what is needed for first success.
-- Guides: be complete for one workflow; include decisions, side effects, and failure handling.
-- References: be exhaustive; document every field, default, enum, nullable value, constraint, response, and error.
-- Troubleshooting: be explicit; assume the reader is blocked and needs observable checks.
-
-Go deep where mistakes are expensive:
-
-- Authentication and secret handling
-- Money movement, billing, permissions, and irreversible actions
-- Webhooks, retries, duplicate events, and ordering
-- Idempotency and concurrency
-- Sandbox versus production differences
-- Versioning, migrations, and backwards compatibility
-- Limits, rate limits, quotas, and timeouts
-- Error codes and recovery paths
-- Data retention, privacy, and compliance-sensitive behavior
-
-Do not bury this detail in a distant reference if developers need it to complete the task safely.
-
-## Examples
-
-Make examples production-shaped, even when using test data:
-
-- Prefer complete copy-pasteable commands or snippets.
-- Use realistic variable names and values.
-- Mark placeholders clearly with angle-bracket names such as `<API_KEY>` or `<CUSTOMER_ID>`.
-- Show expected success output after commands.
-- Show full request and response examples for API references when response shape matters.
-- Keep one conceptual unit per code block.
-- Use language-specific code fences.
-- Avoid toy examples that hide required setup, auth, error handling, or cleanup.
-
-When multiple languages are useful, keep the same scenario across languages so readers can compare equivalents.
-
-## Discoverability and Navigation
-
-Design every page so readers can find it, link to it, and decide quickly whether it answers their question:
-
-- Use goal-oriented titles and headings that match likely search terms.
-- Start each page with a concise answer to "what can I do here?"
-- Include metadata or frontmatter required by the OpenClaw docs index.
-- Add "Read when" hints for docs-list routing when creating or changing OpenClaw docs pages that participate in the docs index.
-- Link from likely entry points, not only from nearby internal taxonomy pages.
-- Keep section headings stable enough for links from issues, PRs, support replies, and chat answers.
-- Order tutorials and examples from prerequisites to advanced tasks; order reference pages alphabetically or topically when that helps lookup.
-- State scope up front when a page is intentionally partial.
-
-## API Reference Pattern
-
-For endpoints, methods, objects, or commands, include:
-
-1. Short purpose statement.
-2. Auth or permission requirements.
-3. Request shape, including path, query, headers, and body fields.
-4. Parameter table with type, requiredness, default, constraints, enum values, and side effects.
-5. Return shape with object lifecycle states.
-6. Error cases with codes, causes, and recovery guidance.
-7. Runnable example request.
-8. Representative successful response.
-9. Related guides and adjacent reference pages.
-
-For nested objects, document child fields near their parent. Do not make readers jump across pages to understand the shape of a single request.
-
-## Verification
-
-Verify docs changes like product changes:
-
-- Run the relevant docs build, docs index, formatter, link checker, or generated-doc check when available.
-- Run commands, snippets, and examples that the page tells users to run whenever feasible.
-- Confirm screenshots, UI labels, CLI output, config keys, flags, defaults, errors, and file paths match current behavior.
-- Prefer executable checks over prose-only review for API, CLI, config, generated reference, and troubleshooting docs.
-- If a verification step is not feasible, say what was not verified and why.
-
-## Completeness Checks
-
-Before finalizing a page, verify:
-
-- The first screen tells readers what they can accomplish.
-- The recommended path is obvious.
-- Prerequisites are explicit and testable.
-- Examples can run with documented inputs.
-- The page has a clear audience: user, operator, plugin author, contributor, or maintainer.
-- Test-mode and production-mode behavior are separated.
-- Security-sensitive values are never exposed in examples.
-- Every warning is attached to the step where it matters.
-- Edge cases are documented where they affect implementation.
-- API fields include types, defaults, constraints, and errors.
-- Troubleshooting starts from observable symptoms.
-- Related links help the reader continue without duplicating the page.
-- The page says where to get support, file issues, or contribute when that is relevant to the reader's next step.
-- The page is complete for the scope it claims, or the limitation is stated up front.
-
-## Review Pass
-
-Edit in this order:
-
-1. Remove repetition and generic explanation.
-2. Move conceptual background below the first useful action unless it is required to choose correctly.
-3. Replace passive or abstract wording with concrete instructions.
-4. Tighten headings until the outline reads like a task map.
-5. Add missing operational details for production safety.
-6. Check examples for copy-paste accuracy.
-7. Add links between guide, reference, SDK, testing, and troubleshooting surfaces.
-8. Check discoverability, addressability, accessibility, and docs-as-code verification.

.agents/skills/openclaw-ghsa-maintainer/SKILL.md

@@ -5,7 +5,7 @@ description: Inspect, patch, validate, publish, or confirm OpenClaw GHSA securit
 
 # OpenClaw GHSA Maintainer
 
-Use this skill for repo security advisory workflow only. Keep general release work in `openclaw-release-maintainer`.
+Use this skill for repo security advisory workflow only. Keep general release work in `release-openclaw-maintainer`.
 
 ## Respect advisory guardrails
 

.agents/skills/openclaw-landable-bug-sweep/SKILL.md

@@ -89,11 +89,11 @@ Reject:
    - if unwritable or wrong shape, create own PR and preserve useful contributor credit
    - if no PR exists, create one
    - add regression test when it fits
-   - changelog for user-facing fixes; thank credited human reporter/contributor
+   - release-note context for user-facing fixes in PR body or commit message; credit human reporter/contributor when known
 6. Review, refresh, and publish:
    - rebase or otherwise refresh the PR branch on current `origin/main`
    - resolve drift, including newly exposed CI failures, rather than counting the PR as ready
-   - changelog-only conflicts are routine on busy `main`; resolve them mechanically when already refreshing, but do not treat them as a real code conflict, a reason to reject the PR, or evidence that the branch needs extra fixup beyond the changelog entry order
+   - do not add `CHANGELOG.md` during normal sweep PRs; release automation generates it from PRs and commits
    - left-test the rebased head with the smallest meaningful local/Testbox/live command that proves the bug
    - run `$autoreview` until no accepted/actionable findings remain before creating, updating, or presenting the PR URL
    - create/update PR with real body and proof fields

.agents/skills/openclaw-pr-maintainer/SKILL.md

@@ -139,12 +139,12 @@ Issue triage is review/prove/patch-local by default:
 2. Fix only issues that are easy, high-confidence, and narrowly owned by the implicated path.
 3. Add focused regression proof when practical.
 4. Stop with the dirty diff, touched files, and test/gate output for maintainer review.
-5. After maintainer approval to ship, make one commit per accepted fix, with its own changelog entry when user-facing.
+5. After maintainer approval to ship, make one commit per accepted fix, with release-note context in the PR body or commit message when user-facing.
 6. Pull/rebase, push, then comment and close only the issues that were fixed or explicitly triaged closed.
 
 Do not batch unrelated issue fixes into one commit. Do not publish, comment, close, or label during the review/prove phase.
 
-Missing changelog is not a PR review finding or merge blocker. If landing/fixing a user-visible change, add/update changelog automatically when practical; never ask or block solely on it.
+Missing `CHANGELOG.md` is not a PR review finding or merge blocker. If landing/fixing a user-visible change, make sure the PR body or commit message captures the release-note context; never ask or block solely on it.
 
 Only list candidates that pass all gates:
 
@@ -168,13 +168,22 @@ Output only qualifying candidates, with: ref, surface, proof, cause, fix sketch,
 
 - Start every PR review with 1-3 plain sentences explaining what the change does and why it matters. Put this before `Findings`.
 - Then list findings first. If none, say `No blocking findings` or `No findings`.
+- Show size near the top as `LOC: +<additions>/-<deletions> (<changedFiles> files)`, using live PR stats or local diff stats.
 - Always answer: bug/behavior being fixed, PR/issue URL and affected surface, provenance for regressions when traceable, and best-fix verdict.
 - For bug/regression fixes, include a compact `Provenance:` line after cause/root-cause when a bounded history pass can identify it. Use `git log -S/-G`, `git blame`, linked PRs/issues, and tests.
-- Provenance must separate roles when they differ: blamed code author username, blamed PR merger/committer username, current PR author username, PR number, and date. Do not collapse them into one "introduced by" actor.
+- Provenance must separate roles when they differ: blamed code author username, blamed PR author username, blamed PR merger/committer username, automerge trigger when known, current PR author username, PR number, and date. Do not collapse them into one "introduced by" actor.
+- If the blamed PR was merged by `clawsweeper[bot]` or another automation, identify the human trigger when practical. Check live PR timeline/comments first; if rate-limited, use gitcrawl/cache or public PR HTML. Look for maintainer command comments such as `@clawsweeper automerge`, `/landpr`, labels/events that armed automerge, and ClawSweeper status comments. Report `automerge triggered by @login`; if not found, say trigger unknown rather than naming the bot as the human decision-maker.
 - For any confirmed bug, run `git blame` on the implicated line(s) after identifying the root cause. Report who broke it as the blamed PR merger/committer, and also name the blamed code author. Include the PR number. If no PR is traceable, use the blamed commit as the provenance: commit SHA, date, and author username. Do not guess a merger or frame missing PR metadata as a separate finding.
 - Phrase provenance as `introduced by`, `made visible by`, or `carried forward by`, with confidence (`clear`, `likely`, `unknown`). If unclear, say what evidence is missing instead of guessing. For features, docs, and refactors, use `Provenance: N/A` or omit it when no broken behavior is being fixed.
 - Keep summaries compact, but include enough proof that the verdict is auditable without rereading the PR.
 
+LOC proof:
+
+```bash
+gh pr view <number> --json additions,deletions,changedFiles \
+  --jq '"LOC: +\(.additions)/-\(.deletions) (\(.changedFiles) files)"'
+```
+
 ## Read beyond the diff
 
 - Review the surrounding code path, not just changed lines. Open the caller, callee, data contracts, adjacent tests, and owner module.
@@ -194,7 +203,7 @@ Output only qualifying candidates, with: ref, surface, proof, cause, fix sketch,
 - Before landing, require:
   1. symptom evidence such as a repro, logs, or a failing test
   2. a verified root cause in code with file/line
-  3. blame-backed provenance for regressions when traceable, including blamed PR merger and date, or commit SHA/date when no PR is traceable
+  3. blame-backed provenance for regressions when traceable, including blamed PR merger and automerge trigger when known, or commit SHA/date when no PR is traceable
   4. a fix that touches the implicated code path
   5. a regression test when feasible, or explicit manual verification plus a reason no test was added
 - If the claim is unsubstantiated or likely wrong, request evidence or changes instead of merging.
@@ -244,9 +253,8 @@ gh search issues --repo openclaw/openclaw --match title,body --limit 50 \
 
 ## Follow PR review and landing hygiene
 
-- Never mention merge conflicts that are relatively easy to resolve, such as
-  `CHANGELOG.md` entries, in review-only output. These are landing mechanics,
-  not correctness findings.
+- Never mention release-note bookkeeping in review-only output. It is landing
+  or release-generation mechanics, not a correctness finding.
 - If bot review conversations exist on your PR, address them and resolve them yourself once fixed.
 - Leave a review conversation unresolved only when reviewer or maintainer judgment is still needed.
 - Before landing any PR with non-trivial code changes, run `$autoreview` until no accepted/actionable findings remain, unless equivalent manual review already covered it, the change is trivial/docs-only, or the user opts out.

.agents/skills/openclaw-pre-release-plugin-testing/agents/openai.yaml

@@ -1,4 +0,0 @@
-interface:
-  display_name: "OpenClaw Plugin Pre-Release Testing"
-  short_description: "Plan plugin release validation"
-  default_prompt: "Use $openclaw-pre-release-plugin-testing to plan or run pre-release OpenClaw plugin validation across package, lifecycle, doctor, gateway, SDK, and live-ish proof."

.agents/skills/openclaw-test-performance/SKILL.md

@@ -98,7 +98,7 @@ barrels, package-boundary tests, or extension suites.
    - add `--keep`/`--id <id-or-slug>` only when several commands must share one
      warmed box; stop it with `pnpm crabbox:stop -- <id-or-slug>`.
 5. If plugin performance is package-artifact sensitive, switch to
-   `openclaw-pre-release-plugin-testing` and Package Acceptance rather than
+   `release-openclaw-plugin-testing` and Package Acceptance rather than
    trusting source-only timing.
 
 ## Metric Collection

.agents/skills/openclaw-testing/SKILL.md

@@ -68,6 +68,7 @@ scripts/crabbox-wrapper.mjs` for Testbox, and `git commit --no-verify` only
 pnpm changed:lanes --json
 pnpm check:changed       # changed typecheck/lint/guards; no Vitest
 pnpm test:changed        # cheap smart changed Vitest targets
+pnpm verify              # full check, then full Vitest
 OPENCLAW_TEST_CHANGED_BROAD=1 pnpm test:changed
 pnpm test <path-or-filter> -- --reporter=verbose
 OPENCLAW_VITEST_MAX_WORKERS=1 pnpm test <path-or-filter>
@@ -89,6 +90,8 @@ status checks or install reconciliation in a linked worktree.
 - `pnpm check` and `pnpm check:changed` do not run Vitest tests. They are for
   typecheck, lint, and guard proof.
 - `pnpm test` and `pnpm test:changed` run Vitest tests.
+- `pnpm verify` runs `pnpm check`, then `pnpm test`, with Crabbox phase markers
+  so remote summaries show which half failed.
 - `pnpm test:changed` is intentionally cheap by default: direct test edits,
   sibling tests, explicit source mappings, and import-graph dependents.
 - `OPENCLAW_TEST_CHANGED_BROAD=1 pnpm test:changed` is the explicit broad
@@ -210,7 +213,7 @@ workflow only spends setup and queue time on that suite.
 ### Release Evidence
 
 After release-candidate validation or before a release decision, record the
-important run ids in the private `openclaw/releases-private` evidence ledger.
+important run ids in the public `openclaw/releases` evidence ledger.
 Use the manual `OpenClaw Release Evidence`
 (`openclaw-release-evidence.yml`) workflow there. It writes durable summaries
 under `evidence/<release-id>/` and commits:
@@ -233,13 +236,13 @@ short release-manager notes there. Do not store raw logs, provider
 prompts/responses, channel transcripts, signing material, or secret-bearing
 config in git; raw logs stay in Actions artifacts.
 
-When `Full Release Validation` completes and
-`OPENCLAW_RELEASES_PRIVATE_DISPATCH_TOKEN` is configured in the public repo, it
-requests the private `OpenClaw Release Evidence From Full Validation` workflow.
-That private workflow reads the parent full-validation run, extracts the child
-CI/release-checks/Telegram run ids from the parent logs, and opens the evidence
-PR automatically. If the token is absent or the run predates this wiring, trigger
-that private workflow manually with the full-validation run id.
+When `Full Release Validation` completes and `OPENCLAW_RELEASES_DISPATCH_TOKEN`
+is configured in the source repo, it requests the public
+`OpenClaw Release Evidence From Full Validation` workflow. That workflow reads
+the parent full-validation run, extracts the child CI/release-checks/Telegram
+run ids from the parent logs, and opens the evidence PR automatically. If the
+token is absent or the run predates this wiring, trigger that workflow manually
+with the full-validation run id.
 
 ### Release Checks
 

.agents/skills/optimizetests/SKILL.md

@@ -1,41 +0,0 @@
----
-name: optimizetests
-description: Optimize OpenClaw slow tests, imports, misplaced coverage, and CI wall time without dropping coverage.
----
-
-# Optimize Tests
-
-Goal: real OpenClaw test/runtime speedups with coverage intact. Do not add shards,
-skip assertions, weaken gates, or tune runner flags as the main fix.
-
-## Runbook
-
-1. Read `docs/help/testing.md`, `docs/ci.md`, and the scoped `AGENTS.md` files
-   for any subtree you will edit.
-2. Establish evidence before edits:
-   - Full ranking: `pnpm test:perf:groups --full-suite --allow-failures --output .artifacts/test-perf/<name>.json`
-   - Targeted file: `timeout 240 /usr/bin/time -l pnpm test <file> --maxWorkers=1 --reporter=verbose`
-   - Import suspicion: add `OPENCLAW_VITEST_IMPORT_DURATIONS=1 OPENCLAW_VITEST_PRINT_IMPORT_BREAKDOWN=1`
-3. Attack highest-return hotspots first:
-   - broad barrels or `importActual()` in hot tests
-   - per-test `vi.resetModules()` plus fresh imports
-   - expensive gateway/server/client setup where reset/reuse proves same behavior
-   - core tests asserting extension-owned behavior
-   - duplicated fixture construction or contract assertions
-4. Prefer production-quality fixes:
-   - narrow runtime seams over broad mocks
-   - pure helpers for static parsing/metadata
-   - injected deps over module resets
-   - extension-owned tests for bundled plugin/provider/channel behavior
-5. After each change, rerun the same benchmark and the proving test lane. Record
-   before/after wall time, Vitest duration, and max RSS when available.
-6. Run `pnpm check:changed`; run broader gates (`pnpm check`, `pnpm test`,
-   `pnpm build`) when touched surfaces require them.
-7. Commit scoped changes with `scripts/committer "<conventional message>" <paths...>`.
-   Push when requested. If CI is red, inspect with `gh run list/view`, fix, push,
-   repeat until current CI is green or a blocker is proven unrelated.
-
-## Output
-
-End with the pushed commit(s), before/after timings, gates run, current CI state,
-and any remaining tail lanes that need separate optimization.

.agents/skills/optimizetests/agents/openai.yaml

@@ -1,6 +0,0 @@
-interface:
-  display_name: "Optimize Tests"
-  short_description: "Benchmark and speed up OpenClaw tests"
-  default_prompt: "Use $optimizetests to benchmark slow OpenClaw tests, optimize imports and duplicated setup, move misplaced core coverage to extensions, verify gates, commit scoped changes, push, and keep CI green without adding shards or dropping coverage."
-policy:
-  allow_implicit_invocation: false

.agents/skills/release-openclaw-announcement/SKILL.md

@@ -0,0 +1,85 @@
+---
+name: release-openclaw-announcement
+description: "Draft or post OpenClaw beta/stable Discord release announcements from changelog, GitHub release, registry, and validation evidence. Use when announcing a beta, stable release, release candidate, or asking what users should test after an OpenClaw release."
+---
+
+# OpenClaw Release Announcement
+
+Use with `release-openclaw-maintainer` after a beta or stable release is live.
+Use with `openclaw-discord` when actually posting to Discord.
+
+## Evidence First
+
+Before drafting focus areas, read real release evidence:
+
+1. Current GitHub release body for the tag.
+2. `CHANGELOG.md` section for the released base version.
+3. Commits since the previous shipped version or the operator-specified base.
+4. Registry/package metadata for the exact version and current dist-tag.
+5. Validation status that is relevant to user confidence.
+
+Do not claim a full changelog audit unless you did it. If you only read the
+generated release notes or top changelog section, say that and either audit
+properly or draft with that limitation.
+
+For beta focus areas, prioritize user-observable changes over internal test or
+CI mechanics:
+
+- install/update paths
+- OS/platform-specific behavior
+- Gateway startup/restart, config, and runtime behavior
+- provider/model/runtime routing
+- plugin loading and local plugin development
+- channels and media paths
+- security/data-loss/user-impact fixes
+
+Do not let late release-branch fixes automatically dominate the announcement.
+If the version includes a large delta from the previous shipped version, rank
+focus areas by the whole release delta and expected user impact; mention late
+fixes in their natural category.
+
+## Required Copy
+
+Every beta announcement must make beta status explicit and include:
+
+- exact version, e.g. `OpenClaw 2026.5.25-beta.1`
+- one-sentence risk framing: beta, useful for testing, not stable promotion
+- focused test areas derived from evidence, not guesswork
+- update command promoted near the top:
+  ```sh
+  openclaw update --channel beta --yes
+  openclaw --version
+  ```
+- fresh install path:
+  `Install from https://openclaw.ai`
+- GitHub release link
+- concise validation note, without making CI the headline
+
+Do not suggest npm install commands in beta announcements unless the operator
+explicitly asks for npm-specific copy or troubleshooting text. It is fine to use
+registry metadata as evidence; do not turn that into public install guidance.
+
+For stable announcements, use the stable channel wording:
+
+```sh
+openclaw update --channel stable --yes
+openclaw --version
+```
+
+Fresh installs still point to `https://openclaw.ai`.
+
+## Style
+
+- Discord Markdown, no tables.
+- Keep it skimmable: short intro, bullets, commands, links.
+- Lead with what users can feel or test, not proof plumbing.
+- Mention validation only after install/update instructions.
+- Be specific about where feedback is useful.
+- Do not mention private local proof paths in public announcements.
+- Do not overstate unverified platforms, channels, or provider behavior.
+
+## Posting
+
+When asked to post, use the configured Discord workflow from
+`openclaw-discord` or the approved OpenClaw relay. Never print tokens.
+For public channels, inspect the final body before sending.

.agents/skills/release-openclaw-announcement/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "OpenClaw Release Announcement"
+  short_description: "Draft Discord beta/stable release announcements from evidence."
+  default_prompt: "Use this skill to draft an OpenClaw beta or stable Discord announcement from changelog, release notes, npm/GitHub release proof, and validation evidence."

.agents/skills/release-openclaw-ci/SKILL.md

@@ -1,11 +1,11 @@
 ---
-name: openclaw-release-ci
+name: release-openclaw-ci
 description: "Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights."
 ---
 
 # OpenClaw Release CI
 
-Use this with `$openclaw-release-maintainer` and `$openclaw-testing` when a release candidate needs full validation, install/update proof, live provider checks, or CI recovery.
+Use this with `$release-openclaw-maintainer` and `$openclaw-testing` when a release candidate needs full validation, install/update proof, live provider checks, or CI recovery.
 
 ## Guardrails
 
@@ -22,7 +22,7 @@ Use this with `$openclaw-release-maintainer` and `$openclaw-testing` when a rele
 Before full release validation:
 
 ```bash
-node .agents/skills/openclaw-release-ci/scripts/verify-provider-secrets.mjs --required openai,anthropic,fireworks
+node .agents/skills/release-openclaw-ci/scripts/verify-provider-secrets.mjs --required openai,anthropic,fireworks
 gh api rate_limit --jq '.resources.core'
 git status --short --branch
 git rev-parse HEAD
@@ -35,6 +35,30 @@ The script prints only provider status and HTTP class, never tokens.
 
 ## Dispatch
 
+Start product performance evidence as early as the release SHA exists, in
+parallel with other release work:
+
+```bash
+gh workflow run openclaw-performance.yml \
+  --repo openclaw/openclaw \
+  --ref main \
+  -f target_ref=<release-sha> \
+  -f profile=release \
+  -f repeat=3 \
+  -f deep_profile=false \
+  -f live_openai_candidate=false \
+  -f fail_on_regression=false
+```
+
+- Do not wait for full release validation to start this early perf signal.
+- Compare available Kova, gateway startup, and CLI startup metrics with earlier
+  release evidence or clawgrit reports before publish/closeout.
+- Call out any regression in the release proof. Treat a major regression as a
+  release blocker until it is fixed, waived by the operator, or proven to be
+  infrastructure noise.
+- Full Release Validation also records advisory product-performance evidence;
+  the early standalone run is for overlap and faster regression discovery.
+
 Prefer the trusted workflow on `main`, target the exact release SHA:
 
 ```bash
@@ -55,7 +79,7 @@ Use `release_profile=stable` unless the operator explicitly asks for the broad a
 Use the summary helper instead of repeated raw polling:
 
 ```bash
-node .agents/skills/openclaw-release-ci/scripts/release-ci-summary.mjs <full-release-run-id>
+node .agents/skills/release-openclaw-ci/scripts/release-ci-summary.mjs <full-release-run-id>
 ```
 
 Then watch only when useful:
@@ -85,7 +109,8 @@ Record:
 
 - release SHA
 - full parent run URL
-- child run IDs and conclusions: CI, Release Checks, Plugin Prerelease, NPM Telegram
+- child run IDs and conclusions: CI, Release Checks, Plugin Prerelease, NPM Telegram, Product Performance
+- performance comparison result versus earlier releases when available
 - targeted local proof commands
 - provider-secret preflight result
 - known gaps or unrelated failures

.agents/skills/release-openclaw-ci/agents/openai.yaml

@@ -1,4 +1,4 @@
 interface:
   display_name: "OpenClaw Release CI"
   short_description: "Verify and debug OpenClaw release validation runs"
-  default_prompt: "Use $openclaw-release-ci to preflight provider secrets, watch full release validation, summarize child runs, and triage only failing release lanes."
+  default_prompt: "Use $release-openclaw-ci to preflight provider secrets, watch full release validation, summarize child runs, and triage only failing release lanes."

.agents/skills/release-openclaw-mac/SKILL.md

@@ -1,26 +1,23 @@
 ---
-name: openclaw-mac-release
+name: release-openclaw-mac
 description: "Run or recover OpenClaw macOS release signing, notarization, appcast, and asset promotion."
 ---
 
 # OpenClaw Mac Release
 
-Use with `$openclaw-release-maintainer`, `$openclaw-release-ci`, and `$one-password` when stable macOS assets, private mac preflight, notarization, appcast promotion, or mac release recovery is involved.
+Use with `$release-openclaw-maintainer`, `$release-openclaw-ci`, `$one-password`, and `$release-private` if it exists when stable macOS assets, private mac preflight, notarization, appcast promotion, or mac release recovery is involved.
 
 ## Credentials
 
-- Canonical ASC item: vault `Molty`, title `API Key - App Store Connect - Personal - Release`.
+- Resolve Peter-owned ASC item refs, key ids, issuer ids, and service-token provenance from `$release-private`.
 - Fields: `private_key_p8`, `key_id`, `issuer_id`.
-- Current known good key id: `AKVLXW849T`.
-- Legacy mirror: vault `Private`, title `API Key - App Store Connect - Personal`; keep it synced for older refs.
 - Stale/revoked key symptom: `xcrun notarytool submit` fails with `HTTP status code: 401. Unauthenticated`.
 - Validate candidate ASC credentials with `xcrun notarytool history` before setting GitHub secrets.
 
 ## 1Password
 
 - Use `$one-password`: all `op` work inside one persistent tmux session, no secret output.
-- Prefer `OP_SERVICE_ACCOUNT_TOKEN` from `~/.profile` for Molty reads.
-- Do not assume `MOLTY_OP_SERVICE_ACCOUNT_TOKEN` is alive; it has previously pointed at a deleted service account.
+- Use the service-token guidance from `$release-private` when available.
 - If a service token fails, run status-only checks: token present/length and `op whoami`; never print token values.
 - If desktop app auth is needed but Touch ID is unavailable, set `OP_BIOMETRIC_UNLOCK_ENABLED=false` for the manual `op account add --signin` path.
 

.agents/skills/release-openclaw-maintainer/SKILL.md

@@ -1,11 +1,11 @@
 ---
-name: openclaw-release-maintainer
+name: release-openclaw-maintainer
 description: Prepare or verify OpenClaw stable/beta releases, changelogs, release notes, publish commands, and artifacts.
 ---
 
 # OpenClaw Release Maintainer
 
-Use this skill for release and publish-time workflow. Keep ordinary development changes and GHSA-specific advisory work outside this skill.
+Use this skill for release and publish-time workflow. Load `$release-private` if it exists before resolving Peter-owned credential locators or private host topology. Keep ordinary development changes and GHSA-specific advisory work outside this skill.
 
 ## Respect release guardrails
 
@@ -23,7 +23,8 @@ Use this skill for release and publish-time workflow. Keep ordinary development
   green. Then branch from that commit so regular development can continue on
   `main` while release validation runs.
 - Before release branching, commit any dirty files in coherent groups, push,
-  pull/rebase, then run `/changelog` on `main` and commit/push/pull that
+  pull/rebase, then generate `CHANGELOG.md` on `main` from merged PRs and all
+  direct commits since the last reachable release tag. Commit/push/pull that
   changelog rewrite immediately before creating the release branch.
 - During release planning, inspect both `src/plugins/compat/registry.ts` and
   `src/commands/doctor/shared/deprecation-compat.ts` before branching and again
@@ -59,8 +60,18 @@ Use this skill for release and publish-time workflow. Keep ordinary development
   fixes that landed after the release branch cut and backport only important
   low-risk fixes. Operators may authorize up to 4 autonomous beta attempts;
   after 4 failed beta attempts, stop and report.
-- Use `/changelog` before version/tag preparation so the top changelog section
-  is deduped and ordered by user impact.
+- As soon as the release candidate SHA exists, dispatch `OpenClaw Performance`
+  with `target_ref=<release-sha>` in parallel with the other release work. Do
+  not wait for full release validation to start the performance signal.
+- Before publish/closeout, compare available product performance metrics with
+  earlier releases: Kova agent-turn/resource metrics, gateway startup
+  ready/listen/RSS/CPU metrics, and CLI startup metrics from release evidence
+  or clawgrit reports. Report regressions explicitly. A major regression is a
+  release blocker unless the operator waives it or the data clearly proves
+  infrastructure noise.
+- Generate the changelog before version/tag preparation so the top changelog
+  section is deduped and ordered by user impact. Use
+  `$openclaw-changelog-update` for the rewrite.
 - Do not create beta-specific `CHANGELOG.md` headings. Beta releases use the
   stable base version section, for example `v2026.4.20-beta.1` uses
   `## 2026.4.20` release notes.
@@ -127,11 +138,25 @@ Use this skill for release and publish-time workflow. Keep ordinary development
 
 ## Build changelog-backed release notes
 
+- `CHANGELOG.md` is release-owned. Normal PRs and direct `main` fixes should
+  not edit it.
 - Before release branching or tagging, rewrite the target `CHANGELOG.md`
-  section from commit history, not just from existing notes: scan commits since
-  the last reachable release tag, add missed user-facing changes, dedupe
-  overlapping entries, and sort each section from most to least interesting for
-  users.
+  section from history, not existing notes. Use the last reachable stable or
+  beta release tag as the base, then inspect every commit through the target
+  release SHA.
+- Include both merged PR commits and direct commits on `main`. Direct commits
+  matter: infer notes from their subject, body, touched files, linked issues,
+  tests, and nearby code when no PR body exists.
+- Prefer PR bodies, issue links, review proof, and commit bodies over commit
+  subjects alone. If a commit fixed an issue directly, the commit body should
+  name the user-visible behavior, affected surface, issue ref, and credited
+  reporter/contributor when known.
+- Treat missing context as a release-note audit gap: inspect the diff and linked
+  issue, draft the best accurate entry, and note the uncertainty for maintainer
+  review rather than inventing impact.
+- Add missed user-facing changes, remove internal-only noise, dedupe overlapping
+  PR/direct-commit entries, and sort each section from most to least interesting
+  for users.
 - Changelog entries should be user-facing, not internal release-process notes.
 - GitHub release and prerelease bodies must use the full matching
   `CHANGELOG.md` version section, not highlights or an excerpt. When creating
@@ -412,7 +437,7 @@ node --import tsx scripts/openclaw-npm-postpublish-verify.ts <published-version>
   - Hard rule: never run `op` directly in the main agent shell during release
     work. Any 1Password CLI use must happen inside that tmux session so prompts
     and alerts are contained and observable.
-  - Use the 1Password item `op://Private/Npmjs` for npm credentials and OTP.
+  - Use `$release-private` for the npm credentials and OTP item.
     Do not print passwords, tokens, or OTPs to the transcript; send them through
     tmux buffers, env vars scoped to the tmux command, or `expect` with
     `log_user 0`.
@@ -540,34 +565,42 @@ node --import tsx scripts/openclaw-npm-postpublish-verify.ts <published-version>
 6. Create `release/YYYY.M.D` from that post-changelog `main` commit.
 7. Make every repo version location match the beta tag before creating it.
 8. Commit release preparation changes on the release branch and push the branch.
-9. Run the fast local beta preflight from the release branch before any npm
-   preflight or publish. Keep expensive Docker, Parallels, and published-package
-   install/update lanes for after the beta is live unless the operator asks to
-   run them before beta publication.
-10. For beta releases, skip mac app build/sign/notarize unless beta scope or a
+9. Immediately dispatch Actions > `OpenClaw Performance` from `main` with
+   `target_ref=<release-sha>`, `profile=release`, `repeat=3`, deep profiling
+   off, live OpenAI off, and regression failure off. Let it run in parallel
+   with preflight and validation work.
+10. Run the fast local beta preflight from the release branch before any npm
+    preflight or publish. Keep expensive Docker, Parallels, and published-package
+    install/update lanes for after the beta is live unless the operator asks to
+    run them before beta publication.
+11. For beta releases, skip mac app build/sign/notarize unless beta scope or a
     release blocker specifically requires it. For stable releases, include the
     mac app, signing, notarization, and appcast path.
-11. Confirm the target npm version is not already published.
-12. Create and push the git tag from the release branch.
-13. Create or refresh the matching GitHub release.
-14. Dispatch Actions > `QA-Lab - All Lanes` against the release tag and wait
+12. Confirm the target npm version is not already published.
+13. Create and push the git tag from the release branch.
+14. Create or refresh the matching GitHub release.
+15. Dispatch Actions > `QA-Lab - All Lanes` against the release tag and wait
     for the mock parity, live Matrix, and live Telegram credentialed-channel
     lanes to pass.
-15. Start `.github/workflows/openclaw-npm-release.yml` from the release branch
+16. Start `.github/workflows/openclaw-npm-release.yml` from the release branch
     with `preflight_only=true`
     and choose the intended `npm_dist_tag` (`beta` default; `latest` only for
     an intentional direct stable publish). Wait for it to pass. Save that run id
     because the real publish requires it to reuse the prepared npm tarball.
-16. For stable releases, start `.github/workflows/macos-release.yml` in
+17. Before real publish, review the early performance run if it has completed.
+    Compare against earlier release evidence or clawgrit reports where
+    available. Call out minor regressions in the release proof; block on major
+    regressions unless waived or proven noisy.
+18. For stable releases, start `.github/workflows/macos-release.yml` in
     `openclaw/openclaw` and wait for the public validation-only run to pass.
-17. For stable releases, start
+19. For stable releases, start
     `openclaw/releases-private/.github/workflows/openclaw-macos-validate.yml`
     with the same tag and wait for the private mac validation lane to pass.
-18. For stable releases, start
+20. For stable releases, start
     `openclaw/releases-private/.github/workflows/openclaw-macos-publish.yml`
     with `preflight_only=true` and wait for it to pass. Save that run id because
     the real publish requires it to reuse the notarized mac artifacts.
-19. If any preflight or validation run fails, fix the issue on a new commit,
+21. If any preflight or validation run fails, fix the issue on a new commit,
     delete the tag and matching GitHub release, recreate them from the fixed
     commit, and rerun all relevant preflights from scratch before continuing.
     Never reuse old preflight results after the commit changes. For pushed or
@@ -575,15 +608,15 @@ node --import tsx scripts/openclaw-npm-postpublish-verify.ts <published-version>
     For preflight-only failures where npm did not publish the beta version,
     delete/recreate the same beta tag and prerelease at the fixed commit instead
     of skipping a prerelease number.
-20. Start `.github/workflows/openclaw-npm-release.yml` from the same branch with
+22. Start `.github/workflows/openclaw-npm-release.yml` from the same branch with
     the same tag for the real publish, choose `npm_dist_tag` (`beta` default,
     `latest` only when you intentionally want direct stable publish), keep it
     the same as the preflight run, and pass the successful npm
     `preflight_run_id`.
-21. Wait for `npm-release` approval from `@openclaw/openclaw-release-managers`.
-22. Run postpublish verification:
+23. Wait for `npm-release` approval from `@openclaw/openclaw-release-managers`.
+24. Run postpublish verification:
     `node --import tsx scripts/openclaw-npm-postpublish-verify.ts <published-version>`.
-23. Run the post-published beta verification roster. First scan current `main`
+25. Run the post-published beta verification roster. First scan current `main`
     for critical fixes that landed after the release branch cut; backport only
     important low-risk fixes before starting expensive lanes, or increment to
     the next beta if the fix must change the already-published package. If any
@@ -597,10 +630,10 @@ node --import tsx scripts/openclaw-npm-postpublish-verify.ts <published-version>
     If a pre-npm lane fails before any tag/package leaves the machine, fix and
     rerun the same intended beta attempt. Repeat up to the operator's
     authorized beta-attempt limit, normally 4.
-24. Announce the beta/stable release on Discord best-effort using the configured secret workflow.
-25. If the operator requested beta only, stop after beta verification and the
+26. Announce the beta/stable release on Discord best-effort using the configured secret workflow.
+27. If the operator requested beta only, stop after beta verification and the
     announcement.
-26. If the stable release was published to `beta`, use the light stable
+28. If the stable release was published to `beta`, use the light stable
     promotion roster when the matching beta already carried the full confidence
     pass: published npm postpublish verify, Docker install/update smoke,
     macOS-only Parallels install/update smoke, and required QA signal.
@@ -608,24 +641,24 @@ node --import tsx scripts/openclaw-npm-postpublish-verify.ts <published-version>
     `openclaw/releases-private/.github/workflows/openclaw-npm-dist-tags.yml`
     workflow to promote that stable version from `beta` to `latest`, then
     verify `latest` now points at that version.
-27. If the stable release was published directly to `latest` and `beta` should
+29. If the stable release was published directly to `latest` and `beta` should
     follow it, start that same private dist-tag workflow to point `beta` at the
     stable version, then verify both `latest` and `beta` point at that version.
-28. For stable releases, start
+30. For stable releases, start
     `openclaw/releases-private/.github/workflows/openclaw-macos-publish.yml`
     for the real publish with the successful private mac `preflight_run_id` and
     wait for success.
-29. Verify the successful real private mac run uploaded the `.zip`, `.dmg`,
+31. Verify the successful real private mac run uploaded the `.zip`, `.dmg`,
     and `.dSYM.zip` artifacts to the existing GitHub release in
     `openclaw/openclaw`.
-30. For stable releases, download `macos-appcast-<tag>` from the successful
+32. For stable releases, download `macos-appcast-<tag>` from the successful
     private mac run, update `appcast.xml` on `main`, and verify the feed. Merge
     or cherry-pick release branch changes back to `main` after stable succeeds.
-31. For beta releases, publish the mac assets only when intentionally requested;
+33. For beta releases, publish the mac assets only when intentionally requested;
     expect no shared production
     `appcast.xml` artifact and do not update the shared production feed unless a
     separate beta feed exists.
-32. After publish, verify npm and the attached release artifacts.
+34. After publish, verify npm and the attached release artifacts.
 
 ## GHSA advisory work
 

.agents/skills/release-openclaw-nightly/SKILL.md

@@ -0,0 +1,288 @@
+---
+name: release-openclaw-nightly
+description: "OpenClaw Tideclaw alpha/nightly release automation: isolated branches, local fixes, release CI, branch retention, and forward-port to main."
+---
+
+# Nightly Release
+
+Use for Tideclaw/OpenClaw alpha/nightly release automation, manual alpha triggers, beta prep, release-branch repair, and post-release forward-port. Load `$release-private` if it exists before using Tideclaw host paths, cron ids, or Discord routing ids.
+
+## Policy
+
+- Alpha/nightly runs every 12h or by manual trigger.
+- Beta is human-triggered from Discord from a proven alpha/release branch.
+- Stable/latest always needs explicit human confirmation.
+- Never publish from a dirty checkout or directly from `main`.
+- Main can be busy or broken; alpha work must be isolated so transient main failures do not block a usable nightly.
+- Publish only after release-branch proof is green.
+- After a successful alpha, forward-port release-branch commits back to `main` and prove main CI green.
+- Forward-port PRs contain only reusable fixes needed to make nightly/release checks pass. They must not contain alpha version bumps, release notes, changelog release entries, tags, generated artifacts, or state-file updates.
+- Keep only alpha/nightly branches from the last 3 days, plus any branch with an active run, open PR, or release tag.
+- Never run broad env/token dumps. For GitHub writes on the Tideclaw host, use the Tideclaw `gh` write wrapper below.
+
+## Identity
+
+Tideclaw should commit under its own machine identity on release branches and forward-port branches:
+
+```bash
+git config user.name "Tideclaw"
+git config user.email "tideclaw@openclaw.ai"
+```
+
+This is good for auditability if commits are clearly machine-authored and gated by CI. Avoid direct pushes to protected `main`; forward-port via PR/automerge unless the repo policy explicitly allows the bot to push after green checks. Include human `Co-authored-by` only when a human supplied the patch or explicit commit text.
+
+## Branch Shape
+
+- Branch prefix: `tideclaw/alpha/`
+- Branch name: `tideclaw/alpha/YYYY-MM-DD-HHMMZ`
+- Base: current `origin/main` SHA at trigger time.
+- State file: resolve from `$release-private` on the Tideclaw host.
+- Release tag: `vYYYY.M.D-alpha.N`
+- npm dist-tag: `alpha`
+
+Do not reuse old alpha branches for a new run. If rerunning the same base SHA, create a new timestamped branch and record why.
+
+## Start
+
+1. Work in the Tideclaw host checkout from `$release-private`.
+2. Fetch first:
+
+```bash
+git fetch origin main --tags --prune
+git switch main
+git merge --ff-only origin/main
+BASE_SHA="$(git rev-parse origin/main)"
+BRANCH="tideclaw/alpha/$(date -u +%Y-%m-%d-%H%MZ)"
+git switch -c "$BRANCH" "$BASE_SHA"
+```
+
+3. Read repo release docs/scripts before changing anything:
+   - `AGENTS.md`
+   - release docs under `docs/`
+   - release scripts under `scripts/`
+   - `.github/workflows/*release*`
+4. Compare `$BASE_SHA` with the last successful alpha state and current git/npm/GitHub alpha tags. If already released, report skip and do not publish.
+
+Manual trigger:
+
+```bash
+CRON_ID="<from release-private>"
+OPENCLAW_ALLOW_ROOT=1 openclaw cron run "$CRON_ID" --expect-final --timeout 21600000
+```
+
+## Discord Alpha Trigger
+
+Tideclaw may run alpha immediately from Discord when a maintainer mentions Tideclaw in `#releases` or `#maintainers`.
+
+Accepted shapes:
+
+```text
+@Tideclaw run alpha now
+@Tideclaw alpha release from main now
+@Tideclaw trigger alpha
+```
+
+Rules:
+
+1. Treat this as a manual alpha trigger equivalent to the alpha cron job.
+2. Start from current `origin/main` and create a fresh `tideclaw/alpha/YYYY-MM-DD-HHMMZ` branch.
+3. Follow the normal alpha workflow: reuse prior fixes, run local checks, fix on the alpha branch, run release CI, publish alpha after green gates, then forward-port reusable fixes via fixes-only PR.
+4. If another alpha/beta/stable release run is already active, report the active branch/run and stop.
+5. `#maintainers` trigger requires an explicit Tideclaw mention; do not react to unmentioned release chatter there.
+6. Resolve Discord role/user ids and live host hotfix notes from `$release-private`.
+
+## Discord Beta Trigger
+
+Tideclaw may run beta releases from `#releases` or mentioned `#maintainers` commands only when a maintainer sends an explicit beta trigger. Treat this as human approval for beta, not for stable/latest.
+
+Accepted shapes:
+
+```text
+@Tideclaw beta release from vYYYY.M.D-alpha.N
+@Tideclaw beta release from tideclaw/alpha/YYYY-MM-DD-HHMMZ
+@Tideclaw beta release from latest proven alpha
+```
+
+Rules:
+
+1. Require the words `beta release` and a source alpha tag/branch, or `latest proven alpha`.
+2. If the source is ambiguous, ask one clarifying question in `#releases` and stop.
+3. Verify the source alpha first: GitHub release, npm `alpha` package, release CI, recorded state file, and branch/tag SHA.
+4. Create a fresh beta branch `tideclaw/beta/YYYY-MM-DD-HHMMZ` from the proven alpha source, not directly from a moving `main`.
+5. Reuse/squash only stabilization fixes already proven on alpha. Do not import unrelated alpha release mechanics unless the beta release docs require them.
+6. Compute beta as `vYYYY.M.D-beta.N`, matching npm `--tag beta`.
+7. Run beta release validation/preflight/full release CI and fix failures on the beta branch.
+8. Publish beta only after green beta gates. Use GitHub Actions/OIDC, never direct npm publish from the host.
+9. Final Discord summary must include source alpha, beta tag/version, branch, fix commits, workflow run IDs, npm/GitHub proof, and any skipped/blocked reason.
+10. After beta publishes, forward-port reusable fixes to `main` using the same fixes-only PR rules below.
+
+## Reuse Prior Fixes
+
+Before running checks, mine recent Tideclaw alpha branches for fixes already made during previous release attempts:
+
+1. Read the Tideclaw state file from `$release-private` for the last successful alpha branch and fix commit SHAs.
+2. List recent remote branches:
+
+```bash
+git for-each-ref refs/remotes/origin/tideclaw/alpha --format='%(refname:short) %(committerdate:iso-strict)'
+```
+
+3. Consider only Tideclaw alpha branches from the last 3 days plus the last successful alpha branch.
+4. For each candidate branch, inspect commits that are not in current `origin/main`:
+
+```bash
+git log --no-merges --reverse --format='%H%x09%s' origin/main..origin/tideclaw/alpha/YYYY-MM-DD-HHMMZ
+```
+
+5. Cherry-pick only real stabilization fixes that still apply to the new alpha branch. Prefer commits recorded as `fixCommitShas` in the state file.
+6. Skip version bumps, changelog release entries, tag artifacts, generated release notes, state-file-only commits, and one-off debug instrumentation.
+7. If a cherry-pick conflicts, inspect whether current main already contains an equivalent fix. If not, resolve minimally and keep the commit message clear.
+8. Record reused commit SHAs separately from newly authored fix SHAs in the alpha state and final Discord summary.
+
+Use `git cherry`, `git range-diff`, and targeted test reruns to avoid duplicating fixes already present on `main`.
+
+## Repair Loop
+
+Use the branch as a release-candidate repair surface:
+
+1. Run narrow local checks first: changed tests, release preflight, type/lint/build gates required by release docs.
+2. If local checks fail, fix on the alpha branch with minimal commits.
+3. Commit each coherent fix as Tideclaw.
+4. Re-run the failed local check after each fix.
+5. Do not hide failures by editing baselines, expected-failure lists, ignore files, or release inventory unless the release docs explicitly require it and the diff is justified.
+6. If a failure is flaky, rerun once; if still red, treat it as real.
+7. If the fix is clearly useful for main, keep it small and forward-portable. Avoid broad refactors during alpha stabilization.
+
+Commit examples:
+
+```bash
+git add <files>
+git commit -m "fix: stabilize alpha release preflight"
+git push -u origin "$BRANCH"
+```
+
+## Release CI
+
+After local proof:
+
+1. Compute the next `vYYYY.M.D-alpha.N` from existing git tags, npm versions, and GitHub releases.
+2. Make the alpha branch package version and release metadata match that tag, commit it, and push the branch.
+3. Run release validation from the alpha branch, using GitHub CLI, not browser/fetch tools. On the Tideclaw host, bare `gh` is a read-only Codex sandbox wrapper; use `/usr/local/bin/gh-tideclaw-write` for write-capable commands such as `workflow run`, `run cancel`, and publish dispatch:
+
+```bash
+GH="/usr/local/bin/gh-tideclaw-write"
+SHA="$(git rev-parse HEAD)"
+TAG="v$(node -p "require('./package.json').version")"
+BRANCH="$(git branch --show-current)"
+
+"$GH" workflow run full-release-validation.yml --repo openclaw/openclaw --ref "$BRANCH" \
+  -f ref="$BRANCH" \
+  -f release_profile=beta \
+  -f rerun_group=all
+
+"$GH" workflow run openclaw-npm-release.yml --repo openclaw/openclaw --ref "$BRANCH" \
+  -f tag="$SHA" \
+  -f preflight_only=true \
+  -f npm_dist_tag=alpha
+```
+
+4. Watch the exact workflow run IDs and head SHA with `gh run list`, `gh run view`, and `gh api`. Read-only `gh` is fine for polling; use `$GH` only when a command mutates GitHub. Do not use Codex browser/fetch for GitHub API polling; prior Tideclaw runs failed there after successful preflight.
+5. For alpha, blocking gates are the ones Tideclaw can repair directly or that prove package safety: normal CI, plugin prerelease, npm preflight, package preparation, install smoke, tag/reachability, and publish verification. Treat cross-OS, live channel, QA Lab, package acceptance, long Docker E2E, and Telegram package E2E failures as advisory; report them in Discord and continue if the blocking gates are green.
+   - If `rerun_group=all` is stuck only on advisory lanes after CI, plugin prerelease, npm preflight, package preparation, and install smoke are green, dispatch a focused Full Release Validation on the same head with `-f rerun_group=install-smoke`. Use that successful focused Full Release Validation run as the publish proof, and include the separate CI/plugin/full advisory run IDs in the Discord summary.
+6. If a blocking gate fails, fix on the alpha branch, push, and rerun only the failed or required release CI. If the commit changes, discard old preflight/full-validation run IDs and rerun them for the new head.
+7. After full validation and npm preflight are green on the same branch head, create and push the release tag from that exact commit:
+
+```bash
+git tag -a "$TAG" "$SHA" -m "openclaw ${TAG#v}"
+git push origin "$TAG"
+```
+
+8. Dispatch the publish wrapper from the same alpha branch. Use the successful npm preflight run ID and full release validation run ID from the same head SHA:
+
+```bash
+"$GH" workflow run openclaw-release-publish.yml --repo openclaw/openclaw --ref "$BRANCH" \
+  -f tag="$TAG" \
+  -f preflight_run_id="$NPM_PREFLIGHT_RUN_ID" \
+  -f full_release_validation_run_id="$FULL_RELEASE_VALIDATION_RUN_ID" \
+  -f npm_dist_tag=alpha \
+  -f plugin_publish_scope=all-publishable \
+  -f publish_openclaw_npm=true \
+  -f release_profile=beta \
+  -f wait_for_clawhub=false
+```
+
+9. Watch the publish wrapper plus child runs. If `openclaw-npm-release.yml` is waiting on the `npm-release` environment and Tideclaw cannot approve it, report that as the only blocker; do not call the release done.
+10. Do not publish npm directly from the host; use GitHub Actions/OIDC.
+
+Important: `openclaw-npm-release.yml` with `preflight_only=true` only prepares artifacts. It does not publish. A successful alpha requires the later `openclaw-release-publish.yml` wrapper, a pushed git tag, npm `alpha` dist-tag proof, and a GitHub prerelease.
+
+## Verify Published Alpha
+
+Release is not done until all are true:
+
+- GitHub tag exists.
+- GitHub Release exists and is marked prerelease.
+- Release body links npm version page, registry tarball, integrity, and CI/proof.
+- `npm view openclaw@<version>` shows the exact version, dist-tag `alpha`, tarball, integrity, and publish time.
+- Installed/package smoke follows repo release docs.
+- The Tideclaw state file from `$release-private` records version, tag, base SHA, branch, fix commit SHAs, workflow run IDs, npm integrity, and timestamp.
+
+Final Discord summary in `#releases`:
+
+- tag/version
+- base SHA
+- branch
+- fix commits
+- workflow run IDs
+- npm/GitHub proof
+- skipped/blocked reason if not released
+
+Use Discord-safe Markdown links with angle-bracket targets. Never print secrets.
+
+## Forward-Port
+
+After a successful alpha, raise a fixes-only PR back to `main`:
+
+1. Create/update a forward-port branch from current `origin/main`:
+
+```bash
+git fetch origin main --prune
+git switch -c "tideclaw/forward-port/$(date -u +%Y-%m-%d-%H%MZ)" origin/main
+```
+
+2. Cherry-pick only release-branch commits that are real fixes required to make nightly/release checks pass.
+3. Exclude alpha version bumps, changelog release entries, release notes, tag artifacts, generated release assets, state-file-only commits, and any commit whose only purpose was publishing the alpha.
+4. If a commit mixes a real fix with release/version changes, split it: replay only the fix hunks into a new commit on the forward-port branch.
+5. Resolve conflicts in favor of the minimal main-compatible fix.
+6. Run the relevant changed/local gate.
+7. Push and open a PR, or use the repo’s allowed bot merge path.
+8. Wait for required main CI to go green. If CI fails, fix on the forward-port branch and rerun.
+9. Report the PR/merge SHA and any commits intentionally not forward-ported.
+
+If `origin/main` is independently red before the forward-port, document the unrelated failing check and still keep the forward-port PR green against its head when possible.
+
+## Branch Retention
+
+Before and after each run, prune old alpha branches:
+
+1. List `origin/tideclaw/alpha/*`.
+2. Keep branches whose timestamp is within the last 3 days UTC.
+3. Keep branches referenced by a live workflow run, open PR, release tag, or state file.
+4. Delete only Tideclaw-owned alpha branches:
+
+```bash
+git push origin --delete tideclaw/alpha/YYYY-MM-DD-HHMMZ
+```
+
+Never delete human branches, beta branches, stable branches, or unknown prefixes.
+
+## Stop Conditions
+
+Stop and report clearly if:
+
+- release docs/scripts disagree on versioning or publish path
+- required secrets/auth are unavailable
+- GitHub Actions cannot be dispatched or observed
+- a required release gate stays red after a real fix attempt
+- npm/GitHub state disagrees after publish
+- forward-port cannot be made green without a larger product decision

.agents/skills/release-openclaw-plugin-testing/SKILL.md

@@ -1,5 +1,5 @@
 ---
-name: openclaw-pre-release-plugin-testing
+name: release-openclaw-plugin-testing
 description: Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E, Package Acceptance, and Testbox proof.
 ---
 

.agents/skills/release-openclaw-plugin-testing/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "OpenClaw Plugin Pre-Release Testing"
+  short_description: "Plan plugin release validation"
+  default_prompt: "Use $release-openclaw-plugin-testing to plan or run pre-release OpenClaw plugin validation across package, lifecycle, doctor, gateway, SDK, and live-ish proof."

.agents/skills/technical-documentation/SKILL.md

@@ -0,0 +1,79 @@
+---
+name: technical-documentation
+description: Build and review high-quality technical docs as well as agent instruction files in your repository.
+license: MIT
+metadata:
+  source: "https://github.com/vincentkoc/dotskills"
+---
+
+# Technical Documentation
+
+## Purpose
+
+Produce and review technical documentation that is clear, actionable, and maintainable for both humans and agents, including contributor-governance files and agent instruction files.
+
+## When to use
+
+- Creating or overhauling docs in an existing product/codebase (brownfield).
+- Building evergreen docs meant to stay accurate and reusable over time.
+- Reviewing doc diffs for structure, clarity, and operational correctness.
+- Running full-repo documentation audits that must include both governance files and product docs surfaces (`docs/`, `README*`, `.md/.mdx/.mdc`, Fern/Sphinx/Mintlify-style sources).
+- Updating or reviewing AGENTS.md and/or CONTRIBUTING.md to keep agent and contributor workflows aligned with current repo practices.
+- Improving repository onboarding/docs that include contribution instructions, issue templates, PR flow, and review gates.
+- Designing governance documentation strategy for repos with alias instruction files (for example `CLAUDE.md`, `AGENT.md`, `.cursorrules`, `.cursor/rules/*`, `.agent/`, `.agents/`, `.pi/`) where `AGENTS.md` is treated as canonical when present and aliases should be kept as compatibility surfaces.
+- Diagnosing agent-file drift where teams had to prompt iteratively to surface missing files, broken commands, or policy conflicts.
+- Applying repository-specific documentation overlays, including OpenClaw page-type, docs IA, preservation, and validation rules when present.
+
+## Workflow
+
+1. Classify task: `build` or `review`; context: `brownfield` or `evergreen`.
+2. Inventory full documentation scope early (governance + product docs): AGENTS/CONTRIBUTING/aliases plus docs directories, framework sources, and root/module READMEs.
+3. Detect multilingual scope (README/docs in multiple languages) and define required parity level.
+4. Read `references/agent-and-contributing.md` for agent instruction and `CONTRIBUTING.md` workflow rules (inventory, canonical/alias mapping, dual-mode balance, deliverable standards, and precedence/conflict handling).
+5. Read `references/principles.md` for the governing ruleset (Matt Palmer & OpenAI).
+6. For OpenClaw docs work, read `references/openclaw.md` before the build/review playbook.
+7. For build tasks, follow `references/build.md`.
+8. For review tasks, follow `references/review.md` and proactively detect issues without waiting for repeated prompts.
+9. For complex or high-risk tasks (build or review), it is acceptable to run longer, deeper, and more exhaustive investigations when needed for confidence.
+10. When available, use sub-agents for bounded parallel discovery/review work, then merge outputs into one coherent final deliverable.
+11. Use `references/tooling.md` when platform/tooling choices affect recommendations.
+12. Run a proactive issue sweep for both governance and docs-content surfaces, and fix high-confidence defects in the same pass unless explicitly asked for report-only mode.
+13. In brownfield mode, prioritize compatibility with current docs IA, tooling, and release state.
+14. In evergreen mode, prioritize timeless wording, update strategy, and durable structure.
+15. Return deliverables plus validation notes, parity status, and remaining gaps.
+
+## Sub-agent orchestration guidance
+
+Prefer sub-agents when the repo is large or the requested change set is broad; use them by default for repo-wide, multi-framework, or high-conflict work.
+
+- `inventory-agent` -> `agents/inventory-agent.md` (`fast` / Claude `haiku`): file/config discovery, coverage map, and missing-path checks.
+- `governance-agent` -> `agents/governance-agent.md` (`thinking` / Claude `sonnet`): AGENTS/CONTRIBUTING/alias precedence, conflicts, and policy drift.
+- `docs-framework-agent` -> `agents/docs-framework-agent.md` (`thinking` / Claude `sonnet`): framework config, relative path base, and file-path vs URL-path mapping checks.
+- `synthesis-agent` -> `agents/synthesis-agent.md` (`long` / Claude `opus`): merge sub-agent outputs into one prioritized fix plan and unified precedence model.
+
+## Inputs
+
+- Doc type (tutorial, how-to, reference, explanation) and audience.
+- File scope or diff scope.
+- Docs framework/tooling constraints (Fern, Mintlify, Sphinx, etc.).
+- Build/review mode and brownfield/evergreen intent.
+- Target agent and human compatibility intent.
+- Docs framework surfaces in scope (for example Fern, Sphinx, Mintlify, Markdown/MDX/MDC/RST/RSC files).
+- Desired investigation depth/time budget (quick pass vs exhaustive review).
+- Execution mode (`single-agent` or `sub-agent-assisted` when available).
+- Remediation mode (`apply-fixes` by default, or `report-only` when requested).
+- Multilingual scope: source-of-truth language, target locales, and parity expectations.
+- Repository-specific overlay constraints, if any.
+
+## Outputs
+
+- Updated draft or review findings with clear next actions.
+- Validation notes (what was checked, what remains).
+- Navigation/maintenance recommendations for long-term quality.
+- Governance-doc alignment summary when AGENTS/CONTRIBUTING were touched.
+- Agent instruction-surface map (primary file, alias files, Codex/Claude/Cursor handling plan).
+- Documentation-surface coverage map (what was reviewed under `/docs`, README hierarchy, and framework-specific source trees).
+- Autodetected issue list with applied fixes (or explicit report-only findings).
+- Delegation notes when sub-agents were used (scope delegated and how findings were merged).
+- Multilingual parity note (in-sync, partial with rationale, or intentionally divergent).
+- Repository-specific overlay notes when one was used.

.agents/skills/technical-documentation/agents/docs-framework-agent.md

@@ -0,0 +1,32 @@
+---
+name: docs-framework-agent
+description: Thinking-focused docs framework checker for config-relative paths and route/file mapping consistency.
+model: sonnet
+tools:
+  - Read
+  - Glob
+  - Grep
+permissionMode: default
+maxTurns: 10
+---
+
+You are the docs-framework sub-agent for technical documentation.
+
+Goals:
+
+- validate framework config-driven docs behavior
+- prevent path-mapping drift between source files and published routes
+
+Tasks:
+
+- detect and read framework config first (Fern/Sphinx/Mintlify/custom)
+- resolve paths relative to the declaring file/config
+- validate both maps:
+  - config -> file exists
+  - config/nav/routing -> URL path is valid and consistent
+
+Return:
+
+- config files reviewed
+- path assumptions made
+- mismatches (`missing file`, `stale route`, `wrong base path`)

.agents/skills/technical-documentation/agents/governance-agent.md

@@ -0,0 +1,30 @@
+---
+name: governance-agent
+description: Thinking-focused governance reviewer for AGENTS/CONTRIBUTING/alias precedence, conflict detection, and policy drift analysis.
+model: sonnet
+tools:
+  - Read
+  - Glob
+  - Grep
+permissionMode: default
+maxTurns: 10
+---
+
+You are the governance sub-agent for technical documentation.
+
+Goals:
+
+- validate AGENTS/CONTRIBUTING/alias alignment and precedence
+- identify policy drift and conflicting instructions
+
+Tasks:
+
+- determine canonical instruction source and alias compatibility mapping
+- detect conflicts across nested scope files and tool-specific rule consumers
+- validate command examples against stated governance expectations
+
+Return:
+
+- precedence model
+- conflict list with severity
+- recommended low-risk remediations

.agents/skills/technical-documentation/agents/inventory-agent.md

@@ -0,0 +1,31 @@
+---
+name: inventory-agent
+description: Fast repo-surface discovery for technical documentation audits. Use for coverage mapping and missing-path detection before deeper review.
+model: haiku
+tools:
+  - Read
+  - Glob
+  - Grep
+  - LS
+permissionMode: default
+maxTurns: 6
+---
+
+You are the inventory sub-agent for technical documentation.
+
+Goals:
+
+- enumerate governance and docs-content surfaces in scope
+- detect missing files, broken references, and obvious command/path failures
+
+Tasks:
+
+- map `AGENTS.md`/`CONTRIBUTING.md`/aliases and docs surfaces (`docs/**`, README hierarchy, `.md/.mdx/.mdc/.rst/.rsc`)
+- list framework config files discovered (Fern/Sphinx/Mintlify or equivalent)
+- report hard failures only, with exact file paths
+
+Return:
+
+- coverage map
+- missing/broken path list
+- unresolved blockers

.agents/skills/technical-documentation/agents/openai.yaml

@@ -0,0 +1,10 @@
+interface:
+  display_name: "Technical Documentation"
+  short_description: "Build and review technical documentation for brownfield and evergreen systems."
+  icon_small: "./assets/icon.jpg"
+  icon_large: "./assets/icon.jpg"
+  brand_color: "#111827"
+  default_prompt: "Build or review technical documentation with a clear, maintainable, and production-ready workflow."
+
+policy:
+  allow_implicit_invocation: true

.agents/skills/technical-documentation/agents/synthesis-agent.md

@@ -0,0 +1,28 @@
+---
+name: synthesis-agent
+description: Long-context synthesis agent that merges sub-agent outputs into one prioritized and deduplicated documentation action plan.
+model: opus
+tools:
+  - Read
+permissionMode: default
+maxTurns: 12
+---
+
+You are the synthesis sub-agent for technical documentation.
+
+Goal:
+
+- merge sub-agent outputs into one coherent, non-duplicated action plan
+
+Tasks:
+
+- prioritize blockers first, then non-blocking improvements
+- normalize to one precedence model for governance decisions
+- remove duplicated recommendations and contradictory fixes
+- keep final output concise and execution-ready
+
+Return:
+
+- prioritized fix plan
+- validation summary (done vs pending)
+- explicit remaining gaps/blockers

.agents/skills/technical-documentation/references/agent-and-contributing.md

@@ -0,0 +1,145 @@
+# AGENT and CONTRIBUTING Principles
+
+This reference consolidates the core rules for agent-policy and contributor-governance docs.
+
+You must:
+
+1. Discover repo-level and nested instruction files with:
+   `rg --files -g 'AGENTS.md' -g 'CONTRIBUTING.md' -g 'CLAUDE.md' -g 'AGENT.md' -g '.cursor/rules/*' -g '.cursorrules' -g '.agent/**' -g '.agents/**' -g '.pi/**' -g 'AGENTS.*.md'`
+2. Read the root and nearest-scope `AGENTS.md`/`CONTRIBUTING.md` pair before editing.
+3. If alias files exist, normalize to one canonical source (`AGENTS.md` preferred when present; otherwise nearest alias), plus compatibility pointers or explicit symlink notes.
+4. Document conflicting instructions and precedence decisions.
+
+## GitHub + AGENTS baseline
+
+Source: https://docs.github.com/en/communities/setting-up-your-project-for-healthy-contributions/setting-guidelines-for-repository-contributors
+Source: https://agents.md/
+Source: https://github.blog/ai-and-ml/github-copilot/how-to-write-a-great-agents-md-lessons-from-over-2500-repositories/
+Source: https://cobusgreyling.substack.com/p/what-is-agentsmd
+Source: https://www.infoq.com/news/2025/08/agents-md/
+
+Use these as default operating principles:
+
+1. Keep `CONTRIBUTING.md` discoverable and actionable (`.github`, root, or `docs`).
+2. Keep agent instructions concrete: real commands, real paths, clear boundaries.
+3. Use explicit behavior boundaries for agents: `Always`, `Ask first`, `Never`.
+4. Keep contributor and agent rules aligned with actual repository workflows.
+5. Ensure clear guidance is provided to agents on if, when and how to raise issues and pull requests.
+
+## Canonical and alias policy
+
+Source: https://agents.md/
+Source: https://github.blog/ai-and-ml/github-copilot/how-to-write-a-great-agents-md-lessons-from-over-2500-repositories/
+
+1. Treat `AGENTS.md` as canonical when present.
+2. If `AGENTS.md` is absent, treat the nearest alias file as canonical.
+3. Keep compatibility surfaces explicit: `AGENTS.md`, `AGENT.md`, `.cursorrules`, `.cursor/rules/*`, `.agent/`, `.agents/`, `.pi/`.
+4. If aliases are used, document how they map back to canonical policy (or symlink when supported).
+5. When repos use `.agents/` as canonical rule storage, keep `.cursor` as a compatibility symlink to `.agents` for Cursor rule auto-loading.
+6. Keep policy DRY: store one shared policy core and expose it via aliases/symlinks instead of duplicating rule text.
+
+## Context-awareness by agent platform
+
+Source: https://github.com/vercel-labs/agent-skills/blob/main/AGENTS.md
+Source: https://github.com/openai/codex/blob/main/AGENTS.md
+
+1. For Cursor and Claude-style glob consumers, keep rule files narrow and bounded.
+2. Avoid over-referencing large path sets that inflate context for glob-based agents.
+3. For Codex-style workflows, prefer explicit file references and deterministic commands.
+4. Keep long runbooks outside top-level policy files; link to scoped docs.
+5. Ensure all agents have a happy path regardless so ensuring everything works across Codex, Claude and other coding agents.
+
+## Symlink and compatibility operations
+
+1. Preferred layout for multi-agent compatibility:
+   - canonical rule directory: `.agents/`
+   - Cursor compatibility path: `.cursor -> .agents` symlink
+   - canonical policy doc: `AGENTS.md` pointing to `.agents` paths where relevant
+2. Validate symlink state before finalizing changes:
+   - if `.agents/` exists and `.cursor` is missing, create `.cursor` symlink to `.agents`
+   - if `.cursor` is a symlink to another target, fix target or document why it must differ
+   - if `.cursor` is a real directory/file, treat as migration conflict and ask before replacement
+3. Validate rule payload through the canonical directory:
+   - rules: `.agents/rules/*.mdc` with valid frontmatter (`description`, `globs`, `alwaysApply` as needed)
+   - commands: `.agents/commands/*.md` when command routing is used
+   - MCP config: `.agents/mcp.json` when MCP is in scope
+4. Keep Codex behavior explicit:
+   - `AGENTS.md` is primary for Codex repository instructions
+   - `.cursor` compatibility is for Cursor auto-loading and does not replace canonical AGENTS policy
+5. Record applied symlink fixes and unresolved compatibility gaps in validation notes.
+
+## Dual-mode and deliverable standards
+
+Source: https://github.blog/ai-and-ml/github-copilot/how-to-write-a-great-agents-md-lessons-from-over-2500-repositories/
+Source: https://agents.md/
+Source: https://github.com/openai/codex/blob/main/AGENTS.md
+Source: https://github.com/vercel-labs/agent-skills/blob/main/AGENTS.md
+
+1. Author one shared policy core (same commands, boundaries, and precedence) for all agents.
+2. For Cursor/Claude-style agents, expose that core through glob-driven and bounded files (small `AGENTS.md`/rule surface).
+3. For Codex, expose that same core through explicit file references with precise scope.
+4. Where styles diverge, prefer the smallest common structure that satisfies both and avoid duplicating policy text.
+5. Treat AGENTS/CONTRIBUTING as first-class deliverables when in scope.
+6. Preserve required structure, constraints, and examples from existing files.
+7. Align wording and commands with active repository instructions.
+
+## Proactive issue discovery and remediation
+
+Source: https://github.blog/ai-and-ml/github-copilot/how-to-write-a-great-agents-md-lessons-from-over-2500-repositories/
+Source: https://github.com/openai/codex/blob/main/AGENTS.md
+Source: https://github.com/vercel-labs/agent-skills/blob/main/AGENTS.md
+
+1. Run a conflict matrix review across AGENTS/aliases/CONTRIBUTING and related command/rule docs before finalizing.
+2. Treat the following as high-priority defects: missing referenced files, non-existent setup commands, command scope mismatches, and branch/commit policy conflicts.
+3. Do not stop at caveat-only notes when a low-risk fix is clear; apply the fix in the same pass.
+4. If a canonical entry file is missing (for example a directory `README.md` that docs depend on), create a minimal actionable file and update references.
+5. Long-running investigations are acceptable when needed to uncover cross-file drift, especially in agent-instruction ecosystems.
+
+## Discovery
+
+1. Agents prefer simple terminal commands so having a well defined `make *` or `npm run *` is ideal
+2. Agents can discover terminal commands through shell completion so providing shell completion helps
+
+## CONTRIBUTING size and scope control
+
+Source: https://contributing.md/how-to-build-contributing-md/
+Source: https://blog.codacy.com/best-practices-to-manage-an-open-source-project
+Source: https://mozillascience.github.io/working-open-workshop/contributing/
+Source: https://github.com/openclaw/openclaw/blob/main/CONTRIBUTING.md
+
+1. Keep root `CONTRIBUTING.md` focused on setup, issue flow, PR flow, testing, and review gates.
+2. Use issue/PR template links instead of embedding every process detail inline.
+3. When the file grows too large, split by domain and link from root.
+4. Move any large content into docs if avalible (for example Mintlify/Fern/Sphinx workflows) to avoid large contributor guide.
+5. Optimize for agent/machine readability as well as humans.
+
+## Example repos to emulate
+
+Source: https://github.com/openclaw/openclaw/blob/main/AGENTS.md
+Source: https://github.com/openclaw/openclaw/blob/main/CONTRIBUTING.md
+Source: https://github.com/openclaw/openclaw/blob/main/VISION.md
+Source: https://github.com/openai/codex/blob/main/AGENTS.md
+Source: https://github.com/processing/p5.js/blob/main/AGENTS.md
+Source: https://github.com/vercel-labs/agent-skills/blob/main/AGENTS.md
+Source: https://github.com/agentsmd/agents.md/blob/main/AGENTS.md
+Source: https://github.com/rails/rails/blob/main/CONTRIBUTING.md
+Source: https://github.com/kubernetes/kubernetes/blob/master/CONTRIBUTING.md
+Source: https://github.com/atom/atom/blob/master/CONTRIBUTING.md
+Source: https://github.com/github/docs/blob/main/CONTRIBUTING.md
+Source: https://github.com/facebook/react/blob/main/CONTRIBUTING.md
+
+1. OpenClaw: strong real-world alias policy and AGENTS/CONTRIBUTING/VISION cohesion.
+2. OpenAI Codex: strict command discipline and explicit scope control.
+3. p5.js: explicit AI-policy guardrails in agent instructions.
+4. Vercel + agentsmd spec: compact, context-efficient AGENTS patterns.
+5. Rails/Kubernetes/Atom/GitHub Docs/React: contributor guidance patterns at different project scales.
+
+## Practical merge policy
+
+When these rules conflict:
+
+1. Preserve contributor and reader task success first.
+2. Preserve instruction clarity and unambiguous boundaries second.
+3. Preserve long-term maintainability and context-efficiency third.
+4. Add extra agent optimization only if it does not reduce human clarity or there is explict need.
+5. Use your judgement as the expert.

.agents/skills/technical-documentation/references/build.md

@@ -0,0 +1,116 @@
+# Build Docs Playbook
+
+Read `principles.md` first, then follow this execution flow.
+
+## 1. Detect and align agent instruction and governance instructions
+
+- Use `references/agent-and-contributing.md` as the source of truth for inventory, canonical/alias mapping, and precedence/conflict handling.
+- Apply the symlink compatibility policy when in scope (`.agents` canonical directory with `.cursor` compatibility symlink when required by tooling).
+- Long-running and extensive build investigations are acceptable when needed to resolve ambiguous or conflicting documentation sources.
+- When available, use sub-agents for bounded parallel inventory/cross-check tasks and merge results into one canonical decision set.
+- Capture required constraints before writing:
+  - nested-agent rules, command/test requirements, PR workflow, and style checks.
+- Use the same command and validation expectations in proposed snippets and examples.
+
+## 2. Inventory product documentation surfaces (not governance only)
+
+- For repo-wide builds, include docs content surfaces in addition to AGENTS/CONTRIBUTING.
+- Inventory docs files and frameworks in scope (examples): `README*.md`, `docs/**`, `**/*.md`, `**/*.mdx`, `**/*.mdc`, `**/*.rst`, `**/*.rsc`, Fern/Mintlify config, Sphinx `conf.py`.
+- Build a coverage map before drafting so governance and product docs are both represented.
+- If scope is ambiguous, default to broader docs discovery first, then narrow intentionally.
+
+## 3. Framework config and path mapping rules
+
+- Detect framework/config first (for example Fern config, Sphinx `conf.py`, Mintlify config, or equivalent).
+- Resolve every referenced path relative to the file/config that declares it, not assumed repo root.
+- Treat filesystem paths and published URL routes as separate mappings; do not infer one from the other without config evidence.
+- Validate both layers:
+  - config -> file exists on disk
+  - config/nav/routing -> URL path is consistent and reachable
+- Record path-mapping assumptions and mismatches in handoff (`missing file`, `stale route`, `wrong base path`).
+
+## 4. Define intent and success
+
+- Audience, prerequisites, and job-to-be-done.
+- Expected reader outcome immediately after completion.
+- Doc type: tutorial, how-to, reference, explanation.
+- Success criteria: what must be true after publish.
+
+## 5. Build structure before prose
+
+- Follow the funnel: what/why, quickstart, next steps.
+- Keep headings informative and scannable.
+- Open each section with the takeaway sentence.
+- Add decision points with concrete branch guidance.
+- For OpenClaw docs work, choose a page type from `references/openclaw.md` before drafting.
+- Keep task-critical OpenClaw configuration inline; link exhaustive defaults, enums, schemas, generated references, and rare debugging workflows.
+
+## 6. Build AGENTS.md and CONTRIBUTING.md intentionally
+
+- Keep AGENTS.md structure consistent with `agents.md` ecosystem patterns:
+  - include YAML frontmatter when present in repo style (`name`, `description`).
+  - state persona scope and explicit instruction boundaries: `Always`, `Ask first`, `Never`.
+  - include concrete commands and representative code examples.
+- For CONTRIBUTING.md, prioritize issue triage flow, PR expectations, setup/test commands, and review gates.
+- Add `Code of Conduct`, `Testing`, `Local checks`, and `PR expectations` sections when missing but required by the repo.
+- If CONTRIBUTING.md is becoming too large, split by scope into linked docs (for example, framework/tool-specific setup and release workflows) and keep the root file as a concise entry point.
+- Keep cross-file consistency: links from CONTRIBUTING.md to AGENTS.md (and vice versa) should be accurate and non-circular.
+- If multiple AGENTS.md files exist, document the directory-level scope and avoid conflicting advice.
+- If a required canonical entry file is missing (for example referenced `README.md` under a major directory), create the file in the same pass instead of adding a caveat-only note.
+- For new entry files, keep them minimal and actionable: purpose, prerequisites, concrete run commands, and pointers to deeper docs.
+
+## 7. Keep agent context tight
+
+- Author once, expose twice:
+  - keep one shared policy core and avoid duplicating guidance in separate agent-specific files.
+  - publish that core through bounded glob-friendly files for Cursor/Claude plus explicit path references for Codex.
+- For Cursor and Claude-style agents, avoid broad references. Use minimal globbing and narrow rule files that each serve one concern (for example, repo-wide setup, test rules, security checks).
+- Keep AGENTS and alias files short-to-medium; move detailed runbooks to linked docs.
+- For Codex, prefer explicit file references and concrete paths for exact reuse.
+- Avoid adding unrelated historical or process details to avoid token/context drift during future tool reads.
+
+## 8. Brownfield build mode
+
+- Match existing terminology, navigation, and component patterns.
+- Preserve existing IA unless there is a documented migration plan.
+- For rewrites, include a migration note from old to new paths.
+- Prefer smallest safe change set that improves utility.
+
+## 9. Evergreen build mode
+
+- Prefer stable concepts over release-tied narrative.
+- Isolate volatile details under clearly marked version sections.
+- Include maintenance signals: owners, refresh triggers, stale criteria.
+- Include lifecycle notes: deprecation and replacement paths.
+
+## 10. Writing constraints
+
+- Use precise language and short, imperative instructions.
+- Keep code examples copy-ready and self-contained.
+- Include common failure modes and safe defaults.
+- Avoid placeholder guidance that cannot be executed.
+
+## 11. Agent and automation readiness
+
+- Keep key facts in text (not image-only).
+- Prefer structured lists/tables when choices matter.
+- Add links and anchors that allow deterministic navigation.
+- Document what can be checked automatically in CI.
+
+## 12. Build validation
+
+- Validate commands and snippets where possible.
+- Verify links and references in changed sections.
+- Run a reference existence sweep for every path/command you introduced.
+- Verify docs-framework consistency when in scope (for example Sphinx/Fern config and referenced doc paths).
+- For OpenClaw docs work, apply the validation checklist in `references/openclaw.md`.
+
+## 13. Multilingual parity mode (when applicable)
+
+- Pick one source-of-truth language for technical accuracy and release timing.
+- Define parity target: full parity, staged parity, or intentional divergence per section.
+- Keep structure aligned across locales (headings, anchors, section order) when possible.
+- Preserve command/code correctness first; localize explanatory text second.
+- If parity is not feasible, add a visible note with missing scope and expected sync window.
+- Run a locale parity check for changed sections (added/removed steps, warnings, prerequisites).
+- Record unresolved checks explicitly in handoff.

.agents/skills/technical-documentation/references/openclaw.md

@@ -0,0 +1,128 @@
+# OpenClaw Documentation Overlay
+
+Use this reference only for OpenClaw docs work. It layers OpenClaw-specific page
+types, navigation, preservation, and validation rules on top of the general
+technical-documentation skill.
+
+## Reader Model
+
+- Lead with the task the reader is trying to complete.
+- Give one recommended path before alternatives.
+- Keep main docs focused on the common path; move dense contracts and rare
+  debugging detail to linked reference or troubleshooting pages.
+- Explain production risks exactly where the reader can make the mistake.
+- Link concepts, guides, references, CLI pages, SDK docs, testing, and
+  troubleshooting so readers can continue without rereading.
+
+## Page Types
+
+Choose the page type before writing or reviewing:
+
+- Overview: route readers to the right product area, integration path, or guide.
+- Quickstart: get a new user to a working result with the fewest safe steps.
+- Topic page: explain a major OpenClaw entity or surface end to end.
+- Guide: walk through one workflow from prerequisites to production readiness.
+- API/SDK/CLI reference: define every object, method, command, option, response,
+  error, enum, default, and version rule in scope.
+- Testing guide: show sandbox setup, fixtures, simulated failures, and live-mode
+  differences.
+- Troubleshooting guide: map observable symptoms to checks, causes, and fixes.
+- Governance file: keep agent/contributor policy concrete, scoped, and aligned
+  with current OpenClaw repo behavior.
+
+## Topic Pages
+
+Use this shape for major-entity pages:
+
+1. Title naming the entity or surface.
+2. Unheaded opening that says what it is, what it owns, and what it does not own.
+3. Requirements, only when setup needs accounts, versions, permissions, plugins,
+   operating systems, or credentials.
+4. Quickstart with the recommended path and smallest reliable verification.
+5. Configuration with task-critical options inline and exhaustive details linked
+   to reference docs.
+6. Major subtopics organized by reader intent, not under a generic "Subtopics"
+   heading.
+7. Troubleshooting with observable failures and concrete checks.
+8. Related links to guides, references, commands, concepts, and adjacent topics.
+
+## Guides
+
+Use this shape for workflow pages:
+
+1. Title naming the outcome, not the implementation detail.
+2. Opening that states what the reader can accomplish.
+3. Before you begin: accounts, keys, permissions, versions, tools, and
+   assumptions.
+4. Choose a path, only when the reader must decide.
+5. Steps with verb-led headings, commands, expected output, and checks.
+6. Test with the smallest reliable proof that the workflow works.
+7. Production readiness: security, retries, limits, observability, migrations,
+   and cleanup.
+8. Troubleshooting near the workflow that causes the failures.
+9. See also links to concepts, references, SDK docs, and adjacent guides.
+
+## Docs IA And Navigation
+
+- Read `docs/docs.json` before navigation changes.
+- Keep topic pages and common workflows on the main reader path.
+- Put exhaustive contracts, generated references, maintainer-only detail, and
+  support material under `Reference` or another clearly scoped support page.
+- Keep generated `plugins/reference/*` children and redirect-only pages out of
+  visible navigation unless explicitly required.
+- For moved pages, include a keep/drop/move/destination matrix in the handoff.
+- Add "Read when" hints for docs-list routing when creating or changing pages
+  that participate in the docs index.
+
+## Source-Backed Content
+
+- CLI docs must match current flags, output, errors, and examples.
+- API/SDK docs must include fields, defaults, enum values, constraints, nullable
+  behavior, lifecycle states, errors, and recovery guidance.
+- Config docs must align exported types, schema/help output, metadata, baselines,
+  and current docs.
+- Dependency-backed behavior must be verified from upstream docs, source, or
+  types before documenting defaults, timing, errors, or API behavior.
+- Separate current behavior, shipped behavior, planned behavior, and maintainer
+  intent.
+
+## Examples
+
+- Prefer complete copy-pasteable commands and snippets.
+- Use realistic variable names and values.
+- Mark placeholders with angle-bracket names such as `<API_KEY>`.
+- Show expected success output when it helps verification.
+- Keep one conceptual unit per code block and use language-specific fences.
+- Avoid examples that hide setup, auth, error handling, or cleanup.
+- Never expose real secrets, live config, phone numbers, private videos, or
+  credentials.
+
+## Preservation Reviews
+
+For rewrites or splits:
+
+- Identify source units before rewriting: headings, paragraphs, tables, examples,
+  CLI/API contracts, warnings, and troubleshooting facts.
+- Map each retained unit to a destination page or section.
+- Do not treat a broad "covered" row as proof for dense source material; use
+  line- or claim-level evidence when the source unit is dense.
+- For dropped content, state whether it is obsolete, duplicated elsewhere,
+  unsupported, or moved to a reference/support page.
+- When a docs-audit artifact is used, verify it is mapped audit data with
+  non-empty `mappings[]`, not only inventory or reindexed JSON.
+
+## Validation
+
+Choose the narrowest proof that covers the touched surface:
+
+- `pnpm docs:list`
+- `pnpm docs:check-mdx`
+- `pnpm docs:check-links`
+- `pnpm docs:check-i18n-glossary`
+- `pnpm format:docs:check` or `pnpm lint:docs`
+- `git diff --check`
+- generated-doc or inventory checks when generated references, plugin catalogs,
+  labeler, or docs scripts changed
+- behavior tests or command probes when docs claim runtime behavior
+
+If proof is blocked, say exactly which command was not run and why.

.agents/skills/technical-documentation/references/principles.md

@@ -0,0 +1,54 @@
+# Documentation Principles
+
+This reference consolidates the core rules used by this skill.
+
+## Matt Palmer: 8 rules for better docs
+
+Source: https://mattpalmer.io/posts/2025/10/8-rules-for-better-docs/
+
+Use these as default operating principles:
+
+1. Write for humans, optimize for agents.
+2. Start with a funnel: what/why, quickstart, next steps.
+3. Use Diataxis to scaffold content.
+4. Write with AI, but structure for agents.
+5. Offload routine docs operations to background agents.
+6. Automate quality with CI.
+7. Automate scaffolding and repetitive workflow tasks.
+8. Make contribution easy and visible.
+
+## OpenAI cookbook: what makes documentation good
+
+Source: https://cookbook.openai.com/articles/what_makes_documentation_good
+
+Key quality constraints:
+
+- Prefer specific and accurate terminology over niche jargon.
+- Keep examples self-contained and minimize dependencies.
+- Prioritize high-value topics over edge-case depth.
+- Do not teach unsafe patterns (for example, exposed secrets).
+- Open with context that helps readers orient quickly.
+- Apply empathy and override rigid rules when it clearly improves outcomes.
+
+## Practical merge policy
+
+When these rules conflict:
+
+1. Preserve reader task success first.
+2. Preserve structural clarity second.
+3. Preserve long-term maintainability third.
+4. Add agent optimization only if it does not reduce human clarity.
+
+For agent-instructions and contributor-governance specifics (AGENTS/aliases/CONTRIBUTING), use `references/agent-and-contributing.md` as the detailed additional source of truth.
+
+When the target repo or request is OpenClaw-specific, layer `references/openclaw.md` on top of these general rules. Otherwise ignore that repo-specific overlay.
+
+## Execution policy for this skill
+
+- Long-running and extensive investigations are allowed for both build and review work when needed to resolve ambiguity or cross-file drift.
+- Use sub-agents when available for bounded parallel discovery, verification, or cross-source comparison.
+- Keep one merged outcome: sub-agent outputs must be normalized into a single consistent recommendation/fix set.
+
+## Multilingual parity rule
+
+When docs exist in multiple languages, target cross-locale parity for task-critical content (steps, warnings, prerequisites, and limits). If full parity is not possible, publish explicit parity status and sync intent.

.agents/skills/technical-documentation/references/review.md

@@ -0,0 +1,121 @@
+# Review Docs Playbook
+
+Read `principles.md` first, then apply this checklist.
+
+## 1. Scope and classification
+
+- Identify doc type and target audience.
+- Confirm brownfield vs evergreen intent.
+- Confirm expected outcome for the reader.
+- For full-repo reviews, explicitly include both governance surfaces and product-doc surfaces (`docs/`, README trees, `.md/.mdx/.mdc`, `.rst/.rsc`, framework docs configs).
+- For OpenClaw docs reviews, apply `references/openclaw.md` for page type, docs IA, preservation, examples, and validation checks.
+
+## 2. Investigation behavior
+
+- Proactively find issues and risks without waiting for repeated prompts.
+- If there are signals of deeper problems, continue investigation beyond the first pass.
+- Long-running and extensive investigations are acceptable when needed for confidence and correctness.
+- When available, use sub-agents for bounded parallel discovery (for example file-inventory, command validation, or cross-doc consistency checks), then merge to one final issue set.
+- When no issues are found, state that explicitly and call out residual risks or validation gaps.
+- Default to `apply-fixes` for high-confidence documentation defects unless the user explicitly requests `report-only`.
+- Do not stop at AGENTS/CONTRIBUTING checks when the task is documentation-wide; continue into docs-content and docs-framework surfaces.
+
+## 3. Governance surface review
+
+- Use `references/agent-and-contributing.md` as the source of truth for inventory, canonical/alias mapping, and precedence/conflict handling.
+  For AGENTS.md:
+
+- confirm persona intent, scope, and command/tool boundaries are explicit.
+- check frontmatter style matches repo conventions when present.
+- ensure `Always`, `Ask first`, and `Never` boundaries are present when expected.
+- require concrete command examples and repo-specific paths to avoid ambiguity.
+
+For CONTRIBUTING.md:
+
+- verify issue/PR workflow is complete and actionable.
+- ensure local setup, lint/test commands, and review criteria are accurate.
+- ensure governance does not conflict with nested AGENTS instructions.
+- flag oversized files that should be split into linked section docs (for example tool-specific setup and release docs).
+
+For agent-platform awareness:
+
+- confirm references are minimal and scoped for Cursor/Claude glob behavior.
+- confirm Codex-facing guidance uses explicit file references.
+- confirm both surfaces represent the same shared policy core (commands, boundaries, and precedence), not divergent guidance.
+- audit `.agents`/`.cursor` compatibility behavior:
+  - verify canonical rule directory and symlink state match repo policy
+  - verify symlink target integrity and platform/tooling expectations
+  - verify AGENTS policy references remain canonical for Codex even when `.cursor` compatibility exists
+- check for context bloat from duplicated policy statements across agent and contributor files.
+- check for conflicting rules, skills and agent instructions
+- check for conflicting information in agent instructions vs codebase
+- check for broken or missing referenced files (for example README/index files named as canonical entry points).
+- check for setup/command drift (for example non-existent install commands, root-level commands that should be module-scoped).
+
+## 4. Product documentation surface review
+
+- Verify docs IA coverage across root/module `README*` files and `docs/**` trees.
+- Review framework-native docs sources in scope (for example Fern, Mintlify, Sphinx, MkDocs) and ensure guidance matches actual source-of-truth files.
+- Check `.md/.mdx/.mdc/.rst/.rsc` for stale commands, missing prerequisites, and broken cross-links.
+- Confirm referenced doc paths and anchors exist.
+- Flag docs that should be split/merged to improve discoverability and maintenance.
+- For OpenClaw docs, check `docs/docs.json`, docs-list routing hints, main path versus `Reference` placement, and generated-reference visibility.
+- For OpenClaw rewrites or page splits, require source-backed keep/drop/move/destination coverage for important claims, warnings, examples, commands, fields, and troubleshooting facts.
+
+## 5. Framework config and path mapping checks
+
+- Detect and read framework config first (for example Fern config, Sphinx `conf.py`, Mintlify config, or equivalent).
+- Resolve path references relative to the declaring file/config.
+- Treat filesystem paths and published URL routes as separate maps; verify both.
+- Flag path-map drift explicitly (`missing file`, `stale route`, `wrong base path`).
+
+## 6. Structural review
+
+- Funnel check: what/why, quickstart, next steps.
+- Validate heading flow and navigation discoverability.
+- Flag critical content trapped in images or buried sections.
+- Check Diataxis alignment and split mixed-purpose sections.
+- For OpenClaw docs, confirm the content matches an explicit page type from `references/openclaw.md`.
+
+## 7. Writing quality review
+
+- Check for concise, scannable paragraphs.
+- Remove ambiguous pronouns and undefined terms.
+- Verify examples are executable and scoped correctly.
+- Verify tone is directive, technical, and non-hand-wavy.
+
+## 8. Brownfield review mode
+
+- Verify compatibility with existing docs IA and conventions.
+- Verify anchors, redirects, and cross-doc links remain valid.
+- Flag regressions in onboarding and task completion paths.
+- Ensure changed terminology is intentionally propagated.
+
+## 9. Evergreen review mode
+
+- Flag date-stamped or brittle wording without version scope.
+- Check ownership and refresh signals are present.
+- Ensure recommendations remain valid after routine product evolution.
+- Flag missing deprecation/migration guidance.
+
+## 10. Tooling and platform review
+
+Read `tooling.md` if platform fit is uncertain.
+
+- Check whether content uses platform primitives effectively.
+- Flag structure that fights the chosen docs platform.
+- Recommend targeted platform-aware improvements.
+
+## 11. Multilingual parity review (when applicable)
+
+- Confirm declared source-of-truth language and expected parity policy.
+- Compare changed sections across locales for step/order/warning drift.
+- Flag missing updates to prerequisites, version notes, limits, and safety guidance.
+- Allow intentional divergence only when rationale is explicit and user-impact is low.
+- Require a reader-visible status note when locale parity is partial.
+
+## 12. Output format
+
+1. Blocking issues (file + required fix)
+2. Non-blocking improvements
+3. Validation notes (done vs pending)

.agents/skills/technical-documentation/references/tooling.md

@@ -0,0 +1,32 @@
+# Documentation Tooling Guide
+
+Source: https://www.mintlify.com/blog/top-7-api-documentation-tools-of-2025
+
+Use this file when deciding build/review expectations for doc platforms.
+
+## Tool-selection checkpoints
+
+- Existing stack lock-in: do not force migration for minor gains.
+- API workflow depth: generated references, OpenAPI support, testability.
+- Collaboration model: docs-as-code, review workflow, versioning.
+- Runtime quality: search, navigation, and copy-ready code snippets.
+- AI readiness: structured content, stable URLs, machine-friendly layout yet human readable.
+- Human readiness: reading complexity, reading UX, navigation depth, minimize jargon.
+
+## Apply in brownfield mode
+
+- Prioritize compatibility with the current platform.
+- Use available components and style conventions before introducing new patterns.
+- Propose migration only when current constraints block critical outcomes.
+
+## Apply in evergreen mode
+
+- Favor platforms and templates that make routine updates low-friction.
+- Standardize section templates to reduce drift.
+- Capture ownership, update cadence, and stale-content detection rules.
+
+## Review implications
+
+- Check whether content uses platform primitives correctly (tabs, callouts, endpoint blocks).
+- Flag docs that are technically correct but hard to scan in the chosen platform.
+- Recommend platform-specific improvements only when they reduce cognitive load.

.agents/skills/verify-release/SKILL.md

@@ -0,0 +1,87 @@
+---
+name: verify-release
+description: "Verify an OpenClaw release is fully published across GitHub, npm, plugins, ClawHub, package smoke, and live Gateway agent turns."
+---
+
+# Verify Release
+
+Use this when asked whether an OpenClaw release is fully released, published,
+promoted, smoke-tested, or live-verified. This is a verification skill, not a
+publish skill; use `$release-openclaw-maintainer` before changing release state.
+
+## Rules
+
+- Resolve short suffixes like `.27` to the concrete CalVer version from the
+  current date/context, then say the resolved version.
+- Verify live state. Do not trust local checkout state, release notes, or old
+  memory as current truth.
+- If the checkout is dirty or divergent, use it only for scripts/reference.
+  For version metadata, fetch from GitHub release/tag or unpack the tag tarball
+  under `/tmp`.
+- Never print secrets. Use inherited live keys only for scoped smoke commands.
+- Keep the final terse: `yes/no`, evidence bullets, caveats, cleanup.
+
+## Core Checks
+
+1. GitHub release:
+   - `gh release view v<VERSION> --repo openclaw/openclaw --json tagName,name,publishedAt,isDraft,isPrerelease,targetCommitish,url,body,assets`
+   - Confirm stable releases are not draft/prerelease.
+   - Confirm release body has npm, CI, plugin npm, ClawHub, mac/appcast evidence
+     links when expected.
+   - Confirm assets expected for stable mac releases are uploaded: zip, dmg,
+     dSYM, dependency evidence when present.
+2. Root npm:
+   - `npm view openclaw@<VERSION> version dist-tags.latest dist.tarball dist.integrity time.<VERSION> --json`
+   - `latest` must equal `<VERSION>` for stable.
+   - Record tarball, integrity, publish time.
+3. Plugin publish set:
+   - Get exact tag metadata from GitHub, not the local checkout when dirty:
+     download `https://api.github.com/repos/openclaw/openclaw/tarball/v<VERSION>`
+     into `/tmp/openclaw-v<VERSION>-src`.
+   - Count `extensions/*/package.json` with
+     `openclaw.release.publishToNpm === true` and
+     `openclaw.release.publishToClawHub === true`.
+   - Compare expected counts to workflow job counts:
+     `gh api repos/openclaw/openclaw/actions/runs/<RUN>/jobs --paginate`.
+   - Each expected npm plugin must have version `<VERSION>` and
+     `dist-tags.latest === <VERSION>`.
+4. ClawHub:
+   - Check the Plugin ClawHub Release workflow conclusion and publish job count.
+   - Use OpenClaw itself for live registry proof:
+     `openclaw plugins search <known-plugin> --json`.
+   - Install one official plugin from ClawHub in an isolated HOME:
+     `openclaw plugins install clawhub:@openclaw/matrix --pin`.
+     Prefer `matrix` unless that plugin is not in the expected set.
+5. Release workflows:
+   - Verify conclusions for release notes evidence links:
+     Full Release Validation, OpenClaw Release Checks, OpenClaw NPM Release,
+     Plugin NPM Release, Plugin ClawHub Release, mac preflight/validation/publish
+     when stable mac assets are expected.
+   - Summarize only relevant successful/failed jobs; ignore routine skipped
+     optional lanes unless the release body promised them.
+6. Published package smoke:
+   - In `/tmp`, isolated HOME:
+     `npm exec --yes --package openclaw@<VERSION> -- openclaw --version`.
+   - Run at least one harmless command that touches the published CLI surface,
+     for example `plugins --help` or `gateway --help`.
+7. Dev Gateway live model smoke:
+   - Use temp HOME/workspace, not the user's normal state:
+     `HOME=/tmp/openclaw-release-smoke/home OPENCLAW_WORKSPACE=/tmp/openclaw-release-smoke/work pnpm openclaw --dev gateway run --auth none --force --verbose`.
+   - Health check via CLI: `openclaw --dev gateway health --json`.
+   - Run one Gateway-backed agent turn with inherited `OPENAI_API_KEY`, short
+     prompt, explicit session key, JSON output, and a known-available model.
+   - If the configured default model fails as unavailable, record that caveat
+     and retry with the newest known-good OpenAI model instead of declaring the
+     release failed.
+   - Stop the gateway and verify the port is not listening.
+
+## Caveats To Report
+
+- Dist-tag caveat: stable `latest` is release truth; if optional `beta` mirrors
+  still point at a beta version, report it as a caveat, not a stable-release
+  blocker, unless the user asked to verify beta promotion.
+- Divergent checkout caveat: say when local source SHA differs from release tag
+  or origin and which live sources were used instead.
+- Smoke caveat: distinguish Gateway-backed agent success from local embedded
+  fallback. A valid Gateway smoke has health OK plus gateway log/run id for the
+  agent call.

.crabbox.yaml

@@ -20,7 +20,8 @@ actions:
   workflow: .github/workflows/crabbox-hydrate.yml
   # Default AWS hydration uses local Actions replay. Use
   # `crabbox actions hydrate --github-runner --job hydrate-github` when the
-  # hydrate job needs GitHub secrets.
+  # hydrate job needs GitHub secrets, or `--github-runner --job
+  # hydrate-windows-daemon` for focused native Windows daemon proof.
   job: hydrate
   ref: main
   runnerLabels:

.gitattributes

@@ -1,3 +1,6 @@
 * text=auto eol=lf
 CLAUDE.md -text
 src/gateway/server-methods/CLAUDE.md -text
+ui/src/i18n/.i18n/* linguist-generated
+ui/src/i18n/locales/*.ts linguist-generated
+ui/src/i18n/locales/en.ts -linguist-generated

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -11,6 +11,8 @@ body:
         Do not speculate or infer beyond the evidence. If a narrative section cannot be answered from the available evidence, respond with exactly `NOT_ENOUGH_INFO`.
 
         If this is a plugin beta-release blocker, rename the issue title to `Beta blocker: <plugin-name> - <summary>` and apply the `beta-blocker` label after filing.
+
+        Please only report one issue per submission. Break multiple issues up into separate submissions.
   - type: dropdown
     id: bug_type
     attributes:

.github/actions/docker-e2e-plan/action.yml

@@ -123,14 +123,14 @@ runs:
       shell: bash
       run: |
         set -euo pipefail
-        docker pull "${OPENCLAW_DOCKER_E2E_BARE_IMAGE}"
+        bash scripts/ci-docker-pull-retry.sh "${OPENCLAW_DOCKER_E2E_BARE_IMAGE}"
 
     - name: Pull shared functional Docker E2E image
       if: inputs.hydrate-artifacts == 'true' && steps.plan.outputs.needs_functional_image == '1'
       shell: bash
       run: |
         set -euo pipefail
-        docker pull "${OPENCLAW_DOCKER_E2E_FUNCTIONAL_IMAGE}"
+        bash scripts/ci-docker-pull-retry.sh "${OPENCLAW_DOCKER_E2E_FUNCTIONAL_IMAGE}"
 
     - name: Validate Docker E2E credentials
       if: inputs.hydrate-artifacts == 'true'

.github/actions/setup-node-env/action.yml

@@ -26,11 +26,23 @@ inputs:
 runs:
   using: composite
   steps:
+    - name: Normalize container toolcache
+      shell: bash
+      run: |
+        set -euo pipefail
+        if [[ -d /__t && ! -e /opt/hostedtoolcache ]]; then
+          mkdir -p /opt
+          ln -s /__t /opt/hostedtoolcache
+        fi
+
     - name: Setup Node.js
-      uses: actions/setup-node@v6
-      with:
-        node-version: ${{ inputs.node-version }}
-        check-latest: false
+      shell: bash
+      env:
+        REQUESTED_NODE_VERSION: ${{ inputs.node-version }}
+      run: |
+        set -euo pipefail
+        source "$GITHUB_ACTION_PATH/../setup-pnpm-store-cache/ensure-node.sh"
+        openclaw_ensure_node "$REQUESTED_NODE_VERSION"
 
     - name: Setup pnpm
       uses: ./.github/actions/setup-pnpm-store-cache
@@ -40,9 +52,10 @@ runs:
 
     - name: Setup Bun
       if: inputs.install-bun == 'true'
-      uses: oven-sh/setup-bun@v2.2.0
-      with:
-        bun-version: "1.3.13"
+      shell: bash
+      run: |
+        set -euo pipefail
+        npm install -g bun@1.3.14
 
     - name: Runtime versions
       shell: bash

.github/actions/setup-pnpm-store-cache/action.yml

@@ -14,7 +14,7 @@ inputs:
     required: false
     default: ""
   use-actions-cache:
-    description: Whether pnpm/action-setup should cache the pnpm store.
+    description: Whether actions/cache should cache the pnpm store.
     required: false
     default: "true"
 outputs:
@@ -47,12 +47,48 @@ runs:
         openclaw_ensure_node "$requested_node"
 
     - name: Setup pnpm from packageManager
-      uses: pnpm/action-setup@0e279bb959325dab635dd2c09392533439d90093
+      shell: bash
+      env:
+        COREPACK_ENABLE_DOWNLOAD_PROMPT: "0"
+        PACKAGE_MANAGER_FILE: ${{ inputs.package-manager-file }}
+      run: |
+        set -euo pipefail
+        package_manager="$(node -e "const fs = require('node:fs'); const path = require('node:path'); const pkg = JSON.parse(fs.readFileSync(path.resolve(process.argv[1]), 'utf8')); process.stdout.write(pkg.packageManager || '')" "$PACKAGE_MANAGER_FILE")"
+        case "$package_manager" in
+          pnpm@*) ;;
+          *)
+            echo "::error::Expected packageManager to pin pnpm, got '${package_manager:-<empty>}'"
+            exit 1
+            ;;
+        esac
+        corepack enable
+        for attempt in 1 2 3; do
+          if corepack prepare "$package_manager" --activate; then
+            exit 0
+          fi
+          sleep $((attempt * 5))
+        done
+        corepack prepare "$package_manager" --activate
+
+    - name: Resolve pnpm store path
+      id: pnpm-store
+      if: ${{ inputs.use-actions-cache == 'true' && runner.os != 'Windows' }}
+      shell: bash
+      run: |
+        set -euo pipefail
+        store_path="$(pnpm store path --silent)"
+        node -e "require('node:fs').mkdirSync(process.argv[1], { recursive: true })" "$store_path"
+        echo "path=$store_path" >> "$GITHUB_OUTPUT"
+
+    - name: Restore pnpm store cache
+      if: ${{ inputs.use-actions-cache == 'true' && runner.os != 'Windows' }}
+      uses: actions/cache@v5
       with:
-        package_json_file: ${{ inputs.package-manager-file }}
-        run_install: false
-        cache: ${{ inputs.use-actions-cache }}
-        cache_dependency_path: ${{ inputs.lockfile-path }}
+        path: ${{ steps.pnpm-store.outputs.path }}
+        key: pnpm-store-${{ runner.os }}-${{ inputs.node-version }}-${{ hashFiles(inputs.lockfile-path) }}
+        restore-keys: |
+          pnpm-store-${{ runner.os }}-${{ inputs.node-version }}-
+          pnpm-store-${{ runner.os }}-
 
     - name: Record pnpm version
       id: pnpm-version

.github/actions/setup-pnpm-store-cache/ensure-node.sh

@@ -8,7 +8,10 @@ openclaw_node_version_matches() {
   fi
   case "$requested" in
     *x)
-      [[ "${actual%%.*}" == "${requested%%.*}" ]]
+      [[ "${actual%%.*}" == "${requested%%.*}" ]] || return 1
+      if [[ "${requested%%.*}" == "22" ]]; then
+        openclaw_node_version_at_least "$actual" "22.19.0"
+      fi
       ;;
     *.*.*)
       [[ "$actual" == "$requested" ]]
@@ -22,15 +25,47 @@ openclaw_node_version_matches() {
   esac
 }
 
+openclaw_node_version_at_least() {
+  local actual="$1"
+  local minimum="$2"
+  local actual_major actual_minor actual_patch minimum_major minimum_minor minimum_patch
+  IFS=. read -r actual_major actual_minor actual_patch <<< "$actual"
+  IFS=. read -r minimum_major minimum_minor minimum_patch <<< "$minimum"
+  actual_minor="${actual_minor:-0}"
+  actual_patch="${actual_patch:-0}"
+  minimum_minor="${minimum_minor:-0}"
+  minimum_patch="${minimum_patch:-0}"
+
+  if (( actual_major != minimum_major )); then
+    (( actual_major > minimum_major ))
+    return
+  fi
+  if (( actual_minor != minimum_minor )); then
+    (( actual_minor > minimum_minor ))
+    return
+  fi
+  (( actual_patch >= minimum_patch ))
+}
+
 openclaw_active_node_version() {
   node -p 'process.versions.node' 2>/dev/null || true
 }
 
 openclaw_prepend_node_bin() {
   local node_bin_dir="$1"
-  export PATH="$node_bin_dir:$PATH"
+  local github_path_dir="${2:-$node_bin_dir}"
+  local shell_node_bin_dir="$node_bin_dir"
+  if command -v cygpath >/dev/null 2>&1; then
+    shell_node_bin_dir="$(cygpath -u "$node_bin_dir" 2>/dev/null || printf '%s' "$node_bin_dir")"
+  fi
+  export PATH="$shell_node_bin_dir:$PATH"
   if [[ -n "${GITHUB_PATH:-}" ]]; then
-    echo "$node_bin_dir" >> "$GITHUB_PATH"
+    local github_node_bin_dir="$github_path_dir"
+    if [[ $# -lt 2 ]] && command -v cygpath >/dev/null 2>&1; then
+      github_node_bin_dir="$shell_node_bin_dir"
+      github_node_bin_dir="$(cygpath -w "$shell_node_bin_dir" 2>/dev/null || printf '%s' "$shell_node_bin_dir")"
+    fi
+    echo "$github_node_bin_dir" >> "$GITHUB_PATH"
   fi
   hash -r
 }
@@ -43,11 +78,15 @@ openclaw_find_toolcache_node() {
     "${RUNNER_TOOL_CACHE:-}" \
     "${AGENT_TOOLSDIRECTORY:-}" \
     "${ACTIONS_RUNNER_TOOL_CACHE:-}" \
+    "${OPENCLAW_CONTAINER_TOOL_CACHE:-/__t}" \
     "/opt/hostedtoolcache" \
     "/home/runner/_work/_tool" \
     "/Users/runner/hostedtoolcache" \
     "/c/hostedtoolcache/windows"
   do
+    if [[ ! -d "$root" && "$root" == *\\* ]] && command -v cygpath >/dev/null 2>&1; then
+      root="$(cygpath -u "$root" 2>/dev/null || printf '%s' "$root")"
+    fi
     if [[ -d "$root/node" ]]; then
       roots+=("$root/node")
     elif [[ "$(basename "$root")" == "node" && -d "$root" ]]; then
@@ -68,6 +107,92 @@ openclaw_find_toolcache_node() {
   return 1
 }
 
+openclaw_resolve_node_download_version() {
+  local requested_node="$1"
+  if [[ "$requested_node" =~ ^v?[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+    [[ "$requested_node" == v* ]] && printf '%s\n' "$requested_node" || printf 'v%s\n' "$requested_node"
+    return 0
+  fi
+
+  local prefix="${requested_node#v}"
+  prefix="${prefix%%[xX]*}"
+  prefix="v${prefix}"
+  [[ "$prefix" == *. ]] || prefix="${prefix}."
+  curl -fsSL https://nodejs.org/dist/index.json |
+    OPENCLAW_NODE_PREFIX="$prefix" python3 -c 'import json, os, sys
+prefix = os.environ["OPENCLAW_NODE_PREFIX"]
+for item in json.load(sys.stdin):
+    version = item.get("version", "")
+    if version.startswith(prefix):
+        print(version)
+        break
+'
+}
+
+openclaw_node_download_platform() {
+  local os_name arch_name
+  os_name="$(uname -s)"
+  arch_name="$(uname -m)"
+  case "$os_name:$arch_name" in
+    Linux:x86_64) printf 'linux-x64\n' ;;
+    Linux:aarch64 | Linux:arm64) printf 'linux-arm64\n' ;;
+    Darwin:x86_64) printf 'darwin-x64\n' ;;
+    Darwin:arm64) printf 'darwin-arm64\n' ;;
+    MINGW*:x86_64 | MSYS*:x86_64 | CYGWIN*:x86_64 | MINGW*:AMD64 | MSYS*:AMD64 | CYGWIN*:AMD64)
+      printf 'win-x64\n'
+      ;;
+    MINGW*:aarch64 | MINGW*:arm64 | MSYS*:aarch64 | MSYS*:arm64 | CYGWIN*:aarch64 | CYGWIN*:arm64) printf 'win-arm64\n' ;;
+    *)
+      return 1
+      ;;
+  esac
+}
+
+openclaw_download_node() {
+  local requested_node="$1"
+  local version platform archive_url install_root temp_root
+  version="$(openclaw_resolve_node_download_version "$requested_node")"
+  platform="$(openclaw_node_download_platform)" || return 1
+  temp_root="${RUNNER_TEMP:-/tmp}"
+  if command -v cygpath >/dev/null 2>&1; then
+    temp_root="$(cygpath -u "$temp_root" 2>/dev/null || printf '%s\n' "$temp_root")"
+  fi
+  install_root="${temp_root}/openclaw-node-${version}-${platform}"
+  if [[ "$platform" == win-* ]]; then
+    local archive_path ps_archive_path ps_install_root ps_bin_dir node_bin_dir
+    archive_path="${temp_root}/node-${version}-${platform}.zip"
+    archive_url="https://nodejs.org/dist/${version}/node-${version}-${platform}.zip"
+    rm -rf "$install_root"
+    mkdir -p "$install_root"
+    echo "Downloading Node ${version} from ${archive_url}"
+    curl -fsSL -o "$archive_path" "$archive_url"
+    ps_archive_path="$archive_path"
+    ps_install_root="$install_root"
+    if command -v cygpath >/dev/null 2>&1; then
+      ps_archive_path="$(cygpath -w "$archive_path")"
+      ps_install_root="$(cygpath -w "$install_root")"
+    fi
+    ps_bin_dir="$ps_install_root\\node-${version}-${platform}"
+    node_bin_dir="$install_root/node-${version}-${platform}"
+    if command -v pwsh >/dev/null 2>&1; then
+      pwsh -NoLogo -NoProfile -Command "Expand-Archive -LiteralPath '${ps_archive_path}' -DestinationPath '${ps_install_root}' -Force"
+      openclaw_prepend_node_bin "$node_bin_dir" "$ps_bin_dir"
+    elif command -v powershell.exe >/dev/null 2>&1; then
+      powershell.exe -NoLogo -NoProfile -Command "Expand-Archive -LiteralPath '${ps_archive_path}' -DestinationPath '${ps_install_root}' -Force"
+      openclaw_prepend_node_bin "$node_bin_dir" "$ps_bin_dir"
+    else
+      unzip -q "$archive_path" -d "$install_root"
+      openclaw_prepend_node_bin "$node_bin_dir"
+    fi
+  else
+    archive_url="https://nodejs.org/dist/${version}/node-${version}-${platform}.tar.xz"
+    mkdir -p "$install_root"
+    echo "Downloading Node ${version} from ${archive_url}"
+    curl -fsSL "$archive_url" | tar -xJ -C "$install_root" --strip-components=1
+    openclaw_prepend_node_bin "$install_root/bin"
+  fi
+}
+
 openclaw_ensure_node() {
   local requested_node="${1:-}"
   requested_node="${requested_node#v}"
@@ -86,6 +211,8 @@ openclaw_ensure_node() {
   if [[ -n "$node_bin" ]]; then
     echo "Using Node $("$node_bin" -p 'process.versions.node') from $node_bin"
     openclaw_prepend_node_bin "$(dirname "$node_bin")"
+  else
+    openclaw_download_node "$requested_node" || true
   fi
 
   active_node_version="$(openclaw_active_node_version)"

.github/codeql/codeql-agent-runtime-boundary-critical-quality.yml

@@ -17,7 +17,8 @@ paths:
   - src/acp/control-plane
   - src/agents/command
   - src/agents/cli-runner
-  - src/agents/pi-embedded-runner
+  - src/agents/embedded-agent-runner
+  - src/agents/sessions
   - src/agents/tools
   - src/agents/*completion*.ts
   - src/agents/*transport*.ts

.github/codeql/codeql-core-auth-secrets-critical-quality.yml

@@ -22,6 +22,8 @@ paths:
   - src/agents/sandbox
   - src/agents/sandbox.ts
   - src/agents/sandbox-*.ts
+  - src/agents/sessions/*auth*.ts
+  - src/agents/sessions/**/*auth*.ts
   - src/cron/service/jobs.ts
   - src/cron/stagger.ts
   - src/gateway/*auth*.ts

.github/codeql/codeql-mcp-process-tool-boundary-critical-security.yml

@@ -24,14 +24,15 @@ paths:
   - src/agents/openclaw-plugin-tools.ts
   - src/agents/openclaw-tools.runtime.ts
   - src/agents/openclaw-tools.registration.ts
-  - src/agents/pi-tool-definition-adapter.ts
-  - src/agents/pi-tools.abort.ts
-  - src/agents/pi-tools.before-tool-call*.ts
-  - src/agents/pi-tools.host-edit.ts
-  - src/agents/pi-tools-parameter-schema.ts
-  - src/agents/pi-embedded-runner/effective-tool-policy.ts
-  - src/agents/pi-embedded-runner/tool-name-allowlist.ts
-  - src/agents/pi-embedded-runner/tool-schema-runtime.ts
+  - src/agents/agent-tool-definition-adapter.ts
+  - src/agents/agent-tools.abort.ts
+  - src/agents/agent-tools.before-tool-call*.ts
+  - src/agents/agent-tools.read.ts
+  - src/agents/agent-tools-parameter-schema.ts
+  - src/agents/sessions/tools/**
+  - src/agents/embedded-agent-runner/effective-tool-policy.ts
+  - src/agents/embedded-agent-runner/tool-name-allowlist.ts
+  - src/agents/embedded-agent-runner/tool-schema-runtime.ts
   - src/agents/tools/gateway-tool.ts
   - src/agents/tools/message-tool.ts
   - src/agents/tools/sessions-send-tool.ts

.github/codex/prompts/docs-agent.md

@@ -12,7 +12,7 @@ Hard limits:
 - Do not change production code, tests, package metadata, generated baselines, lockfiles, or CI config.
 - Keep changes minimal and factual.
 - Use "plugin/plugins" in user-facing docs/UI/changelog; `extensions/` is only the internal workspace layout.
-- Do not add a changelog entry unless the docs update describes a user-facing behavior/API change from the triggering commit.
+- Do not add `CHANGELOG.md` entries during normal docs work. Capture user-facing release-note context in the PR body or commit message instead.
 
 Allowed paths:
 

.github/labeler.yml

@@ -10,6 +10,11 @@
           - "extensions/file-transfer/**"
           - "docs/nodes/index.md"
           - "docs/plugins/sdk-runtime.md"
+"plugin: pixverse":
+  - changed-files:
+      - any-glob-to-any-file:
+          - "extensions/pixverse/**"
+          - "docs/providers/pixverse.md"
 "channel: discord":
   - changed-files:
       - any-glob-to-any-file:
@@ -491,6 +496,7 @@
   - changed-files:
       - any-glob-to-any-file:
           - "extensions/diffs/**"
+          - "extensions/diffs-language-pack/**"
 "extensions: elevenlabs":
   - changed-files:
       - any-glob-to-any-file:

.github/workflows/ci-build-artifacts-testbox.yml

@@ -61,7 +61,7 @@ jobs:
             git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               -c "http.extraheader=AUTHORIZATION: basic ${auth_header}" \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \

.github/workflows/ci-check-testbox.yml

@@ -59,7 +59,7 @@ jobs:
             git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               -c "http.extraheader=AUTHORIZATION: basic ${auth_header}" \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
@@ -132,6 +132,5 @@ jobs:
       - name: Run Testbox
         uses: useblacksmith/run-testbox@5ca05834db1d3813554d1dd109e5f2087a8d7cbc
         if: success()
-        continue-on-error: true
         env:
           FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"

.github/workflows/ci.yml

@@ -76,13 +76,24 @@ jobs:
       android_matrix: ${{ steps.manifest.outputs.android_matrix }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
-        with:
-          ref: ${{ inputs.target_ref || github.sha }}
-          fetch-depth: 1
-          fetch-tags: false
-          persist-credentials: true
-          submodules: false
+        env:
+          CHECKOUT_REPO: ${{ github.repository }}
+          CHECKOUT_REF: ${{ inputs.target_ref || github.sha }}
+          CHECKOUT_FALLBACK_REF: ${{ github.sha }}
+          GITHUB_EVENT_NAME: ${{ github.event_name }}
+        run: |
+          set -euo pipefail
+          git init "$GITHUB_WORKSPACE"
+          git -C "$GITHUB_WORKSPACE" config gc.auto 0
+          git -C "$GITHUB_WORKSPACE" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
+          if ! git -C "$GITHUB_WORKSPACE" fetch --no-tags --depth=1 origin "+${CHECKOUT_REF}:refs/remotes/origin/checkout"; then
+            if [ "$GITHUB_EVENT_NAME" != "workflow_dispatch" ] || [ "$CHECKOUT_REF" = "$CHECKOUT_FALLBACK_REF" ]; then
+              exit 1
+            fi
+            echo "::warning::workflow_dispatch target_ref '$CHECKOUT_REF' is unavailable; falling back to head SHA '$CHECKOUT_FALLBACK_REF'"
+            git -C "$GITHUB_WORKSPACE" fetch --no-tags --depth=1 origin "+${CHECKOUT_FALLBACK_REF}:refs/remotes/origin/checkout"
+          fi
+          git -C "$GITHUB_WORKSPACE" checkout --detach refs/remotes/origin/checkout
 
       - name: Resolve checkout SHA
         id: checkout_ref
@@ -199,6 +210,7 @@ jobs:
           if (runNodeFull) {
             checksFastCoreTasks.push(
               { check_name: "checks-fast-bundled-protocol", runtime: "node", task: "bundled-protocol" },
+              { check_name: "checks-fast-bun-launcher", runtime: "bun", task: "bun-launcher" },
             );
           } else {
             if (runNodeFastCiRouting) {
@@ -299,13 +311,24 @@ jobs:
       PRE_COMMIT_HOME: .cache/pre-commit-security-fast
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
-        with:
-          ref: ${{ inputs.target_ref || github.sha }}
-          fetch-depth: 1
-          fetch-tags: false
-          persist-credentials: true
-          submodules: false
+        env:
+          CHECKOUT_REPO: ${{ github.repository }}
+          CHECKOUT_REF: ${{ inputs.target_ref || github.sha }}
+          CHECKOUT_FALLBACK_REF: ${{ github.sha }}
+          GITHUB_EVENT_NAME: ${{ github.event_name }}
+        run: |
+          set -euo pipefail
+          git init "$GITHUB_WORKSPACE"
+          git -C "$GITHUB_WORKSPACE" config gc.auto 0
+          git -C "$GITHUB_WORKSPACE" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
+          if ! git -C "$GITHUB_WORKSPACE" fetch --no-tags --depth=1 origin "+${CHECKOUT_REF}:refs/remotes/origin/checkout"; then
+            if [ "$GITHUB_EVENT_NAME" != "workflow_dispatch" ] || [ "$CHECKOUT_REF" = "$CHECKOUT_FALLBACK_REF" ]; then
+              exit 1
+            fi
+            echo "::warning::workflow_dispatch target_ref '$CHECKOUT_REF' is unavailable; falling back to head SHA '$CHECKOUT_FALLBACK_REF'"
+            git -C "$GITHUB_WORKSPACE" fetch --no-tags --depth=1 origin "+${CHECKOUT_FALLBACK_REF}:refs/remotes/origin/checkout"
+          fi
+          git -C "$GITHUB_WORKSPACE" checkout --detach refs/remotes/origin/checkout
 
       - name: Ensure security base commit
         if: github.event_name != 'workflow_dispatch'
@@ -335,22 +358,20 @@ jobs:
           fi
           echo "PRE_COMMIT_CONFIG_PATH=$trusted_config" >> "$GITHUB_ENV"
 
-      - name: Setup Python
+      - name: Resolve Python runtime
         id: setup-python
-        uses: actions/setup-python@v6
-        with:
-          python-version: "3.12"
-
-      - name: Restore pre-commit cache
-        uses: actions/cache@v5
-        with:
-          path: .cache/pre-commit-security-fast
-          key: pre-commit-security-fast-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('.pre-commit-config.yaml') }}
-          restore-keys: |
-            pre-commit-security-fast-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-
+        run: |
+          set -euo pipefail
+          python3 --version
+          version="$(python3 - <<'PY'
+          import platform
+          print(platform.python_version())
+          PY
+          )"
+          echo "python-version=${version}" >> "$GITHUB_OUTPUT"
 
       - name: Install pre-commit
-        run: python -m pip install --disable-pip-version-check pre-commit==4.2.0
+        run: python3 -m pip install --disable-pip-version-check pre-commit==4.2.0
 
       - name: Detect committed private keys
         run: pre-commit run --config "${PRE_COMMIT_CONFIG_PATH:-.pre-commit-config.yaml}" --all-files detect-private-key
@@ -383,10 +404,12 @@ jobs:
           pre-commit run --config "${PRE_COMMIT_CONFIG_PATH:-.pre-commit-config.yaml}" zizmor --files "${workflow_files[@]}"
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: "24.x"
-          check-latest: false
+        env:
+          REQUESTED_NODE_VERSION: "24.x"
+        run: |
+          set -euo pipefail
+          source .github/actions/setup-pnpm-store-cache/ensure-node.sh
+          openclaw_ensure_node "$REQUESTED_NODE_VERSION"
 
       - name: Audit production dependencies
         run: node scripts/pre-commit/pnpm-audit-prod.mjs --audit-level=high
@@ -411,7 +434,6 @@ jobs:
         env:
           CHECKOUT_REPO: ${{ github.repository }}
           CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
-          CHECKOUT_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
 
@@ -427,10 +449,10 @@ jobs:
             reset_checkout_dir
             git init "$workdir" >/dev/null
             git config --global --add safe.directory "$workdir"
-            git -C "$workdir" remote add origin "https://x-access-token:${CHECKOUT_TOKEN}@github.com/${CHECKOUT_REPO}.git"
+            git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
@@ -468,9 +490,6 @@ jobs:
           NODE_OPTIONS: --max-old-space-size=8192
         run: pnpm build:ci-artifacts
 
-      - name: Build Control UI
-        run: pnpm ui:build
-
       - name: Check Control UI i18n
         if: needs.preflight.outputs.run_control_ui_i18n == 'true'
         run: pnpm ui:i18n:check
@@ -513,7 +532,24 @@ jobs:
         run: pnpm test:build:singleton
 
       - name: Check CLI startup memory
-        run: pnpm test:startup:memory
+        shell: bash
+        run: |
+          set +e
+          pnpm test:startup:memory
+          status=$?
+          if [[ -f .artifacts/startup-memory/summary.md ]]; then
+            cat .artifacts/startup-memory/summary.md >> "$GITHUB_STEP_SUMMARY"
+          fi
+          exit "$status"
+
+      - name: Upload startup memory report
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: startup-memory
+          path: .artifacts/startup-memory/
+          if-no-files-found: ignore
+          retention-days: 7
 
       - name: Run built artifact checks
         id: built_artifact_checks
@@ -546,6 +582,20 @@ jobs:
             pids+=("$!")
           }
 
+          if [ "$RUN_GATEWAY_WATCH" = "true" ]; then
+            gateway_watch_log="${RUNNER_TEMP}/gateway-watch.log"
+            echo "starting gateway-watch: node scripts/check-gateway-watch-regression.mjs --skip-build --ready-timeout-ms 5000"
+            if node scripts/check-gateway-watch-regression.mjs --skip-build --ready-timeout-ms 5000 >"$gateway_watch_log" 2>&1; then
+              result="success"
+            else
+              result="failure"
+            fi
+            echo "::group::gateway-watch log"
+            cat "$gateway_watch_log"
+            echo "::endgroup::"
+            results["gateway-watch"]="$result"
+          fi
+
           if [ "$RUN_CHANNELS" = "true" ]; then
             start_check "channels" env \
               NODE_OPTIONS=--max-old-space-size=8192 \
@@ -560,10 +610,6 @@ jobs:
               node scripts/run-vitest.mjs run --config test/vitest/vitest.full-core-support-boundary.config.ts
           fi
 
-          if [ "$RUN_GATEWAY_WATCH" = "true" ]; then
-            start_check "gateway-watch" node scripts/check-gateway-watch-regression.mjs --skip-build --ready-timeout-ms 5000
-          fi
-
           for index in "${!pids[@]}"; do
             name="${names[$index]}"
             log="${logs[$index]}"
@@ -619,7 +665,6 @@ jobs:
         env:
           CHECKOUT_REPO: ${{ github.repository }}
           CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
-          CHECKOUT_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
 
@@ -635,10 +680,10 @@ jobs:
             reset_checkout_dir
             git init "$workdir" >/dev/null
             git config --global --add safe.directory "$workdir"
-            git -C "$workdir" remote add origin "https://x-access-token:${CHECKOUT_TOKEN}@github.com/${CHECKOUT_REPO}.git"
+            git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
@@ -662,7 +707,7 @@ jobs:
       - name: Setup Node environment
         uses: ./.github/actions/setup-node-env
         with:
-          install-bun: "false"
+          install-bun: ${{ matrix.task == 'bun-launcher' && 'true' || 'false' }}
 
       - name: Run ${{ matrix.task }} (${{ matrix.runtime }})
         env:
@@ -683,6 +728,9 @@ jobs:
             ci-routing)
               pnpm test src/commands/status.scan-result.test.ts src/scripts/ci-changed-scope.test.ts test/scripts/test-projects.test.ts
               ;;
+            bun-launcher)
+              OPENCLAW_TEST_BUN_LAUNCHER=1 pnpm test test/openclaw-launcher.e2e.test.ts
+              ;;
             *)
               echo "Unsupported checks-fast task: $TASK" >&2
               exit 1
@@ -706,7 +754,6 @@ jobs:
         env:
           CHECKOUT_REPO: ${{ github.repository }}
           CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
-          CHECKOUT_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
 
@@ -722,10 +769,10 @@ jobs:
             reset_checkout_dir
             git init "$workdir" >/dev/null
             git config --global --add safe.directory "$workdir"
-            git -C "$workdir" remote add origin "https://x-access-token:${CHECKOUT_TOKEN}@github.com/${CHECKOUT_REPO}.git"
+            git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
@@ -787,7 +834,6 @@ jobs:
         env:
           CHECKOUT_REPO: ${{ github.repository }}
           CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
-          CHECKOUT_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
 
@@ -803,10 +849,10 @@ jobs:
             reset_checkout_dir
             git init "$workdir" >/dev/null
             git config --global --add safe.directory "$workdir"
-            git -C "$workdir" remote add origin "https://x-access-token:${CHECKOUT_TOKEN}@github.com/${CHECKOUT_REPO}.git"
+            git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
@@ -865,7 +911,6 @@ jobs:
         env:
           CHECKOUT_REPO: ${{ github.repository }}
           CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
-          CHECKOUT_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
 
@@ -881,10 +926,10 @@ jobs:
             reset_checkout_dir
             git init "$workdir" >/dev/null
             git config --global --add safe.directory "$workdir"
-            git -C "$workdir" remote add origin "https://x-access-token:${CHECKOUT_TOKEN}@github.com/${CHECKOUT_REPO}.git"
+            git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
@@ -941,7 +986,6 @@ jobs:
         env:
           CHECKOUT_REPO: ${{ github.repository }}
           CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
-          CHECKOUT_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
 
@@ -957,10 +1001,10 @@ jobs:
             reset_checkout_dir
             git init "$workdir" >/dev/null
             git config --global --add safe.directory "$workdir"
-            git -C "$workdir" remote add origin "https://x-access-token:${CHECKOUT_TOKEN}@github.com/${CHECKOUT_REPO}.git"
+            git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
@@ -1064,7 +1108,6 @@ jobs:
         env:
           CHECKOUT_REPO: ${{ github.repository }}
           CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
-          CHECKOUT_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
 
@@ -1080,10 +1123,10 @@ jobs:
             reset_checkout_dir
             git init "$workdir" >/dev/null
             git config --global --add safe.directory "$workdir"
-            git -C "$workdir" remote add origin "https://x-access-token:${CHECKOUT_TOKEN}@github.com/${CHECKOUT_REPO}.git"
+            git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
@@ -1195,7 +1238,6 @@ jobs:
         env:
           CHECKOUT_REPO: ${{ github.repository }}
           CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
-          CHECKOUT_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
 
@@ -1211,10 +1253,10 @@ jobs:
             reset_checkout_dir
             git init "$workdir" >/dev/null
             git config --global --add safe.directory "$workdir"
-            git -C "$workdir" remote add origin "https://x-access-token:${CHECKOUT_TOKEN}@github.com/${CHECKOUT_REPO}.git"
+            git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
@@ -1345,7 +1387,6 @@ jobs:
         env:
           CHECKOUT_REPO: ${{ github.repository }}
           CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
-          CHECKOUT_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
 
@@ -1361,10 +1402,10 @@ jobs:
             reset_checkout_dir
             git init "$workdir" >/dev/null
             git config --global --add safe.directory "$workdir"
-            git -C "$workdir" remote add origin "https://x-access-token:${CHECKOUT_TOKEN}@github.com/${CHECKOUT_REPO}.git"
+            git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
@@ -1391,12 +1432,13 @@ jobs:
           install-bun: "false"
 
       - name: Checkout ClawHub docs source
-        uses: actions/checkout@v6
-        with:
-          repository: openclaw/clawhub
-          path: clawhub-source
-          fetch-depth: 1
-          persist-credentials: true
+        run: |
+          set -euo pipefail
+          git init clawhub-source
+          git -C clawhub-source config gc.auto 0
+          git -C clawhub-source remote add origin "https://github.com/openclaw/clawhub.git"
+          git -C clawhub-source fetch --no-tags --depth=1 origin "+HEAD:refs/remotes/origin/checkout"
+          git -C clawhub-source checkout --detach refs/remotes/origin/checkout
 
       - name: Check docs
         env:
@@ -1412,11 +1454,16 @@ jobs:
     timeout-minutes: 20
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
-        with:
-          ref: ${{ needs.preflight.outputs.checkout_revision }}
-          persist-credentials: true
-          submodules: false
+        env:
+          CHECKOUT_REPO: ${{ github.repository }}
+          CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
+        run: |
+          set -euo pipefail
+          git init "$GITHUB_WORKSPACE"
+          git -C "$GITHUB_WORKSPACE" config gc.auto 0
+          git -C "$GITHUB_WORKSPACE" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
+          git -C "$GITHUB_WORKSPACE" fetch --no-tags --depth=1 origin "+${CHECKOUT_SHA}:refs/remotes/origin/checkout"
+          git -C "$GITHUB_WORKSPACE" checkout --detach refs/remotes/origin/checkout
 
       - name: Setup Python
         uses: actions/setup-python@v6
@@ -1455,11 +1502,16 @@ jobs:
       matrix: ${{ fromJson(needs.preflight.outputs.checks_windows_matrix) }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
-        with:
-          ref: ${{ needs.preflight.outputs.checkout_revision }}
-          persist-credentials: true
-          submodules: false
+        env:
+          CHECKOUT_REPO: ${{ github.repository }}
+          CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
+        run: |
+          set -euo pipefail
+          git init "$GITHUB_WORKSPACE"
+          git -C "$GITHUB_WORKSPACE" config gc.auto 0
+          git -C "$GITHUB_WORKSPACE" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
+          git -C "$GITHUB_WORKSPACE" fetch --no-tags --depth=1 origin "+${CHECKOUT_SHA}:refs/remotes/origin/checkout"
+          git -C "$GITHUB_WORKSPACE" checkout --detach refs/remotes/origin/checkout
 
       - name: Try to exclude workspace from Windows Defender (best-effort)
         shell: pwsh
@@ -1481,15 +1533,17 @@ jobs:
           }
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: 24.x
-          check-latest: false
+        env:
+          REQUESTED_NODE_VERSION: "22.x"
+        run: |
+          set -euo pipefail
+          source .github/actions/setup-pnpm-store-cache/ensure-node.sh
+          openclaw_ensure_node "$REQUESTED_NODE_VERSION"
 
       - name: Setup pnpm
         uses: ./.github/actions/setup-pnpm-store-cache
         with:
-          node-version: 24.x
+          node-version: 22.x
 
       - name: Runtime versions
         run: |
@@ -1548,11 +1602,16 @@ jobs:
       matrix: ${{ fromJson(needs.preflight.outputs.macos_node_matrix) }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
-        with:
-          ref: ${{ needs.preflight.outputs.checkout_revision }}
-          persist-credentials: true
-          submodules: false
+        env:
+          CHECKOUT_REPO: ${{ github.repository }}
+          CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
+        run: |
+          set -euo pipefail
+          git init "$GITHUB_WORKSPACE"
+          git -C "$GITHUB_WORKSPACE" config gc.auto 0
+          git -C "$GITHUB_WORKSPACE" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
+          git -C "$GITHUB_WORKSPACE" fetch --no-tags --depth=1 origin "+${CHECKOUT_SHA}:refs/remotes/origin/checkout"
+          git -C "$GITHUB_WORKSPACE" checkout --detach refs/remotes/origin/checkout
 
       - name: Setup Node environment
         uses: ./.github/actions/setup-node-env
@@ -1589,11 +1648,16 @@ jobs:
     timeout-minutes: 20
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
-        with:
-          ref: ${{ needs.preflight.outputs.checkout_revision }}
-          persist-credentials: true
-          submodules: false
+        env:
+          CHECKOUT_REPO: ${{ github.repository }}
+          CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
+        run: |
+          set -euo pipefail
+          git init "$GITHUB_WORKSPACE"
+          git -C "$GITHUB_WORKSPACE" config gc.auto 0
+          git -C "$GITHUB_WORKSPACE" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
+          git -C "$GITHUB_WORKSPACE" fetch --no-tags --depth=1 origin "+${CHECKOUT_SHA}:refs/remotes/origin/checkout"
+          git -C "$GITHUB_WORKSPACE" checkout --detach refs/remotes/origin/checkout
 
       - name: Install XcodeGen / SwiftLint / SwiftFormat
         run: brew install xcodegen swiftlint swiftformat
@@ -1693,7 +1757,6 @@ jobs:
         env:
           CHECKOUT_REPO: ${{ github.repository }}
           CHECKOUT_SHA: ${{ needs.preflight.outputs.checkout_revision }}
-          CHECKOUT_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
 
@@ -1709,10 +1772,10 @@ jobs:
             reset_checkout_dir
             git init "$workdir" >/dev/null
             git config --global --add safe.directory "$workdir"
-            git -C "$workdir" remote add origin "https://x-access-token:${CHECKOUT_TOKEN}@github.com/${CHECKOUT_REPO}.git"
+            git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM 30s git -C "$workdir" \
+            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
               -c protocol.version=2 \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1

.github/workflows/codeql-critical-quality.yml

@@ -71,7 +71,9 @@ on:
       - "src/acp/control-plane/**"
       - "src/agents/cli-runner/**"
       - "src/agents/command/**"
-      - "src/agents/pi-embedded-runner/**"
+      - "src/agents/embedded-agent-runner/**"
+      - "src/agents/sessions/**"
+      - "src/agents/sessions/tools/**"
       - "src/agents/tools/**"
       - "src/agents/*completion*.ts"
       - "src/agents/*transport*.ts"
@@ -222,7 +224,15 @@ jobs:
                   network_runtime=true
                   session_diagnostics=true
                   ;;
-                src/acp/control-plane/*|src/agents/cli-runner/*|src/agents/command/*|src/agents/pi-embedded-runner/*|src/agents/tools/*|src/agents/*completion*.ts|src/agents/*transport*.ts|src/agents/model-*.ts|src/agents/openclaw-tools*.ts|src/agents/provider-*.ts|src/agents/session*.ts|src/agents/tool-call*.ts|src/auto-reply/reply/agent-runner*.ts|src/auto-reply/reply/commands*.ts|src/auto-reply/reply/directive-handling*.ts|src/auto-reply/reply/dispatch-*.ts|src/auto-reply/reply/get-reply-run*.ts|src/auto-reply/reply/provider-dispatcher*.ts|src/auto-reply/reply/queue*.ts|src/auto-reply/reply/reply-run-registry*.ts|src/auto-reply/reply/session*.ts)
+                src/agents/sessions/tools/*)
+                  agent=true
+                  mcp_process=true
+                  ;;
+                src/agents/sessions/*auth*.ts|src/agents/sessions/**/*auth*.ts)
+                  agent=true
+                  core_auth_secrets=true
+                  ;;
+                src/acp/control-plane/*|src/agents/cli-runner/*|src/agents/command/*|src/agents/embedded-agent-runner/*|src/agents/sessions/*|src/agents/tools/*|src/agents/*completion*.ts|src/agents/*transport*.ts|src/agents/model-*.ts|src/agents/openclaw-tools*.ts|src/agents/provider-*.ts|src/agents/session*.ts|src/agents/tool-call*.ts|src/auto-reply/reply/agent-runner*.ts|src/auto-reply/reply/commands*.ts|src/auto-reply/reply/directive-handling*.ts|src/auto-reply/reply/dispatch-*.ts|src/auto-reply/reply/get-reply-run*.ts|src/auto-reply/reply/provider-dispatcher*.ts|src/auto-reply/reply/queue*.ts|src/auto-reply/reply/reply-run-registry*.ts|src/auto-reply/reply/session*.ts)
                   agent=true
                   ;;
                 src/auto-reply/reply/post-compaction-context.ts|src/auto-reply/reply/queue/*|src/auto-reply/reply/startup-context.ts|src/commands/doctor-session-*.ts|src/commands/session-store-targets.ts|src/commands/sessions*.ts|src/infra/diagnostic-*.ts|src/infra/diagnostics-timeline.ts|src/infra/session-delivery-queue*.ts|src/logging/diagnostic*.ts)

.github/workflows/codeql.yml

@@ -19,6 +19,15 @@ on:
       - ".github/workflows/**"
       - "packages/**"
       - "src/**"
+  push:
+    branches:
+      - main
+    paths:
+      - ".github/actions/**"
+      - ".github/codeql/**"
+      - ".github/workflows/**"
+      - "packages/**"
+      - "src/**"
   schedule:
     - cron: "0 6 * * *"
 

.github/workflows/crabbox-hydrate.yml

@@ -41,7 +41,7 @@ env:
 jobs:
   hydrate:
     name: hydrate
-    if: ${{ inputs.crabbox_job != 'hydrate-github' }}
+    if: ${{ inputs.crabbox_job != 'hydrate-github' && inputs.crabbox_job != 'hydrate-windows-daemon' }}
     runs-on: [self-hosted, "${{ inputs.crabbox_runner_label }}"]
     timeout-minutes: 120
     steps:
@@ -72,7 +72,24 @@ jobs:
             echo "PNPM_HOME=$PNPM_HOME"
           } >> "$GITHUB_ENV"
 
+          package_manager="$(node -e "const fs = require('node:fs'); const pkg = JSON.parse(fs.readFileSync('package.json', 'utf8')); process.stdout.write(pkg.packageManager || '')")"
+          case "$package_manager" in
+            pnpm@*) ;;
+            *)
+              echo "::error::Expected packageManager to pin pnpm, got '${package_manager:-<empty>}'"
+              exit 1
+              ;;
+          esac
           corepack enable --install-directory "$PNPM_HOME"
+          for attempt in 1 2 3; do
+            if corepack prepare "$package_manager" --activate; then
+              break
+            fi
+            if [ "$attempt" = 3 ]; then
+              corepack prepare "$package_manager" --activate
+            fi
+            sleep $((attempt * 5))
+          done
           node_bin="$(dirname "$(node -p 'process.execPath')")"
           echo "NODE_BIN=$node_bin" >> "$GITHUB_ENV"
           echo "$node_bin" >> "$GITHUB_PATH"
@@ -114,7 +131,7 @@ jobs:
             ln -sfn . "$PNPM_CONFIG_MODULES_DIR/node_modules"
           fi
 
-      - name: Prepare Crabbox shell
+      - name: Fetch main ref
         shell: bash
         run: |
           set -euo pipefail
@@ -123,6 +140,11 @@ jobs:
             git fetch --no-tags --depth=50 origin "+refs/heads/main:refs/remotes/origin/main"
           fi
 
+      - name: Prepare Crabbox shell
+        shell: bash
+        run: |
+          set -euo pipefail
+
           node_bin="$(dirname "$(node -p 'process.execPath')")"
           sudo ln -sf "$node_bin/node" /usr/local/bin/node
           sudo ln -sf "$node_bin/npm" /usr/local/bin/npm
@@ -141,7 +163,13 @@ jobs:
 
           if ! command -v docker >/dev/null 2>&1; then
             echo "docker not found; installing fallback engine"
-            curl -fsSL https://get.docker.com | sudo sh
+            curl --fail --show-error --location \
+              --connect-timeout "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_CONNECT_TIMEOUT_SECONDS:-15}" \
+              --max-time "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_TIMEOUT_SECONDS:-300}" \
+              --retry "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_RETRIES:-3}" \
+              --retry-delay "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_RETRY_DELAY_SECONDS:-5}" \
+              --retry-all-errors \
+              https://get.docker.com | sudo sh
           fi
 
           if command -v systemctl >/dev/null 2>&1; then
@@ -166,7 +194,12 @@ jobs:
             esac
             buildx_version="${DOCKER_BUILDX_VERSION:-v0.15.1}"
             mkdir -p "$HOME/.docker/cli-plugins"
-            curl -fsSL \
+            curl --fail --show-error --location \
+              --connect-timeout "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_CONNECT_TIMEOUT_SECONDS:-15}" \
+              --max-time "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_TIMEOUT_SECONDS:-300}" \
+              --retry "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_RETRIES:-3}" \
+              --retry-delay "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_RETRY_DELAY_SECONDS:-5}" \
+              --retry-all-errors \
               "https://github.com/docker/buildx/releases/download/${buildx_version}/buildx-${buildx_version}.linux-${buildx_arch}" \
               -o "$HOME/.docker/cli-plugins/docker-buildx"
             chmod 0755 "$HOME/.docker/cli-plugins/docker-buildx"
@@ -217,7 +250,7 @@ jobs:
             fi
           }
           {
-            for key in CI GITHUB_ACTIONS GITHUB_WORKSPACE GITHUB_REPOSITORY GITHUB_RUN_ID GITHUB_RUN_NUMBER GITHUB_RUN_ATTEMPT GITHUB_REF GITHUB_REF_NAME GITHUB_SHA GITHUB_EVENT_NAME GITHUB_ACTOR RUNNER_OS RUNNER_ARCH RUNNER_TEMP RUNNER_TOOL_CACHE XDG_CACHE_HOME COREPACK_HOME PNPM_HOME PNPM_CONFIG_CHILD_CONCURRENCY PNPM_CONFIG_MODULES_DIR PNPM_CONFIG_NETWORK_CONCURRENCY PNPM_CONFIG_STORE_DIR PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN PNPM_CONFIG_VIRTUAL_STORE_DIR; do
+            for key in CI GITHUB_ACTIONS GITHUB_WORKSPACE GITHUB_REPOSITORY GITHUB_RUN_ID GITHUB_RUN_NUMBER GITHUB_RUN_ATTEMPT GITHUB_REF GITHUB_REF_NAME GITHUB_SHA GITHUB_EVENT_NAME GITHUB_ACTOR RUNNER_OS RUNNER_ARCH RUNNER_TEMP RUNNER_TOOL_CACHE XDG_CACHE_HOME COREPACK_HOME NODE_BIN PNPM_HOME PNPM_CONFIG_CHILD_CONCURRENCY PNPM_CONFIG_MODULES_DIR PNPM_CONFIG_NETWORK_CONCURRENCY PNPM_CONFIG_STORE_DIR PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN PNPM_CONFIG_VIRTUAL_STORE_DIR PATH; do
               write_export "$key"
             done
           } > "${env_file}.tmp"
@@ -264,6 +297,200 @@ jobs:
             sleep 15
           done
 
+  hydrate-windows-daemon:
+    name: hydrate-windows-daemon
+    if: ${{ inputs.crabbox_job == 'hydrate-windows-daemon' }}
+    runs-on: [self-hosted, "${{ inputs.crabbox_runner_label }}"]
+    timeout-minutes: 120
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v6
+        with:
+          node-version: "24"
+
+      - name: Fetch main ref
+        shell: powershell
+        run: |
+          $ErrorActionPreference = "Stop"
+
+          if (git rev-parse --is-inside-work-tree 2>$null) {
+            git fetch --no-tags --depth=50 origin "+refs/heads/main:refs/remotes/origin/main"
+          }
+
+      - name: Setup pnpm and dependencies
+        shell: powershell
+        env:
+          CI: "true"
+          COREPACK_ENABLE_DOWNLOAD_PROMPT: "0"
+        run: |
+          $ErrorActionPreference = "Stop"
+
+          $workspace = (Get-Location).Path
+          $cacheRoot = if ($env:RUNNER_TEMP) { $env:RUNNER_TEMP } else { [System.IO.Path]::GetTempPath() }
+          $env:XDG_CACHE_HOME = Join-Path $cacheRoot "cache"
+          $env:COREPACK_HOME = Join-Path $env:XDG_CACHE_HOME "corepack"
+          $env:PNPM_HOME = Join-Path $cacheRoot "pnpm-home"
+          $env:PNPM_CONFIG_STORE_DIR = Join-Path $cacheRoot "openclaw-pnpm-store"
+          $env:PNPM_CONFIG_MODULES_DIR = Join-Path $workspace "node_modules"
+          $env:PNPM_CONFIG_VIRTUAL_STORE_DIR = Join-Path $workspace "node_modules\.pnpm"
+          $env:PNPM_CONFIG_CHILD_CONCURRENCY = "4"
+          $env:PNPM_CONFIG_NETWORK_CONCURRENCY = "8"
+          $env:PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN = "false"
+          $env:PNPM_CONFIG_SIDE_EFFECTS_CACHE = "false"
+          function Add-GitHubCommandLine([string]$Path, [string]$Value) {
+            $Value | Out-File -FilePath $Path -Encoding utf8 -Append
+          }
+          New-Item -ItemType Directory -Force `
+            $env:XDG_CACHE_HOME, `
+            $env:COREPACK_HOME, `
+            $env:PNPM_HOME, `
+            $env:PNPM_CONFIG_STORE_DIR | Out-Null
+          $env:PATH = "$env:PNPM_HOME;$env:PATH"
+          @(
+            "XDG_CACHE_HOME=$env:XDG_CACHE_HOME"
+            "COREPACK_HOME=$env:COREPACK_HOME"
+            "PNPM_HOME=$env:PNPM_HOME"
+            "PNPM_CONFIG_STORE_DIR=$env:PNPM_CONFIG_STORE_DIR"
+            "PNPM_CONFIG_MODULES_DIR=$env:PNPM_CONFIG_MODULES_DIR"
+            "PNPM_CONFIG_VIRTUAL_STORE_DIR=$env:PNPM_CONFIG_VIRTUAL_STORE_DIR"
+            "PNPM_CONFIG_CHILD_CONCURRENCY=$env:PNPM_CONFIG_CHILD_CONCURRENCY"
+            "PNPM_CONFIG_NETWORK_CONCURRENCY=$env:PNPM_CONFIG_NETWORK_CONCURRENCY"
+            "PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN=$env:PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN"
+            "PNPM_CONFIG_SIDE_EFFECTS_CACHE=$env:PNPM_CONFIG_SIDE_EFFECTS_CACHE"
+          ) | ForEach-Object { Add-GitHubCommandLine $env:GITHUB_ENV $_ }
+          Add-GitHubCommandLine $env:GITHUB_PATH $env:PNPM_HOME
+
+          $packageManager = (Get-Content package.json -Raw | ConvertFrom-Json).packageManager
+          if (-not $packageManager -or -not $packageManager.StartsWith("pnpm@")) {
+            Write-Error "Expected packageManager to pin pnpm, got '$packageManager'"
+          }
+          corepack enable --install-directory $env:PNPM_HOME
+          for ($attempt = 1; $attempt -le 3; $attempt++) {
+            corepack prepare $packageManager --activate
+            if ($LASTEXITCODE -eq 0) {
+              break
+            }
+            if ($attempt -eq 3) {
+              exit $LASTEXITCODE
+            }
+            Start-Sleep -Seconds ($attempt * 5)
+          }
+          $nodeBin = Split-Path -Parent (node -p "process.execPath")
+          Add-GitHubCommandLine $env:GITHUB_ENV "NODE_BIN=$nodeBin"
+          Add-GitHubCommandLine $env:GITHUB_PATH $nodeBin
+          $env:PATH = "$nodeBin;$env:PATH"
+
+          node -v
+          npm -v
+          pnpm -v
+
+          $installArgs = @(
+            "install",
+            "--filter",
+            "openclaw",
+            "--prefer-offline",
+            "--ignore-scripts=true",
+            "--config.engine-strict=false",
+            "--config.enable-pre-post-scripts=false",
+            "--config.side-effects-cache=false",
+            "--frozen-lockfile",
+            "--child-concurrency=$env:PNPM_CONFIG_CHILD_CONCURRENCY",
+            "--modules-dir=$env:PNPM_CONFIG_MODULES_DIR",
+            "--network-concurrency=$env:PNPM_CONFIG_NETWORK_CONCURRENCY",
+            "--store-dir=$env:PNPM_CONFIG_STORE_DIR",
+            "--virtual-store-dir=$env:PNPM_CONFIG_VIRTUAL_STORE_DIR"
+          )
+          pnpm @installArgs
+          if ($LASTEXITCODE -ne 0) {
+            exit $LASTEXITCODE
+          }
+          $corepackShimDir = Join-Path $nodeBin "node_modules\corepack\shims"
+          if (Test-Path $corepackShimDir) {
+            $env:PNPM_HOME = $corepackShimDir
+            Add-GitHubCommandLine $env:GITHUB_ENV "PNPM_HOME=$env:PNPM_HOME"
+            Add-GitHubCommandLine $env:GITHUB_PATH $env:PNPM_HOME
+          }
+
+      - name: Mark Crabbox ready
+        shell: powershell
+        env:
+          CRABBOX_ID: ${{ inputs.crabbox_id }}
+          CRABBOX_JOB: ${{ inputs.crabbox_job }}
+        run: |
+          $ErrorActionPreference = "Stop"
+          $job = if ($env:CRABBOX_JOB) { $env:CRABBOX_JOB } else { "hydrate-windows-daemon" }
+          if (-not $env:CRABBOX_ID -or $env:CRABBOX_ID -notmatch '^[A-Za-z0-9._-]+$') {
+            Write-Error "Invalid crabbox_id"
+          }
+          $actionsRoot = Join-Path $HOME ".crabbox\actions"
+          New-Item -ItemType Directory -Force $actionsRoot | Out-Null
+          $state = Join-Path $actionsRoot "$env:CRABBOX_ID.env"
+          $envFile = Join-Path $actionsRoot "$env:CRABBOX_ID.env.ps1"
+          $servicesFile = Join-Path $actionsRoot "$env:CRABBOX_ID.services"
+          $keys = @(
+            "CI", "GITHUB_ACTIONS", "GITHUB_WORKSPACE", "GITHUB_REPOSITORY",
+            "GITHUB_RUN_ID", "GITHUB_RUN_NUMBER", "GITHUB_RUN_ATTEMPT",
+            "GITHUB_REF", "GITHUB_REF_NAME", "GITHUB_SHA", "GITHUB_EVENT_NAME",
+            "GITHUB_ACTOR", "RUNNER_OS", "RUNNER_ARCH", "RUNNER_TEMP",
+            "RUNNER_TOOL_CACHE", "XDG_CACHE_HOME", "COREPACK_HOME", "NODE_BIN",
+            "PNPM_HOME", "PNPM_CONFIG_CHILD_CONCURRENCY", "PNPM_CONFIG_MODULES_DIR",
+            "PNPM_CONFIG_NETWORK_CONCURRENCY", "PNPM_CONFIG_STORE_DIR",
+            "PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN", "PNPM_CONFIG_VIRTUAL_STORE_DIR",
+            "PNPM_CONFIG_SIDE_EFFECTS_CACHE", "PATH"
+          )
+          $envLines = foreach ($key in $keys) {
+            $value = [Environment]::GetEnvironmentVariable($key)
+            if ($value) {
+              "$key=$value"
+            }
+          }
+          $utf8NoBom = [System.Text.UTF8Encoding]::new($false)
+          [System.IO.File]::WriteAllLines("$envFile.tmp", $envLines, $utf8NoBom)
+          Move-Item -Force "$envFile.tmp" $envFile
+          [System.IO.File]::WriteAllLines(
+            "$servicesFile.tmp",
+            @("# Docker containers visible from the hydrated runner", "docker not available on native Windows hydration"),
+            $utf8NoBom
+          )
+          Move-Item -Force "$servicesFile.tmp" $servicesFile
+          $stateLines = @(
+            "WORKSPACE=$env:GITHUB_WORKSPACE",
+            "RUN_ID=$env:GITHUB_RUN_ID",
+            "JOB=$job",
+            "ENV_FILE=$envFile",
+            "SERVICES_FILE=$servicesFile",
+            "READY_AT=$((Get-Date).ToUniversalTime().ToString("yyyy-MM-ddTHH:mm:ssZ"))"
+          )
+          [System.IO.File]::WriteAllLines("$state.tmp", $stateLines, $utf8NoBom)
+          Move-Item -Force "$state.tmp" $state
+
+      - name: Keep Crabbox job alive
+        shell: powershell
+        env:
+          CRABBOX_ID: ${{ inputs.crabbox_id }}
+          CRABBOX_KEEP_ALIVE_MINUTES: ${{ inputs.crabbox_keep_alive_minutes }}
+        run: |
+          $ErrorActionPreference = "Stop"
+          if (-not $env:CRABBOX_ID -or $env:CRABBOX_ID -notmatch '^[A-Za-z0-9._-]+$') {
+            Write-Error "Invalid crabbox_id"
+          }
+          $minutes = 90
+          if ($env:CRABBOX_KEEP_ALIVE_MINUTES -match '^[0-9]+$') {
+            $minutes = [int]$env:CRABBOX_KEEP_ALIVE_MINUTES
+          }
+          $stop = Join-Path $HOME ".crabbox\actions\$env:CRABBOX_ID.stop"
+          $deadline = (Get-Date).AddMinutes($minutes)
+          while ((Get-Date) -lt $deadline) {
+            if (Test-Path $stop) {
+              exit 0
+            }
+            Start-Sleep -Seconds 15
+          }
+
   hydrate-github:
     name: hydrate-github
     if: ${{ inputs.crabbox_job == 'hydrate-github' }}
@@ -307,7 +534,13 @@ jobs:
 
           if ! command -v docker >/dev/null 2>&1; then
             echo "docker not found; installing fallback engine"
-            curl -fsSL https://get.docker.com | sudo sh
+            curl --fail --show-error --location \
+              --connect-timeout "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_CONNECT_TIMEOUT_SECONDS:-15}" \
+              --max-time "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_TIMEOUT_SECONDS:-300}" \
+              --retry "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_RETRIES:-3}" \
+              --retry-delay "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_RETRY_DELAY_SECONDS:-5}" \
+              --retry-all-errors \
+              https://get.docker.com | sudo sh
           fi
 
           if command -v systemctl >/dev/null 2>&1; then
@@ -332,7 +565,12 @@ jobs:
             esac
             buildx_version="${DOCKER_BUILDX_VERSION:-v0.15.1}"
             mkdir -p "$HOME/.docker/cli-plugins"
-            curl -fsSL \
+            curl --fail --show-error --location \
+              --connect-timeout "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_CONNECT_TIMEOUT_SECONDS:-15}" \
+              --max-time "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_TIMEOUT_SECONDS:-300}" \
+              --retry "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_RETRIES:-3}" \
+              --retry-delay "${OPENCLAW_CRABBOX_HYDRATE_DOWNLOAD_RETRY_DELAY_SECONDS:-5}" \
+              --retry-all-errors \
               "https://github.com/docker/buildx/releases/download/${buildx_version}/buildx-${buildx_version}.linux-${buildx_arch}" \
               -o "$HOME/.docker/cli-plugins/docker-buildx"
             chmod 0755 "$HOME/.docker/cli-plugins/docker-buildx"
@@ -406,7 +644,7 @@ jobs:
             fi
           }
           {
-            for key in CI GITHUB_ACTIONS GITHUB_WORKSPACE GITHUB_REPOSITORY GITHUB_RUN_ID GITHUB_RUN_NUMBER GITHUB_RUN_ATTEMPT GITHUB_REF GITHUB_REF_NAME GITHUB_SHA GITHUB_EVENT_NAME GITHUB_ACTOR RUNNER_OS RUNNER_ARCH RUNNER_TEMP RUNNER_TOOL_CACHE PNPM_CONFIG_CHILD_CONCURRENCY PNPM_CONFIG_MODULES_DIR PNPM_CONFIG_NETWORK_CONCURRENCY PNPM_CONFIG_STORE_DIR PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN PNPM_CONFIG_VIRTUAL_STORE_DIR; do
+            for key in CI GITHUB_ACTIONS GITHUB_WORKSPACE GITHUB_REPOSITORY GITHUB_RUN_ID GITHUB_RUN_NUMBER GITHUB_RUN_ATTEMPT GITHUB_REF GITHUB_REF_NAME GITHUB_SHA GITHUB_EVENT_NAME GITHUB_ACTOR RUNNER_OS RUNNER_ARCH RUNNER_TEMP RUNNER_TOOL_CACHE NODE_BIN PNPM_HOME PNPM_CONFIG_CHILD_CONCURRENCY PNPM_CONFIG_MODULES_DIR PNPM_CONFIG_NETWORK_CONCURRENCY PNPM_CONFIG_STORE_DIR PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN PNPM_CONFIG_VIRTUAL_STORE_DIR PATH; do
               write_export "$key"
             done
           } > "${env_file}.tmp"

.github/workflows/docker-release.yml

@@ -75,6 +75,7 @@ jobs:
       contents: read
     outputs:
       digest: ${{ steps.build.outputs.digest }}
+      browser_digest: ${{ steps.build-browser.outputs.digest }}
     steps:
       - name: Checkout
         uses: actions/checkout@v6
@@ -102,14 +103,18 @@ jobs:
           set -euo pipefail
           tags=()
           slim_tags=()
-          if [[ "${SOURCE_REF}" == "refs/heads/main" ]]; then
-            tags+=("${IMAGE}:main-amd64")
-            slim_tags+=("${IMAGE}:main-slim-amd64")
+          browser_tags=()
+          browser_supported=0
+          if grep -q '^ARG OPENCLAW_INSTALL_BROWSER' Dockerfile; then
+            browser_supported=1
           fi
           if [[ "${SOURCE_REF}" == refs/tags/v* ]]; then
             version="${SOURCE_REF#refs/tags/v}"
             tags+=("${IMAGE}:${version}-amd64")
             slim_tags+=("${IMAGE}:${version}-slim-amd64")
+            if [[ "${browser_supported}" == "1" ]]; then
+              browser_tags+=("${IMAGE}:${version}-browser-amd64")
+            fi
           fi
           if [[ ${#tags[@]} -eq 0 ]]; then
             echo "::error::No amd64 tags resolved for ref ${SOURCE_REF}"
@@ -119,6 +124,9 @@ jobs:
             echo "value<<EOF"
             printf "%s\n" "${tags[@]}" "${slim_tags[@]}"
             echo "EOF"
+            echo "browser<<EOF"
+            printf "%s\n" "${browser_tags[@]}"
+            echo "EOF"
           } >> "$GITHUB_OUTPUT"
 
       - name: Resolve OCI labels (amd64)
@@ -162,6 +170,91 @@ jobs:
           provenance: mode=max
           push: true
 
+      - name: Build and push amd64 browser image
+        id: build-browser
+        if: steps.tags.outputs.browser != ''
+        # WARNING: KEEP THE OFFICIAL DOCKER ACTION HERE; DO NOT SWITCH THIS BACK TO BLACKSMITH BLINDLY.
+        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
+        with:
+          context: .
+          platforms: linux/amd64
+          cache-from: |
+            type=gha,scope=docker-release-amd64
+            type=gha,scope=docker-release-browser-amd64
+          cache-to: type=gha,mode=max,scope=docker-release-browser-amd64
+          build-args: |
+            OPENCLAW_EXTENSIONS=diagnostics-otel,codex
+            OPENCLAW_INSTALL_BROWSER=1
+          tags: ${{ steps.tags.outputs.browser }}
+          labels: ${{ steps.labels.outputs.value }}
+          sbom: true
+          provenance: mode=max
+          push: true
+
+      - name: Smoke test amd64 runtime workspace templates
+        shell: bash
+        env:
+          IMAGE_REFS: ${{ steps.tags.outputs.value }}
+        run: |
+          set -euo pipefail
+          mapfile -t image_refs <<< "${IMAGE_REFS}"
+          image_ref="${image_refs[0]}"
+          if [[ -z "${image_ref}" ]]; then
+            echo "::error::No amd64 image ref resolved for runtime template smoke"
+            exit 1
+          fi
+          docker run --rm --entrypoint /bin/sh "${image_ref}" -lc '
+            set -eu
+            test -f /app/src/agents/templates/HEARTBEAT.md
+            temp_root="$(mktemp -d)"
+            trap "rm -rf \"${temp_root}\"" EXIT
+            mkdir -p "${temp_root}/home" "${temp_root}/cwd"
+            cd "${temp_root}/cwd"
+            set +e
+            HOME="${temp_root}/home" \
+            USERPROFILE="${temp_root}/home" \
+            OPENCLAW_HOME="${temp_root}/home" \
+            OPENCLAW_NO_ONBOARD=1 \
+            OPENCLAW_SUPPRESS_NOTES=1 \
+            OPENCLAW_DISABLE_BUNDLED_PLUGINS=1 \
+            OPENCLAW_DISABLE_BUNDLED_ENTRY_SOURCE_FALLBACK=1 \
+            AWS_EC2_METADATA_DISABLED=true \
+            AWS_SHARED_CREDENTIALS_FILE="${temp_root}/home/.aws/credentials" \
+            AWS_CONFIG_FILE="${temp_root}/home/.aws/config" \
+              node /app/openclaw.mjs agent --message "workspace bootstrap smoke" --session-id "workspace-bootstrap-smoke" --local --timeout 1 --json \
+              >"${temp_root}/out.log" 2>&1
+            status="$?"
+            set -e
+            if grep -F "Missing workspace template:" "${temp_root}/out.log"; then
+              cat "${temp_root}/out.log"
+              exit 1
+            fi
+            test -f "${temp_root}/home/.openclaw/workspace/HEARTBEAT.md"
+            if [ "${status}" -ne 0 ]; then
+              cat "${temp_root}/out.log"
+            fi
+          '
+
+      - name: Smoke test amd64 browser image
+        if: steps.tags.outputs.browser != ''
+        shell: bash
+        env:
+          IMAGE_REFS: ${{ steps.tags.outputs.browser }}
+        run: |
+          set -euo pipefail
+          mapfile -t image_refs <<< "${IMAGE_REFS}"
+          image_ref="${image_refs[0]}"
+          if [[ -z "${image_ref}" ]]; then
+            echo "::error::No amd64 browser image ref resolved"
+            exit 1
+          fi
+          docker run --rm --entrypoint /bin/sh "${image_ref}" -lc '
+            set -eu
+            browser="$(find /home/node/.cache/ms-playwright -maxdepth 5 -type f \( -name chrome -o -name chromium -o -name chrome-headless-shell \) -print | head -1)"
+            test -n "${browser}"
+            "${browser}" --version
+          '
+
   # Build arm64 image. Default and slim tags point to the same slim runtime.
   build-arm64:
     needs: [approve_manual_backfill]
@@ -173,6 +266,7 @@ jobs:
       contents: read
     outputs:
       digest: ${{ steps.build.outputs.digest }}
+      browser_digest: ${{ steps.build-browser.outputs.digest }}
     steps:
       - name: Checkout
         uses: actions/checkout@v6
@@ -200,14 +294,18 @@ jobs:
           set -euo pipefail
           tags=()
           slim_tags=()
-          if [[ "${SOURCE_REF}" == "refs/heads/main" ]]; then
-            tags+=("${IMAGE}:main-arm64")
-            slim_tags+=("${IMAGE}:main-slim-arm64")
+          browser_tags=()
+          browser_supported=0
+          if grep -q '^ARG OPENCLAW_INSTALL_BROWSER' Dockerfile; then
+            browser_supported=1
           fi
           if [[ "${SOURCE_REF}" == refs/tags/v* ]]; then
             version="${SOURCE_REF#refs/tags/v}"
             tags+=("${IMAGE}:${version}-arm64")
             slim_tags+=("${IMAGE}:${version}-slim-arm64")
+            if [[ "${browser_supported}" == "1" ]]; then
+              browser_tags+=("${IMAGE}:${version}-browser-arm64")
+            fi
           fi
           if [[ ${#tags[@]} -eq 0 ]]; then
             echo "::error::No arm64 tags resolved for ref ${SOURCE_REF}"
@@ -217,6 +315,9 @@ jobs:
             echo "value<<EOF"
             printf "%s\n" "${tags[@]}" "${slim_tags[@]}"
             echo "EOF"
+            echo "browser<<EOF"
+            printf "%s\n" "${browser_tags[@]}"
+            echo "EOF"
           } >> "$GITHUB_OUTPUT"
 
       - name: Resolve OCI labels (arm64)
@@ -260,6 +361,91 @@ jobs:
           provenance: mode=max
           push: true
 
+      - name: Build and push arm64 browser image
+        id: build-browser
+        if: steps.tags.outputs.browser != ''
+        # WARNING: KEEP THE OFFICIAL DOCKER ACTION HERE; DO NOT SWITCH THIS BACK TO BLACKSMITH BLINDLY.
+        uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v7.1.0
+        with:
+          context: .
+          platforms: linux/arm64
+          cache-from: |
+            type=gha,scope=docker-release-arm64
+            type=gha,scope=docker-release-browser-arm64
+          cache-to: type=gha,mode=max,scope=docker-release-browser-arm64
+          build-args: |
+            OPENCLAW_EXTENSIONS=diagnostics-otel,codex
+            OPENCLAW_INSTALL_BROWSER=1
+          tags: ${{ steps.tags.outputs.browser }}
+          labels: ${{ steps.labels.outputs.value }}
+          sbom: true
+          provenance: mode=max
+          push: true
+
+      - name: Smoke test arm64 runtime workspace templates
+        shell: bash
+        env:
+          IMAGE_REFS: ${{ steps.tags.outputs.value }}
+        run: |
+          set -euo pipefail
+          mapfile -t image_refs <<< "${IMAGE_REFS}"
+          image_ref="${image_refs[0]}"
+          if [[ -z "${image_ref}" ]]; then
+            echo "::error::No arm64 image ref resolved for runtime template smoke"
+            exit 1
+          fi
+          docker run --rm --entrypoint /bin/sh "${image_ref}" -lc '
+            set -eu
+            test -f /app/src/agents/templates/HEARTBEAT.md
+            temp_root="$(mktemp -d)"
+            trap "rm -rf \"${temp_root}\"" EXIT
+            mkdir -p "${temp_root}/home" "${temp_root}/cwd"
+            cd "${temp_root}/cwd"
+            set +e
+            HOME="${temp_root}/home" \
+            USERPROFILE="${temp_root}/home" \
+            OPENCLAW_HOME="${temp_root}/home" \
+            OPENCLAW_NO_ONBOARD=1 \
+            OPENCLAW_SUPPRESS_NOTES=1 \
+            OPENCLAW_DISABLE_BUNDLED_PLUGINS=1 \
+            OPENCLAW_DISABLE_BUNDLED_ENTRY_SOURCE_FALLBACK=1 \
+            AWS_EC2_METADATA_DISABLED=true \
+            AWS_SHARED_CREDENTIALS_FILE="${temp_root}/home/.aws/credentials" \
+            AWS_CONFIG_FILE="${temp_root}/home/.aws/config" \
+              node /app/openclaw.mjs agent --message "workspace bootstrap smoke" --session-id "workspace-bootstrap-smoke" --local --timeout 1 --json \
+              >"${temp_root}/out.log" 2>&1
+            status="$?"
+            set -e
+            if grep -F "Missing workspace template:" "${temp_root}/out.log"; then
+              cat "${temp_root}/out.log"
+              exit 1
+            fi
+            test -f "${temp_root}/home/.openclaw/workspace/HEARTBEAT.md"
+            if [ "${status}" -ne 0 ]; then
+              cat "${temp_root}/out.log"
+            fi
+          '
+
+      - name: Smoke test arm64 browser image
+        if: steps.tags.outputs.browser != ''
+        shell: bash
+        env:
+          IMAGE_REFS: ${{ steps.tags.outputs.browser }}
+        run: |
+          set -euo pipefail
+          mapfile -t image_refs <<< "${IMAGE_REFS}"
+          image_ref="${image_refs[0]}"
+          if [[ -z "${image_ref}" ]]; then
+            echo "::error::No arm64 browser image ref resolved"
+            exit 1
+          fi
+          docker run --rm --entrypoint /bin/sh "${image_ref}" -lc '
+            set -eu
+            browser="$(find /home/node/.cache/ms-playwright -maxdepth 5 -type f \( -name chrome -o -name chromium -o -name chrome-headless-shell \) -print | head -1)"
+            test -n "${browser}"
+            "${browser}" --version
+          '
+
   # Create multi-platform manifests
   create-manifest:
     needs: [approve_manual_backfill, build-amd64, build-arm64]
@@ -294,18 +480,25 @@ jobs:
           set -euo pipefail
           tags=()
           slim_tags=()
-          if [[ "${SOURCE_REF}" == "refs/heads/main" ]]; then
-            tags+=("${IMAGE}:main")
-            slim_tags+=("${IMAGE}:main-slim")
+          browser_tags=()
+          browser_supported=0
+          if grep -q '^ARG OPENCLAW_INSTALL_BROWSER' Dockerfile; then
+            browser_supported=1
           fi
           if [[ "${SOURCE_REF}" == refs/tags/v* ]]; then
             version="${SOURCE_REF#refs/tags/v}"
             tags+=("${IMAGE}:${version}")
             slim_tags+=("${IMAGE}:${version}-slim")
+            if [[ "${browser_supported}" == "1" ]]; then
+              browser_tags+=("${IMAGE}:${version}-browser")
+            fi
             # Manual backfills should only republish the requested version tags.
             if [[ "${IS_MANUAL_BACKFILL}" != "1" && "$version" =~ ^[0-9]+\.[0-9]+\.[0-9]+(-[0-9]+)?$ ]]; then
-              tags+=("${IMAGE}:latest")
-              slim_tags+=("${IMAGE}:slim")
+              tags+=("${IMAGE}:latest" "${IMAGE}:main")
+              slim_tags+=("${IMAGE}:slim" "${IMAGE}:main-slim")
+              if [[ "${browser_supported}" == "1" ]]; then
+                browser_tags+=("${IMAGE}:latest-browser" "${IMAGE}:main-browser")
+              fi
             fi
           fi
           if [[ ${#tags[@]} -eq 0 ]]; then
@@ -316,25 +509,39 @@ jobs:
             echo "value<<EOF"
             printf "%s\n" "${tags[@]}" "${slim_tags[@]}"
             echo "EOF"
+            echo "browser<<EOF"
+            printf "%s\n" "${browser_tags[@]}"
+            echo "EOF"
           } >> "$GITHUB_OUTPUT"
 
       - name: Create and push manifest
         shell: bash
         env:
           TAGS: ${{ steps.tags.outputs.value }}
+          BROWSER_TAGS: ${{ steps.tags.outputs.browser }}
           AMD64_DIGEST: ${{ needs.build-amd64.outputs.digest }}
           ARM64_DIGEST: ${{ needs.build-arm64.outputs.digest }}
+          AMD64_BROWSER_DIGEST: ${{ needs.build-amd64.outputs.browser_digest }}
+          ARM64_BROWSER_DIGEST: ${{ needs.build-arm64.outputs.browser_digest }}
         run: |
           set -euo pipefail
           mapfile -t tags <<< "${TAGS}"
-          args=()
-          for tag in "${tags[@]}"; do
-            [ -z "$tag" ] && continue
-            args+=("-t" "$tag")
-          done
-          docker buildx imagetools create "${args[@]}" \
-            "${AMD64_DIGEST}" \
-            "${ARM64_DIGEST}"
+          mapfile -t browser_tags <<< "${BROWSER_TAGS}"
+          create_manifest() {
+            local amd64_digest="$1"
+            local arm64_digest="$2"
+            shift 2
+            local args=()
+            for tag in "$@"; do
+              [ -z "$tag" ] && continue
+              args+=("-t" "$tag")
+            done
+            docker buildx imagetools create "${args[@]}" "$amd64_digest" "$arm64_digest"
+          }
+          create_manifest "${AMD64_DIGEST}" "${ARM64_DIGEST}" "${tags[@]}"
+          if [[ -n "${BROWSER_TAGS}" ]]; then
+            create_manifest "${AMD64_BROWSER_DIGEST}" "${ARM64_BROWSER_DIGEST}" "${browser_tags[@]}"
+          fi
 
   verify-attestations:
     needs: [create-manifest]
@@ -372,21 +579,39 @@ jobs:
           slim_multi_refs=()
           amd64_refs=()
           arm64_refs=()
-          if [[ "${SOURCE_REF}" == "refs/heads/main" ]]; then
-            multi_refs+=("${IMAGE}:main")
-            slim_multi_refs+=("${IMAGE}:main-slim")
-            amd64_refs+=("${IMAGE}:main-amd64" "${IMAGE}:main-slim-amd64")
-            arm64_refs+=("${IMAGE}:main-arm64" "${IMAGE}:main-slim-arm64")
+          browser_supported=0
+          if [[ "${SOURCE_REF}" == refs/tags/v* ]]; then
+            tag="${SOURCE_REF#refs/tags/}"
+            git fetch --depth=1 origin "refs/tags/${tag}:refs/tags/${tag}"
+            if git show "${SOURCE_REF}:Dockerfile" | grep -q '^ARG OPENCLAW_INSTALL_BROWSER'; then
+              browser_supported=1
+            fi
+          elif grep -q '^ARG OPENCLAW_INSTALL_BROWSER' Dockerfile; then
+            browser_supported=1
           fi
           if [[ "${SOURCE_REF}" == refs/tags/v* ]]; then
             version="${SOURCE_REF#refs/tags/v}"
             multi_refs+=("${IMAGE}:${version}")
             slim_multi_refs+=("${IMAGE}:${version}-slim")
-            amd64_refs+=("${IMAGE}:${version}-amd64" "${IMAGE}:${version}-slim-amd64")
-            arm64_refs+=("${IMAGE}:${version}-arm64" "${IMAGE}:${version}-slim-arm64")
+            amd64_refs+=(
+              "${IMAGE}:${version}-amd64"
+              "${IMAGE}:${version}-slim-amd64"
+            )
+            arm64_refs+=(
+              "${IMAGE}:${version}-arm64"
+              "${IMAGE}:${version}-slim-arm64"
+            )
+            if [[ "${browser_supported}" == "1" ]]; then
+              multi_refs+=("${IMAGE}:${version}-browser")
+              amd64_refs+=("${IMAGE}:${version}-browser-amd64")
+              arm64_refs+=("${IMAGE}:${version}-browser-arm64")
+            fi
             if [[ "${IS_MANUAL_BACKFILL}" != "1" && "$version" =~ ^[0-9]+\.[0-9]+\.[0-9]+(-[0-9]+)?$ ]]; then
-              multi_refs+=("${IMAGE}:latest")
-              slim_multi_refs+=("${IMAGE}:slim")
+              multi_refs+=("${IMAGE}:latest" "${IMAGE}:main")
+              slim_multi_refs+=("${IMAGE}:slim" "${IMAGE}:main-slim")
+              if [[ "${browser_supported}" == "1" ]]; then
+                multi_refs+=("${IMAGE}:latest-browser" "${IMAGE}:main-browser")
+              fi
             fi
           fi
           if [[ ${#multi_refs[@]} -eq 0 || ${#amd64_refs[@]} -eq 0 || ${#arm64_refs[@]} -eq 0 ]]; then

.github/workflows/full-release-validation.yml

@@ -58,6 +58,7 @@ on:
           - qa-parity
           - qa-live
           - npm-telegram
+          - performance
       live_suite_filter:
         description: Optional exact live/E2E suite id, or comma-separated QA live lanes such as qa-live-matrix,qa-live-telegram; blank runs all selected live suites
         required: false
@@ -79,7 +80,7 @@ on:
         default: ""
         type: string
       evidence_package_spec:
-        description: Optional published package spec to prove in the private release evidence report
+        description: Optional published package spec to prove in the release evidence report
         required: false
         default: ""
         type: string
@@ -181,6 +182,11 @@ jobs:
             else
               echo "- Normal CI: skipped by rerun group"
             fi
+            if [[ "$RERUN_GROUP" == "all" || "$RERUN_GROUP" == "performance" ]]; then
+              echo "- Product performance: \`OpenClaw Performance\` with \`target_ref=${TARGET_SHA}\`"
+            else
+              echo "- Product performance: skipped by rerun group"
+            fi
             if [[ "$RERUN_GROUP" == "all" || "$RERUN_GROUP" == "plugin-prerelease" ]]; then
               echo "- Plugin prerelease: \`Plugin Prerelease\` with \`target_ref=${TARGET_SHA}\`"
             else
@@ -219,7 +225,7 @@ jobs:
           } >> "$GITHUB_STEP_SUMMARY"
 
   docker_runtime_assets_preflight:
-    name: Verify Docker runtime-assets prune path
+    name: Verify Docker runtime image assets
     needs: [resolve_target]
     if: inputs.rerun_group == 'all'
     runs-on: ubuntu-24.04
@@ -239,11 +245,54 @@ jobs:
           DOCKER_BUILDKIT: "1"
         run: |
           set -euo pipefail
-          timeout --foreground --kill-after=30s 35m docker build \
+          timeout --kill-after=30s 35m docker build \
             --target runtime-assets \
             --build-arg OPENCLAW_EXTENSIONS="diagnostics-otel,codex" \
             .
 
+      - name: Build and smoke test final Docker runtime image
+        env:
+          DOCKER_BUILDKIT: "1"
+          TARGET_SHA: ${{ needs.resolve_target.outputs.sha }}
+        run: |
+          set -euo pipefail
+          image_ref="openclaw-release-runtime-smoke:${TARGET_SHA}"
+          timeout --kill-after=30s 35m docker build \
+            --build-arg OPENCLAW_EXTENSIONS="diagnostics-otel,codex" \
+            -t "${image_ref}" \
+            .
+          docker run --rm --entrypoint /bin/sh "${image_ref}" -lc '
+            set -eu
+            test -f /app/src/agents/templates/HEARTBEAT.md
+            temp_root="$(mktemp -d)"
+            trap "rm -rf \"${temp_root}\"" EXIT
+            mkdir -p "${temp_root}/home" "${temp_root}/cwd"
+            cd "${temp_root}/cwd"
+            set +e
+            HOME="${temp_root}/home" \
+            USERPROFILE="${temp_root}/home" \
+            OPENCLAW_HOME="${temp_root}/home" \
+            OPENCLAW_NO_ONBOARD=1 \
+            OPENCLAW_SUPPRESS_NOTES=1 \
+            OPENCLAW_DISABLE_BUNDLED_PLUGINS=1 \
+            OPENCLAW_DISABLE_BUNDLED_ENTRY_SOURCE_FALLBACK=1 \
+            AWS_EC2_METADATA_DISABLED=true \
+            AWS_SHARED_CREDENTIALS_FILE="${temp_root}/home/.aws/credentials" \
+            AWS_CONFIG_FILE="${temp_root}/home/.aws/config" \
+              node /app/openclaw.mjs agent --message "workspace bootstrap smoke" --session-id "workspace-bootstrap-smoke" --local --timeout 1 --json \
+              >"${temp_root}/out.log" 2>&1
+            status="$?"
+            set -e
+            if grep -F "Missing workspace template:" "${temp_root}/out.log"; then
+              cat "${temp_root}/out.log"
+              exit 1
+            fi
+            test -f "${temp_root}/home/.openclaw/workspace/HEARTBEAT.md"
+            if [ "${status}" -ne 0 ]; then
+              cat "${temp_root}/out.log"
+            fi
+          '
+
   normal_ci:
     name: Run normal full CI
     needs: [resolve_target, docker_runtime_assets_preflight]
@@ -281,7 +330,7 @@ jobs:
                   printf '%s\n' "$output"
                   return 0
                 fi
-                if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* ]]; then
+                if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
                   echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
                   sleep $((attempt * 10))
                   continue
@@ -411,7 +460,7 @@ jobs:
                   printf '%s\n' "$output"
                   return 0
                 fi
-                if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* ]]; then
+                if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
                   echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
                   sleep $((attempt * 10))
                   continue
@@ -551,7 +600,7 @@ jobs:
                   printf '%s\n' "$output"
                   return 0
                 fi
-                if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* ]]; then
+                if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
                   echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
                   sleep $((attempt * 10))
                   continue
@@ -853,7 +902,7 @@ jobs:
                 printf '%s\n' "$output"
                 return 0
               fi
-              if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* ]]; then
+              if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
                 echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
                 sleep $((attempt * 10))
                 continue
@@ -938,9 +987,127 @@ jobs:
             exit 1
           fi
 
+  performance:
+    name: Run product performance evidence
+    needs: [resolve_target, docker_runtime_assets_preflight]
+    if: ${{ always() && needs.resolve_target.result == 'success' && contains(fromJSON('["all","performance"]'), inputs.rerun_group) && (inputs.rerun_group != 'all' || needs.docker_runtime_assets_preflight.result == 'success') }}
+    runs-on: ubuntu-24.04
+    timeout-minutes: 120
+    outputs:
+      run_id: ${{ steps.dispatch.outputs.run_id }}
+      url: ${{ steps.dispatch.outputs.url }}
+      conclusion: ${{ steps.dispatch.outputs.conclusion }}
+    steps:
+      - name: Dispatch and monitor OpenClaw Performance
+        id: dispatch
+        env:
+          GH_TOKEN: ${{ github.token }}
+          TARGET_SHA: ${{ needs.resolve_target.outputs.sha }}
+          CHILD_WORKFLOW_REF: ${{ github.ref_name }}
+        run: |
+          set -euo pipefail
+
+          gh_with_retry() {
+            local output status attempt
+            for attempt in 1 2 3 4 5 6; do
+              set +e
+              output="$(gh "$@" 2>&1)"
+              status=$?
+              set -e
+              if [[ "$status" -eq 0 ]]; then
+                printf '%s\n' "$output"
+                return 0
+              fi
+              if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
+                echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
+                sleep $((attempt * 10))
+                continue
+              fi
+              printf '%s\n' "$output" >&2
+              return "$status"
+            done
+            printf '%s\n' "$output" >&2
+            return "$status"
+          }
+
+          {
+            echo "### Product performance"
+            echo
+            echo "- Target SHA: \`${TARGET_SHA}\`"
+            echo "- Profile: \`release\`"
+            echo "- Repeat: \`3\`"
+            echo "- Deep profile: \`false\`"
+            echo "- Live OpenAI candidate: \`false\`"
+            echo "- Release impact: advisory"
+          } >> "$GITHUB_STEP_SUMMARY"
+
+          before_json="$(gh_with_retry run list --workflow openclaw-performance.yml --event workflow_dispatch --limit 100 --json databaseId --jq '[.[].databaseId]')"
+
+          gh_with_retry workflow run openclaw-performance.yml \
+            --ref "$CHILD_WORKFLOW_REF" \
+            -f target_ref="$TARGET_SHA" \
+            -f profile=release \
+            -f repeat=3 \
+            -f deep_profile=false \
+            -f live_openai_candidate=false \
+            -f fail_on_regression=false
+
+          run_id=""
+          for _ in $(seq 1 60); do
+            run_id="$(
+              BEFORE_IDS="$before_json" gh_with_retry run list --workflow openclaw-performance.yml --event workflow_dispatch --limit 50 --json databaseId,createdAt \
+                --jq 'map(select(.databaseId as $id | (env.BEFORE_IDS | fromjson | index($id) | not))) | sort_by(.createdAt) | reverse | .[0].databaseId // empty'
+            )"
+            if [[ -n "$run_id" ]]; then
+              break
+            fi
+            sleep 5
+          done
+
+          if [[ -z "$run_id" ]]; then
+            echo "::warning::Could not find dispatched run for openclaw-performance.yml."
+            exit 0
+          fi
+
+          echo "Dispatched openclaw-performance.yml: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
+          echo "run_id=${run_id}" >> "$GITHUB_OUTPUT"
+
+          cancel_child() {
+            if [[ -n "${run_id:-}" ]]; then
+              echo "Cancelling child workflow openclaw-performance.yml: ${run_id}" >&2
+              gh run cancel "$run_id" >/dev/null 2>&1 || true
+            fi
+          }
+          trap cancel_child EXIT INT TERM
+
+          poll_count=0
+          while true; do
+            status="$(gh_with_retry run view "$run_id" --json status --jq '.status')"
+            if [[ "$status" == "completed" ]]; then
+              break
+            fi
+            poll_count=$((poll_count + 1))
+            if (( poll_count % 10 == 0 )); then
+              echo "Still waiting on openclaw-performance.yml: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
+              gh_with_retry run view "$run_id" --json jobs --jq '.jobs[] | select(.status != "completed") | {name, status, url}' || true
+            fi
+            sleep 30
+          done
+          trap - EXIT INT TERM
+
+          conclusion="$(gh_with_retry run view "$run_id" --json conclusion --jq '.conclusion')"
+          url="$(gh_with_retry run view "$run_id" --json url --jq '.url')"
+          echo "openclaw-performance.yml finished with ${conclusion}: ${url}"
+          echo "url=${url}" >> "$GITHUB_OUTPUT"
+          echo "conclusion=${conclusion}" >> "$GITHUB_OUTPUT"
+          if [[ "$conclusion" != "success" ]]; then
+            echo "::warning::OpenClaw Performance is advisory and ended with ${conclusion}: ${url}"
+            gh_with_retry run view "$run_id" --json jobs --jq '.jobs[] | select(.conclusion != "success" and .conclusion != "skipped") | {name, conclusion, url}' || true
+          fi
+
   summary:
     name: Verify full validation
-    needs: [resolve_target, docker_runtime_assets_preflight, normal_ci, plugin_prerelease, release_checks, npm_telegram]
+    needs: [resolve_target, docker_runtime_assets_preflight, normal_ci, plugin_prerelease, release_checks, npm_telegram, performance]
     if: always()
     runs-on: ubuntu-24.04
     timeout-minutes: 5
@@ -952,10 +1119,12 @@ jobs:
           PLUGIN_PRERELEASE_RUN_ID: ${{ needs.plugin_prerelease.outputs.run_id }}
           RELEASE_CHECKS_RUN_ID: ${{ needs.release_checks.outputs.run_id }}
           NPM_TELEGRAM_RUN_ID: ${{ needs.npm_telegram.outputs.run_id }}
+          PERFORMANCE_RUN_ID: ${{ needs.performance.outputs.run_id }}
           NORMAL_CI_RESULT: ${{ needs.normal_ci.result }}
           PLUGIN_PRERELEASE_RESULT: ${{ needs.plugin_prerelease.result }}
           RELEASE_CHECKS_RESULT: ${{ needs.release_checks.result }}
           NPM_TELEGRAM_RESULT: ${{ needs.npm_telegram.result }}
+          PERFORMANCE_RESULT: ${{ needs.performance.result }}
           DOCKER_RUNTIME_ASSETS_PREFLIGHT_RESULT: ${{ needs.docker_runtime_assets_preflight.result }}
           RERUN_GROUP: ${{ inputs.rerun_group }}
           TARGET_SHA: ${{ needs.resolve_target.outputs.sha }}
@@ -963,6 +1132,29 @@ jobs:
         run: |
           set -euo pipefail
 
+          gh_with_retry() {
+            local output status attempt
+            for attempt in 1 2 3 4 5 6; do
+              set +e
+              output="$(gh "$@" 2>&1)"
+              status=$?
+              set -e
+              if [[ "$status" -eq 0 ]]; then
+                printf '%s\n' "$output"
+                return 0
+              fi
+              if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
+                echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
+                sleep $((attempt * 10))
+                continue
+              fi
+              printf '%s\n' "$output" >&2
+              return "$status"
+            done
+            printf '%s\n' "$output" >&2
+            return "$status"
+          }
+
           release_check_blocking_job() {
             case "$1" in
               "resolve_target" | \
@@ -1019,7 +1211,7 @@ jobs:
             fi
 
             local run_json status conclusion url attempt head_sha
-            run_json="$(gh run view "$run_id" --json status,conclusion,url,attempt,headSha,jobs)"
+            run_json="$(gh_with_retry run view "$run_id" --json status,conclusion,url,attempt,headSha,jobs)"
             status="$(jq -r '.status' <<< "$run_json")"
             conclusion="$(jq -r '.conclusion' <<< "$run_json")"
             url="$(jq -r '.url' <<< "$run_json")"
@@ -1066,7 +1258,7 @@ jobs:
               fi
 
               local run_json row
-              run_json="$(gh run view "$run_id" --json status,conclusion,url,createdAt,updatedAt,headSha)"
+              run_json="$(gh_with_retry run view "$run_id" --json status,conclusion,url,createdAt,updatedAt,headSha)"
               row="$(
                 jq -r --arg label "$label" '
                   def ts: fromdateiso8601;
@@ -1088,6 +1280,7 @@ jobs:
             append_child_row "plugin_prerelease" "$PLUGIN_PRERELEASE_RUN_ID" "$PLUGIN_PRERELEASE_RESULT"
             append_child_row "release_checks" "$RELEASE_CHECKS_RUN_ID" "$RELEASE_CHECKS_RESULT"
             append_child_row "npm_telegram" "$NPM_TELEGRAM_RUN_ID" "$NPM_TELEGRAM_RESULT"
+            append_child_row "product_performance" "$PERFORMANCE_RUN_ID" "$PERFORMANCE_RESULT"
           }
 
           summarize_child_timing() {
@@ -1101,7 +1294,7 @@ jobs:
               echo
               echo "### Slowest jobs: ${label}"
               echo
-              gh run view "$run_id" --json jobs --jq '
+              gh_with_retry run view "$run_id" --json jobs --jq '
                 def ts: fromdateiso8601;
                 "| Job | Result | Minutes |",
                 "| --- | --- | ---: |",
@@ -1118,7 +1311,7 @@ jobs:
               echo
               echo "### Longest queues: ${label}"
               echo
-              gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/jobs?per_page=100" --jq ".jobs[] | @json" | jq -sr '
+              gh_with_retry api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/jobs?per_page=100" --jq ".jobs[] | @json" | jq -sr '
                 def ts: fromdateiso8601;
                 "| Job | Result | Queue minutes | Run minutes |",
                 "| --- | --- | ---: | ---: |",
@@ -1147,7 +1340,7 @@ jobs:
             fi
 
             local run_json status conclusion artifacts_json
-            run_json="$(gh run view "$run_id" --json status,conclusion,url,jobs)"
+            run_json="$(gh_with_retry run view "$run_id" --json status,conclusion,url,jobs)"
             status="$(jq -r '.status' <<< "$run_json")"
             conclusion="$(jq -r '.conclusion' <<< "$run_json")"
             if [[ "$status" == "completed" && "$conclusion" == "success" ]]; then
@@ -1170,7 +1363,7 @@ jobs:
               echo
               echo "Artifacts:"
               artifacts_json="$(
-                gh api "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/artifacts?per_page=100" 2>/dev/null || true
+                gh_with_retry api "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/artifacts?per_page=100" 2>/dev/null || true
               )"
               if [[ -n "${artifacts_json// }" ]]; then
                 jq -r '
@@ -1246,6 +1439,7 @@ jobs:
           summarize_child_timing "plugin_prerelease" "$PLUGIN_PRERELEASE_RUN_ID"
           summarize_child_timing "release_checks" "$RELEASE_CHECKS_RUN_ID"
           summarize_child_timing "npm_telegram" "$NPM_TELEGRAM_RUN_ID"
+          summarize_child_timing "product_performance" "$PERFORMANCE_RUN_ID"
 
           if [[ "$failed" != "0" ]]; then
             summarize_failed_child "normal_ci" "$NORMAL_CI_RUN_ID"
@@ -1256,9 +1450,9 @@ jobs:
 
           exit "$failed"
 
-      - name: Request private evidence update
+      - name: Request release evidence update
         env:
-          RELEASE_PRIVATE_DISPATCH_TOKEN: ${{ secrets.OPENCLAW_RELEASES_PRIVATE_DISPATCH_TOKEN }}
+          RELEASES_DISPATCH_TOKEN: ${{ secrets.OPENCLAW_RELEASES_DISPATCH_TOKEN }}
           TARGET_REF: ${{ inputs.ref }}
           PACKAGE_SPEC: ${{ inputs.evidence_package_spec || inputs.npm_telegram_package_spec }}
           GITHUB_RUN_ID_VALUE: ${{ github.run_id }}
@@ -1266,11 +1460,11 @@ jobs:
         run: |
           set -euo pipefail
           if [[ "$RELEASE_CHECKS_RESULT" == "skipped" ]]; then
-            echo "Release checks were skipped by rerun group; skipping automatic private evidence update."
+            echo "Release checks were skipped by rerun group; skipping automatic release evidence update."
             exit 0
           fi
-          if [[ -z "${RELEASE_PRIVATE_DISPATCH_TOKEN// }" ]]; then
-            echo "OPENCLAW_RELEASES_PRIVATE_DISPATCH_TOKEN is not configured; skipping automatic private evidence update."
+          if [[ -z "${RELEASES_DISPATCH_TOKEN// }" ]]; then
+            echo "OPENCLAW_RELEASES_DISPATCH_TOKEN is not configured; skipping automatic release evidence update."
             exit 0
           fi
 
@@ -1289,7 +1483,7 @@ jobs:
           fi
           release_id="$(printf '%s' "$release_id" | tr '/:@ ' '----' | tr -cd 'A-Za-z0-9._-')"
           if [[ -z "$release_id" ]]; then
-            echo "::warning::Could not derive release evidence id from target ref '${TARGET_REF}'; skipping automatic private evidence update."
+            echo "::warning::Could not derive release evidence id from target ref '${TARGET_REF}'; skipping automatic release evidence update."
             exit 0
           fi
 
@@ -1315,18 +1509,18 @@ jobs:
           if ! curl --fail-with-body \
             -X POST \
             -H "Accept: application/vnd.github+json" \
-            -H "Authorization: Bearer ${RELEASE_PRIVATE_DISPATCH_TOKEN}" \
+            -H "Authorization: Bearer ${RELEASES_DISPATCH_TOKEN}" \
             -H "X-GitHub-Api-Version: 2022-11-28" \
-            https://api.github.com/repos/openclaw/releases-private/dispatches \
+            https://api.github.com/repos/openclaw/releases/dispatches \
             -d "$payload"; then
-            echo "::warning::Automatic private release evidence dispatch failed; child workflow validation remains authoritative."
+            echo "::warning::Automatic release evidence dispatch failed; child workflow validation remains authoritative."
             {
-              echo "### Private release evidence dispatch failed"
+              echo "### Release evidence dispatch failed"
               echo
-              echo "Child workflow validation remains authoritative. Backfill durable evidence from \`openclaw/releases-private\`:"
+              echo "Child workflow validation remains authoritative. Backfill durable evidence from \`openclaw/releases\`:"
               echo
               echo "\`\`\`bash"
-              echo "gh workflow run openclaw-release-evidence-from-full-validation.yml --repo openclaw/releases-private --ref main -f full_validation_run_id=${GITHUB_RUN_ID_VALUE} -f release_id=${release_id} -f release_ref=${TARGET_REF} -f package_spec=${evidence_package_spec}"
+              echo "gh workflow run openclaw-release-evidence-from-full-validation.yml --repo openclaw/releases --ref main -f full_validation_run_id=${GITHUB_RUN_ID_VALUE} -f release_id=${release_id} -f release_ref=${TARGET_REF} -f package_spec=${evidence_package_spec}"
               echo "\`\`\`"
             } >> "$GITHUB_STEP_SUMMARY"
           fi
@@ -1343,6 +1537,7 @@ jobs:
           PLUGIN_PRERELEASE_RUN_ID: ${{ needs.plugin_prerelease.outputs.run_id }}
           RELEASE_CHECKS_RUN_ID: ${{ needs.release_checks.outputs.run_id }}
           NPM_TELEGRAM_RUN_ID: ${{ needs.npm_telegram.outputs.run_id }}
+          PERFORMANCE_RUN_ID: ${{ needs.performance.outputs.run_id }}
         run: |
           set -euo pipefail
           manifest_dir="${RUNNER_TEMP}/full-release-validation"
@@ -1361,6 +1556,7 @@ jobs:
             --arg pluginPrereleaseRunId "$PLUGIN_PRERELEASE_RUN_ID" \
             --arg releaseChecksRunId "$RELEASE_CHECKS_RUN_ID" \
             --arg npmTelegramRunId "$NPM_TELEGRAM_RUN_ID" \
+            --arg performanceRunId "$PERFORMANCE_RUN_ID" \
             '{
               version: 1,
               workflowName: $workflowName,
@@ -1376,7 +1572,8 @@ jobs:
                 normalCi: $normalCiRunId,
                 pluginPrerelease: $pluginPrereleaseRunId,
                 releaseChecks: $releaseChecksRunId,
-                npmTelegram: $npmTelegramRunId
+                npmTelegram: $npmTelegramRunId,
+                productPerformance: $performanceRunId
               }
             }' > "${manifest_dir}/full-release-validation-manifest.json"
 

.github/workflows/install-smoke.yml

@@ -121,7 +121,7 @@ jobs:
       # builder stalls; an explicit buildx invocation fails closed instead.
       - name: Build root Dockerfile smoke image
         run: |
-          timeout 45m docker buildx build \
+          timeout --kill-after=30s 45m docker buildx build \
             --progress=plain \
             --load \
             --build-arg OPENCLAW_EXTENSIONS=matrix \
@@ -132,7 +132,7 @@ jobs:
 
       - name: Run root Dockerfile CLI smoke
         run: |
-          docker run --rm --entrypoint sh openclaw-dockerfile-smoke:local -lc '
+          timeout --kill-after=30s 20m docker run --rm --entrypoint sh openclaw-dockerfile-smoke:local -lc '
             which openclaw &&
             openclaw --version &&
             node -e "
@@ -163,7 +163,7 @@ jobs:
 
       - name: Smoke test Dockerfile with matrix extension build arg
         run: |
-          docker run --rm --entrypoint sh openclaw-ext-smoke:local -lc '
+          timeout --kill-after=30s 20m docker run --rm --entrypoint sh openclaw-ext-smoke:local -lc '
             which openclaw &&
             openclaw --version &&
             node -e "
@@ -235,7 +235,7 @@ jobs:
           IMAGE_REF: ${{ needs.preflight.outputs.dockerfile_image }}
         run: |
           set -euo pipefail
-          if timeout 180s docker pull "$IMAGE_REF"; then
+          if timeout --kill-after=30s 180s docker pull "$IMAGE_REF"; then
             echo "exists=true" >> "$GITHUB_OUTPUT"
             echo "Using existing root Dockerfile smoke image: \`$IMAGE_REF\`" >> "$GITHUB_STEP_SUMMARY"
           else
@@ -256,7 +256,7 @@ jobs:
         env:
           IMAGE_REF: ${{ needs.preflight.outputs.dockerfile_image }}
         run: |
-          timeout 45m docker buildx build \
+          timeout --kill-after=30s 45m docker buildx build \
             --progress=plain \
             --push \
             --build-arg OPENCLAW_EXTENSIONS=matrix \
@@ -320,13 +320,13 @@ jobs:
       - name: Pull root Dockerfile smoke image
         env:
           IMAGE_REF: ${{ needs.root_dockerfile_image.outputs.image_ref }}
-        run: timeout 600s docker pull "$IMAGE_REF"
+        run: timeout --kill-after=30s 600s docker pull "$IMAGE_REF"
 
       - name: Run root Dockerfile CLI smoke
         env:
           IMAGE_REF: ${{ needs.root_dockerfile_image.outputs.image_ref }}
         run: |
-          docker run --rm --entrypoint sh "$IMAGE_REF" -lc '
+          timeout --kill-after=30s 20m docker run --rm --entrypoint sh "$IMAGE_REF" -lc '
             which openclaw &&
             openclaw --version &&
             node -e "
@@ -359,7 +359,7 @@ jobs:
         env:
           IMAGE_REF: ${{ needs.root_dockerfile_image.outputs.image_ref }}
         run: |
-          docker run --rm --entrypoint sh "$IMAGE_REF" -lc '
+          timeout --kill-after=30s 20m docker run --rm --entrypoint sh "$IMAGE_REF" -lc '
             which openclaw &&
             openclaw --version &&
             node -e "
@@ -426,7 +426,7 @@ jobs:
       - name: Pull root Dockerfile smoke image
         env:
           IMAGE_REF: ${{ needs.root_dockerfile_image.outputs.image_ref }}
-        run: timeout 600s docker pull "$IMAGE_REF"
+        run: timeout --kill-after=30s 600s docker pull "$IMAGE_REF"
 
       - name: Set up Blacksmith Docker Builder
         uses: useblacksmith/setup-docker-builder@722e97d12b1d06a961800dd6c05d79d951ad3c80 # v1
@@ -435,7 +435,7 @@ jobs:
 
       - name: Build installer smoke image
         run: |
-          timeout 20m docker buildx build \
+          timeout --kill-after=30s 20m docker buildx build \
             --progress=plain \
             --load \
             -t openclaw-install-smoke:local \
@@ -444,7 +444,7 @@ jobs:
 
       - name: Build installer non-root image
         run: |
-          timeout 20m docker buildx build \
+          timeout --kill-after=30s 20m docker buildx build \
             --progress=plain \
             --load \
             -t openclaw-install-nonroot:local \
@@ -475,13 +475,22 @@ jobs:
 
       - name: Run Rocky Linux installer smoke
         run: |
-          timeout 20m docker run --rm \
+          timeout --kill-after=30s 20m docker run --rm \
             -e OPENCLAW_NO_ONBOARD=1 \
             -e OPENCLAW_NO_PROMPT=1 \
             -v "$PWD/scripts/install.sh:/tmp/install.sh:ro" \
             rockylinux:9@sha256:d7be1c094cc5845ee815d4632fe377514ee6ebcf8efaed6892889657e5ddaaa6 \
             bash -lc 'dnf install -y -q ca-certificates tar gzip xz findutils which sudo >/dev/null && bash /tmp/install.sh --install-method npm --version latest --no-onboard --no-prompt --verify && openclaw --version'
 
+      - name: Run Rocky Linux CLI installer smoke
+        run: |
+          timeout --kill-after=30s 20m docker run --rm \
+            -e OPENCLAW_NO_ONBOARD=1 \
+            -e OPENCLAW_NO_PROMPT=1 \
+            -v "$PWD/scripts/install-cli.sh:/tmp/install-cli.sh:ro" \
+            rockylinux:9@sha256:d7be1c094cc5845ee815d4632fe377514ee6ebcf8efaed6892889657e5ddaaa6 \
+            bash -lc 'dnf install -y -q ca-certificates tar gzip xz findutils which sudo >/dev/null && bash /tmp/install-cli.sh --prefix /tmp/openclaw-cli --version latest --no-onboard && /tmp/openclaw-cli/bin/openclaw --version'
+
   bun_global_install_smoke:
     needs: [preflight, root_dockerfile_image]
     if: needs.preflight.outputs.run_full_install_smoke == 'true' && needs.preflight.outputs.run_bun_global_install_smoke == 'true'
@@ -503,7 +512,7 @@ jobs:
       - name: Pull root Dockerfile smoke image
         env:
           IMAGE_REF: ${{ needs.root_dockerfile_image.outputs.image_ref }}
-        run: timeout 600s docker pull "$IMAGE_REF"
+        run: timeout --kill-after=30s 600s docker pull "$IMAGE_REF"
 
       - name: Setup Node environment for Bun smoke
         uses: ./.github/actions/setup-node-env

.github/workflows/macos-release.yml

@@ -93,8 +93,8 @@ jobs:
             echo "It does not sign, notarize, or upload macOS assets."
             echo
             echo "Next step:"
-            echo "- Run \`openclaw/releases-private/.github/workflows/openclaw-macos-validate.yml\` with tag \`${RELEASE_TAG}\` and wait for the private mac validation lane to pass."
-            echo "- Run \`openclaw/releases-private/.github/workflows/openclaw-macos-publish.yml\` with tag \`${RELEASE_TAG}\` and \`preflight_only=true\` for the full private mac preflight."
-            echo "- For the real publish path, run the same private mac publish workflow from \`main\` with the successful private preflight \`preflight_run_id\` so it promotes the prepared artifacts instead of rebuilding them."
-            echo "- For stable releases, the private publish workflow also publishes the signed \`appcast.xml\` to public \`main\`, or opens an appcast PR if direct push is blocked."
+            echo "- Run \`openclaw/releases/.github/workflows/openclaw-macos-validate.yml\` with tag \`${RELEASE_TAG}\` and wait for the macOS validation lane to pass."
+            echo "- Run \`openclaw/releases/.github/workflows/openclaw-macos-publish.yml\` with tag \`${RELEASE_TAG}\` and \`preflight_only=true\` for the full macOS preflight."
+            echo "- For the real publish path, run the same macOS publish workflow from \`main\` with the successful preflight \`preflight_run_id\` so it promotes the prepared artifacts instead of rebuilding them."
+            echo "- For stable releases, the publish workflow also publishes the signed \`appcast.xml\` to public \`main\`, or opens an appcast PR if direct push is blocked."
           } >> "$GITHUB_STEP_SUMMARY"

.github/workflows/mantis-telegram-desktop-proof.yml

@@ -48,6 +48,8 @@ env:
   OPENCLAW_BUILD_PRIVATE_QA: "1"
   OPENCLAW_ENABLE_PRIVATE_QA_CLI: "1"
   CRABBOX_REF: main
+  CRABBOX_AWS_REGION: us-east-1
+  CRABBOX_CAPACITY_REGIONS: us-east-1
   MANTIS_OUTPUT_DIR: .artifacts/qa-e2e/mantis/telegram-desktop-proof
 
 jobs:
@@ -223,6 +225,7 @@ jobs:
       - name: Checkout harness ref
         uses: actions/checkout@v6
         with:
+          ref: main
           persist-credentials: false
           fetch-depth: 0
 
@@ -238,9 +241,6 @@ jobs:
           set -euo pipefail
 
           git fetch --no-tags origin +refs/heads/main:refs/remotes/origin/main
-          if [[ -n "${PR_NUMBER:-}" ]]; then
-            git fetch --no-tags origin "+refs/pull/${PR_NUMBER}/head:refs/remotes/origin/pr/${PR_NUMBER}" || true
-          fi
 
           resolve_commit() {
             local input_ref="$2"
@@ -254,7 +254,6 @@ jobs:
           }
 
           baseline_revision="$(resolve_commit baseline "$BASELINE_REF")"
-          candidate_revision="$(resolve_commit candidate "$CANDIDATE_REF")"
           if ! git merge-base --is-ancestor "$baseline_revision" refs/remotes/origin/main; then
             echo "baseline ref '${BASELINE_REF}' resolved to ${baseline_revision}, which is not on main." >&2
             exit 1
@@ -268,6 +267,11 @@ jobs:
           pr_state="$(jq -r '.state' <<<"$pr_head")"
           pr_head_sha="$(jq -r '.head_sha' <<<"$pr_head")"
           pr_head_repo="$(jq -r '.head_repo' <<<"$pr_head")"
+          candidate_revision="$CANDIDATE_REF"
+          if [[ ! "$candidate_revision" =~ ^[0-9a-f]{40}$ ]]; then
+            echo "candidate ref '${CANDIDATE_REF}' is not an immutable commit SHA." >&2
+            exit 1
+          fi
           if [[ "$pr_state" != "open" || "$candidate_revision" != "$pr_head_sha" ]]; then
             echo "candidate ref '${CANDIDATE_REF}' resolved to ${candidate_revision}, which is not the open PR head." >&2
             exit 1
@@ -422,7 +426,7 @@ jobs:
           {
             printf '%s\n' 'Defaults env_keep += "CODEX_HOME CODEX_INTERNAL_ORIGINATOR_OVERRIDE"'
             printf '%s\n' 'Defaults env_keep += "BASELINE_REF BASELINE_SHA CANDIDATE_REF CANDIDATE_SHA"'
-            printf '%s\n' 'Defaults env_keep += "CRABBOX_ACCESS_CLIENT_ID CRABBOX_ACCESS_CLIENT_SECRET CRABBOX_COORDINATOR CRABBOX_COORDINATOR_TOKEN CRABBOX_LEASE_ID CRABBOX_PROVIDER"'
+            printf '%s\n' 'Defaults env_keep += "CRABBOX_ACCESS_CLIENT_ID CRABBOX_ACCESS_CLIENT_SECRET CRABBOX_COORDINATOR CRABBOX_COORDINATOR_TOKEN CRABBOX_AWS_REGION CRABBOX_CAPACITY_REGIONS CRABBOX_LEASE_ID CRABBOX_PROVIDER"'
             printf '%s\n' 'Defaults env_keep += "GH_TOKEN MANTIS_CANDIDATE_TRUST MANTIS_INSTRUCTIONS MANTIS_OUTPUT_DIR MANTIS_PR_NUMBER"'
             printf '%s\n' 'Defaults env_keep += "OPENCLAW_BUILD_PRIVATE_QA OPENCLAW_ENABLE_PRIVATE_QA_CLI OPENCLAW_QA_CONVEX_SECRET_CI OPENCLAW_QA_CONVEX_SITE_URL OPENCLAW_QA_CREDENTIAL_OWNER_ID OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR_TOKEN"'
             printf '%s\n' 'Defaults env_keep += "OPENCLAW_TELEGRAM_USER_CRABBOX_BIN OPENCLAW_TELEGRAM_USER_CRABBOX_PROVIDER OPENCLAW_TELEGRAM_USER_DRIVER_SCRIPT OPENCLAW_TELEGRAM_USER_PROOF_CMD"'
@@ -451,6 +455,8 @@ jobs:
           CRABBOX_ACCESS_CLIENT_SECRET: ${{ secrets.CRABBOX_ACCESS_CLIENT_SECRET }}
           CRABBOX_COORDINATOR: ${{ secrets.CRABBOX_COORDINATOR || secrets.OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR }}
           CRABBOX_COORDINATOR_TOKEN: ${{ secrets.CRABBOX_COORDINATOR_TOKEN || secrets.OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR_TOKEN }}
+          CRABBOX_AWS_REGION: ${{ env.CRABBOX_AWS_REGION }}
+          CRABBOX_CAPACITY_REGIONS: ${{ env.CRABBOX_CAPACITY_REGIONS }}
           CRABBOX_LEASE_ID: ${{ needs.resolve_request.outputs.lease_id }}
           CRABBOX_PROVIDER: ${{ needs.resolve_request.outputs.crabbox_provider }}
           GH_TOKEN: ${{ github.token }}
@@ -492,8 +498,11 @@ jobs:
             exit 0
           fi
           status=0
-          mapfile -d '' session_files < <(sudo find .artifacts/qa-e2e -path '*/telegram-user-crabbox/*/session.json' -type f -print0)
+          mapfile -d '' session_files < <(sudo find .artifacts/qa-e2e -name session.json -type f -print0)
           for session_file in "${session_files[@]}"; do
+            if ! sudo -u codex node -e 'const fs = require("fs"); const session = JSON.parse(fs.readFileSync(process.argv[1], "utf8")); process.exit(session.command === "telegram-user-crabbox-session" ? 0 : 1);' "$session_file"; then
+              continue
+            fi
             lease_file="${session_file%/session.json}/.session/lease.json"
             if [[ ! -f "$lease_file" ]]; then
               continue
@@ -508,8 +517,11 @@ jobs:
               status=1
             fi
           done
-          mapfile -d '' lease_files < <(sudo find .artifacts/qa-e2e -path '*/telegram-user-crabbox/*/.session/lease.json' -type f -print0)
+          mapfile -d '' lease_files < <(sudo find .artifacts/qa-e2e -path '*/.session/lease.json' -type f -print0)
           for lease_file in "${lease_files[@]}"; do
+            if ! sudo -u codex node -e 'const fs = require("fs"); const lease = JSON.parse(fs.readFileSync(process.argv[1], "utf8")); process.exit(lease.kind === "telegram-user" ? 0 : 1);' "$lease_file"; then
+              continue
+            fi
             if ! sudo -u codex env \
               OPENCLAW_QA_CONVEX_SECRET_CI="$OPENCLAW_QA_CONVEX_SECRET_CI" \
               OPENCLAW_QA_CONVEX_SITE_URL="$OPENCLAW_QA_CONVEX_SITE_URL" \

.github/workflows/mantis-telegram-live.yml

@@ -44,6 +44,8 @@ env:
   OPENCLAW_BUILD_PRIVATE_QA: "1"
   OPENCLAW_ENABLE_PRIVATE_QA_CLI: "1"
   CRABBOX_REF: main
+  CRABBOX_AWS_REGION: us-east-1
+  CRABBOX_CAPACITY_REGIONS: us-east-1
 
 jobs:
   authorize_actor:
@@ -383,6 +385,8 @@ jobs:
           OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR_TOKEN: ${{ secrets.OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR_TOKEN }}
           CRABBOX_ACCESS_CLIENT_ID: ${{ secrets.CRABBOX_ACCESS_CLIENT_ID }}
           CRABBOX_ACCESS_CLIENT_SECRET: ${{ secrets.CRABBOX_ACCESS_CLIENT_SECRET }}
+          CRABBOX_AWS_REGION: ${{ env.CRABBOX_AWS_REGION }}
+          CRABBOX_CAPACITY_REGIONS: ${{ env.CRABBOX_CAPACITY_REGIONS }}
           CRABBOX_LEASE_ID: ${{ needs.resolve_request.outputs.lease_id }}
           CRABBOX_PROVIDER: ${{ needs.resolve_request.outputs.crabbox_provider }}
           SCENARIO_INPUT: ${{ needs.resolve_request.outputs.scenario }}

.github/workflows/openclaw-cross-os-release-checks-reusable.yml

@@ -553,6 +553,15 @@ jobs:
           use-actions-cache: "false"
 
       - name: Download candidate artifact
+        id: download_candidate
+        continue-on-error: true
+        uses: actions/download-artifact@v8
+        with:
+          name: openclaw-cross-os-release-checks-candidate-${{ github.run_id }}
+          path: ${{ runner.temp }}/openclaw-cross-os-release-checks/candidate
+
+      - name: Retry candidate artifact download
+        if: ${{ steps.download_candidate.outcome == 'failure' }}
         uses: actions/download-artifact@v8
         with:
           name: openclaw-cross-os-release-checks-candidate-${{ github.run_id }}
@@ -560,11 +569,38 @@ jobs:
 
       - name: Download baseline artifact
         if: ${{ matrix.suite == 'packaged-upgrade' }}
+        id: download_baseline
+        continue-on-error: true
         uses: actions/download-artifact@v8
         with:
           name: openclaw-cross-os-release-checks-baseline-${{ github.run_id }}
           path: ${{ runner.temp }}/openclaw-cross-os-release-checks/baseline
 
+      - name: Retry baseline artifact download
+        if: ${{ matrix.suite == 'packaged-upgrade' && steps.download_baseline.outcome == 'failure' }}
+        uses: actions/download-artifact@v8
+        with:
+          name: openclaw-cross-os-release-checks-baseline-${{ github.run_id }}
+          path: ${{ runner.temp }}/openclaw-cross-os-release-checks/baseline
+
+      - name: Verify release-check inputs
+        shell: bash
+        env:
+          CANDIDATE_TGZ: ${{ runner.temp }}/openclaw-cross-os-release-checks/candidate/${{ needs.prepare.outputs.candidate_file_name }}
+          BASELINE_TGZ: ${{ runner.temp }}/openclaw-cross-os-release-checks/baseline/${{ needs.prepare.outputs.baseline_file_name }}
+          OUTPUT_DIR: ${{ runner.temp }}/openclaw-cross-os-release-checks/${{ matrix.artifact_name }}-${{ matrix.suite }}
+          SUITE: ${{ matrix.suite }}
+        run: |
+          mkdir -p "${OUTPUT_DIR}"
+          if [[ ! -f "${CANDIDATE_TGZ}" ]]; then
+            echo "::error::candidate artifact missing: ${CANDIDATE_TGZ}"
+            exit 1
+          fi
+          if [[ "${SUITE}" == "packaged-upgrade" ]] && [[ ! -f "${BASELINE_TGZ}" ]]; then
+            echo "::error::baseline artifact missing: ${BASELINE_TGZ}"
+            exit 1
+          fi
+
       - name: Run cross-OS release checks
         shell: bash
         env:
@@ -615,7 +651,8 @@ jobs:
           if [[ -f "${SUMMARY_PATH}" ]]; then
             cat "${SUMMARY_PATH}" >> "$GITHUB_STEP_SUMMARY"
           else
-            echo "No summary generated." >> "$GITHUB_STEP_SUMMARY"
+            mkdir -p "$(dirname "${SUMMARY_PATH}")"
+            echo "No summary generated." | tee "${SUMMARY_PATH}" >> "$GITHUB_STEP_SUMMARY"
           fi
 
       - name: Upload release-check artifacts

.github/workflows/openclaw-live-and-e2e-checks-reusable.yml

@@ -102,6 +102,11 @@ on:
           - beta
           - stable
           - full
+      use_github_hosted_runners:
+        description: Use GitHub-hosted runners instead of Blacksmith runners
+        required: false
+        default: false
+        type: boolean
       advisory:
         description: Treat failures as advisory for the caller
         required: false
@@ -208,6 +213,11 @@ on:
         required: false
         default: stable
         type: string
+      use_github_hosted_runners:
+        description: Use GitHub-hosted runners instead of Blacksmith runners
+        required: false
+        default: true
+        type: boolean
     secrets:
       OPENAI_API_KEY:
         required: false
@@ -474,7 +484,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_live_suites && !inputs.live_models_only && (inputs.live_suite_filter == '' || inputs.live_suite_filter == 'live-cache')
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     timeout-minutes: 20
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -524,7 +534,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_repo_e2e && inputs.live_suite_filter == ''
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ inputs.release_test_profile == 'full' && 90 || 60 }}
     env:
       OPENCLAW_VITEST_MAX_WORKERS: "2"
@@ -556,7 +566,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_repo_e2e && (inputs.live_suite_filter == '' || inputs.live_suite_filter == 'openshell-e2e')
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
@@ -630,7 +640,7 @@ jobs:
     if: inputs.include_release_path_suites && inputs.docker_lanes == ''
     name: Docker E2E (${{ matrix.label }})
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
@@ -921,7 +931,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.docker_lanes != ''
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-4vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-4vcpu-ubuntu-2404' }}
     timeout-minutes: 5
     outputs:
       groups_json: ${{ steps.groups.outputs.groups_json }}
@@ -950,7 +960,7 @@ jobs:
     if: inputs.docker_lanes != ''
     name: Docker E2E targeted lanes (${{ matrix.group.label }})
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 60
     strategy:
       fail-fast: false
@@ -1182,7 +1192,7 @@ jobs:
     if: inputs.include_openwebui && !inputs.include_release_path_suites && inputs.docker_lanes == ''
     name: Docker E2E (openwebui)
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 60
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -1308,7 +1318,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_release_path_suites || inputs.include_openwebui || inputs.docker_lanes != ''
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ inputs.release_test_profile == 'full' && 90 || 60 }}
     permissions:
       actions: read
@@ -1551,7 +1561,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_live_suites && (inputs.live_suite_filter == '' || startsWith(inputs.live_suite_filter, 'live-') || startsWith(inputs.live_suite_filter, 'docker-live-models'))
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 60
     permissions:
       contents: read
@@ -1624,7 +1634,7 @@ jobs:
     needs: [validate_selected_ref, prepare_live_test_image]
     if: inputs.include_live_suites && inputs.live_model_providers == '' && (inputs.live_suite_filter == '' || inputs.live_suite_filter == 'docker-live-models')
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 45
     strategy:
       fail-fast: false
@@ -1775,7 +1785,7 @@ jobs:
     needs: [validate_selected_ref, prepare_live_test_image]
     if: inputs.include_live_suites && inputs.live_model_providers != '' && (inputs.live_suite_filter == '' || inputs.live_suite_filter == 'docker-live-models')
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 45
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -1847,7 +1857,6 @@ jobs:
           normalize_provider() {
             local value="${1,,}"
             case "$value" in
-              z.ai|z-ai) echo "zai" ;;
               opencode|opencode-go) echo "opencode-go" ;;
               open-router|openrouter) echo "openrouter" ;;
               *) echo "$value" ;;
@@ -1949,7 +1958,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_live_suites && !inputs.live_models_only && (inputs.live_suite_filter == '' || (startsWith(inputs.live_suite_filter, 'native-live-') && !startsWith(inputs.live_suite_filter, 'native-live-extensions-media') && inputs.live_suite_filter != 'native-live-extensions-a-k'))
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
@@ -1977,7 +1986,7 @@ jobs:
           - suite_id: native-live-src-gateway-profiles-anthropic-opus
             suite_group: native-live-src-gateway-profiles-anthropic
             label: Native live gateway profiles Anthropic Opus
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=anthropic OPENCLAW_LIVE_GATEWAY_MODELS=anthropic/claude-opus-4-7 node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
+            command: OPENCLAW_LIVE_GATEWAY_THINKING=low OPENCLAW_LIVE_GATEWAY_PROVIDERS=anthropic OPENCLAW_LIVE_GATEWAY_MODELS=anthropic/claude-opus-4-7 node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
             timeout_minutes: 30
             profile_env_only: false
             advisory: true
@@ -1985,7 +1994,7 @@ jobs:
           - suite_id: native-live-src-gateway-profiles-anthropic-sonnet-haiku
             suite_group: native-live-src-gateway-profiles-anthropic
             label: Native live gateway profiles Anthropic Sonnet/Haiku
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=anthropic OPENCLAW_LIVE_GATEWAY_MODELS=anthropic/claude-sonnet-4-6,anthropic/claude-haiku-4-5 node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
+            command: OPENCLAW_LIVE_GATEWAY_THINKING=low OPENCLAW_LIVE_GATEWAY_PROVIDERS=anthropic OPENCLAW_LIVE_GATEWAY_MODELS=anthropic/claude-sonnet-4-6,anthropic/claude-haiku-4-5 node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
             timeout_minutes: 30
             profile_env_only: false
             advisory: true
@@ -2251,6 +2260,7 @@ jobs:
         env:
           OPENCLAW_LIVE_COMMAND: ${{ matrix.command }}
           OPENCLAW_LIVE_SUITE_ADVISORY: ${{ matrix.advisory }}
+        shell: bash
         run: |
           set +e
           bash .release-harness/scripts/ci-live-command-retry.sh
@@ -2270,7 +2280,7 @@ jobs:
     needs: [validate_selected_ref, prepare_live_test_image]
     if: inputs.include_live_suites && !inputs.live_models_only && (inputs.live_suite_filter == '' || startsWith(inputs.live_suite_filter, 'live-'))
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
@@ -2278,13 +2288,13 @@ jobs:
         include:
           - suite_id: live-gateway-docker
             label: Docker live gateway OpenAI
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=openai OPENCLAW_LIVE_GATEWAY_MODELS=openai/gpt-5.5 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=1 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=300000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            command: OPENCLAW_LIVE_GATEWAY_THINKING=low OPENCLAW_LIVE_GATEWAY_PROVIDERS=openai OPENCLAW_LIVE_GATEWAY_MODELS=openai/gpt-5.5 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=1 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=600000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
             timeout_minutes: 40
             profile_env_only: false
             profiles: beta minimum stable full
           - suite_id: live-gateway-anthropic-docker
             label: Docker live gateway Anthropic
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=anthropic OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=180000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            command: OPENCLAW_LIVE_GATEWAY_THINKING=low OPENCLAW_LIVE_GATEWAY_PROVIDERS=anthropic OPENCLAW_LIVE_GATEWAY_MODELS=anthropic/claude-sonnet-4-6,anthropic/claude-haiku-4-5 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=600000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
             timeout_minutes: 40
             profile_env_only: false
             profiles: stable full
@@ -2469,6 +2479,7 @@ jobs:
         env:
           OPENCLAW_LIVE_COMMAND: ${{ matrix.command }}
           OPENCLAW_LIVE_SUITE_ADVISORY: ${{ matrix.advisory }}
+        shell: bash
         run: |
           set +e
           bash .release-harness/scripts/ci-live-command-retry.sh
@@ -2488,7 +2499,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_live_suites && !inputs.live_models_only && (inputs.live_suite_filter == '' || startsWith(inputs.live_suite_filter, 'native-live-extensions-media') || inputs.live_suite_filter == 'native-live-extensions-a-k')
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     container:
       image: ghcr.io/openclaw/openclaw-live-media-runner:ubuntu-24.04
       credentials:
@@ -2656,6 +2667,7 @@ jobs:
         if: contains(matrix.profiles, inputs.release_test_profile) && (inputs.live_suite_filter == '' || inputs.live_suite_filter == matrix.suite_id || (inputs.live_suite_filter == 'native-live-extensions-media-video' && startsWith(matrix.suite_id, 'native-live-extensions-media-video-')))
         env:
           OPENCLAW_LIVE_SUITE_ADVISORY: ${{ matrix.advisory }}
+        shell: bash
         run: |
           set +e
           ${{ matrix.command }}

.github/workflows/openclaw-npm-release.yml

@@ -47,8 +47,8 @@ jobs:
   # KEEP THIS WORKFLOW SHORT AND DETERMINISTIC OR IT CAN GET STUCK AND JEOPARDIZE THE RELEASE.
   # RELEASE-TIME LIVE OR END-TO-END VALIDATION BELONGS IN openclaw-release-checks.yml.
   # SECURITY NOTE: TOKEN-BASED npm dist-tag mutation moved to
-  # openclaw/releases-private/.github/workflows/openclaw-npm-dist-tags.yml
-  # so this public workflow can stay focused on OIDC publish only.
+  # openclaw/releases/.github/workflows/openclaw-npm-dist-tags.yml
+  # so this source workflow can stay focused on OIDC publish only.
   preflight_openclaw_npm:
     if: ${{ inputs.preflight_only }}
     runs-on: ubuntu-latest

.github/workflows/openclaw-performance.yml

@@ -307,7 +307,36 @@ jobs:
             exit 1
           fi
           report_md="${report_json%.json}.md"
+          effective_status="$status"
+          if [[ "$FAIL_ON_REGRESSION" == "true" && "$status" != "0" ]]; then
+            if REPORT_JSON="$report_json" node <<'NODE'
+          const fs = require("node:fs");
+          const report = JSON.parse(fs.readFileSync(process.env.REPORT_JSON, "utf8"));
+          const statuses = report.summary?.statuses ?? {};
+          const nonPassStatuses = Object.entries(statuses)
+            .filter(([status, count]) => status !== "PASS" && Number(count) > 0);
+          const baselineRegressionCount =
+            Number(report.baseline?.comparison?.regressionCount ?? report.gate?.baseline?.regressionCount ?? 0);
+          const gate = report.gate;
+          const toleratedPartial =
+            gate?.verdict === "PARTIAL" &&
+            Number(gate.blockingCount ?? 0) === 0 &&
+            baselineRegressionCount === 0 &&
+            nonPassStatuses.length === 0;
+          if (!toleratedPartial) {
+            process.exit(1);
+          }
+          NODE
+            then
+              effective_status=0
+              {
+                echo "Kova returned a partial release-gate verdict for filtered performance coverage, but all selected scenarios passed and no baseline regression was reported."
+                echo
+              } >> "$GITHUB_STEP_SUMMARY"
+            fi
+          fi
           echo "status=$status" >> "$GITHUB_OUTPUT"
+          echo "effective_status=$effective_status" >> "$GITHUB_OUTPUT"
           echo "report_json=$report_json" >> "$GITHUB_OUTPUT"
           echo "report_md=$report_md" >> "$GITHUB_OUTPUT"
 
@@ -344,8 +373,43 @@ jobs:
           EOF
           cat "$summary_path" >> "$GITHUB_STEP_SUMMARY"
 
-          if [[ "$FAIL_ON_REGRESSION" == "true" && "$status" != "0" ]]; then
-            exit "$status"
+          if [[ "$FAIL_ON_REGRESSION" == "true" && "$effective_status" != "0" ]]; then
+            exit "$effective_status"
+          fi
+
+      - name: Fetch previous source performance baseline
+        if: ${{ steps.lane.outputs.run == 'true' && matrix.lane == 'mock-provider' && steps.clawgrit.outputs.present == 'true' }}
+        env:
+          CLAWGRIT_REPORTS_TOKEN: ${{ secrets.CLAWGRIT_REPORTS_TOKEN }}
+        shell: bash
+        run: |
+          set -euo pipefail
+          reports_root=".artifacts/clawgrit-baseline"
+          mkdir -p "$reports_root"
+          git -C "$reports_root" init -b main
+          git -C "$reports_root" remote add origin "https://x-access-token:${CLAWGRIT_REPORTS_TOKEN}@github.com/openclaw/clawgrit-reports.git"
+          if ! git -C "$reports_root" fetch --depth=1 origin main; then
+            echo "No previous source performance baseline could be fetched." >> "$GITHUB_STEP_SUMMARY"
+            exit 0
+          fi
+          git -C "$reports_root" checkout -B main FETCH_HEAD
+          ref_slug="$(printf '%s' "${TESTED_REF}" | tr -c 'A-Za-z0-9._-' '-')"
+          pointer="${reports_root}/openclaw-performance/${ref_slug}/latest-mock-provider.json"
+          if [[ ! -f "$pointer" ]]; then
+            echo "No previous source performance baseline exists for ${TESTED_REF}." >> "$GITHUB_STEP_SUMMARY"
+            exit 0
+          fi
+          if ! latest_path="$(node -e "const fs=require('node:fs'); const data=JSON.parse(fs.readFileSync(process.argv[1],'utf8')); const value=String(data.path || ''); if (!/^openclaw-performance\\/[A-Za-z0-9._-]+\\/[0-9]+-[0-9]+\\/mock-provider$/u.test(value)) process.exit(1); process.stdout.write(value);" "$pointer")"; then
+            echo "Previous source performance baseline pointer is invalid." >> "$GITHUB_STEP_SUMMARY"
+            exit 0
+          fi
+          baseline_source="${reports_root}/${latest_path}/source"
+          if [[ -d "$baseline_source" ]]; then
+            baseline_source="$(realpath "$baseline_source")"
+            echo "SOURCE_PERF_BASELINE_DIR=$baseline_source" >> "$GITHUB_ENV"
+            echo "Using source performance baseline: ${latest_path}/source" >> "$GITHUB_STEP_SUMMARY"
+          else
+            echo "Previous source performance baseline has no source directory." >> "$GITHUB_STEP_SUMMARY"
           fi
 
       - name: Run OpenClaw source performance probes
@@ -359,7 +423,7 @@ jobs:
           fi
 
           mkdir -p "$SOURCE_PERF_DIR/mock-hello"
-          if ! node -e "const fs=require('node:fs'); const scripts=require('./package.json').scripts||{}; process.exit(scripts['test:gateway:cpu-scenarios'] && scripts.openclaw && fs.existsSync('scripts/bench-cli-startup.ts') ? 0 : 1)"; then
+          if ! node -e "const fs=require('node:fs'); const scripts=require('./package.json').scripts||{}; process.exit(scripts['test:gateway:cpu-scenarios'] && scripts['test:extensions:memory'] && scripts.openclaw && fs.existsSync('scripts/bench-cli-startup.ts') && fs.existsSync('scripts/profile-extension-memory.mjs') ? 0 : 1)"; then
             cat > "$SOURCE_PERF_DIR/index.md" <<EOF
           # OpenClaw Source Performance
 
@@ -371,7 +435,7 @@ jobs:
 
           - Tested ref: ${TESTED_REF}
           - Tested SHA: ${TESTED_SHA}
-          - Required scripts: test:gateway:cpu-scenarios, openclaw, scripts/bench-cli-startup.ts
+          - Required scripts: test:gateway:cpu-scenarios, test:extensions:memory, openclaw, scripts/bench-cli-startup.ts, scripts/profile-extension-memory.mjs
           EOF
             cat "$SOURCE_PERF_DIR/index.md" >> "$GITHUB_STEP_SUMMARY"
             exit 0
@@ -391,6 +455,9 @@ jobs:
             --startup-case fiftyPlugins \
             --startup-case fiftyStartupLazyPlugins
 
+          pnpm test:extensions:memory \
+            -- --json "$SOURCE_PERF_DIR/extension-memory.json"
+
           for run_index in $(seq 1 "$source_runs"); do
             run_dir="$SOURCE_PERF_DIR/mock-hello/run-$(printf '%03d' "$run_index")"
             pnpm openclaw qa suite \
@@ -460,9 +527,13 @@ jobs:
           cleanup_gateway
           trap - EXIT
 
-          node "$PERFORMANCE_HELPER_DIR/scripts/openclaw-performance-source-summary.mjs" \
+          summary_args=(node "$PERFORMANCE_HELPER_DIR/scripts/openclaw-performance-source-summary.mjs" \
             --source-dir "$SOURCE_PERF_DIR" \
-            --output "$SOURCE_PERF_DIR/index.md"
+            --output "$SOURCE_PERF_DIR/index.md")
+          if [[ -n "${SOURCE_PERF_BASELINE_DIR:-}" && -d "$SOURCE_PERF_BASELINE_DIR" ]]; then
+            summary_args+=(--baseline-source-dir "$SOURCE_PERF_BASELINE_DIR")
+          fi
+          "${summary_args[@]}"
 
           cat "$SOURCE_PERF_DIR/index.md" >> "$GITHUB_STEP_SUMMARY"
 
@@ -480,25 +551,31 @@ jobs:
           retention-days: ${{ matrix.deep_profile == 'true' && 14 || 30 }}
 
       - name: Prepare clawgrit reports checkout
+        id: clawgrit_reports
         if: ${{ steps.kova.outputs.report_json != '' && steps.clawgrit.outputs.present == 'true' }}
         env:
           CLAWGRIT_REPORTS_TOKEN: ${{ secrets.CLAWGRIT_REPORTS_TOKEN }}
         shell: bash
         run: |
           set -euo pipefail
+          echo "ready=false" >> "$GITHUB_OUTPUT"
           reports_root=".artifacts/clawgrit-reports"
           mkdir -p "$reports_root"
           git -C "$reports_root" init -b main
           git -C "$reports_root" remote add origin "https://x-access-token:${CLAWGRIT_REPORTS_TOKEN}@github.com/openclaw/clawgrit-reports.git"
-          if git -C "$reports_root" ls-remote --exit-code --heads origin main >/dev/null 2>&1; then
-            git -C "$reports_root" fetch --depth=1 origin main
+          if timeout 60s git -C "$reports_root" ls-remote --exit-code --heads origin main >/dev/null 2>&1; then
+            if ! timeout 120s git -C "$reports_root" fetch --depth=1 origin main; then
+              echo "::warning::Skipping optional clawgrit report publish because the reports checkout fetch timed out or failed."
+              exit 0
+            fi
             git -C "$reports_root" checkout -B main FETCH_HEAD
           else
             git -C "$reports_root" checkout -B main
           fi
+          echo "ready=true" >> "$GITHUB_OUTPUT"
 
       - name: Publish to clawgrit reports
-        if: ${{ steps.kova.outputs.report_json != '' && steps.clawgrit.outputs.present == 'true' }}
+        if: ${{ steps.kova.outputs.report_json != '' && steps.clawgrit.outputs.present == 'true' && steps.clawgrit_reports.outputs.ready == 'true' }}
         env:
           CLAWGRIT_REPORTS_TOKEN: ${{ secrets.CLAWGRIT_REPORTS_TOKEN }}
         shell: bash
@@ -571,6 +648,9 @@ jobs:
               exit 0
             fi
             sleep $((attempt * 2))
-            git -C "$reports_root" fetch --depth=1 origin main
+            timeout 120s git -C "$reports_root" fetch --depth=1 origin main || {
+              echo "::warning::Skipping optional clawgrit report rebase because the reports fetch timed out or failed."
+              exit 0
+            }
             git -C "$reports_root" rebase FETCH_HEAD
           done

.github/workflows/openclaw-release-checks.yml

@@ -946,7 +946,7 @@ jobs:
             --concurrency "${QA_PARITY_CONCURRENCY}" \
             --model "${OPENCLAW_CI_OPENAI_MODEL}" \
             --alt-model "openai/gpt-5.5-alt" \
-            --runtime-pair pi,codex \
+            --runtime-pair openclaw,codex \
             --output-dir ".artifacts/qa-e2e/runtime-parity"
 
       - name: Run standard runtime parity tier
@@ -959,7 +959,7 @@ jobs:
             --concurrency "${QA_PARITY_CONCURRENCY}" \
             --model "${OPENCLAW_CI_OPENAI_MODEL}" \
             --alt-model "openai/gpt-5.5-alt" \
-            --runtime-pair pi,codex \
+            --runtime-pair openclaw,codex \
             --output-dir ".artifacts/qa-e2e/runtime-parity-standard"
 
       - name: Run soak runtime parity tier
@@ -973,7 +973,7 @@ jobs:
             --concurrency "${QA_PARITY_CONCURRENCY}" \
             --model "${OPENCLAW_CI_OPENAI_MODEL}" \
             --alt-model "openai/gpt-5.5-alt" \
-            --runtime-pair pi,codex \
+            --runtime-pair openclaw,codex \
             --output-dir ".artifacts/qa-e2e/runtime-parity-soak"
 
       - name: Generate runtime parity report

.github/workflows/openclaw-release-publish.yml

@@ -265,7 +265,7 @@ jobs:
         run: |
           set -euo pipefail
           RUN_JSON="$(gh run view "$FULL_RELEASE_VALIDATION_RUN_ID" --repo "$GITHUB_REPOSITORY" --json workflowName,headBranch,event,status,conclusion,url)"
-          printf '%s' "$RUN_JSON" | node -e 'const fs = require("node:fs"); const run = JSON.parse(fs.readFileSync(0, "utf8")); const checks = [["workflowName", "Full Release Validation"], ["headBranch", process.env.EXPECTED_WORKFLOW_BRANCH], ["event", "workflow_dispatch"], ["status", "completed"], ["conclusion", "success"]]; for (const [key, expected] of checks) { if (run[key] !== expected) { console.error(`Referenced full release validation run ${process.env.FULL_RELEASE_VALIDATION_RUN_ID} must have ${key}=${expected}, got ${run[key] ?? "<missing>"}.`); process.exit(1); } } console.log(`Using full release validation run ${process.env.FULL_RELEASE_VALIDATION_RUN_ID}: ${run.url}`);'
+          printf '%s' "$RUN_JSON" | node -e 'const fs = require("node:fs"); const run = JSON.parse(fs.readFileSync(0, "utf8")); const checks = [["workflowName", "Full Release Validation"], ["event", "workflow_dispatch"], ["status", "completed"], ["conclusion", "success"]]; for (const [key, expected] of checks) { if (run[key] !== expected) { console.error(`Referenced full release validation run ${process.env.FULL_RELEASE_VALIDATION_RUN_ID} must have ${key}=${expected}, got ${run[key] ?? "<missing>"}.`); process.exit(1); } } const allowedBranches = new Set(["main", process.env.EXPECTED_WORKFLOW_BRANCH].filter(Boolean)); if (!allowedBranches.has(run.headBranch)) { console.error(`Referenced full release validation run ${process.env.FULL_RELEASE_VALIDATION_RUN_ID} must have headBranch in ${[...allowedBranches].join(", ")}, got ${run.headBranch ?? "<missing>"}.`); process.exit(1); } console.log(`Using full release validation run ${process.env.FULL_RELEASE_VALIDATION_RUN_ID}: ${run.url}`);'
 
           manifest="${RUNNER_TEMP}/full-release-validation-manifest/full-release-validation-manifest.json"
           if [[ ! -f "$manifest" ]]; then
@@ -810,7 +810,7 @@ jobs:
             `- npm package: https://www.npmjs.com/package/openclaw/v/${process.env.RELEASE_VERSION}`,
             `- registry tarball: ${process.env.RELEASE_TARBALL}`,
             `- integrity: \`${process.env.RELEASE_INTEGRITY}\``,
-            `- full release CI report: https://github.com/openclaw/releases-private/blob/main/evidence/${process.env.RELEASE_VERSION}/release-evidence.md`,
+            `- full release CI report: https://github.com/openclaw/releases/blob/main/evidence/${process.env.RELEASE_VERSION}/release-evidence.md`,
             `- release publish: https://github.com/${process.env.RELEASE_REPO}/actions/runs/${process.env.RELEASE_PUBLISH_RUN_ID}`,
             `- npm preflight: https://github.com/${process.env.RELEASE_REPO}/actions/runs/${process.env.PREFLIGHT_RUN_ID}`,
             `- full release validation: https://github.com/${process.env.RELEASE_REPO}/actions/runs/${process.env.FULL_RELEASE_VALIDATION_RUN_ID}`,

.github/workflows/opengrep-precise.yml

@@ -44,7 +44,7 @@ jobs:
         uses: actions/checkout@v6
         with:
           ref: ${{ github.sha }}
-          fetch-depth: 1
+          fetch-depth: 0
           fetch-tags: false
           persist-credentials: false
           submodules: false

.github/workflows/plugin-prerelease.yml

@@ -344,7 +344,7 @@ jobs:
           OPENCLAW_EXTENSION_BATCH_PARALLEL: 2
           OPENCLAW_VITEST_MAX_WORKERS: 1
           OPENCLAW_EXTENSION_BATCH: ${{ matrix.extensions_csv }}
-        run: pnpm test:extensions:batch -- "$OPENCLAW_EXTENSION_BATCH"
+        run: pnpm test:extensions:batch "$OPENCLAW_EXTENSION_BATCH" -- --exclude extensions/codex/src/app-server/run-attempt.test.ts
 
   plugin-prerelease-inspector:
     permissions:

.github/workflows/qa-live-transports-convex.yml

@@ -52,6 +52,7 @@ env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.x"
   OPENCLAW_CI_OPENAI_MODEL: ${{ vars.OPENCLAW_CI_OPENAI_MODEL || 'openai/gpt-5.5' }}
+  OPENCLAW_CI_OPENAI_FALLBACK_MODEL: ${{ vars.OPENCLAW_CI_OPENAI_FALLBACK_MODEL || 'openai/gpt-5.4' }}
   OPENCLAW_BUILD_PRIVATE_QA: "1"
   OPENCLAW_ENABLE_PRIVATE_QA_CLI: "1"
 
@@ -288,8 +289,8 @@ jobs:
             --runtime-parity-tier live-only \
             --concurrency "${QA_PARITY_CONCURRENCY}" \
             --model "${OPENCLAW_CI_OPENAI_MODEL}" \
-            --alt-model "${OPENCLAW_CI_OPENAI_MODEL}" \
-            --runtime-pair pi,codex \
+            --alt-model "${OPENCLAW_CI_OPENAI_FALLBACK_MODEL}" \
+            --runtime-pair openclaw,codex \
             --fast \
             --allow-failures \
             --output-dir "${output_dir}/runtime-suite"
@@ -373,7 +374,7 @@ jobs:
             --output-dir "${output_dir}" \
             --provider-mode live-frontier \
             --model "${OPENCLAW_CI_OPENAI_MODEL}" \
-            --alt-model "${OPENCLAW_CI_OPENAI_MODEL}" \
+            --alt-model "${OPENCLAW_CI_OPENAI_FALLBACK_MODEL}" \
             --profile "${INPUT_MATRIX_PROFILE}" \
             --fast
           )
@@ -457,7 +458,7 @@ jobs:
             --output-dir "${output_dir}" \
             --provider-mode live-frontier \
             --model "${OPENCLAW_CI_OPENAI_MODEL}" \
-            --alt-model "${OPENCLAW_CI_OPENAI_MODEL}" \
+            --alt-model "${OPENCLAW_CI_OPENAI_FALLBACK_MODEL}" \
             --profile "${{ matrix.profile }}" \
             --fast
           )
@@ -555,7 +556,7 @@ jobs:
             --output-dir "${output_dir}" \
             --provider-mode live-frontier \
             --model "${OPENCLAW_CI_OPENAI_MODEL}" \
-            --alt-model "${OPENCLAW_CI_OPENAI_MODEL}" \
+            --alt-model "${OPENCLAW_CI_OPENAI_FALLBACK_MODEL}" \
             --fast \
             --credential-source convex \
             --credential-role ci \
@@ -649,7 +650,7 @@ jobs:
             --output-dir "${output_dir}" \
             --provider-mode live-frontier \
             --model openai/gpt-5.5 \
-            --alt-model openai/gpt-5.5 \
+            --alt-model "${OPENCLAW_CI_OPENAI_FALLBACK_MODEL}" \
             --fast \
             --credential-source convex \
             --credential-role ci \
@@ -746,7 +747,7 @@ jobs:
             --output-dir "${output_dir}" \
             --provider-mode live-frontier \
             --model "${OPENCLAW_CI_OPENAI_MODEL}" \
-            --alt-model "${OPENCLAW_CI_OPENAI_MODEL}" \
+            --alt-model "${OPENCLAW_CI_OPENAI_FALLBACK_MODEL}" \
             --fast \
             --credential-source convex \
             --credential-role ci \
@@ -840,7 +841,7 @@ jobs:
             --output-dir "${output_dir}" \
             --provider-mode live-frontier \
             --model "${OPENCLAW_CI_OPENAI_MODEL}" \
-            --alt-model "${OPENCLAW_CI_OPENAI_MODEL}" \
+            --alt-model "${OPENCLAW_CI_OPENAI_FALLBACK_MODEL}" \
             --fast \
             --credential-source convex \
             --credential-role ci \

.github/workflows/sandbox-common-smoke.yml

@@ -42,7 +42,7 @@ jobs:
         run: |
           set -euo pipefail
 
-          docker build -t openclaw-sandbox-smoke-base:bookworm-slim - <<'EOF'
+          timeout --kill-after=30s 5m docker build -t openclaw-sandbox-smoke-base:bookworm-slim - <<'EOF'
           FROM debian:bookworm-slim
           RUN useradd --create-home --shell /bin/bash sandbox
           USER sandbox
@@ -63,5 +63,5 @@ jobs:
             FINAL_USER=sandbox \
             scripts/sandbox-common-setup.sh
 
-          u="$(docker run --rm openclaw-sandbox-common-smoke:bookworm-slim sh -lc 'id -un')"
+          u="$(timeout --kill-after=30s 2m docker run --rm openclaw-sandbox-common-smoke:bookworm-slim sh -lc 'id -un')"
           test "$u" = "sandbox"

.github/workflows/tui-pty.yml

@@ -38,4 +38,4 @@ jobs:
           install-bun: "false"
 
       - name: Run TUI PTY tests
-        run: timeout 120s node scripts/run-vitest.mjs run --config test/vitest/vitest.tui-pty.config.ts
+        run: timeout --kill-after=30s 120s node scripts/run-vitest.mjs run --config test/vitest/vitest.tui-pty.config.ts

.github/workflows/website-installer-sync.yml

@@ -75,14 +75,14 @@ jobs:
 
       - name: install.sh in Docker
         run: |
-          docker run --rm \
+          timeout --kill-after=30s 20m docker run --rm \
             -v "$PWD/scripts/install.sh:/tmp/install.sh:ro" \
             node:24-bookworm-slim \
             bash -lc 'bash /tmp/install.sh --version latest && openclaw --version'
 
       - name: install-cli.sh in Docker
         run: |
-          docker run --rm \
+          timeout --kill-after=30s 20m docker run --rm \
             -e OPENCLAW_NO_ONBOARD=1 \
             -e OPENCLAW_NO_PROMPT=1 \
             -v "$PWD/scripts/install-cli.sh:/tmp/install-cli.sh:ro" \

.github/workflows/workflow-sanity.yml

@@ -26,7 +26,16 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        env:
+          CHECKOUT_REPO: ${{ github.repository }}
+          CHECKOUT_SHA: ${{ github.sha }}
+        run: |
+          set -euo pipefail
+          git init "$GITHUB_WORKSPACE"
+          git -C "$GITHUB_WORKSPACE" config gc.auto 0
+          git -C "$GITHUB_WORKSPACE" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
+          git -C "$GITHUB_WORKSPACE" fetch --no-tags --depth=1 origin "+${CHECKOUT_SHA}:refs/remotes/origin/checkout"
+          git -C "$GITHUB_WORKSPACE" checkout --detach refs/remotes/origin/checkout
 
       - name: Fail on tabs in workflow files
         run: |
@@ -58,7 +67,16 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        env:
+          CHECKOUT_REPO: ${{ github.repository }}
+          CHECKOUT_SHA: ${{ github.sha }}
+        run: |
+          set -euo pipefail
+          git init "$GITHUB_WORKSPACE"
+          git -C "$GITHUB_WORKSPACE" config gc.auto 0
+          git -C "$GITHUB_WORKSPACE" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
+          git -C "$GITHUB_WORKSPACE" fetch --no-tags --depth=1 origin "+${CHECKOUT_SHA}:refs/remotes/origin/checkout"
+          git -C "$GITHUB_WORKSPACE" checkout --detach refs/remotes/origin/checkout
 
       - name: Install actionlint
         shell: bash
@@ -90,7 +108,16 @@ jobs:
     runs-on: ubuntu-24.04
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        env:
+          CHECKOUT_REPO: ${{ github.repository }}
+          CHECKOUT_SHA: ${{ github.sha }}
+        run: |
+          set -euo pipefail
+          git init "$GITHUB_WORKSPACE"
+          git -C "$GITHUB_WORKSPACE" config gc.auto 0
+          git -C "$GITHUB_WORKSPACE" remote add origin "https://github.com/${CHECKOUT_REPO}.git"
+          git -C "$GITHUB_WORKSPACE" fetch --no-tags --depth=1 origin "+${CHECKOUT_SHA}:refs/remotes/origin/checkout"
+          git -C "$GITHUB_WORKSPACE" checkout --detach refs/remotes/origin/checkout
 
       - name: Setup Node environment
         uses: ./.github/actions/setup-node-env

.gitignore

@@ -128,7 +128,8 @@ mantis/
 !.agents/skills/control-ui-e2e/**
 !.agents/skills/gitcrawl/
 !.agents/skills/gitcrawl/**
-!.agents/skills/openclaw-docs/**
+!.agents/skills/technical-documentation/
+!.agents/skills/technical-documentation/**
 !.agents/skills/openclaw-refactor-docs/
 !.agents/skills/openclaw-refactor-docs/**
 !.agents/skills/openclaw-debugging/
@@ -167,6 +168,8 @@ mantis/
 !.agents/skills/tag-duplicate-prs-issues/**
 !.agents/skills/autoreview/
 !.agents/skills/autoreview/**
+.agents/skills/**/__pycache__/
+.agents/skills/**/*.py[cod]
 
 # Agent credentials and memory (NEVER COMMIT)
 /memory/
@@ -246,6 +249,8 @@ extensions/qa-lab/web/dist/
 # Generated bundled plugin runtime dependency manifests
 extensions/**/.openclaw-runtime-deps.json
 extensions/**/.openclaw-runtime-deps-stamp.json
+extensions/diffs/assets/viewer-runtime.js
+extensions/diffs-language-pack/assets/viewer-runtime.js
 
 # Output dir for scripts/run-opengrep.sh (local opengrep scans)
 /.opengrep-out/

.oxfmtrc.jsonc

@@ -30,6 +30,7 @@
     "docker-compose.yml",
     "dist/",
     "docs/_layouts/",
+    "extensions/diffs/assets/viewer-runtime.js",
     "**/*.json",
     "node_modules/",
     "patches/",

.oxlintrc.json

@@ -182,6 +182,7 @@
     "dist-runtime/",
     "docs/_layouts/",
     "extensions/diffs/assets/viewer-runtime.js",
+    "extensions/diffs-language-pack/assets/viewer-runtime.js",
     "node_modules/",
     "patches/",
     "pnpm-lock.yaml",

AGENTS.md

@@ -23,10 +23,11 @@ Skills own workflows; root owns hard policy and routing.
 - ClawSweeper-owned schema, labels, close reasons, protected-label gates, maintainer-item gates, and mutation rules live in `openclaw/clawsweeper`.
 - Review workers read this full root `AGENTS.md` before judging; no reliance on search snippets, `head`, partial ranges, local excerpts, or truncated copies. Then read every scoped `AGENTS.md` that owns touched paths.
 - Optional integrations, providers, channels, skill bundles, MCP surfaces, and service workflows route to plugins, ClawHub, or owner repos when current seams suffice. Keep core items for missing core/plugin APIs, bundled regressions, security/core hardening, or maintainer product decisions.
-- Plugin APIs, provider routing, auth/session state, persisted preferences, config loading, migrations, setup, startup checks, and fallback behavior are compatibility/upgrade-sensitive. Treat config breaks, removed fallbacks, fail-closed changes, or new operator action as merge risk even with green CI.
+- Plugin APIs, provider routing, auth/session state, persisted preferences, config loading, config/default additions, migrations, setup, startup checks, and fallback behavior are compatibility/upgrade-sensitive. Treat config breaks, new config/default surfaces, removed fallbacks, fail-closed changes, stricter validation, or new operator action as merge risk even with green CI when they can affect existing users, upgrades, provider/plugin behavior, or maintainer operations.
+- For PRs that add, remove, or change config/default surfaces with possible compatibility, upgrade, provider/plugin, operator, setup, startup, or fallback impact, ClawSweeper review should emit a `reviewMetrics` entry when practical. The metric should name the count and direction of the changes, such as added, changed, or removed config/default surfaces, and explain why the metric matters before merge. When the metric indicates concrete merge risk, also surface the concern in `risks`, use `mergeRiskLabels` when the risk matches the label rubric, make `bestSolution` name the desired pre-merge state, and ensure `labelJustifications` explain the specific reason rather than restating the label.
 - Review whole decision surfaces, not only the touched runtime, provider, channel, harness, plugin seam, or context path. Check sibling Codex/Pi-style runtimes, provider/model routing, channel delivery, gateway/protocol, plugin SDK, and context-management paths when relevant.
 - One-sided fixes need sibling-surface proof, an explanation for why siblings are unaffected, or explicit follow-up work.
-- User-facing `fix`, `feat`, and `perf` changes need `CHANGELOG.md` before landing; contributor PR authors are not blocked solely on maintainer-owned changelog work. Never request thanks for bot/forbidden handles: `@openclaw`, `@clawsweeper`, `@codex`, `@steipete`.
+- Changelog findings: see Docs / Changelog.
 - Public ClawSweeper comments prefer `https://docs.openclaw.ai/...` when a public docs page exists; structured evidence still cites repo files, lines, SHAs.
 - Findings need current source, shipped/current behavior, tests/CI evidence, and dependency contract proof when dependency-backed behavior is involved. Validation is judged against touched and sibling surfaces plus this file's commands; real behavior proof matters for user-visible changes, with Telegram/Desktop proof for Telegram-visible behavior when feasible.
 - Prefer findings for concrete behavior regressions, missing changed-surface proof, owner-boundary violations, security/API contract issues, or docs/config mismatches.
@@ -55,11 +56,19 @@ Skills own workflows; root owns hard policy and routing.
 - Internal bundled plugins ship in core dist; bundled-only facade loader ok only for them.
 - External official plugins own package/deps and are excluded from core dist; core uses registry-aware `facade-runtime` or generic contracts.
 - Externalizing a bundled plugin: update package excludes, official catalogs, docs, tests, and prove core runtime paths resolve installed plugin roots before root-dep removal.
-- Legacy config repair belongs in `openclaw doctor --fix`, not startup/load-time core migrations. Runtime paths use canonical contracts.
+- Runtime reads canonical config only. No silent compat for old/malformed config keys. If a config change invalidates existing files, add a matching `openclaw doctor --fix` migration. Core/auth config repairs live in core doctor; plugin-owned config repairs live in that plugin's doctor contract (`legacyConfigRules` / `normalizeCompatibilityConfig`).
 - Fix shape: default to clean bounded refactor, not smallest patch. Move ownership to right boundary; delete stale abstractions, duplicate policy, dead branches, wrappers, fallback stacks.
+- Fix observed local failures with generic product rules; do not hardcode names, ids, log phrases, or user examples in prod code unless they are an explicit contract.
+- Tests may use observed examples, but prod literals need a short contract reason.
+- Compatibility is opt-in. "Shipped" means reachable from a release Git tag; main/GitHub/PR/unreleased code is not shipped.
+- Refactor default: one canonical path. Delete the old path unless user explicitly wants compat or the shipped public contract is obvious and cited.
+- Keep old behavior only for an explicit public API/config/plugin SDK/data contract, tagged upgrade path, security/migration boundary, dependency contract, or observed prod state.
+- If unsure, ask before preserving compat. Do not keep aliases, shims, fallback stacks, stale names, or obsolete tests just in case.
+- Tests alone do not make internals contracts. If compat stays, name the contract and migration/removal plan in code, test, or PR.
 - Lean code is a goal. No internal shims, aliases, legacy names, broad fallbacks, or defensive branches just to reduce diff or handle unrealistic edge cases.
-- Handle real production states, shipped upgrade paths, security boundaries, and dependency contracts. Public/hostile/observed malformed input gets care; hypothetical malformed input does not.
-- Public plugin SDK/API is the compat exception. New API first, old path only via named compat/deprecation metadata, docs, warnings when useful, tests for old+new, planned removal.
+- Handle real production states, tagged upgrade paths, security boundaries, and dependency contracts. Public/hostile/observed malformed input gets care; hypothetical malformed input does not.
+- Deprecate shipped public contracts only.
+- Plugin SDK exception: shipped external API gets new API first plus named compat/deprecation, small tests/docs if useful, removal plan.
 - Migrate internal/bundled callers to modern API in the same change. Do not let internal compat become permanent architecture.
 - Channels are implementation under `src/channels/**`; plugin authors get SDK seams. Providers own auth/catalog/runtime hooks; core owns generic loop.
 - Hot paths should carry prepared facts forward: provider id, model ref, channel id, target, capability family, attachment class. Do not rediscover with broad plugin/provider/channel/capability loaders.
@@ -67,7 +76,8 @@ Skills own workflows; root owns hard policy and routing.
 - Gateway/plugin metadata is process-stable: installs, manifests, catalogs, generated paths, bundled metadata. Changes require restart or explicit owner reload/install/doctor flow.
 - Runtime hot paths: no freshness polling (`stat`/`realpath`/JSON reread/hash). Reuse current snapshots, install records, discovery, lookup tables, root scopes, resolved paths.
 - Process-local metadata caches ok when lifecycle-owned and bounded/single-slot. Freshness exceptions need named owner + tests.
-- Inline code comments: brief notes for tricky, bug-prone, or previously buggy logic.
+- Inline comments: preserve reviewer context at the code site. Use for cross-path/state invariants, platform/dependency caps, deterministic ordering, compact encoded state, lifecycle ordering, ownership boundaries, session/id adoption, queue-depth symmetry, fallbacks, or intentional caller differences.
+- Comment shape: 1-3 short lines; state why the branch/helper exists, what contract it protects, and the bad outcome if removed. Cite nearby constants/helpers when useful. No syntax narration, PR/user-specific lore, or obvious mechanics.
 - Gateway protocol changes: additive first; incompatible needs versioning/docs/client follow-through.
 - Protocol version bumps: explicit owner confirmation only; never automatic/generated.
 - Config contract: exported types, schema/help, metadata, baselines, docs aligned. Retired public keys stay retired; compat in raw migration/doctor only.
@@ -79,7 +89,6 @@ Skills own workflows; root owns hard policy and routing.
 - Runtime: Node 22.19+; Node 24 recommended. Keep Node + Bun paths working.
 - Package manager/runtime: repo defaults only. No swaps without approval.
 - Install: `pnpm install` (keep Bun lock/patches aligned if touched).
-- Sharp/Homebrew libvips source-build fail: `SHARP_IGNORE_GLOBAL_LIBVIPS=1 pnpm install`.
 - CLI: `pnpm openclaw ...` or `pnpm dev`; build: `pnpm build`.
 - Tests in a normal source checkout: `pnpm test <path-or-filter> [vitest args...]`, `pnpm test:changed`, `pnpm test:serial`, `pnpm test:coverage`; never raw `vitest`.
 - Tests in a Codex worktree or linked/sparse checkout: avoid direct local `pnpm test*`; use `node scripts/run-vitest.mjs <path-or-filter>` for tiny explicit-file proof, or Crabbox/Testbox for anything broader.
@@ -116,7 +125,6 @@ Skills own workflows; root owns hard policy and routing.
 - Do not leave associated issues open for hypothetical future repros. Close with rationale; ask for a new issue or reopen only if concrete new evidence appears. Close comment states: decision, why, supported alternative, and what evidence would change the decision.
 - PR review answer: bug/behavior, URL(s), affected surface, provenance for regressions when traceable, best-fix judgment, evidence from code/tests/CI/current or shipped behavior.
 - Issue/PR final answer: last line is the full GitHub URL.
-- Changelog: PR landings/fixes need one unless pure test/internal. Do not mention missing changelog as a review finding; Codex handles it during fix/landing.
 - PR verification: before merge, post exact local commands, CI/Testbox run IDs, before/after proof when used, and known proof gaps.
 - Issue fixed on `main` with proof: comment proof + commit/PR, then close.
 - After landing or requested close/sweep: search duplicates; comment proof + canonical commit/PR/release before closing.
@@ -124,8 +132,10 @@ Skills own workflows; root owns hard policy and routing.
 - `ship` that fixes an issue: after push, comment proof + commit link, then close the issue.
 - GH comments with backticks, `$`, or shell snippets: use heredoc/body file, not inline double-quoted `--body`.
 - PR create: real body required. Include Summary + Verification; mention refs, behavior, and proof.
+- PR create/refresh: keep PR branches takeover-ready. Use a branch maintainers can push to, or for fork PRs ensure `maintainer_can_modify` / GitHub's `Allow edits by maintainers` is enabled unless explicitly told otherwise or GitHub's Actions/secrets warning makes that unsafe.
+- GitHub issue/PR create: read `$agent-transcript`; ask about sanitized transcript logs when available.
 - Real behavior proof section is parsed. Use exact `field: value` labels: `Behavior addressed`, `Real environment tested`, `Exact steps or command run after this patch`, `Evidence after fix`, `Observed result after fix`, `What was not tested`.
-- PR artifacts/screenshots: attach to PR/comment/external artifact store. Do not commit `.github/pr-assets`.
+- PR artifacts/screenshots: attach to PR/comment/external artifact store. Never push screenshots, videos, proof images, or proof assets to OpenClaw or any product repo branch, including temp artifact branches. Use Crabbox artifact publishing plus the manifest URL. Do not commit `.github/pr-assets`.
 - CI polling: exact SHA, relevant checks only, minimal fields. Skip routine noise (`Auto response`, `Labeler`, docs agents, performance/stale). Logs only after failure/completion or concrete need.
 - Maintainers: may skip/ignore `Real behavior proof` when local tests or Crabbox verified behavior; record proof in PR verification.
 - `/landpr`: use `~/.codex/prompts/landpr.md`; do not idle on `auto-response` or `check-docs`.
@@ -136,14 +146,27 @@ Skills own workflows; root owns hard policy and routing.
 - No `@ts-nocheck`. Lint suppressions only intentional + explained.
 - External boundaries: prefer `zod` or existing schema helpers.
 - Runtime branching: discriminated unions/closed codes over freeform strings. Avoid semantic sentinels (`?? 0`, empty object/string).
+- Cross-function state: when valid combos matter, return a closed mode/result shape. Avoid parallel nullable fields or derived booleans that callers must keep in sync; make impossible states unrepresentable.
 - Formatter-friendly shape: when oxfmt explodes an expression vertically, extract named booleans, payloads, or small helpers. Do not change width or use format-ignore for local compactness.
 - Calls should be boring: complex decisions happen above; call args/object fields are names, literals, or simple property reads.
 - Prefer early returns over nested condition pyramids. Split code into gather -> normalize -> decide -> act.
 - Use named intermediates only for domain meaning or readability; avoid temp-variable soup.
+- Code size matters. Prefer small clear code; maintainability includes not growing LOC without payoff.
+- Refactors should delete about as much local complexity as they add. If LOC grows, the new ownership/API needs to clearly pay for it.
+- Before adding helpers/files, check whether existing code can absorb the behavior with less new surface.
+- Keep APIs narrow: export only current caller needs; keep types/helpers local by default.
+- Return the smallest useful shape. Avoid broad result objects, flags, metadata unless callers use them.
+- Avoid adapter layers that only rename fields. Move real responsibility or leave code local.
+- Inline simple one-use objects/spreads when clearer. Extract only when it removes duplication or hard logic.
+- Tests prove behavior/regressions, not every internal branch.
+- For non-trivial refactors, check `git diff --numstat` before closeout. If LOC grew, trim or explain why.
+- Prefer existing narrow helpers over repeated casts/guards. Add local helpers when 2+ nearby call sites share real boundary logic.
+- Prefer ctor parameter properties for injected deps/config. Do not ban them for erasable-syntax purity.
+- Prefer `satisfies` for registries/config maps; derive types from schemas when a runtime schema already exists.
+- Table-drive repetitive tests when it reduces code and keeps failure names clear.
 - Dynamic import: no static+dynamic import for same prod module. Use `*.runtime.ts` lazy boundary. After edits: `pnpm build`; check `[INEFFECTIVE_DYNAMIC_IMPORT]`.
 - Cycles: keep `pnpm check:import-cycles` + architecture/madge green.
 - Classes: no prototype mixins/mutations. Prefer inheritance/composition. Tests prefer per-instance stubs.
-- Comments: brief, only non-obvious logic.
 - Split files around ~700 LOC when clarity/testability improves.
 - Naming: **OpenClaw** product/docs; `openclaw` CLI/package/path/config.
 - English: American spelling.
@@ -162,12 +185,12 @@ Skills own workflows; root owns hard policy and routing.
 
 ## Docs / Changelog
 
-- Use `$openclaw-docs` for docs writing/review. Docs change with behavior/API.
+- Use `$technical-documentation` for docs writing/review. Docs change with behavior/API.
 - Codex harness upgrade (`extensions/codex/package.json` `@openai/codex`): refresh `docs/plugins/codex-harness.md` model snapshot from the new harness `model/list`.
 - Docs final answers: include relevant full `https://docs.openclaw.ai/...` URL(s). If issue/PR work too, GitHub URL last.
-- Changelog entries: active version `### Changes`/`### Fixes`; single-line bullets only.
-- Contributor PR authors should not edit `CHANGELOG.md`; maintainer/AI adds entries during landing/merge.
-- Contributor-facing changelog entries thank credited human `@author`. Never thank bots, `@openclaw`, `@clawsweeper`, or `@steipete`; if unknown, omit thanks.
+- `CHANGELOG.md`: release-owned. Do not edit for normal PRs, direct `main` fixes, or `ship it`; only explicit release/changelog generation may rewrite it. Do not ask contributors/agents for changelog edits.
+- User-facing `fix`/`feat`/`perf`: put release-note context in PR body, squash message, or direct commit: behavior, surface, issue/PR refs, credited human author/reporter.
+- Release generation: derive `CHANGELOG.md` from merged PRs + all direct `main` commits. Entries: active `### Changes`/`### Fixes`, single-line, thank credited humans; never thank bots/forbidden handles: `@openclaw`, `@clawsweeper`, `@codex`, `@steipete`.
 
 ## Git
 
@@ -176,7 +199,7 @@ Skills own workflows; root owns hard policy and routing.
 - No manual stash/autostash unless explicit. No branch/worktree changes unless requested.
 - `main`: no merge commits; rebase on latest `origin/main` before push. After one green run plus clean rebase sanity, do not chase moving `main` with repeated full gates.
 - User says `commit`: your changes only. `commit all`: all changes in grouped chunks. `push`: may `git pull --rebase` first.
-- User says `ship it`: changelog if needed, commit intended changes, pull --rebase, push.
+- User says `ship it`: commit intended changes, pull --rebase, push.
 - Do not delete/rename unexpected files; ask if blocking, else ignore.
 - Bulk PR close/reopen >5: ask with count/scope.
 
@@ -187,7 +210,8 @@ Skills own workflows; root owns hard policy and routing.
 - Dependency patches/overrides/vendor changes need explicit approval. `pnpm-workspace.yaml` patched dependencies use exact versions only.
 - Lockfiles/shrinkwrap are security surface: review `pnpm-lock.yaml`, `npm-shrinkwrap.json`, `package-lock.json`; root/plugin npm packages ship shrinkwrap, not package-lock.
 - Carbon pins owner-only: do not change `@buape/carbon` unless Shadow (`@thewilloftheshadow`, verified by `gh`) asks.
-- Releases/publish/version bumps need explicit approval. Use `$openclaw-release-maintainer`.
+- Releases/publish/version bumps need explicit approval. Use `$release-openclaw-maintainer`.
+- Backport means apply to newest open `release/` branch unless user names another target.
 - GHSA/advisories: `$openclaw-ghsa-maintainer` / `$security-triage`. Secret scanning: `$openclaw-secret-scanning-maintainer`.
 - Beta tag/version match: `vYYYY.M.D-beta.N` -> npm `YYYY.M.D-beta.N --tag beta`.
 
@@ -198,7 +222,7 @@ Skills own workflows; root owns hard policy and routing.
 - SwiftUI: Observation (`@Observable`, `@Bindable`) over new `ObservableObject`.
 - Mac gateway: dev watch = `pnpm gateway:watch`; managed installs = `openclaw gateway restart/status --deep`; logs = `./scripts/clawlog.sh`. No launchd/ad-hoc tmux.
 - Mac app permission testing: stable app path + real signing identity required. No `--no-sign`, `SIGN_IDENTITY=-`, or raw debug binary; TCC prompts/listing won't stick.
-- Version bump surfaces live in `$openclaw-release-maintainer`.
+- Version bump surfaces live in `$release-openclaw-maintainer`.
 - Parallels: `$openclaw-parallels-smoke`; Discord roundtrip: `$parallels-discord-roundtrip`.
 - Crabbox/WebVNC human demos: keep remote desktop visible/windowed; no fullscreen remote browser unless video/capture-style output.
 - ClawSweeper ops: `$clawsweeper`. Deployed hook sessions may post one concise `#clawsweeper` note only when surprising/actionable/risky; if using message tool, reply exactly `NO_REPLY`.

CHANGELOG.md

@@ -2,110 +2,299 @@
 
 Docs: https://docs.openclaw.ai
 
-## Unreleased
+## 2026.5.28
+
+### Highlights
+
+- Agent and Codex runtime recovery is steadier: subagents keep cwd/workspace separation, hook context stays prompt-local, session locks release on timeout abort, stale restart continuations are avoided, and Codex app-server/helper failures no longer tear down shared runtime state. (#87218, #86875, #87409, #87399, #87375)
+- Channel delivery and session identity got safer across outbound plugin hooks, Matrix room ids, iMessage reactions/approvals, Slack final replies, Discord recovered tool warnings, and Microsoft Teams service URL trust checks. (#73706, #75670, #87366, #87451, #87334)
+- CLI, auth, doctor, and provider paths fail faster and recover more clearly: malformed numeric/version options are rejected, OAuth and local service startup requests are bounded, legacy `api_key` auth profiles migrate to canonical form, and restart guidance is actionable. (#87398, #86281, #87361)
+- Plugin and Gateway hot paths do less repeated work while preserving cache correctness for install records, config JSON parsing, tool search catalogs, session stores, manifest model rows, auto-enabled plugin config, browser tokens, and viewer assets. (#86699)
+- Release, QA, and E2E validation now bound more log, artifact, harness, and cross-OS waits so failing lanes produce proof instead of hanging or false-greening.
 
 ### Changes
 
+- Status: show active subagent details in status output.
+- Diffs: split the default language pack and expand default Diffs language coverage while keeping the host floor aligned. (#87370, #87372) Thanks @RomneyDa.
+- ClawHub: add plugin display names plus skill verification and trust surfaces. (#87354, #86699) Thanks @thewilloftheshadow and @Patrick-Erichsen.
+- iOS: refresh the dev app with Pro Command, Chat, Agents, and Settings tabs wired to gateway sessions, diagnostics, chat, and realtime Talk. (#87367) Thanks @Solvely-Colin.
+- Docs: clarify Codex computer-use setup, paste-token stdin auth setup, macOS gateway sleep troubleshooting, native Codex hook relay recovery, container model auth, install deployment cards, device-token admin gating, and backport targets. (#87313, #63050) Thanks @bdjben, @liaoandi, and @thewilloftheshadow.
+
 ### Fixes
 
-- Scripts: remove stale Knip unused-file allowlist entries so the dead-code gate fails only on current findings.
+- Tighten phone-control mutation authorization [AI]. (#87150) Thanks @pgondhi987.
+- Clarify directive persistence authorization policy [AI]. (#86369) Thanks @pgondhi987.
+- Agents/Codex: keep spawned agent cwd/workspace state separated, keep hook context prompt-local, release session locks on timeout abort, avoid session event queue self-wait, preserve shared app-server state across startup or helper failures, keep native hook relay alive across restarts, route workspace memory through tools, resolve Codex runtime models first, report quarantined dynamic tools, format `skills` command output, and bound compaction/steering retries. (#87218, #86875, #86123, #87399, #87375, #87383, #87400) Thanks @mbelinky, @Alix-007, @luoyanglang, @yetval, and @sjf.
+- Channels: thread canonical session keys into outbound hooks, preserve Matrix room-id case, keep fallback tool warnings mention-inert, retain delivered Slack final replies during late cleanup, continue iMessage polling after denied reactions, suppress duplicate native exec approvals, preserve Telegram SecretRef prompt config, suppress Discord recovered tool warnings, and block untrusted Teams service URLs. (#73706, #75670, #87366, #87451, #87334) Thanks @zeroaltitude, @lukeboyett, @xiaotian, and @eleqtrizit.
+- CLI/auth/doctor/providers: reject malformed numeric/timeout/subcommand-version inputs, wait for respawn child shutdown, bound Codex and GitHub Copilot OAuth/token requests, warm provider auth off the main thread, honor Codex response timeouts, bound local service startup, resolve GPT-5.5 without cached catalog, migrate legacy memory auto-provider config, rewrite non-canonical `api_key` auth profiles, and make doctor restart follow-ups actionable. (#87398, #86281, #87361) Thanks @Patrick-Erichsen, @samzong, @giodl73-repo, and @alkor2000.
+- Gateway/security/session state: expire browser tokens after auth rotation, scope assistant idempotency dedupe, drain probe client closes, avoid stale restart continuation reuse, preserve retry-after fallbacks, bound webchat image and artifact transcript scans, include seconds in inbound metadata timestamps, and evict current plugin-state namespaces at row caps.
+- File transfer: handle late tar stdin pipe errors after archive validation or unpacking has already settled.
+- Performance: trust install-record caches between reloads, prefer native JSON parsing, reuse unchanged tool-search catalogs, skip unchanged store serialization, add precomputed session patch writers, reduce store clone allocations, cache manifest model catalog rows and auto-enabled plugin config, and slim current metadata identity caches.
+- Docker/release/QA: package runtime workspace templates, stream cross-OS served artifacts, preserve sparse Crabbox run artifacts, bound OpenClaw instance logs, plugin gauntlet relay logs, MCP channel buffers, kitchen-sink scans, agent-turn assertions, and release scenario logs, and keep release/google live guards current.
+
+## 2026.5.27
+
+### Highlights
+
+- Safer local/runtime boundaries: OpenClaw now rejects unsafe command wrappers, malformed CLI numeric options, unsafe Node runtime env overrides, no-auth Tailscale exposure, and non-admin device-role pairing approvals before they can affect live runs. (#87308, #87305, #87292, #87146)
+- Matrix and auto-reply delivery are steadier: mention previews stay inert, final mention replies deliver normally, shared-DM notices are awaited, MXID parsing ignores filenames, and reasoning-prefixed `NO_REPLY` responses stay suppressed.
+- Provider and agent reliability improved across OpenAI-compatible embeddings, cached token usage, Anthropic/Codex/Claude runtime state, unsupported tool-schema quarantine, heartbeat templates, and session fallback errors. (#85269, #82062, #85416, #86855)
+- Plugin and package release paths got tighter: Pixverse ships as an external video plugin with region selection, package exclusions and shrinkwrap inventory match the published npm shape, and release/package smoke commands fail bounded instead of hanging.
+- Gateway hot paths do less rediscovery by reusing current plugin metadata fingerprints, stable plugin index fingerprints, read-only session metadata, active working stores, status fast paths, and auth/env snapshots. (#86439)
+
+### Changes
+
+- Memory: add a core OpenAI-compatible embedding provider for local and hosted OpenAI-style endpoints, with config, doctor, and docs support. (#85269) Thanks @dutifulbob.
+- Plugin SDK: mark memory-specific embedding provider registration as deprecated compatibility and surface non-bundled usage in plugin compatibility diagnostics. (#85072) Thanks @mbelinky.
+- Pixverse: add video generation provider support, API region selection, and external plugin publishing.
+- Plugins: expose approval action metadata for plugin-driven approval surfaces.
+
+### Fixes
+
+- Security/CLI/runtime: harden hostname normalization for repeated trailing dots, block side-effecting command wrappers, reject unsafe Node runtime env overrides, reject loose numeric CLI and gateway options, require admin approval for node device-role pairing, and reject no-auth Tailscale exposure. (#87305, #87292, #87308, #87146) Thanks @pgondhi987.
+- Doctor: validate runtime tool schemas for every configured embedded agent while skipping ACP-only profiles, so bad non-default plugin or MCP tools are reported before assistant turns.
+- Telegram: route `sendMessage` action replies through durable outbound delivery so completed agent responses remain retryable when the gateway send path times out. (#87261) Thanks @mbelinky.
+- Matrix/auto-reply: keep draft previews mention-inert, preserve final mention delivery, send mention finals normally, await shared DM notices, ignore filename-embedded MXIDs, and suppress reasoning-prefixed `NO_REPLY` responses.
+- Agents/providers: add OpenAI-compatible cache retention, forward cached token usage in chat completions, preserve runtime context before active user turns, strip stale Anthropic thinking, load Claude CLI OAuth for Pi auth profiles, avoid false Codex runtime live switches, and quarantine unsupported tool schemas. (#82062, #87167, #86855)
+- Gateway/performance: cache plugin metadata fingerprints and stable plugin index fingerprints, borrow read-only session metadata safely, keep the active session working store hot, keep status on a bounded fast path, and preserve model auth profile suffixes. (#86439)
+- Package/install/release: align npm package exclusions and inventory, omit unpacked test helpers, skip Homebrew until macOS packages need it, cap tsdown heap in containers, bound install/release smoke waits, and harden post-publish verification.
+- Codex/Auth: bound ChatGPT OAuth token exchange and refresh requests, and honor cancellation across Codex and Anthropic OAuth login flows.
+- QA/E2E/CI: bound Telegram, kitchen-sink, Open WebUI, ClawHub, MCP, Discord, realtime, labeler, and GitHub API waits; fail empty explicit test, live-media, gateway CPU, startup benchmark, plugin gauntlet, and beta-smoke runs instead of false-greening.
+- Agents/Codex: keep spawned agent bootstrap files rooted in the agent workspace while running task commands, transcripts, and compaction from the requested cwd. (#87218) Thanks @mbelinky.
+
+## 2026.5.26
+
+### Highlights
+
+- Faster Gateway and replies: startup avoids repeated plugin, channel, session, usage-cost, warning, scheduled-service, and filesystem scans; visible replies separate user-facing sends from slower follow-up work; Gateway runtime/session caches churn less under load.
+- Transcripts are core: transcript-backed meeting summaries, source-provider chunks, cleaned user turns, media provenance, Codex mirrors, WebChat replies, and CLI/TUI replay now use one more reliable transcript path.
+- More channels are production-ready: Telegram keeps typing/progress context and forum topics, iMessage handles attachment roots, remote media staging, and duplicate local Messages sources, WhatsApp restores group/media behavior, Discord improves voice playback and model picking, and Signal/iMessage/WhatsApp get reaction approvals.
+- Better voice and Talk: realtime Talk runs can be inspected, steered, cancelled, or followed up from Web UI and Discord voice; wake-name handling is more tolerant without letting ambient speech trigger agents.
+- Safer content boundaries: Browser snapshot reads honor SSRF policy, system-event text cannot spoof nested prompt markers, fetched file text is wrapped as external content, ClickClack inbound sender allowlists run before agent dispatch, stale device tokens are rejected, and serialized tool-call text is scrubbed from replies.
+- Providers, Codex, and local models are steadier: named auth profiles, OpenAI sampling params, Codex app-server resume/timeout/usage-limit recovery, dynamic tool-schema guards, xAI usage-limit surfacing, Ollama top-p normalization, and local approval resolution reduce provider-specific dead ends.
+- More reliable install/update/release paths: Alpine installs, trusted runtime fallback roots, stable update channels, Docker/package timeouts, Windows Scheduled Tasks, Windows/macOS proof lanes, Testbox/Crabbox delegation, plugin publish checks, and macOS runner bootstraps all got hardened.
+- Better observability: Activity tab, gateway secret-prep traces, tool/model stream progress, explicit fast-mode status, systemd Gateway hygiene, OpenTelemetry LLM spans, release performance evidence, and richer telemetry signals make failures easier to inspect.
+
+### Changes
+
+- Transcripts: add core transcript capture and source-provider support for transcript-backed meeting summaries, including the renamed Transcripts docs, CLI surface, source-provider chunks, and cleaned user-turn persistence.
+- Auth: add named model login profiles and supported credential migration for Hermes, OpenCode, and Codex auth profiles, with explicit opt-out and non-interactive controls. (#85667) Thanks @fuller-stack-dev.
+- Diagnostics: trace gateway secret preparation, classify skill/tool usage, surface model stream progress, add OpenTelemetry LLM content spans, and expose alertable telemetry for blocked tools, failover, stale sessions, liveness, oversized payloads, and webhook ingress. (#83019, #80370, #86191)
+- Channels: add Signal reaction approvals, iMessage thumb approval reactions, and WhatsApp thumb approval reaction support so mobile approval flows work without textual `/approve` commands. (#85894, #85952, #85477)
+- Agents/API: forward OpenAI sampling params through the Gateway and expose estimated context-budget status for active agent runs. (#84094)
+- TUI/status: queue prompts submitted while an agent is busy and show explicit fast-mode state plus richer systemd Gateway hygiene in status output. (#86722, #87115, #86976)
+- Exec approvals: hide durable approval actions that are unavailable for the current prompt and keep approval runtime tokens local-only so stale prompts cannot offer misleading controls. (#86270, #86359)
+- Plugin SDK: add reaction approval helpers and keep diagnostic event root exports discoverable across function-name and alias-bound module graphs. (#86735, #87084)
+- Android/iOS: add the Android pair-new-gateway action and improve mobile Talk mode surfaces, including iOS realtime Talk mode and Android offline voice/gateway recovery. (#86798, #86355) Thanks @ngutman.
+- Performance: cache plugin metadata snapshots, package realpaths, stable gateway metadata, model cost indexes, channel resolution, usage-cost indexes, and session/auth hot-path facts so common Gateway and reply paths do less rediscovery. (#84649, #85843, #86517, #86678)
+- Voice: expose shared realtime turn-context tracking through the realtime voice SDK and reuse it for Discord speaker attribution and wake-name context recovery.
+- Voice: reuse shared realtime output activity tracking in Google Meet command and node audio bridges, including recent-output checks for local barge-in detection.
+- Voice: expose shared realtime output activity tracking through the realtime voice SDK and reuse it for Discord playback activity and barge-in decisions.
+- Voice: expose shared realtime consult question matching, speakable-result extraction, and alias-aware forced-consult coordination through the realtime voice SDK, then reuse it in Gateway Talk, Voice Call, and Discord voice paths.
+- Voice: share activation-name matching and consult-transcript screening through the realtime voice SDK so Discord, browser voice, and meeting surfaces can reuse one implementation.
+- Cron: default `cron.maxConcurrentRuns` to 8 so scheduled automations and their isolated agent turns can make progress in parallel without explicit configuration.
+- QA-Lab: add `qa coverage --match <query>` so focused proof selection can discover matching scenarios from existing metadata before running live or remote lanes.
+- Discord/model picker: surface an alpha-bucket select (e.g. `A–G (12) · H–N (18) · O–Z (5)`) when the provider list or a provider's model list exceeds 25 items, so configs with `provider/*` wildcards stay one click from the right page instead of paginating through prev/next; falls back to numeric chunks when every item shares the same first letter. (#86181) Thanks @rendrag-git.
+- Control UI: add an ephemeral Activity tab for sanitized live tool activity summaries without persisting raw telemetry. Fixes #12831. Thanks @BunsDev.
+- Build: include `ui:build` in the `full` and `ciArtifacts` profiles of `scripts/build-all.mjs` so `pnpm build` always rebuilds `dist/control-ui` after `tsdown` cleans `dist`, removing the second-command requirement and the missing-asset failure mode for source/runtime installs and CI artifact uploads. (#85206)
+- iOS: improve Talk mode with direct realtime voice sessions, compact toolbar status, and responsive voice waveform feedback. (#86355) Thanks @ngutman.
+- Media: replace the Sharp image backend with Rastermill for metadata, resizing, EXIF orientation, and PNG alpha-preserving optimization so OpenClaw no longer installs Sharp or the WhatsApp Jimp fallback for image processing. (#86437)
+- Codex: update the bundled Codex CLI to 0.134.0 and keep native compaction disabled for budget-triggered app-server turns so OpenClaw owns the recovery boundary. (#86772)
+
+### Fixes
+
+- Memory/security: reject prompt-like text submitted through the explicit `memory_store` tool before embedding or storage, matching the existing auto-capture prompt-injection filter. (#87142)
+- Gateway/security: enable the default auth rate limiter for remote non-browser and HTTP gateway auth failures when `gateway.auth.rateLimit` is unset, while preserving the loopback exemption. (#87148)
+- Prompt hardening: route untrusted group prompt metadata through sanitized untrusted structured context while preserving trusted operator-configured group system prompts and aligning the plugin SDK docs/test helpers. (#87144)
+- Security/content boundaries: validate Browser snapshot tab URLs against SSRF policy before ChromeMCP or direct CDP reads, sanitize queued system-event text so untrusted plugin/channel labels cannot spoof nested prompt markers, wrap fetched file text and metadata as external content, apply ClickClack `allowFrom` sender allowlists before agent dispatch, reject RPCs from invalidated device-token clients during rotation, require staged sandbox media refs, and scrub serialized tool-call text from replies. (#78526, #87094, #87062, #83741, #70707, #86924) Thanks @zsxsoft, @ttzero25, and @mmaps.
+- Transcripts/user turns: persist CLI, WebChat, media, follow-up, hook, and Codex-mirror user turns to the admitted session target; keep cleaned transcript text, inline image routing, provenance metadata, replay hooks, and fallback paths idempotent when runtimes fail or restart.
+- TUI/status/onboarding/UI: queue busy TUI prompts instead of dropping them, preserve the configured default model during onboarding, show failed tool results as errors, show config-open failures in Control UI, keep status JSON plugin scans healthy, preserve xAI usage-limit errors locally, and expose explicit fast-mode/systemd state. (#86722, #87000, #85786, #87108, #87001, #86614, #87115, #86976)
+- Plugin commands/SDK: preserve plugin LLM command auth, bind native plugin command dispatch to the host agent's LLM auth, keep `onDiagnosticEvent` exports discoverable through `Function.name`, stabilize diagnostic event root aliases, correlate pathless read diagnostics, suppress transient runner failures in channel command paths, and repair local approval resolution. (#85936, #87084, #86977, #87069, #86771)
+- Codex/providers: keep WebChat delivery hints out of user prompts, avoid false queued-terminal idle timeouts, share the native hook relay registry, quarantine unsupported dynamic tool schemas, preserve Claude resumed-session system prompts, normalize greedy Ollama `top_p`, preserve per-agent thinking defaults for ingress runs, and avoid native compaction takeover on budget-triggered Codex turns. (#87096, #73950, #87049, #86689, #86772)
+- Gateway/perf/release: reuse startup-warning metadata and prepared auth stores, avoid cloning live-switch and lifecycle session caches on read paths, defer warning and scheduled-service fallback imports, trim Gateway session/startup/runtime CPU churn, skip duplicate turn session touches, stop chat timeout fallback cascades, drop stale subagent announce history, bound benchmark/watch/kitchen-sink teardown waits, bound macOS/package/onboarding/plugin smoke commands, bound install finalization probes, resolve Parallels npm-update commands from guest `PATH`, and bootstrap raw AWS macOS Node/pnpm commands through `/usr/bin/env`. (#86997)
+- Reply/perf: reduce visible reply delivery latency by preserving Telegram typing/progress context, lazy-loading slash-command startup metadata, avoiding hot-path model hydration, flag-gating Codex profiler timing, deferring context compaction maintenance, and tracking delivery timing. (#86989, #86990, #86991, #86992, #86993, #86994) Thanks @keshavbotagent.
+- Reply/source delivery: keep TUI, Control UI, media, TTS, transcript, and Codex source-reply finals live without duplicate terminal events or stale replay artifacts.
+- Agents/replay: repair legacy tool results before replay, preserve `sessions_spawn` transcript payloads, restore current guard checks, stage sandboxed workspace media, and keep duplicate transcripts tool display metadata from reappearing. (#82203, #86934, #87025) Thanks @martingarramon, @vincentkoc, and @joshavant.
+- Agents/sessions: handle active-fallback failures in `sessions_send` so fallback routing reports the real failure and does not leave callers with an ambiguous dropped send. (#86638)
+- Agents/hooks/subagents: enforce default hook agent allowlists, recover failed subagent lifecycle completions, and keep node task lifecycle cleanup from closing the Gateway listener. (#86101)
+- Codex: project newer OpenClaw chat history into resumed app-server threads and keep Codex turn timeouts inside the Codex runtime boundary so timeouts do not poison shared app-server clients or fall through to unrelated provider fallback. (#86677, #86476) Thanks @TurboTheTurtle and @pashpashpash.
+- Config/doctor/update: narrow profiled tool-section doctor repair, keep runtime-injected legacy web-search provider config out of user-authored config validation, and keep prerelease tags excluded from stable updater resolution. (#87030, #86818, #86559) Thanks @joshavant, @luoyanglang, and @stevenepalmer.
+- Doctor/runtime: validate active bundled MCP tool schemas through the same runtime projection path so unsupported MCP input schemas are reported and quarantined instead of poisoning assistant startup.
+- CLI/Windows: add a Windows-only stack-size respawn for stack-heavy startup paths, default CLI logs to local timestamps, and validate timeout/banner TTY state more strictly. (#87031, #85387) Thanks @giodl73-repo and @vincentkoc.
+- Locking/security: require owner identity proof before stale plugin lock removal, memoize session lock owner arguments, and avoid writing default exec approval stores unless policy state actually changed. (#86814, #86964) Thanks @Alix-007 and @vincentkoc.
+- Install/release: bound Docker package build, inventory, pack, and tarball preparation with process-group timeouts; pin shrinkwrap patch drift to the pnpm lock; harden macOS restart and dSYM packaging; and run release Docker/live timeout wrappers in the foreground so child processes cannot wedge gates.
+- QA/Telegram: bound Telegram user credential tar and broker calls so live proof setup fails with a timeout instead of waiting for the outer Crabbox job deadline.
+- QA/Tool Search: bound gateway E2E HTTP probes, run only the fixture plugin, and clean up temporary fixture trees after the compact tool-catalog proof completes.
+- Telegram/network: treat `ENETDOWN` as a transient pre-connect network failure so Telegram sends, gateway unhandled-rejection handling, and cron network retries follow the same recovery path as sibling network outages. (#86762) Thanks @TurboTheTurtle.
+- Telegram: preserve inbound text entities, overlapping DM replies, account topic cache sidecars, outbound reply context, targeted bot-command mentions, durable group retry targets, forum topic names, and native progress callbacks. (#83873, #85361, #85555, #85656, #85709, #86299, #86553) Thanks @SebTardif, @luoyanglang, and @neeravmakwana.
+- iMessage: read image attachments from local Messages attachment roots, dedupe duplicate local Messages-source accounts, seed direct DM history, fix image/group media attachment commands, advance catchup cursors after live handling, and keep slash-command acknowledgements in the source conversation. (#82642, #85475, #86569, #86705, #86706, #86770) Thanks @homer-byte, @TurboTheTurtle, @swang430, and @OmarShahine.
+- WhatsApp/QQ/Twitch/IRC/Slack: restore WhatsApp ack identity and group-drop warnings, make QQ Bot media respect `OPENCLAW_HOME`, serialize Twitch auth disconnects, store IRC channel routes canonically, and keep Slack downloaded files out of reply media. (#83833, #85309, #85777, #85794, #85906, #86318, #86697) Thanks @sliverp, @neeravmakwana, and @Kailigithub.
+- Discord/voice: improve voice playback and wake replies, bucket large model picker menus, merge media captions into one message, route metadata through configured proxies, restore numeric channel sends, suppress self-reply echoes, and tighten wake matching without breaking fuzzy wake phrases. (#80227, #86238, #86487, #86571, #86595, #86601)
+- Codex: preserve native web-search metadata, keep oversized native thread reuse, bridge CLI API-key auth into the app server, preserve sandbox bootstrap path style, recover context-window prompt errors, honor yolo approval policy, disable native thread personality, and route compaction through Codex auth. (#85378, #85542, #85891, #85909, #86408)
+- Agents/runtime: enforce session lock max-hold reclaim, release embedded-attempt locks on all exits, treat aborted subagent runs as terminal, avoid runtime model hydration on hot paths, disclose scoped session list counts, derive overflow budgets from provider errors, and keep fallback errors scoped to the active model candidate. (#70473, #85764, #86014, #86134, #86427, #86944) Thanks @openperf, @fuller-stack-dev, @zhangguiping-xydt, and @ferminquant.
+- Config/update/doctor: retry config recovery after failed backup restore, skip shell env fallback on Windows, exclude prerelease tags from the stable git channel, support deep config edits, warn instead of aborting on unreadable cron stores, prune stale bundled plugin paths, and avoid duplicate restart prompts when the Gateway is already healthy. (#85739, #85787, #86060, #86260, #86384, #86533) Thanks @liaoyl830.
+- Install/release: support Alpine CLI installs and runtime floors, prefer trusted startup argv runtime fallback roots, reject stale CLI node runtimes, avoid npm `min-release-age` installer failures, bound npm/package/Docker install phases, restore config parent ownership in Docker, seed Docker lockfile package tarballs before prune, make release/plugin prerelease checks fail closed instead of hanging or false-greening, and use host-visible Crabbox local work roots for Docker-backed proof. (#85491)
+- Windows daemon: keep Scheduled Task gateway launches running on battery power and avoid workgroup-machine prompts for a domain user during task installation. (#59299)
+- Security: avoid printing Gateway tokens in Docker, validate plugin model-pattern regexes safely, escape transcript metadata field names, harden session allowlist glob matching, audit Claude permission overrides under YOLO, and require explicit allow for ACP auto approvals. (#85849, #85934, #86046, #86557)
+- Media/images: replace Sharp with Rastermill, keep EXIF normalization best-effort, normalize HEIC/HEIF before image descriptions, route Codex image API keys through OpenAI, preserve image compression metadata, and auto-scale live tool result caps. (#85776, #86037, #86437, #86857, #86923)
+- Memory: prevent semantic vector indexes from silently degrading when embeddings are unavailable, stop doctor OOMs on large session stores, preserve sidecar hooks/artifacts, write fallback dream diaries, use CJK-aware dreaming dedupe, and avoid per-file watcher FD fan-out. (#80613, #82928, #85060, #85704, #85967, #86701) Thanks @brokemac79, @openperf, and @yaaboo-gif.
+- Agents/sessions: include visibility metadata on restricted `sessions_list` results so scoped counts are clearly reported without widening access or exposing hidden-session counts. (#86944) Thanks @ferminquant.
+- Gateway/DNS: validate wide-area discovery domains before deriving zone paths or writing zone files, so invalid `discovery.wideArea.domain` and `dns setup --domain` values fail with a DNS-name diagnostic instead of falling through to unrelated configuration errors. Thanks @mmaps.
+- Agents/BTW: route fallback side-question streams through the embedded stream resolver so Anthropic-compatible MiniMax requests use the same capped transport as normal chat. (#86312) Thanks @neeravmakwana.
+- Telegram: treat `/command@TargetBot` bot-command entities as explicit mentions for the addressed bot so `requireMention` groups no longer drop targeted commands or captions. Fixes #84462. (#86553) Thanks @luoyanglang.
+- CI: bound Docker/Bash E2E tarball npm installs with `OPENCLAW_E2E_NPM_INSTALL_TIMEOUT` so package, onboarding, plugin, and upgrade lanes fail instead of hanging on a stuck npm install.
+- CI: fail Parallels npm-update smoke jobs after the guest command timeout and cleanup backstop instead of only logging a timeout line.
+- CI: bound kitchen-sink RPC HTTP probes so stalled gateway readiness or response bodies fail and retry instead of wedging the walker.
+- CI: bound Telegram user Crabbox proof Bot API calls so stalled Telegram responses fail instead of wedging credential and desktop proof cleanup.
+- CI: bound MCP channel stdio client initialization so Docker channel proof fails and closes the bridge transport instead of waiting for the outer job timeout.
+- CI: keep `OPENCLAW_TESTBOX=1 pnpm check:changed` delegating to Blacksmith Testbox through Crabbox without forwarding local Testbox or worker env into the remote command.
+- CI: send KILL after the TERM grace period for manual checkout fetch timeouts so stuck Testbox and workflow checkout retries cannot hang behind a wedged `git fetch`.
+- CI: send KILL after the TERM grace period for Bun global install smoke command timeouts so trapped `openclaw` child processes cannot wedge the scheduled install smoke.
+- iMessage: thread current channel/account inbound attachment roots into the image tool so iMessage-saved attachments under `~/Library/Messages/Attachments` (including the wildcard `/Users/*/Library/Messages/Attachments` root) are read through the existing inbound path policy instead of being rejected as `path-not-allowed`. Literal `localRoots` stays workspace-scoped. Fixes #30170. (#86569)
+- QQ Bot: respect `OPENCLAW_HOME` for outbound media path resolution so `<qqmedia>` sends no longer silently fail when `HOME` and `OPENCLAW_HOME` differ (Docker / multi-user hosts). Persisted QQ Bot data (sessions, known users, refs) stays anchored on the OS home for upgrade compatibility. Fixes #83562. Thanks @sliverp.
+- Update: report the primary malformed `openclaw.extensions` payload error without adding a duplicate missing-main diagnostic. (#86596) Thanks @ferminquant.
+- Control UI: keep host-local Markdown file paths inert while preserving app-relative links. (#86620) Thanks @BryanTegomoh.
+- Gateway: dampen repeated unauthenticated device-required probes per URL while preserving explicit-auth and paired recovery paths. (#86575) Thanks @ferminquant.
+- IRC: store inbound channel routes with the canonical `channel:#name` target and join transient channel sends before writing. (#85906) Thanks @Kailigithub.
+- Usage: surface unknown all-zero model pricing as missing cost entries instead of a confident `$0` total. (#85882) Thanks @MichaelZelbel.
+- Agents/Codex: honor yolo app-server approval policy only for the full `never` plus `danger-full-access` case. (#85909) Thanks @earlvanze.
+- Gateway/Gmail: clear Gmail watcher renewal intervals on re-entry so hot reloads do not leak lifecycle timers. (#82947) Thanks @SebTardif.
+- Logging: exit cleanly on broken stdout/stderr pipes without masking existing failure exit codes. (#80059) Thanks @pavelzak.
+- Gateway/security: escape transcript metadata field names while extracting oversized session line prefixes. (#85934) Thanks @SebTardif.
+- Plugins/security: validate manifest model pattern regexes with the safe-regex compiler so unsafe patterns are ignored before matching. (#86046) Thanks @SebTardif.
+- Discord: route gateway metadata REST lookups through the configured Discord proxy so proxied accounts do not fall back to direct `discord.com` connections before opening the WebSocket. Fixes #80227. Thanks @Clivilwalker.
+- Agents/media: hydrate current-turn image attachments from filename-derived MIME types so active vision can see generated or forwarded images whose source omitted an image content type. (#84812) Thanks @marchpure.
+- Agents/fs: point workspace-only scratch-path guidance at in-workspace temp directories while keeping host-root writes rejected by the tool guard. (#86501) Thanks @tianxiaochannel-oss88.
+- Agents/media: keep async cron media completions scoped to their run session while preserving direct delivery for stale generated-media success and failure notifications. (#86529) Thanks @ai-hpc.
+- Gateway: emit plugin `session_end`/`session_start` hooks when `agent.send` rotates or replaces a session id, keeping hook lifecycle state aligned with `sessions.changed` notifications. Fixes #83507. (#85875) Thanks @brokemac79.
+- OpenShell/SSH: reject malformed generated exec commands before sandbox/session setup so unresolved workflow placeholders fail fast instead of reaching the remote shell. Fixes #72373. Thanks @brokemac79.
+- Google: stop normalizing `gemini-3.1-flash-lite` to the retired preview endpoint and update Flash Lite alias guidance to the GA model id. Fixes #86151. (#86240) Thanks @SebTardif.
+- Installer: make Alpine apk installs cover Git, verify the Node runtime floor, try `nodejs-current`, and report Alpine version guidance when repositories only provide older Node packages.
+- Agents/status: prefer the active Claude CLI OAuth auth label over an unused Anthropic env API-key label for equivalent runtime aliases. Fixes #80184. (#86570) Thanks @brokemac79.
+- Agents/media: send direct fallback for generated media still missing after an active requester wake fails. (#85489) Thanks @fuller-stack-dev.
+- Agents: derive overflow compaction budgets from provider-reported and synthetic over-budget token counts so confirmed context overflows compact before retrying. (#70473) Thanks @fuller-stack-dev.
+- Agents/Codex: recover Codex context-window prompt errors through overflow compaction and surface reset guidance when recovery is exhausted. (#85542) Thanks @fuller-stack-dev.
+- Agents/Codex: allow Codex app-server runs to bootstrap from `CODEX_API_KEY` or `OPENAI_API_KEY` when no Codex auth profile is configured.
+- Agents/Codex: keep selected Codex runtime routing on OpenAI-Codex while preserving direct OpenAI API-key compaction fallback. (#86408) Thanks @funmerlin and @VACInc.
+- Agent transcript: include OpenClaw agent session logs when finding local transcript candidates.
+- Crabbox: bootstrap raw AWS macOS shell commands wrapped in absolute `time` paths so RSS probes can run Node and pnpm on fresh macOS runners.
+- Crabbox: bootstrap raw AWS macOS shell commands even when setup statements precede Node or pnpm usage.
+- TUI/local: skip unnecessary secret resolution, gateway model catalog loading, bootstrap, and skill scans in explicit local-model runs so startup reaches the model request faster.
+- Sessions/doctor: load large session stores without clone amplification during read-only doctor checks and reclaim stale `sessions.json.*.tmp` sidecars. Fixes #56827. Thanks @openperf.
+- Tests: clean successful plugin gateway gauntlet isolated temp roots while keeping an explicit preservation switch for failed/debug runs.
+- Plugins/perf: reuse derived plugin metadata snapshots for the lifetime of the process so reply-time skill setup no longer rescans plugin metadata on every turn.
+- Discord/OpenAI voice: keep wake-name master consults using the current speaker context after ignored ambient transcripts and shorten the default capture silence grace.
+- Doctor: skip redundant Gateway restart prompts when a recent supervisor restart leaves the Gateway healthy. Fixes #86518. (#86533) Thanks @liaoyl830.
+- Cron: restore suspended cron lanes to the configured/default concurrency instead of falling back to one after quota or circuit-breaker auto-resume.
+- Gateway: keep session-only Control UI tool-start mirrors flowing during diagnostic queue pressure instead of silently dropping non-terminal tool updates.
+- Agents/memory: return optional not-found context for missing date-only daily memory reads instead of logging benign first-run `ENOENT` failures. Fixes #82928. Thanks @galiniliev.
+- Discord: merge streamed text captions into following media block replies so captions and attachments send as one message. (#86487) Thanks @neeravmakwana.
+- Gateway: avoid sending duplicate tool-event frames to Control UI connections that are subscribed by both run and session.
+- Discord/OpenAI voice: accept broader edge-position fuzzy wake-name transcripts while keeping ambient speech gated.
+- Discord/OpenAI voice: accept longer leading wake-name mistranscripts such as "Open Club" for OpenClaw.
+- Agents/OpenAI-compatible: stop ModelStudio-compatible chat requests before sending system/tool-only payloads that have no usable user or assistant turn. (#86177) Thanks @TurboTheTurtle.
+- Gateway/plugins: reuse plugin package realpath checks while building installed plugin indexes so startup avoids repeated filesystem resolution work.
+- Kilo Gateway: send string `stop` sequences as arrays so Kilo accepts OpenAI-compatible chat completions. (#86461) Thanks @SebTardif.
+- Discord/OpenAI voice: accept leading fuzzy wake-name transcripts such as "Monty" or "Moti" for a Molty agent while keeping ambient speech gated.
+- Media understanding: convert HEIC and HEIF images to JPEG before image description providers run so iPhone photos work in direct and configured image-description flows. (#86037)
+- Agents: release embedded-attempt session locks from outer teardown so post-prompt exceptions cannot wedge later requests behind `SessionWriteLockTimeoutError`. Fixes #86014. Thanks @openperf.
+- Discord/OpenAI voice: rotate Realtime sessions at provider max duration without logging the expected session-expiry event as an error.
+- Sessions: skip metadata-only entries during QMD-slugified session lookup so one incomplete row does not block transcript hit resolution. (#86327) Thanks @abnershang.
+- Agents/media: derive bundled plugin local-media trust from plugin tool metadata instead of importing the full plugin registry on subscription paths. (#84409) Thanks @samzong.
+- Image tool: keep config-backed custom-provider API keys usable for auto-discovered vision models, including deferred image-tool execution without env keys or auth profiles. (#85733)
+- Memory/local embeddings: run local GGUF embeddings in an isolated worker sidecar and degrade to configured fallback or keyword search on worker failure so native embedding crashes do not take down the Gateway. (#85348) Thanks @osolmaz.
+- Gateway: clear the runtime config snapshot before `SIGUSR1` in-process restarts so config changes survive the next gateway loop. (#86388) Thanks @XuZehan-iCenter.
+- Models: show OAuth delegation markers as configured `models.json` auth while keeping runtime route usability checks strict. (#86378) Thanks @rohitjavvadi.
+- Cron: seed active scheduled and manual cron task rows with a progress summary so status surfaces do not look blank while jobs run. (#86313) Thanks @ferminquant.
+- Cron: preserve unsupported persisted cron payload rows during routine store writes while keeping those rows non-runnable. Fixes #84922. (#86415) Thanks @IWhatsskill.
+- Updater: exclude prerelease git tags from stable channel resolution so source updates do not check out newer alpha/rc/preview/canary tags. (#86260) Thanks @stevenepalmer.
+- Security/Audit: flag webhook `hooks.token` reuse of active Gateway password auth in `openclaw security audit` while keeping password-mode startup compatibility. (#84338) Thanks @coygeek.
+- QQBot: derive the outbound reply watchdog from configured agent and provider timeouts so slow local model replies are not cut off at five minutes. Fixes #85267. (#85271) Thanks @SymbolStar.
+- Agents/heartbeat: stop heartbeat turns after the first valid `heartbeat_respond` so repeated response loops do not burn tokens. (#86357) Thanks @udaymanish6.
+- Tasks: keep retained lost tasks out of default status health counts, explain their cleanup window during maintenance, and prune lost task records after 24 hours instead of the general 7-day terminal retention.
+- Memory-core: keep REM dreaming focused on live light-staged memories and mark staged entries as considered so old recall history no longer dominates fresh candidates. (#86302) Thanks @SebTardif.
+- Memory: abort sync instead of downgrading an existing semantic vector index to FTS-only when the configured embedding provider is temporarily unavailable. (#85704) Thanks @yaaboo-gif.
+- Telegram: propagate forum topic names through the account-scoped topic cache for native command context and topic create/edit actions. (#86299) Thanks @SebTardif.
+- Slack: keep downloaded read-only files out of reply media so Slack file reads do not echo files back to the conversation. (#86318) Thanks @neeravmakwana.
+- Cron: accept leading-plus relative durations such as `+5m` for one-shot `--at` schedules. (#86341) Thanks @mushuiyu886.
+- Agents/media: preserve async-started media tool metadata so background generation starts no longer surface generic incomplete-turn warnings while replay stays unsafe. (#85933) Thanks @fuller-stack-dev.
+- Docker E2E: dedupe scheduler lane resources so npm/service package lanes are not over-counted and serialized unnecessarily.
+- QA/diagnostics: add a collector-backed OpenTelemetry smoke lane, make the OTLP payload leak check scenario-aware, and keep source QA builds from failing on optional dependency imports resolved through pnpm's temp module path.
+- Crabbox: bootstrap Git metadata for sparse remote changed gates so raw synced workspaces can run `pnpm check:changed` from the intended diff.
+- xAI/LM Studio: avoid buffering ordinary bracketed or `final` prose until stream completion while watching for plain-text tool-call fallbacks.
+- Doctor: warn and continue when the cron job store exists but cannot be read so later health checks still run. Fixes #86102. (#86384) Thanks @1052326311.
+- Discord: suppress a bot's previous reply body and referenced media from prompt context when a user replies to that bot message, while keeping reply metadata for routing. (#86238) Thanks @fuller-stack-dev.
+- Discord: restore bare numeric channel IDs for outbound message-tool sends while keeping explicit DM targets unambiguous. (#86571) Thanks @joshavant.
+- Docker E2E: avoid rebuilding the Control UI twice while preparing the shared OpenClaw package tarball for package-backed scenario runs.
+- Tests: avoid rebuilding the Control UI twice during the installer Docker smoke now that `pnpm build` includes `ui:build`.
+- Tests: give QA config mutation RPCs enough native Windows budget to finish gateway config writes and restart settle after hot scenario runs.
+- Tests: keep the gateway restart-inflight QA scenario focused on restart recovery on native Windows by allowing expected embedded prompt handoff errors and using the Windows-safe timeout budget.
+- QA-Lab: make the synthetic OpenAI provider honor generic `reply exactly:` directives after required kickoff reads so restart-recovery scenarios do not fall through to generic repo-summary prose.
+- Gateway: abort active `agent` RPC runs during forced restart shutdown so stale in-process turns cannot keep writing a session after the Gateway lifecycle restarts.
+- Crabbox: sync clean sparse worktrees through a temporary full checkout even when reusing an existing lease so tracked build-time files are not omitted.
+- Build: route `scripts/ui.js` through the shared pnpm runner and keep Control UI chunking helpers in sparse-included source so native Windows Corepack builds can produce `dist/control-ui`.
+- Tests: give the memory fallback QA scenario enough turn budget to exercise native Windows gateway runs instead of failing on the client timeout while the mock agent is still dispatching.
+- Tests: collect QA gateway CPU/RSS metrics on native Windows and give the channel baseline enough turn budget to report slow gateway runs instead of timing out before proof.
+- Install/update: bypass npm `min-release-age` policies with `--min-release-age=0` instead of `--before` so hosted installers keep working on npm versions that reject the combined config. (#84749) Thanks @TeodoroRodrigo.
+- Diagnostics: reclaim wedged session lanes when stale active-run bookkeeping blocks queued work despite no forward progress. Fixes #85639. Thanks @openperf.
+- WebChat: keep message-tool replies visible in the chat while still summarizing internal tool results for the model. Fixes #86347. Thanks @shakkernerd.
+- Gateway/perf: fail startup benchmark samples when the Gateway process exits before benchmark teardown, including signal deaths after readiness probes.
+- Gateway/perf: fail restart benchmark samples when the Gateway exits before benchmark teardown, including clean exits and signal deaths after successful restart probes.
+- Agents/tests: keep model catalog visibility on static selection helpers so catalog visibility checks avoid the broad model-selection barrel import.
+- Agents/commitments: serialize commitment store load-modify-save writes so concurrent heartbeat and CLI updates no longer lose dismissal, sent, or attempt state. (#81153) Thanks @ai-hpc.
+- xAI/LM Studio: promote plain-text tool-call fallbacks into structured tool calls and strip leaked internal tool syntax before user-facing delivery. (#86222) Thanks @fuller-stack-dev.
+- CLI: suppress benign self-update version-skew warnings during package post-update finalization.
+- Gateway/perf: tighten restart and startup benchmark failure handling so long profiling runs, failed probes, and fresh Linux runners no longer produce false passing or `n/a` results.
+- Checks: keep intentional Knip unused-file findings optional so full CI and sparse proof workspaces stay aligned.
+- Docker: restore writable `~/.config` in runtime images. Fixes #85968. Thanks @hkoessler and @Bartok9.
+- Plugin SDK: keep legacy root diagnostic subscriptions connected when built plugin SDK aliases resolve diagnostic helpers through a separate module graph.
+- Diagnostics: export alertable OTel and Prometheus signals for blocked tools, model failover, stale sessions, liveness warnings, oversized payloads, and webhook ingress while fixing shared OTLP endpoints with query strings.
+- Tests: normalize macOS canonical temp paths in exec allowlists, fs-safe trash assertions, installed plugin matching, Telegram topic-name stores, and built ACPX MCP server expectations so native macOS proof runners cover the intended behavior.
+- Codex/app-server: preserve message-tool-only source reply delivery mode on active runs so sub-agent completion wakeups can steer the active Codex turn instead of being rejected. (#86287) Thanks @ferminquant.
+- Tests: sample the Windows kitchen-sink RPC gateway directly and serialize RSS probes so native runs keep the memory guard active.
 - Tests: normalize bundled plugin lifecycle probe paths and state-root lookup so native Windows release sweeps accept valid packaged plugin installs.
+- Agents/Claude CLI: route live native Bash permission requests through OpenClaw exec policy so Claude turns no longer stall on `control_request`, and document that OpenClaw exec policy is authoritative. Fixes #80819. (#86330, from #81971) Thanks @guthirry and @sallyom.
+- Security audit: warn when YOLO OpenClaw exec policy overrides a restrictive raw Claude `--permission-mode` for managed live sessions. (#86557) Thanks @sallyom.
 - Config: keep benign legacy metadata write anomalies out of default doctor and config command output while preserving explicit anomaly logging for diagnostics.
-- Agents/Codex: route budget preflight compaction through the persisted Codex session model so Slack threads do not require separate plain OpenAI auth. Thanks @amknight.
 - Codex: log when implicit app-server `never` approvals are promoted for OpenClaw tool policy, including whether the trigger was a `before_tool_call` hook or trusted tool policy.
+- Codex harness: make subscription usage-limit errors without reset times explain that OpenClaw cannot determine the reset and point users to wait until Codex is available, use another Codex account, or switch to another configured model/provider. Thanks @amknight.
 - Google Vertex: support production ADC modes such as Workload Identity Federation, service-account credentials, and metadata-server ADC for the native Vertex transport. (#83971) Thanks @damianFelixPago.
 - Telegram: route normal `[telegram][diag]` polling diagnostics through `runtime.log` while keeping non-diag warnings and persistence failures on `runtime.error`, so healthy polling startup no longer looks like an error. Fixes #82957. (#82958) Thanks @galiniliev.
+- Providers/Ollama: strip inline Kimi cloud reasoning prefixes from streamed and final visible replies while keeping ordinary Kimi answers append-only. (#86286) Thanks @jason-allen-oneal.
 
-## 2026.5.25
+- Gateway: require Talk secret authority before setup-code handoff can include Talk secrets. (#85690) Thanks @ngutman.
+- Agents: keep fallback error reporting scoped to the active model candidate so stale prior-provider quota/auth text is not reported for later fallback attempts. (#86134) Thanks @zhangguiping-xydt.
+- iMessage: dedupe watcher startup when `channels.imessage.accounts` lists both `default` and a named account that point at the same local Messages source, so the gateway no longer spawns two `imsg rpc` processes or doubles inbound replies; the dedupe is scoped to watcher startup, leaving duplicate accounts addressable for outbound sends, status, and capability listings, and `openclaw doctor` flags the redundant account with a rebinding hint. Fixes #65141. (#86705) Thanks @swang430.
 
-### Fixes
-
-- Installer: let the local-prefix CLI installer use Alpine's `apk` Node.js, npm, and Git packages on musl Linux instead of downloading glibc Node tarballs that fail `node:sqlite`.
-- Scripts: use `git grep` to prefilter tracked conflict-marker scans so changed checks avoid reading every repository file on clean runs.
-- Plugins: allow linked local plugin paths to probe TypeScript source entries without requiring compiled package output, restoring source-checkout plugin development on native Windows.
-- CLI: route source-checkout build output to stderr before launching OpenClaw commands so stale local builds do not corrupt `--json` stdout.
-- Installer: install Node.js through `apk` on Alpine Linux instead of falling through to the NodeSource package-manager path.
-- Agents/perf: cache manifest-backed CLI provider descriptors and fallback provider resolution so model fallback retries avoid repeated bundled provider runtime scans while still invalidating across plugin reloads.
-- Installer: detect musl Linux shells such as Alpine as Linux instead of rejecting them before npm install.
-- Scripts: run direct Node package scripts with env overrides through a cross-platform launcher so gateway, TUI, and Docker-all entrypoints work on native Windows.
-- Tests: run Vitest import timing entrypoints through a Node wrapper so native Windows package scripts can collect import diagnostics.
-- Control UI: split large build-time runtime dependencies into stable chunks so Linux/Docker install and package builds stay below the app chunk warning threshold.
-- Tests: run `test:max` and `test:changed:max` through a Node wrapper so high-worker Vitest entrypoints work on native Windows.
-- Tests: retry transient loopback HTTP resets in the kitchen-sink RPC walk so native Windows readiness probes do not fail after the gateway is already ready.
-- Tests: run `test:serial` through a Node wrapper so targeted serial Vitest commands work on native Windows.
-- Tests: normalize Vitest config path assertions so the infra config suite runs on native Windows paths.
-- Scripts: run the optional Discord native opus installer through the shared pnpm launcher and Windows CI coverage so native Windows installs avoid shell-mode package-manager shims.
-- Installer: avoid the incompatible generated `--before` install filter when raw npm `min-release-age` config is present. (#85491) Thanks @TurboTheTurtle.
-- Agents/MCP: bound bundled MCP `tools/list` catalog discovery so hung MCP servers do not block session tool materialization. (#85063) Thanks @nxmxbbd.
-- Scripts: run generated-module formatting through the shared pnpm launcher and Windows CI coverage so native Windows generator checks avoid shell-mode package-manager shims.
-- Channels/iMessage: recover malformed anchorless group watch payloads by GUID before debounce/routing, and drop unrecoverable payloads instead of replying to the sender DM. Fixes #84470. Refs #84503. Thanks @zhangguiping-xydt and @zqchris.
-- Channels/iMessage: advance the startup catchup cursor from live-handled rows after a completed catchup pass, including rows received while catchup is still running, so restarts do not replay them. (#85475) Thanks @TurboTheTurtle.
-- Tests: mount the shared Windows command helper into bare Docker E2E harness containers so published upgrade-survivor config walks can start on Linux.
-- Tests: keep the plugin binding command escape Docker smoke focused on its intended Vitest cases and skip source-only install lifecycle scripts.
-- Tests: let the generic plugin install E2E assertions use a configurable temp root and Windows home-relative install paths.
-- Tests: keep kitchen-sink plugin assertion fixtures on a configurable temp root so native Windows runs no longer skip full-surface diagnostic coverage.
-- Tests: fail Gateway startup benchmarks when a child startup never produces ready probes or process metrics instead of reporting all `n/a` samples as passing.
-- Config/secrets: allow exec SecretRef ids to include `#` selectors so AWS-style `secret#json_key` ids validate consistently. (#80731) Thanks @TurboTheTurtle.
-- Tests: keep the Telegram user credential helper on platform temp and path APIs so native Windows credential export and restore commands do not write through POSIX-only paths.
-- Installer: include the optional verify phase in the progress counter so `--verify` shows `[4/4] Verifying installation` instead of `[4/3]`.
-- Crabbox: let the wrapper find a sibling Crabbox checkout from linked Git worktrees so Codex worktrees can run remote gates without a PATH shim.
-- Scripts: tolerate the standard `--` option separator in shared script flag parsing so perf/test helpers accept package-manager argument forwarding.
-- Tests: preserve `--` passthrough arguments in live-media, live-shard, and extension batch harnesses so Vitest filters are not misread or silently ignored.
-- Crabbox: default AWS macOS runner requests to on-demand capacity so EC2 Mac proof commands do not fail on the unsupported Spot market default.
-- Tests: run upgrade-survivor config recipe commands through the Windows npm shim so native Windows package walks keep baseline config coverage.
-- Image tool: use bundled Anthropic media limits when resolving image compression policy without provider-runtime hooks.
-- Tests: fail the kitchen-sink RPC Docker walk when gateway RSS sampling is unavailable instead of silently disabling the per-process memory guard.
-- Tests: suppress the current Rolldown plugin timing warning format in the Vitest wrapper so tiny focused runs do not drown useful stderr in repeated build-timing noise.
-- Models/OpenRouter: use endpoint-specific OpenRouter context limits from `top_provider` metadata so provider-routed models no longer overstate available context. (#85949) Thanks @TurboTheTurtle.
-- Crabbox: sync clean sparse-checkout remote changed gates from a temporary full checkout with local-only commits overlaid as worktree changes so git-backed script checks can seed the runner repository.
-- Agents: avoid loading bundled channel plugins while resolving completion delivery policy and queue defaults on subagent handoff paths.
-- Tests: allow split Vitest config shards through the explicit-target preflight so CI shard jobs run their intended projects.
-- Tests: make startup memory and startup bench smoke scripts build CLI startup artifacts when run from a fresh source checkout.
-- iMessage: mark authorized slash-command turns as text-sourced commands so `/status`, `/new`, and `/restart` acknowledgements return to the source conversation. (#82642) thanks @homer-byte.
-- Crabbox: install Corepack shims into the writable hydration `PNPM_HOME` so local AWS runner hydration no longer tries to overwrite `/usr/local/bin/pnpm`.
-- Live tests: fail Gateway live model sweeps when selected coverage is lost to timeouts or stale high-signal filters instead of reporting false missing-profile coverage, and pin Docker OpenAI gateway coverage to the current `gpt-5.5` lane.
-- Tests: fail Docker resource-ceiling checks when stats samples or configured limits are invalid instead of silently reporting zero peaks.
-- Agents: fail closed when provider-less session models match multiple provider-prefixed runtime policies so CLI runtime routing no longer depends on config order. (#85970) Thanks @potterdigital.
-
-## 2026.5.24
+## 2026.5.22
 
 ### Changes
 
-- iMessage: support thumb-approval reactions — `👍` (Like tapback) resolves an approval as `allow-once` and `👎` resolves as `deny`, with the explicit-approver allowlist read from `channels.imessage.allowFrom`; `allow-always` stays on the manual `/approve <id> allow-always` text fallback. Mirrors the WhatsApp behavior from #85477.
 - Gateway/perf: reuse process-stable channel catalog reads, avoid repeated bundled-channel boundary checks, and rotate gateway watch CPU profiles so benchmark runs do not accumulate unbounded artifacts.
-- Gateway/perf: cache stable install-record, channel-catalog, bundled-channel, and Telegram session-store metadata during process-local hot paths to reduce repeated JSON and manifest reads.
 - Gateway/perf: reuse immutable plugin metadata snapshots across startup, config, model, channel, setup, and secret metadata readers so hot paths avoid repeated plugin file stats and manifest registry reloads.
-- Talk/realtime: let WebUI and Discord voice callers ask for active OpenClaw run status, cancel, steer, or queue follow-up work while a consult is still running. (#84231) Thanks @Solvely-Colin.
-- Discord/voice: add realtime wake-name gating with agent-name defaults and raise profile bootstrap context budget for longer `USER.md`/`SOUL.md` files.
 - Gateway/perf: lazy-load startup-idle plugin work, core gateway method handlers, and the embedded ACPX runtime so Gateway health and ready signals no longer wait on unused handler trees or ACPX probes.
 - Gateway/perf: cache plugin SDK public-surface alias maps and skip irrelevant macOS Linuxbrew PATH probes so Gateway startup avoids repeated filesystem walks and slow missing-directory stats.
-- Image tool: add adaptive model-aware image compression with an `agents.defaults.imageQuality` preference for choosing token-efficient, balanced, or high-detail media handling.
-- Meeting Notes: add a source-only external meeting-notes plugin and SDK source-provider contract outside the core npm package, with auto-start capture config, manual transcript imports, read-only `openclaw meeting-notes` CLI access, and Discord voice as the first live source.
-- Meeting Notes/Discord: release channel account startup before meeting-notes auto-capture, wait for the Discord voice manager during gateway boot, and stop plugin services before channel shutdown so voice capture state remains available during startup and cleanup.
+- Transcripts: add the initial transcript capture and source-provider foundation, including auto-start capture config, manual transcript imports, read-only transcript access, and Discord voice as the first live source.
 - Docs/channels/config: add Signal `configPath`, Telegram wildcard topic defaults, local-time backup archive names, Termux home fallback, include-path validation, secret-scanner-safe placeholder guidance, Gemini CLI/Antigravity media guidance, and macOS VM auto-login guidance. Thanks @NorseGaud, @yudistiraashadi, @huangqian8, @VibhorGautam, @maweibin, @tianxingleo, @IgnacioPro, and @xzcxzcyy-claw.
 - Docs: clarify model-usage portability, Codex migration prerequisites, status bootstrap wording, thread-bound subagent limits, hook ownership, and config-preserving safety guidance. Thanks @aniruddhaadak80, @leno23, @TomDjerry, @matthewxmurphy, @vincentkoc, and @stablegenius49.
 - Docs: clarify README onboarding and Gateway startup paths, WhatsApp QR/408 recovery, cron output language prompts, skill advanced features, gateway upstream 403 troubleshooting, and plugin fallback override guidance. Thanks @deepujain, @Zacxxx, @Jah-yee, @neyric, @usimic, @Renu-Cybe, @BigUncle, and @SeashoreShi.
 - Docs: clarify context-pruning ratio bounds, local dashboard recovery, CLI env markers, remote onboarding token behavior, and Peekaboo Bridge permissions for subprocess agents. Thanks @ayesha-aziz123, @dishraters, @hougangdev, and @brandonlipman.
 - Docs: clarify browser CDP diagnostics, Plugin SDK allowlist imports, status-reaction timing defaults, queue steering behavior, limited-tool troubleshooting, cron HEARTBEAT handling, Telegram multi-agent groups, Bitwarden SecretRef setup, and EasyRunner deployments. Thanks @Quratulain-bilal, @mbelinky, @Mickey-, @vancece, @xenouzik, @posigit, @surlymochan, @janaka, and @choiking.
-- CLI/models: let `openclaw models auth login` store a single returned provider auth profile under a requested `--profile-id`, and document named Codex OAuth profile setup. (#49315) Thanks @DanielLSM.
 - Crabbox/Testbox: run clean sparse-checkout Testbox syncs from a temporary full checkout and route remote changed gates through Corepack pnpm.
 - Docs: clarify IPv4-only Gateway BYOH binding, trusted-proxy scope clearing, Android pairing approval, macOS Accessibility grants, Zalo profile env vars, password-store SecretRef setup, and Chinese memory navigation. Thanks @itskai-dev, @gwh7078, @longstoryscott, @MoeJaberr, and @yuaiccc.
 - Docs: consolidate GLM under Z.AI, add the Upstash Box install guide and Gateway exposure runbook, clarify MEDIA directives, Copilot and Voyage setup, config path quoting, real behavior proof, and memory-file write guidance. Thanks @BobDu, @alitariksahin, @Jefsky, @musaabhasan, @OmerZeyveli, @leno23, @WuKongAI-CMU, @luoyanglang, and @majin1102.
 - Docs: clarify media provider credentials, Codex/OpenClaw code-mode boundaries, Slack and Telegram ack reactions, Feishu dynamic agents, secrets plaintext boundaries, memory guidance, and Chinese glossary terms. Thanks @nielskaspers, @cosmopolitan033, @drclaw-iq, @alexgduarte, @zccyman, @chengoak, and @cassthebandit.
 - Packaging: exclude documentation images and assets from the npm tarball, reducing published package size without affecting runtime docs search or CLI behavior. Thanks @SebTardif.
 - Media understanding: stop auto-probing Gemini CLI and use Antigravity CLI only as a lower-priority image/video fallback after configured provider APIs.
-- Diagnostics: emit sanitized `secrets.prepare` timeline spans for Gateway secret preparation so operators can distinguish secret startup latency without exposing provider names, secret ids, or secret values. (#83019) Thanks @samzong.
-- Diagnostics: export bounded skill usage metrics/spans and tool source/owner labels for core, plugin, MCP, and channel tool execution without exposing raw paths or session identifiers. (#80370) Thanks @gauravprasadgp.
 - Agents/subagents: limit default sub-agent bootstrap context to `AGENTS.md` and `TOOLS.md`, keeping persona, identity, user, memory, heartbeat, and setup files out of delegated workers by default. (#85283) Thanks @100yenadmin.
-- Maintainer skills: require clean autoreview before surfacing bug-sweep PR URLs and treat changelog-only conflicts as routine busy-main churn.
 - Maintainer skills: exclude plugin SDK/API boundary work from `openclaw-landable-bug-sweep` so bugbash sweeps stay focused on small paper-cut fixes.
 - QA-Lab/diagnostics: extend the OpenTelemetry smoke harness to prove trace, metric, and log export, and add first-class Prometheus and observability smoke aliases.
 - Plugin SDK: add a generic channel-message poll sender so channel plugins can expose poll delivery without depending on channel-specific SDK facades.
-- Plugin SDK/cron delivery: route cron delivery through the modern target resolver and outbound session-route APIs, deprecate parser-backed target helpers and `plugin-sdk/messaging-targets`, and move bundled callers to `plugin-sdk/channel-targets`.
 - Crabbox: keep the local wrapper's provider validation synced with the installed Crabbox binary while preserving supported aliases such as `docker` and `blacksmith`. (#85302) Thanks @hxy91819.
 - Maintainer skills: add `openclaw-landable-bug-sweep` for producing five small, reviewed, CI-green OpenClaw bugfix PRs from issue/PR sweeps.
 - Control UI/chat: add search and Load More pagination to the chat session picker, keeping initial session loads bounded while making older conversations reachable. (#85237) Thanks @amknight.
 - CLI/onboarding: start classic onboarding when bare `openclaw` runs before an authored config exists, while keeping configured installs on Crestodian. (#72343) Thanks @fuller-stack-dev.
+- Agents/runtime: internalize the former Pi agent runtime into OpenClaw, remove legacy package dependencies, and keep Pi-named SDK aliases only as deprecated plugin compatibility.
 - Discord: allow configuring a bounded `agentComponents.ttlMs` callback registry lifetime for long-running component workflows, with per-account overrides and a 24-hour cap. (#84189) Thanks @100menotu001.
 - xAI/Grok: reuse xAI OAuth auth profiles for Grok `web_search`, thread active-agent auth through web search, add Grok model aliases, and let media providers declare default operation timeouts. (#85182) Thanks @fuller-stack-dev.
 - Plugin SDK: add row-level session workflow helpers and deprecate `loadSessionStore` so plugins can read and patch sessions without depending on the legacy whole-store shape. (#84693) Thanks @efpiva.
@@ -131,74 +320,21 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
-- Gateway/update: avoid fetching unrelated tags during dev-channel git updates so moved release tags do not block branch-based updates. (#84737) Thanks @rubencu.
-- CLI/update: suppress the expected future-config warning while an old update parent hands off to the freshly installed post-core process.
-- MiniMax: store OAuth token expiry as an absolute millisecond timestamp so OAuth profiles no longer appear expired on every request. (#83480) Thanks @NianJiuZst.
-- Agents/Anthropic: strip missing or blank thinking signatures for signed-thinking providers even when recovery supplies a narrow replay policy without signature preservation. Fixes #84430. (#84448) Thanks @NianJiuZst.
-- Agents/channels: send a visible notice when an aborted main session cannot be resumed after restart, including Telegram group targets. (#85805) Thanks @pfrederiksen.
-- Discord/voice: serialize overlapping voice joins, retry aborted startup readiness within the configured timeout, upgrade meeting-notes-only sessions to realtime when the normal follow join arrives, detach promoted meeting-notes ownership without leaving voice, and include `OpenClaw` in default realtime wake names.
-- Gateway/restart: honor the configured restart drain budget for embedded runs and avoid spending the deferral timeout twice after forced restart timeouts. (#85708) Thanks @Kaspre.
-- Gateway/boot: run `BOOT.md` startup checks in an isolated boot session so gateway restarts do not overwrite the agent's main session mapping. (#85479)
-- Meeting Notes: include a speaker-labeled transcript section in generated summaries so Discord group voice captures show who said each captured utterance.
-- Discord/voice: recover stale realtime playback state when Discord stream-close/player-idle events do not arrive, and keep generated runtime plugin aliases available after postbuild rewrites.
-- Discord/voice: keep realtime playback running when meeting notes attaches to an existing voice session or a realtime consult starts, and route realtime user transcripts into meeting notes.
-- Config/secrets: preflight active runtime SecretRefs before root and include config writes persist, and roll back unchanged file/env state when post-write refresh fails. Fixes #46531. (#84454) Thanks @samzong.
-- CLI/models: preserve SecretRef-backed custom provider `apiKey` markers when `models status` regenerates `models.json`, avoiding resolved plaintext secrets on disk. Fixes #84632. (#84658) Thanks @NianJiuZst.
-- WhatsApp/auto-reply: deliver deferred media replies through the foreground reply fence so overlapping no-reply turns no longer hide already visible responses. (#85517) Thanks @cavit99.
-- Sessions/security: replace agent-to-agent wildcard allowlist regexes with a precompiled linear matcher so cross-agent access checks avoid backtracking-prone patterns. (#85849) Thanks @SebTardif.
-- WebChat: keep the run-complete indicator in progress until deferred history replay renders the assistant reply, so Done no longer appears before response text. (#85374) Thanks @neeravmakwana.
-- Agents/tools: give timed-out or cancelled process trees a bounded SIGTERM cleanup window before SIGKILL while preserving tree-aware cancellation. Fixes #66399. (#85865) Thanks @IWhatsskill.
-- Agents/subagents: treat aborted subagent stop reasons as killed terminal failures so parent sessions get error announcements instead of silent success. Fixes #72293. (#85860) Thanks @IWhatsskill.
-- Agents/providers: clamp proxy-like OpenAI Chat Completions output caps against the final request payload so strict local/API-compatible servers no longer reject prompts that already consume part of the context window. Fixes #83086. (#85889) Thanks @rendrag-git.
-- Agents/compaction: skip agent-harness preflight for provider-owned CLI runtime sessions so over-threshold Claude CLI sessions continue through normal compaction instead of failing on a missing harness. Fixes #84857. (#84878) Thanks @zhangguiping-xydt.
-- Codex/app-server: keep successful native hook relays available through a short post-turn grace window so late Codex hook subprocesses can finish policy enforcement without clearing a replacement relay. (#83987) Thanks @Kaspre.
-- Control UI/config: save form-mode edits from the source config snapshot so runtime-only provider defaults like empty `models.providers.<id>.baseUrl` are not written back and rejected. Fixes #85831. Thanks @garyd9.
-- Browser/existing-session: launch Chrome DevTools MCP with usage statistics disabled by default so its telemetry watchdog stays off unless an operator explicitly opts in. (#85886) Thanks @rohitjavvadi.
-- Telegram: normalize legacy durable group retry targets before retry sends, polls, and pins so group retries keep using the real chat id. (#85656) Thanks @luoyanglang.
-- Agents/PDF: route MiniMax PDF fallback policy through plugin metadata so MiniMax uses text extraction instead of VLM image fallback. (#85590, fixes #85575) Thanks @neeravmakwana.
-- CLI/plugins: tighten timeout, numeric option, media payload, permission, profile/TLS, plugin metadata, JSON, and remote URL handling; prevent stuck progress/app-server/IRC/Synology/Twitch waits; and keep imported chat history ordering stable.
-- Telegram/config: suppress the missing `accounts.default` warning when `channels.telegram.defaultAccount` names a configured account that also sorts first. Fixes #83948. Thanks @crypto86m.
-- Telegram: serialize visible topic replies through core reply-lane admission so heartbeat and queued follow-up turns cannot continue ownerless or misroute responses. (#85709) Thanks @jalehman.
-- CLI/node: print node status recovery hints on stdout consistently while keeping status errors on stderr. Fixes #83925. Thanks @davinci282828.
 - WebChat: summarize internal message-tool source replies so tool cards no longer duplicate the visible reply body. (#84773) Thanks @jason-allen-oneal.
-- Gateway/WebChat: hide duplicate `gateway-injected` assistant rows when Cursor ACP already persisted the same `acp-runtime` reply. Fixes #85741. Thanks @lxf-lxf.
-- WebChat: scope the visible attachment button to its own composer file input so clicking Upload reliably opens the file picker. (#83952, fixes #47983) Thanks @jason-allen-oneal.
 - Gateway: preserve deferred lifecycle-error cleanup across later non-terminal events so provider timeouts can persist failed session state instead of leaving sessions stuck running. (#85256, fixes #63819) Thanks @samzong.
-- Gateway/update: stop treating inherited macOS `XPC_SERVICE_NAME` values as launchd supervision during update respawn, so GUI-spawned gateways use detached respawn instead of exiting for a missing LaunchAgent. Fixes #85224. Thanks @richardmqq.
-- Gateway: stop sending duplicate message-phase `sessions.changed` websocket events after displayable `session.message` transcript updates. (#84834)
 - Agents/subagents: report tool-only child progress during timeout summaries instead of showing no visible output.
 - Telegram/ACP: preserve explicit `:topic:` conversation suffixes when inbound ACP targets do not carry a separate thread id.
 - Browser/proxy: bypass the managed proxy for the exact local managed Chrome CDP readiness and DevTools WebSocket endpoints, so `openclaw browser start` works when the operator proxy blocks loopback egress. (#83255) Thanks @lightcap.
 - Ollama: bypass the managed proxy for configured local embedding origins while keeping SSRF guardrails on unconfigured targets. Thanks @Kaspre.
 - OpenAI/images: route Codex API-key image generation through the native OpenAI Images API instead of the Codex OAuth streaming backend, avoiding 401s from valid API keys.
 - Agents/OpenAI completions: omit empty tool payload fields for proxy-like OpenAI-compatible endpoints so strict vLLM-style servers accept tool-free turns. (#85835) Thanks @rendrag-git.
-- Sandbox: keep workspace skill mounts read-only for remote container-cwd file operations and reject symlinked skill roots before creating protected overlays. (#85591) Thanks @jason-allen-oneal.
-- Scripts/Windows: route remaining QA, release, profile, and live-media `pnpm` launches through the managed runner so native Windows avoids brittle `.cmd` execution and shell-argv warnings.
-- Release: align generated config/API baselines and the meeting-notes plugin version so release preflight stays green on native Windows.
-- Install/Windows: run Git hook setup through a Node prepare helper so native Windows installs no longer print POSIX shell errors.
-- Checks/Windows: chunk and serialize extension oxlint shards on native Windows so changed gates avoid Go-backed linter memory spikes.
-- Release/Windows: run installed `openclaw.cmd` verification through explicit `cmd.exe` wrapping so npm prepublish/postpublish checks avoid Node shell-argv warnings.
-- Release/Windows: run release-check npm pack/install/root probes through the shared npm runner so native Windows avoids bare `npm` lookup and `.cmd` shell-argv handling.
-- Release/Windows: run cross-OS release check `.cmd` shims through explicit `cmd.exe` wrapping so native Windows install and gateway probes avoid Node shell-argv handling.
-- Control UI/Windows: run i18n Pi, npm, and pnpm helper commands through explicit Windows runners so native Windows translation sync avoids brittle `.cmd` launches.
-- Scripts/Windows: run the Z.AI fallback repro through the shared pnpm runner so native Windows avoids raw `.cmd` launches.
-- Codex/Windows: run app-server protocol formatting through the shared pnpm runner so native Windows avoids raw `.cmd` launches.
-- Plugins/Windows: run plugin npm package staging through the shared npm runner so native Windows release checks avoid bare `npm` lookup and `.cmd` shell-argv handling.
 - Checks/Windows: route full `pnpm check` stage commands through the managed child runner so Windows avoids Node shell-argv deprecation warnings there too.
-- Agents/fs: allow workspace-only host write/edit tools to write through in-workspace symlink directory parents while preserving outside-workspace symlink rejection. Fixes #84696. Thanks @garbagenetwork.
 - Checks/Windows: run managed child commands through explicit `cmd.exe` wrapping instead of Node shell mode with argv, avoiding Node 24 subprocess deprecation warnings during changed checks.
 - Gateway: omit internal stream-error placeholder entries from agent prompt history so failed assistant turns are not replayed as model-authored text. (#85652) Thanks @anyech.
 - Sessions: enforce the session write-lock max-hold policy during lock acquisition so long-held locks can be reclaimed before the stale-lock window. (#85764) Thanks @njuboy11.
-- Sessions/status: preserve user-facing model, fallback, usage, and cost attribution when internal subagent handoff runs use fallback models. (#85726, fixes #85082) Thanks @brokemac79.
-- Install/update: honor `OPENCLAW_HOME` when deriving default dev checkout and installer onboarding paths, while keeping explicit `OPENCLAW_GIT_DIR` and `OPENCLAW_CONFIG_PATH` overrides authoritative. Fixes #54014. Thanks @robertPiro.
 - Models: prune retired Groq, GitHub Copilot, OpenAI, xAI, and old Claude catalog entries, with doctor migration to upgrade existing configs to current provider refs.
-- Plugins/Gateway: treat non-empty return values from plugin gateway method handlers as successful responses so `openclaw gateway call` no longer times out after completed plugin work. Fixes #59470. Thanks @HTMG23.
 - Doctor/update: recognize junction-backed source checkouts as git installs by comparing canonical paths before showing package-manager update guidance. Fixes #82215. Thanks @igormf.
 - Channels: honor `/verbose on` for tool/progress summaries across direct chats, groups, channels, and forum topics while preserving quiet default behavior. (#85488) Thanks @kurplunkin.
-- Update: keep the detached gateway restart handoff best-effort when the restart script process cannot be spawned. (#83892) Thanks @davinci282828.
-- Windows/config: skip POSIX login-shell env fallback on native Windows so startup no longer warns about missing `/bin/sh`. Fixes #84795. Thanks @JIRBOY.
-- Telegram: persist the prompt-context message cache through plugin state and record bot-authored replies after sends and draft streaming so later turns can include prior assistant replies without relying on the JSON sidecar. (#85231) Thanks @keshavbotagent.
-- Agents/subagents: keep Codex persona and user workspace files turn-scoped so native Codex subagents inherit only shared tool guidance by default. (#85811) Thanks @lastguru-net.
 - CLI/skills: show an all-ready note with next-step commands when skill setup has no missing dependencies to install. (#85032) Thanks @aniruddhaadak80.
 - Microsoft Foundry: route DeepSeek V4 Pro and Flash models through the Foundry Responses API while keeping older DeepSeek models on their existing path. (#85549) Thanks @roslinmahmud.
 - Status/usage: show configured cost estimates for AWS SDK models in full usage output while keeping token-only usage replies cost-free. (#85619) Thanks @ItsOtherMauridian.
@@ -207,7 +343,6 @@ Docs: https://docs.openclaw.ai
 - Telegram: send local `path`/`filePath` and structured attachment media from `sendMessage` actions instead of dropping them or sending text-only messages. (#85219) Thanks @keshavbotagent.
 - Sessions/status: show the estimated context budget when fresh provider usage is unavailable and clear stale estimates across session resets and compaction boundaries. (#84830) Thanks @giodl73-repo.
 - Gateway/config: pin relative `OPENCLAW_STATE_DIR` overrides to an absolute path at startup so later working-directory changes cannot retarget gateway state. (#52264) Thanks @PerfectPan.
-- Checks/Parallels: make changed-lane scripts, shrinkwrap generation, and Parallels package smoke host commands run through native Windows-safe paths and `npm`/`pnpm` shims.
 - Release/package: run npm release, prepublish, and postpublish verification through Windows-safe npm command shims so native Windows checks can execute `npm.cmd` instead of treating it as a binary.
 - Agents/harness: pass CLI runtime aliases through harness selection so provider-owned CLI aliases no longer get rejected before reaching the right runtime. (#85631) Thanks @potterdigital.
 - Secrets: show the irreversible apply warning after interactive `secrets configure` confirmation so confirmed migrations still get the final safety prompt. (#85638) Thanks @alkor2000.
@@ -219,13 +354,10 @@ Docs: https://docs.openclaw.ai
 - Providers/Anthropic: migrate 1M context handling to GA-capable Claude 4.x models by sizing eligible models at 1M without the retired `context-1m-2025-08-07` beta, ignoring that retired beta in older configs, and preserving OAuth-required Anthropic beta headers. (#45613) Thanks @haoyu-haoyu.
 - Cron/Telegram: parse forum-topic delivery targets through the Telegram plugin instead of cron core, including `:topic:` and `:topicId` forms for announce delivery. Thanks @etticat.
 - Twitch: keep stale message-handler cleanup callbacks from removing newer handler registrations for the same account, preserving inbound message delivery after reconnects. Fixes #83888. (#85425) Thanks @alkor2000.
-- Control UI/chat: keep light-mode model, thinking, config, and agents select arrows visible without tiling background icons. Fixes #85713. Thanks @Linux2010.
 - Memory/LanceDB: expose public memory artifacts through the active memory provider bridge so memory-wiki imports durable memory files, daily notes, dream reports, and event logs without depending on memory-core internals. Fixes #83604. (#85060) Thanks @brokemac79.
 - Crabbox: keep AWS hydration compatible with local Actions replay by inlining the hydrate workflow's Node/pnpm setup instead of invoking repo-local composite actions.
 - Agents/subagents: simplify native sub-agent completion handoff so children report their latest visible assistant result to the requester without using `message`, while keeping parent-owned message-tool delivery policy intact. Fixes #85070. (#85089) Thanks @brokemac79.
 - Docker setup: stop printing the Gateway bearer token in setup logs and printed follow-up commands.
-- Gateway: defer channel account startup work until HTTP readiness and remove startup model prewarm, avoiding startup event-loop stalls and timer-delay warnings.
-- Models/perf: reuse plugin metadata during models.json planning, keep bundled catalog augmentation manifest/static, and use static provider catalogs for metadata-only startup discovery so provider model normalization, auth discovery, and Gateway startup metadata do not reload broad plugin runtimes.
 - Agents: let embedded compaction fallback retries proceed when PI-compatible candidates do not need agent harness plugin preparation.
 - Agents/tools: honor configured custom provider API keys when deciding whether media, image-generation, video-generation, music-generation, and PDF tools are available. (#85570)
 - StepFun: stop advertising stale generic API key auth choices so onboarding only offers runtime-backed Standard and Step Plan choices.
@@ -233,18 +365,12 @@ Docs: https://docs.openclaw.ai
 - Windows installer: fail Git checkout installs when `pnpm install` or `pnpm build` fails instead of writing a wrapper to a missing CLI build.
 - Sessions: surface previous-transcript archive failures during `/new` rotation so disk rename errors are logged instead of silently hiding stranded transcript files. Fixes #81984. (#85586, from #82081) Thanks @0xghost42.
 - TUI/agents: mirror internal-ui message-tool replies into final chat output so message-tool-only agents remain visible in `openclaw tui`. Fixes #85538. Thanks @danpolasek.
-- Gateway/TUI: preserve source-reply metadata through reply normalization and emit message-tool-only agent replies over the live chat stream so `openclaw tui` renders Codex replies without waiting for a history refresh. Thanks @shakkernerd.
-- Codex/TUI: keep long source-reply runs alive after Codex reasoning completes so delayed visible `message` calls can still reach `openclaw tui`. Thanks @shakkernerd.
-- TUI: keep quiet active runs busy after the response watchdog notice instead of reopening the prompt and encouraging duplicate submissions while the backend turn is still running. Thanks @shakkernerd.
-- Agents: preserve the latest assistant thinking blocks while stripping invalid replay signatures from older turns, and retry Anthropic thinking failures without thinking replay. Fixes #85557. Thanks @bryanbaer.
 - Agents: keep parallel OpenAI-compatible tool-call deltas in separate argument buffers so interleaved tool calls no longer corrupt streamed arguments. (#82263) Thanks @luna-system.
-- Telegram: avoid false pairing prompts after transient pairing-store read failures while preserving configured `allowFrom` and per-DM pairing authorization. (#85555)
 - Memory/doctor: report missing or unusable QMD workspace directories as workspace failures instead of generic binary failures. (#63167) Thanks @sercada.
 - Debug proxy: record CONNECT client-socket errors and destroy the paired upstream socket so abrupt client disconnects no longer leak tunnel resources. (#82444) Thanks @SebTardif.
 - Diffs: continue hydrating later diff cards when one card fails so a single broken card no longer blanks the whole diff viewer. (#84775) Thanks @cosmopolitan033.
 - Mac app: use the native settings sidebar window chrome so the sidebar toggle stays on the left and content no longer clips under oversized titlebar padding.
 - QA-Lab/Codex: bundle auth/plugin fixture imports for flow scenarios and let terminal async media tools end Codex app-server turns without timing out. (#80397, refs #80323) Thanks @100yenadmin.
-- WhatsApp: persist inbound message delivery state through plugin state before dispatch and delay read receipts until handler completion, so retryable failures can redeliver without adding a plugin-local disk cache. Thanks @samzong.
 - Gateway/agents: preserve fresh session overrides and metadata when stale cached agent-session entries race with store updates, so subagent model/provider overrides and routing policy survive concurrent writes. (#19328) Thanks @CodeReclaimers.
 - Control UI/chat: keep chat session search inline with the session selector so the header no longer shows a duplicate standalone search row.
 - Control UI/chat: collapse focused-mode header chrome and suppress hidden-header scroll updates so focus mode no longer jumps while scrolling. Thanks @amknight.
@@ -257,11 +383,9 @@ Docs: https://docs.openclaw.ai
 - CLI/agents: default new omitted-account bindings to all accounts when the channel has multiple configured accounts, and clarify account-scope docs. (#49769) Thanks @Gcaufy.
 - Codex app-server: let authorized `/codex` control commands such as `/codex detach` escape plugin-owned conversation bindings while keeping unknown or unauthorized slash text routed to the bound plugin. Fixes #85157. (#85188) Thanks @TurboTheTurtle.
 - Auto-reply/models: keep `/models` browse replies fast by sharing the bounded read-only catalog path with Gateway model listing. (#84735) Thanks @safrano9999.
-- Browser/Doctor: read macOS Chrome app bundle versions from `Info.plist` before spawning Chrome and extend the fallback version probe timeout, avoiding false cold-cache warnings from Gatekeeper latency. Fixes #85418. Thanks @davidcittadini.
 - Codex app-server: disable native Code Mode when the effective exec host is `node` and keep OpenClaw `exec`/`process` available, so `/exec host=node` routes shell commands through the selected node instead of the gateway. Fixes #85012. (#85090) Thanks @sahilsatralkar.
 - Agents: bound embedded auto-compaction session write-lock watchdogs to the compaction timeout instead of the full run timeout, so stuck compaction cannot hold the live session lock for the whole run window. (#84949) Thanks @luoyanglang.
 - Gateway/agents: return phase-aware `agent.wait` timeout attribution and only cool auth profiles on provider-started timeouts. Refs #65504. Thanks @100yenadmin.
-- Gateway/systemd: launch managed update handoff helpers in a transient user scope so systemd-supervised Update Now flows survive the gateway unit restart. Fixes #84068.
 - Gateway: defer provider auth-state prewarm until after startup readiness so early gateway tool/session requests are not blocked by provider auth discovery. (#85272) Thanks @dutifulbob.
 - Gateway/models: coalesce provider auth-state rewarms after auth-profile failures and log event-loop delay for warm/rewarm work, so provider auth bursts no longer stack full auth sweeps behind channel replies.
 - Gateway/models: stop cancelled provider auth-state prewarms from continuing full provider sweeps, so reload and auth-failure bursts no longer keep startup busy.
@@ -276,7 +400,6 @@ Docs: https://docs.openclaw.ai
 - Control UI/logs: strip ANSI escape sequences from displayed Gateway log messages so color codes no longer appear as raw text. Fixes #64399. Thanks @guguangxin-eng.
 - Docker: pre-create the workspace and auth-profile config mount points with `node` ownership so first-run named volumes do not start root-owned. Fixes #85076. Thanks @Noerr.
 - Telegram: pass configured markdown table mode through outbound markdown chunking so chunked sends render tables consistently. Fixes #85085. Thanks @ShuaiHui.
-- Diagnostics/OTel: drop snake_case diagnostic id attributes alongside camelCase ids so exported telemetry cannot leak run, session, message, chat, trace, or tool-call identifiers. (#72645) Thanks @Lion0710.
 - CLI/update: preserve managed Gateway service environment during package cutovers so macOS LaunchAgent repair/restart reads the pre-update service state instead of caller shell state. (#83026)
 - Agents/providers: honor per-model `api` and `baseUrl` overrides in custom provider auth hooks and transport selection. Fixes #80487. (#80488) Thanks @huveewomg.
 - Gateway/restart: eager-load the lifecycle runtime before in-place upgrade signal handling so package replacement does not deadlock restart imports. (#84890) Thanks @myps6415.
@@ -287,11 +410,9 @@ Docs: https://docs.openclaw.ai
 - Gateway chat: broadcast returned agent-run error payloads after an agent starts so ACP/WebChat clients receive terminal idle-timeout errors. Fixes #84945.
 - Gateway chat display: preserve OpenAI-compatible `prompt_tokens`, `completion_tokens`, and `total_tokens` usage fields in sanitized chat history so llama.cpp sessions keep context counts. Fixes #77992. Thanks @MarTT79.
 - Dashboard/CLI: allow macOS browser launching through `open` even when SSH environment variables are present, while preserving Linux SSH no-display protection. Fixes #67088. Thanks @theglove44.
-- Codex app-server: keep native web search observations out of mirrored chat transcripts while preserving available action query metadata in tool progress telemetry. Fixes #85109. Thanks @ugitmebaby.
+- Codex app-server: keep native web search observations out of mirrored chat transcripts while preserving tool progress telemetry. Fixes #85109. Thanks @ugitmebaby.
 - OpenCode Go: strip unsupported Kimi reasoning replay fields before provider requests so repeated `kimi-k2.6` turns do not fail schema validation. Fixes #83812. Thanks @Sleeck.
 - Browser/CDP: add a WSL2 portproxy self-loop hint when Chrome DevTools endpoints accept connections but return an empty HTTP reply. Fixes #59209. Thanks @Owlock.
-- Agents/tools: add bounded tool-policy audit log entries that identify which allow/deny rule removed tools or blocked a sandboxed tool call. Fixes #55801. Thanks @justinjkline.
-- CLI/logs: read implicit local Gateway logs through the passive backend client path so `openclaw logs --follow` does not register as a paired device, and use the active Linux systemd journal instead of stale configured-file fallbacks when live local RPC is unavailable. Fixes #83656 and #66841.
 - Agents/OpenAI: preserve structured provider error code, type, and redacted body metadata on boundary-aware transport failures.
 - Doctor/Codex: point native Codex asset warnings at the canonical `openclaw migrate plan codex` preview command. Fixes #84948. Thanks @markoa.
 - CLI/models: make `capability model auth logout --agent` remove auth profiles from the selected non-default agent store. Fixes #85092. Thanks @islandpreneur007.
@@ -354,7 +475,6 @@ Docs: https://docs.openclaw.ai
 - CLI/update: pre-pack GitHub/git package update targets before the staged npm install, restoring `openclaw update --tag main` for one-off package updates. (#81296) Thanks @fuller-stack-dev.
 - Gateway: mirror successful same-source message-tool sends into session transcripts so delivered replies stay in later history/context. (#84837) Thanks @iFiras-Max1.
 - Media generation: keep image, music, and video completion delivery from duplicating or losing task ownership when generated media finishes through active session replies. (#84006) Thanks @fuller-stack-dev.
-- CLI/doctor: remove stale bundled plugin load paths from old versioned OpenClaw package roots after pnpm/npm upgrades. Fixes #58626. Thanks @solink7.
 - Infra/json: retry transient `File changed during read` races while loading JSON state so config and state reads recover instead of failing the turn. (#84285)
 - Plugins/providers: fail closed for workspace provider plugins during setup-mode discovery unless explicitly trusted, preventing untrusted workspace plugin code from running during provider setup. (#81069) Thanks @mmaps.
 - Providers/Ollama: resolve configured Ollama Cloud `OLLAMA_API_KEY` markers to the real discovery key so cloud provider entries keep authenticated model catalog access. (#85037)
@@ -381,7 +501,6 @@ Docs: https://docs.openclaw.ai
 - Update/doctor: prune stale local bundled plugin install records that point at old compiled bundled output so current bundled plugin schemas win after upgrade. (#84863) Thanks @fuller-stack-dev.
 - Providers/Ollama: preserve native Ollama tool-call IDs across assistant replay so Gemini over Ollama Cloud can keep its hidden function-call thought-signature handle.
 - Discord: keep session recovery and `/stop` abort ownership on the source dispatch lane while bound ACP turns continue routing to their target session, so stalled pre-run work and late replies are cleared instead of leaking after stop. Fixes #84477. (#85100) Thanks @joshavant.
-- Discord/voice-call: keep forced realtime voice consult diagnostics in debug logs instead of agent prompts, so callers do not hear OpenClaw policy text when the provider misses `openclaw_agent_consult`. (#84411) Thanks @fuller-stack-dev.
 - Codex app-server: mark missing turn completion after observed execution as replay-unsafe and release the session so follow-up turns can run. Fixes #84076. (#85107) Thanks @joshavant.
 - Codex app-server: give visible `message` dynamic tool sends a longer timeout budget so slow channel delivery can return its own result or error instead of hitting the 30-second Codex wrapper. (#85216) Thanks @amknight.
 - Codex app-server: add a dedicated post-tool raw assistant completion idle timeout config so trusted heavy turns can wait longer after tool handoff without weakening final assistant release.
@@ -390,7 +509,6 @@ Docs: https://docs.openclaw.ai
 - PDF tool: time out idle remote PDF body reads after 120 seconds so stalled remote documents return an error instead of wedging the session. Fixes #68649. (#84768) Thanks @luoyanglang.
 - Diagnostics/OpenTelemetry plugin: suppress handled OTLP exporter promise rejections so collector shutdowns no longer crash the Gateway. (#81085) Thanks @luoyanglang.
 - Agents/exec: omit raw command text and env values from denied exec failure logs while keeping safe correlation metadata. Fixes #85049. (#85140) Thanks @joshavant.
-- Media-understanding: restore the 4096-token default for image descriptions so reasoning-capable vision models no longer truncate before returning text, while preserving smaller model caps. (#84932) Thanks @scotthuang.
 - Media/audio: skip empty structured sherpa-onnx transcripts instead of treating the raw JSON payload as spoken text. (#84667) Thanks @TurboTheTurtle.
 - Agents/exec: preserve inherited XDG base-directory environment values for subprocesses while still rejecting agent-supplied XDG overrides. Fixes #84854. (#85139) Thanks @joshavant.
 - Node/Linux: keep `OPENCLAW_GATEWAY_TOKEN` out of generated systemd unit files by writing node service token values to a node-specific env file. (#84408)
@@ -433,6 +551,8 @@ Docs: https://docs.openclaw.ai
 
 ### Fixes
 
+- Agents: validate a forced plugin harness against the candidate provider/model before pinning it, so unsupported fallback-chain candidates fail with a clear harness error instead of producing a late `Model provider X not found` from the underlying harness. Codex harness `supports()` now also accepts the canonical `openai` and `openai-codex` routing ids so documented Codex configs keep working. Thanks @cathrynlavery.
+- Control UI/WebChat: keep selected external-channel sessions live by mirroring Codex prompts at turn start, streaming hidden runs only to exact selected-session subscribers, and deduplicating accumulated stream snapshots around tool cards. Fixes #83528, #82611, refs #83949. Thanks @BunsDev.
 - CLI/tasks: include stale-running task maintenance decisions in `openclaw tasks maintenance --json` so retained and reconcile candidates explain backing-session, cron, CLI, and wedged-subagent state. (#84691) Thanks @efpiva.
 - Codex app-server: keep system-prompt reports working when bootstrap hooks provide workspace files with only a path and content, so hook-supplied SOUL/IDENTITY/TOOLS/USER context still reports injected characters correctly. (#84736) Thanks @JARVIS-Glasses.
 - Providers/MiniMax music: stop advertising `durationSeconds` control and remove prompt-injected duration hints, so `music_generate` reports MiniMax duration as an unsupported override instead of suggesting MiniMax can enforce track length. Fixes #84508. Thanks @neeravmakwana.
@@ -569,6 +689,7 @@ Docs: https://docs.openclaw.ai
 - CLI: reject explicit port numbers above 65535 before they reach Gateway or Node bind paths. Fixes #83900. (#84008) Thanks @hclsys.
 - Codex app-server: preserve plugin tool auth profiles when Codex owns model transport so OpenClaw dynamic tools can resolve their provider credentials. (#83603) Thanks @rubencu.
 - Memory/search: scan the JS-side fallback vector path (used when the sqlite-vec index is unavailable or has a mismatched dimension) in bounded rowid batches and yield to the event loop between batches so large chunk tables can no longer pin the Node.js main thread for multi-second windows. Also keeps the SQL prepared statement rooted in a local so node:sqlite cannot finalize it mid-scan under heap pressure. Fixes #81172. Thanks @dev23xyz-oss.
+- Telegram: preserve inbound bold, italic, code, preformatted, strikethrough, underline, spoiler, and text-link entities as markdown in the agent-facing prompt body. Fixes #52859.
 - Backup: dereference hardlinks during archive creation and reject unsafe hardlink targets during verification so archives that pass `backup verify` do not fail broad extraction on macOS tar. Fixes #54242. Thanks @jason-allen-oneal.
 - Memory Wiki: preserve fs-safe diagnostics when bridge source page writes fail for non-symlink filesystem safety reasons, so directory collisions are reported with the underlying error code. (#83776) Thanks @TurboTheTurtle.
 - Telegram: keep forum topics from blocking sibling topic traffic by routing inbound serialization, media/text buffers, and account API queues on topic-aware lanes. (#83829)
@@ -1796,6 +1917,7 @@ Docs: https://docs.openclaw.ai
 - Agents/read tool: treat positive offsets beyond EOF as empty ranges instead of surfacing the upstream read error, so stale pagination cursors no longer crash tool calls while unrelated read failures still fail loud. Fixes #62466. (#75536) Thanks @vyctorbrzezowski.
 - Google/Gemini: normalize retired Gemini 3 Pro Preview refs left in Google API-key onboarding model allowlists and fallbacks, so setup-emitted config keeps testing `google/gemini-3.1-pro-preview` instead of `google/gemini-3-pro-preview`.
 - Telegram/context: bound selected topic context to the active session so messages from before `/new` or `/reset` are not replayed into later turns. (#80848) Thanks @VACInc.
+- Docs/providers/openai: clarify that OpenAI Realtime voice goes through the OpenAI Platform Realtime API and requires Platform credits — Codex/ChatGPT subscription quota does not cover this route. Fixes #76498. Thanks @lonexreb.
 - Google/Gemini: normalize retired nested Gemini 3 Pro Preview ids when resolving exact configured proxy-provider refs, so `kilocode/google/gemini-3-pro-preview` resolves to `kilocode/google/gemini-3.1-pro-preview` for Gemini 3.1 testing.
 - CLI: strip generic OSC terminal escape payloads from sanitized output fields, preventing clipboard/title escape bodies from leaking into commitment tables and other terminal-safe text. Thanks @shakkernerd.
 - Codex app-server: match connector-backed plugin approval elicitations by stable connector id so enabled destructive actions no longer fall through to display-name-only rejection.
@@ -2040,6 +2162,7 @@ Docs: https://docs.openclaw.ai
 - Telegram/groups: include the recent local chat window and nearby reply-target window as generic inbound context so stale reply ancestry does not overshadow the live group conversation.
 - Plugins/Nix: allow externally configured plugin roots under `/nix/store` to load in `OPENCLAW_NIX_MODE=1` while keeping normal external plugin hardlink rejection unchanged. Thanks @joshp123.
 - Nextcloud Talk: include the required bot `response` feature in setup, explain missing `--feature response` on rejected sends, and surface missing response capability in doctor/status checks. Fixes #78935. (#79657) Thanks @joshavant.
+- Cron/diagnostics: emit the existing `message.queued`, `session.state` (processing/idle), and `message.processed` lifecycle events for isolated-cron agent turns in `runCronIsolatedAgentTurn`, matching the dispatch and embedded-runner paths so subscribers (diagnostics OTLP, OTel exporters, custom observability plugins) get per-run session attribution instead of bucketing isolated cron LLM calls under static fallback ids. Events are gated on `isDiagnosticsEnabled(cfg)` so the documented `diagnostics.enabled: false` master toggle continues to silence the recorder. (#79214) Thanks @arniesaha.
 - fix(discord): gate user allowlist name resolution [AI]. (#79002) Thanks @pgondhi987.
 - fix(msteams): gate startup user allowlist resolution [AI]. (#79003) Thanks @pgondhi987.
 - Infra/fetch-timeout: pass `operation` and `url` context to `buildTimeoutAbortSignal` from the music-generate reference fetch and the Matrix guarded redirect transport, so the `fetch timeout reached; aborting operation` warning carries actionable structured fields instead of a bare line. Fixes #79195. Thanks @pandadev66.

CONTRIBUTING.md

@@ -107,6 +107,7 @@ For coordinated change sets that genuinely need more than 20 PRs, join the **#cl
 
 - Test locally with your OpenClaw instance
 - External PRs must include a filled **Real behavior proof** section in the PR body. Show the real setup you tested, the exact command or steps you ran after the patch, after-fix evidence, the observed result, and anything you did not test. Screenshots, recordings, terminal screenshots, console output, copied live output, linked artifacts, and redacted runtime logs all count. Unit tests, mocks, snapshots, lint, typechecks, and CI are useful but do not satisfy this requirement by themselves. Maintainers may apply `proof: override` only when the proof gate should not apply.
+- Keep PRs takeover-ready: open them from a branch maintainers can push to. For fork PRs, leave GitHub's **Allow edits by maintainers** option enabled so maintainers can finish urgent fixes, changelog entries, or merge prep when needed. If GitHub shows **Allow edits and access to secrets by maintainers**, enable it only when that workflow/secrets access is acceptable and say so in the PR.
 - Do not edit `CHANGELOG.md` in contributor PRs. Maintainers or ClawSweeper add the changelog entry when landing user-facing changes.
 - Run tests: `pnpm build && pnpm check && pnpm test`
 - For iterative local commits, `scripts/committer --fast "message" <files...>` passes `FAST_COMMIT=1` through to the pre-commit hook so it skips the repo-wide `pnpm check`. Only use it when you've already run equivalent targeted validation for the touched surface.

Dockerfile

@@ -178,6 +178,7 @@ COPY --from=runtime-assets --chown=node:node /app/package.json .
 COPY --from=runtime-assets --chown=node:node /app/pnpm-workspace.yaml .
 COPY --from=runtime-assets --chown=node:node /app/patches ./patches
 COPY --from=runtime-assets --chown=node:node /app/openclaw.mjs .
+COPY --from=runtime-assets --chown=node:node /app/src/agents/templates ./src/agents/templates
 COPY --from=runtime-assets --chown=node:node /app/${OPENCLAW_BUNDLED_PLUGIN_DIR} ./${OPENCLAW_BUNDLED_PLUGIN_DIR}
 COPY --from=runtime-assets --chown=node:node /app/skills ./skills
 COPY --from=runtime-assets --chown=node:node /app/docs ./docs
@@ -287,12 +288,17 @@ RUN ln -sf /app/openclaw.mjs /usr/local/bin/openclaw \
 
 # Pre-create default named-volume mount points so first-run Docker volumes copy
 # node ownership from the image instead of starting as root-owned directories.
-RUN install -d -m 0700 -o node -g node \
+# NOTE: /home/node/.config must be created with node ownership first so that
+# the leaf /home/node/.config/openclaw inherits the correct parent permissions.
+# Without this, install -d leaves /home/node/.config as root:root (issue #85968).
+RUN install -d -m 0755 -o node -g node /home/node/.config && \
+    install -d -m 0700 -o node -g node \
       /home/node/.openclaw \
       /home/node/.openclaw/workspace \
       /home/node/.config/openclaw && \
     stat -c '%U:%G %a' /home/node/.openclaw | grep -qx 'node:node 700' && \
     stat -c '%U:%G %a' /home/node/.openclaw/workspace | grep -qx 'node:node 700' && \
+    stat -c '%U:%G %a' /home/node/.config | grep -qx 'node:node 755' && \
     stat -c '%U:%G %a' /home/node/.config/openclaw | grep -qx 'node:node 700'
 
 ENV NODE_ENV=production

LICENSE

@@ -19,3 +19,6 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
+
+Third-party notices for incorporated or adapted code are recorded in
+THIRD_PARTY_NOTICES.md.

README.md

@@ -25,7 +25,7 @@ If you want a personal, single-user assistant that feels local, fast, and always
 
 Supported channels include: WhatsApp, Telegram, Slack, Discord, Google Chat, Signal, iMessage, IRC, Microsoft Teams, Matrix, Feishu, LINE, Mattermost, Nextcloud Talk, Nostr, Synology Chat, Tlon, Twitch, Zalo, Zalo Personal, WeChat, QQ, WebChat.
 
-[Website](https://openclaw.ai) · [Docs](https://docs.openclaw.ai) · [Vision](VISION.md) · [DeepWiki](https://deepwiki.com/openclaw/openclaw) · [Getting Started](https://docs.openclaw.ai/start/getting-started) · [Updating](https://docs.openclaw.ai/install/updating) · [Showcase](https://docs.openclaw.ai/start/showcase) · [FAQ](https://docs.openclaw.ai/help/faq) · [Onboarding](https://docs.openclaw.ai/start/wizard) · [Nix](https://github.com/openclaw/nix-openclaw) · [Docker](https://docs.openclaw.ai/install/docker) · [Discord](https://discord.gg/clawd)
+[Website](https://openclaw.ai) · [Docs](https://docs.openclaw.ai) · [Vision](VISION.md) · [Third-party notices](THIRD_PARTY_NOTICES.md) · [DeepWiki](https://deepwiki.com/openclaw/openclaw) · [Getting Started](https://docs.openclaw.ai/start/getting-started) · [Updating](https://docs.openclaw.ai/install/updating) · [Showcase](https://docs.openclaw.ai/start/showcase) · [FAQ](https://docs.openclaw.ai/help/faq) · [Onboarding](https://docs.openclaw.ai/start/wizard) · [Nix](https://github.com/openclaw/nix-openclaw) · [Docker](https://docs.openclaw.ai/install/docker) · [Discord](https://discord.gg/clawd)
 
 New install? Start here: [Getting started](https://docs.openclaw.ai/start/getting-started)
 
@@ -306,7 +306,7 @@ See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines, maintainers, and how to s
 AI/vibe-coded PRs welcome! 🤖
 
 Special thanks to [Mario Zechner](https://mariozechner.at/) for his support and for
-[pi-mono](https://github.com/badlogic/pi-mono).
+[pi-mono](https://github.com/earendil-works/pi-mono).
 Special thanks to Adam Doppelt for the lobster.bot domain.
 
 Thanks to all clawtributors:

SECURITY.md

@@ -98,7 +98,7 @@ These are frequently reported but are typically closed with no code change:
 - Reports that treat `POST /tools/invoke` under shared-secret bearer auth (`gateway.auth.mode="token"` or `"password"`) as a narrower per-request/per-scope authorization surface. That endpoint is designed as the same trusted-operator HTTP boundary: shared-secret bearer auth is full operator access there, narrower `x-openclaw-scopes` values do not reduce that path, and owner-only tool policy follows the shared-secret operator contract.
 - Reports that only show differences in heuristic detection/parity (for example obfuscation-pattern detection on one exec path but not another, such as `node.invoke -> system.run` parity gaps) without demonstrating bypass of auth, approvals, allowlist enforcement, sandboxing, or other documented trust boundaries.
 - Reports that only show an ACP tool can indirectly execute, mutate, orchestrate sessions, or reach another tool/runtime without demonstrating bypass of ACP prompt/approval, allowlist enforcement, sandboxing, or another documented trust boundary. ACP silent approval is intentionally limited to narrow readonly classes; parity-only indirect-command findings are hardening, not vulnerabilities.
-- Reports that only show untrusted media bytes reaching a maintained native decoder dependency (for example Sharp/libvips/libheif) without proving the shipped dependency version is vulnerable and demonstrating crash, memory corruption, data exposure, or a boundary bypass through OpenClaw. JavaScript header sniffing and image dimension fast-paths are preflight/UX checks, not the security boundary for native decoder correctness.
+- Reports that only show untrusted media bytes reaching a maintained native decoder dependency (for example image codec libraries such as libheif) without proving the shipped dependency version is vulnerable and demonstrating crash, memory corruption, data exposure, or a boundary bypass through OpenClaw. JavaScript header sniffing and image dimension fast-paths are preflight/UX checks, not the security boundary for native decoder correctness.
 - Reports whose only impact is transient extra memory, CPU, or allocation work from decoding, base64 expansion, media transcoding, serialization, or other format conversion after the input was already accepted under OpenClaw's configured size/trust limits, including base64 decode-before-size-estimate findings. These are performance issues, not vulnerabilities, unless the report demonstrates unauthenticated amplification, bypass of configured limits, crash/process termination, persistent resource exhaustion, data exposure, or another documented boundary bypass.
 - ReDoS/DoS claims that require trusted operator configuration input (for example catastrophic regex in `sessionFilter` or `logging.redactPatterns`) without a trust-boundary bypass.
 - Archive/install extraction claims that require pre-existing local filesystem priming in trusted state (for example planting symlink/hardlink aliases under destination directories such as skills/tools paths) without showing an untrusted path that can create/control that primitive.

THIRD_PARTY_NOTICES.md

@@ -0,0 +1,37 @@
+# Third-party notices
+
+This file records third-party notices for code or substantial implementation
+portions incorporated into OpenClaw source, beyond normal package-manager
+dependency metadata.
+
+## Pi / pi-mono
+
+Portions of OpenClaw were adapted from Pi / pi-mono, and OpenClaw also depends
+on `@earendil-works/pi-tui` for terminal UI rendering.
+
+- Upstream: https://github.com/earendil-works/pi-mono
+- Package family: `@earendil-works/pi-*`
+- License: MIT
+- Copyright: Copyright (c) 2025 Mario Zechner
+
+MIT License
+
+Copyright (c) 2025 Mario Zechner
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

VISION.md

@@ -38,6 +38,15 @@ Contribution rules:
 - Do not open large batches of tiny PRs at once; each PR has review cost.
 - For very small related fixes, grouping into one focused PR is encouraged.
 
+Configuration compatibility:
+
+OpenClaw runtime code reads the current configuration schema only.
+We do not keep long-lived aliases or compatibility branches that silently accept old, renamed, or malformed config keys.
+
+When a config change makes existing user config invalid, the same change needs a doctor migration.
+`openclaw doctor --fix` should detect the old shape, explain it, back it up when needed, and rewrite it to the canonical format.
+Core-owned config and auth state are repaired in core doctor code; plugin-owned config is repaired by that plugin's doctor contract.
+
 ## Security
 
 Security in OpenClaw is a deliberate tradeoff: strong defaults without killing capability.

appcast.xml

@@ -2,6 +2,262 @@
 <rss xmlns:sparkle="http://www.andymatuschak.org/xml-namespaces/sparkle" version="2.0">
     <channel>
         <title>OpenClaw</title>
+        <item>
+            <title>2026.5.27</title>
+            <pubDate>Thu, 28 May 2026 12:12:19 +0000</pubDate>
+            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
+            <sparkle:version>2026052790</sparkle:version>
+            <sparkle:shortVersionString>2026.5.27</sparkle:shortVersionString>
+            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
+            <description><![CDATA[<h2>OpenClaw 2026.5.27</h2>
+<h3>Highlights</h3>
+<ul>
+<li>Stronger security and content boundaries: group prompt text is kept out of the system prompt, repeated-dot hostnames are normalized, side-effecting command wrappers and unsafe Node runtime env overrides are blocked, no-auth Tailscale exposure is rejected, and node/device-role approvals now require admin authority. (#87144, #87305, #87292, #87308, #87146) Thanks @eleqtrizit and @pgondhi987.</li>
+<li>More reliable Codex app-server runs: Codex runtime models resolve first, workspace memory is routed through tools, shared app-server clients survive startup and spawned-helper failures, native hook relay generations survive restarts and rotate on fresh fallbacks, and false runtime live switches are avoided. (#87383, #87403, #87375, #72574, #87428) Thanks @yetval.</li>
+<li>Faster Gateway and reply paths: session reads, plugin metadata fingerprints, auth env snapshots, auto-enabled plugin config, tool-search catalogs, and stable metadata caches do less hot-path rediscovery while visible replies no longer inherit hidden cleanup timeouts. (#86439, #87044) Thanks @keshavbotagent.</li>
+<li>Better provider and model coverage: OpenAI-compatible embedding providers are core, DeepInfra catalog browsing loads the full credential-aware model set, Pixverse adds video generation and API region selection, VLLM thinking params are wired, Claude CLI OAuth overlays load for PI auth profiles, and bare direct Anthropic model ids work. (#85269, #84549, #87167) Thanks @dutifulbob, @ats3v, and @joshavant.</li>
+<li>Channel delivery is steadier: Telegram <code>sendMessage</code> actions use durable outbound delivery, iMessage suppresses duplicate native exec approval prompts and sends, Slack keeps delivered final replies during late cleanup, Matrix mention previews/finals are stricter, QQBot fallback approval buttons honor slash-command auth, Discord guild requester checks are tighter, recovered Discord tool-warning artifacts stay out of successful replies, and Google Chat stops thread sends in DMs. (#87261, #87154) Thanks @mbelinky and @eleqtrizit.</li>
+<li>Release, package, and CI proof paths are harder to wedge: npm/package inventory honors dist exclusions, shrinkwrap override pins merge correctly, Docker runtime workspace templates are packaged and smoked, release postpublish checks are stricter, beta smoke rejects empty runs, and E2E log/probe waits are bounded.</li>
+</ul>
+<h3>Changes</h3>
+<ul>
+<li>Memory: add a core OpenAI-compatible embedding provider for local and hosted OpenAI-style endpoints, with config, doctor, and docs support. (#85269) Thanks @dutifulbob.</li>
+<li>Plugin SDK: mark memory-specific embedding provider registration as deprecated compatibility and surface non-bundled usage in plugin compatibility diagnostics. (#85072) Thanks @mbelinky.</li>
+<li>Providers: add the Pixverse video generation provider, API region selection, docs, and external plugin packaging support.</li>
+<li>DeepInfra: load the full model catalog when users browse models during onboarding, preserve configured API-key catalogs, refresh media/video defaults, and keep pricing/default model metadata aligned. (#84549) Thanks @ats3v.</li>
+<li>Plugin SDK: expose plugin approval action metadata and stop exporting Vitest test helpers from the public SDK surface. (#87120) Thanks @RomneyDa.</li>
+<li>Channel SDK: move channel message compatibility into core, remove old channel turn runtime aliases, and preserve runtime catalog markdown metadata for plugins.</li>
+<li>ClawHub: add plugin display metadata so catalog/package listings use cleaner names. (#87354) Thanks @thewilloftheshadow.</li>
+<li>Agents: split the heartbeat runtime template out of docs assets and add compatibility repair for legacy heartbeat template content. (#85416) Thanks @hxy91819.</li>
+</ul>
+<h3>Fixes</h3>
+<ul>
+<li>Security/content boundaries: route untrusted group prompt metadata outside system prompts, normalize repeated trailing hostname dots, block side-effecting command wrappers, reject unsafe Node runtime env overrides, reject no-auth Tailscale exposure, block untrusted Microsoft Teams service URLs, enforce <code>/allowlist configWrites</code> origin policy, gate QQBot fallback approval buttons, and require admin for node/device-role approvals. (#87144, #87305, #87292, #87308, #87146, #87154, #87334) Thanks @eleqtrizit and @pgondhi987.</li>
+<li>Codex: resolve Codex runtime models before generic routing, route workspace memory through tools, preserve shared app-server clients after startup and spawned-helper failures, preserve native hook relay generations across restarts and fresh fallbacks, keep raw reasoning/source-reply guards intact, report quarantined dynamic tools, keep the attempt watchdog armed for queued terminal turns, and route Codex OAuth compaction through OpenAI-Codex. (#87383, #87403, #87375, #72574, #87428) Thanks @yetval.</li>
+<li>Agents/runtime: avoid session event queue self-waits, bound compaction wake and steering retries, preserve grace for pending error diagnostics, avoid false Codex runtime live switches, avoid stale restart continuation reuse, preserve session fallback errors, suppress duplicate Claude CLI skill prompts, keep runtime context before active user turns, strip stale Anthropic thinking, quarantine unsupported tool schemas, recover completed write timeouts safely, release retained session write locks on timeout abort, and validate forced plugin harness support before pinning. (#86123, #55424, #86855, #74341, #87278) Thanks @luoyanglang, @cathrynlavery, and @openperf.</li>
+<li>Reply/session delivery: keep visible turn admission unbounded, keep visible fallback delivery on latest targets, preserve bridge hook context, classify direct fallback targets by channel grammar, report approval resolutions in bridge mode, and avoid stale source-reply artifacts. (#87044) Thanks @keshavbotagent.</li>
+<li>Channels: make Telegram <code>sendMessage</code> action replies durable and preserve SecretRef prompt config, suppress duplicate iMessage native exec approval prompts and sends, keep iMessage approval polling alive after denied reactions, keep Slack delivered final replies during late cleanup, keep Matrix mention previews/finals mention-inert and normally delivered, ignore filename-embedded Matrix IDs, suppress recovered Discord tool-warning artifacts from successful replies, suppress Google Chat thread sends in DMs, and harden Discord guild requester checks. (#87261, #87452) Thanks @mbelinky.</li>
+<li>Memory: salvage QMD search JSON after nonzero exits and keep workspace memory routing through the Codex tool path where possible. (#87225, #87383, #87403) Thanks @osolmaz.</li>
+<li>Providers/models: forward cached token usage in OpenAI-compatible chat completions, load Claude CLI OAuth overlays for PI auth profiles, send bare direct Anthropic model ids, wire configured VLLM thinking params, honor OpenAI-compatible cache retention, normalize OpenAI Responses replay tool ids, resolve OpenAI <code>gpt-5.5</code> without a cached catalog, preserve <code>retry-after</code> fallback handling, bound GitHub Copilot auth requests, and load DeepInfra custom/live catalogs consistently. (#82062, #87167, #84549) Thanks @caz0075, @joshavant, and @ats3v.</li>
+<li>Gateway/performance: borrow read-only session metadata and active session working stores, cache current/stable plugin metadata fingerprints, cache auto-enabled plugin config, slim metadata identity caches, trust current metadata lifecycle caches, stabilize isolated cron prompt-cache affinity, persist model auth profile suffixes, drain probe client closes, expire browser tokens after auth rotation, and keep default status fast paths bounded. Thanks @ferminquant.</li>
+<li>CLI/help/config: reject loose or malformed numeric options for gateway timeouts, model limits, directory limits, message options, webhooks, and partial values; respect subcommand version options; route generated/root/plugin help targets correctly; keep skills JSON output flushing naturally; and keep plugin descriptor loading quiet in root help. (#87398) Thanks @Patrick-Erichsen.</li>
+<li>Plugin state/tool search: evict the current namespace when plugin rows hit caps, reuse unchanged tool-search catalogs, align the release catalog reuse wrapper, and keep fallback tool warnings mention-inert.</li>
+<li>Install/package/release: match npm globstar exclusions, honor dist package exclusions in inventory, omit unpacked test helpers, skip Homebrew until macOS packages need it, package Docker runtime workspace templates, smoke Docker runtime templates during full validation, merge nested shrinkwrap override pins, preserve forked shrinkwrap pins, pin aged <code>lru-cache</code>, harden postpublish verification, accept main full-validation proof, and reject empty beta smoke runs.</li>
+<li>E2E/QA/Crabbox: bound Telegram, Open WebUI, ClawHub, Matrix, Tool Search, MCP, gateway network, bundled runtime, kitchen-sink, codex media, config reload, and agent-turn assertion waits; prefer Azure for Windows targets; reinitialize invalid changed-gate git dirs; full-sync sparse container runs; and fail empty explicit test requests. (#87186)</li>
+</ul>
+<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
+]]></description>
+            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.5.27/OpenClaw-2026.5.27.zip" length="54488811" type="application/octet-stream" sparkle:edSignature="c5w2T1UO6vpPs70hyYH93cIyWEOd5sl5z2NkhU53E+XQBSd+jAr+xd0qf3KzWbeX2mfXYMQmnx+VMls3L22EDg=="/>
+        </item>
+        <item>
+            <title>2026.5.26</title>
+            <pubDate>Wed, 27 May 2026 12:24:26 +0000</pubDate>
+            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
+            <sparkle:version>2026052690</sparkle:version>
+            <sparkle:shortVersionString>2026.5.26</sparkle:shortVersionString>
+            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
+            <description><![CDATA[<h2>OpenClaw 2026.5.26</h2>
+<h3>Highlights</h3>
+<ul>
+<li>Faster Gateway and replies: startup avoids repeated plugin, channel, session, usage-cost, warning, scheduled-service, and filesystem scans; visible replies separate user-facing sends from slower follow-up work; Gateway runtime/session caches churn less under load.</li>
+<li>Transcripts are core: transcript-backed meeting summaries, source-provider chunks, cleaned user turns, media provenance, Codex mirrors, WebChat replies, and CLI/TUI replay now use one more reliable transcript path.</li>
+<li>More channels are production-ready: Telegram keeps typing/progress context and forum topics, iMessage handles attachment roots, remote media staging, and duplicate local Messages sources, WhatsApp restores group/media behavior, Discord improves voice playback and model picking, and Signal/iMessage/WhatsApp get reaction approvals.</li>
+<li>Better voice and Talk: realtime Talk runs can be inspected, steered, cancelled, or followed up from Web UI and Discord voice; wake-name handling is more tolerant without letting ambient speech trigger agents.</li>
+<li>Safer content boundaries: Browser snapshot reads honor SSRF policy, system-event text cannot spoof nested prompt markers, fetched file text is wrapped as external content, ClickClack inbound sender allowlists run before agent dispatch, stale device tokens are rejected, and serialized tool-call text is scrubbed from replies.</li>
+<li>Providers, Codex, and local models are steadier: named auth profiles, OpenAI sampling params, Codex app-server resume/timeout/usage-limit recovery, dynamic tool-schema guards, xAI usage-limit surfacing, Ollama top-p normalization, and local approval resolution reduce provider-specific dead ends.</li>
+<li>More reliable install/update/release paths: Alpine installs, trusted runtime fallback roots, stable update channels, Docker/package timeouts, Windows Scheduled Tasks, Windows/macOS proof lanes, Testbox/Crabbox delegation, plugin publish checks, and macOS runner bootstraps all got hardened.</li>
+<li>Better observability: Activity tab, gateway secret-prep traces, tool/model stream progress, explicit fast-mode status, systemd Gateway hygiene, OpenTelemetry LLM spans, release performance evidence, and richer telemetry signals make failures easier to inspect.</li>
+</ul>
+<h3>Changes</h3>
+<ul>
+<li>Transcripts: add core transcript capture and source-provider support for transcript-backed meeting summaries, including the renamed Transcripts docs, CLI surface, source-provider chunks, and cleaned user-turn persistence.</li>
+<li>Auth: add named model login profiles and supported credential migration for Hermes, OpenCode, and Codex auth profiles, with explicit opt-out and non-interactive controls. (#85667) Thanks @fuller-stack-dev.</li>
+<li>Diagnostics: trace gateway secret preparation, classify skill/tool usage, surface model stream progress, add OpenTelemetry LLM content spans, and expose alertable telemetry for blocked tools, failover, stale sessions, liveness, oversized payloads, and webhook ingress. (#83019, #80370, #86191)</li>
+<li>Channels: add Signal reaction approvals, iMessage thumb approval reactions, and WhatsApp thumb approval reaction support so mobile approval flows work without textual <code>/approve</code> commands. (#85894, #85952, #85477)</li>
+<li>Agents/API: forward OpenAI sampling params through the Gateway and expose estimated context-budget status for active agent runs. (#84094)</li>
+<li>TUI/status: queue prompts submitted while an agent is busy and show explicit fast-mode state plus richer systemd Gateway hygiene in status output. (#86722, #87115, #86976)</li>
+<li>Exec approvals: hide durable approval actions that are unavailable for the current prompt and keep approval runtime tokens local-only so stale prompts cannot offer misleading controls. (#86270, #86359)</li>
+<li>Plugin SDK: add reaction approval helpers and keep diagnostic event root exports discoverable across function-name and alias-bound module graphs. (#86735, #87084)</li>
+<li>Android/iOS: add the Android pair-new-gateway action and improve mobile Talk mode surfaces, including iOS realtime Talk mode and Android offline voice/gateway recovery. (#86798, #86355) Thanks @ngutman.</li>
+<li>Performance: cache plugin metadata snapshots, package realpaths, stable gateway metadata, model cost indexes, channel resolution, usage-cost indexes, and session/auth hot-path facts so common Gateway and reply paths do less rediscovery. (#84649, #85843, #86517, #86678)</li>
+<li>Voice: expose shared realtime turn-context tracking through the realtime voice SDK and reuse it for Discord speaker attribution and wake-name context recovery.</li>
+<li>Voice: reuse shared realtime output activity tracking in Google Meet command and node audio bridges, including recent-output checks for local barge-in detection.</li>
+<li>Voice: expose shared realtime output activity tracking through the realtime voice SDK and reuse it for Discord playback activity and barge-in decisions.</li>
+<li>Voice: expose shared realtime consult question matching, speakable-result extraction, and alias-aware forced-consult coordination through the realtime voice SDK, then reuse it in Gateway Talk, Voice Call, and Discord voice paths.</li>
+<li>Voice: share activation-name matching and consult-transcript screening through the realtime voice SDK so Discord, browser voice, and meeting surfaces can reuse one implementation.</li>
+<li>Cron: default <code>cron.maxConcurrentRuns</code> to 8 so scheduled automations and their isolated agent turns can make progress in parallel without explicit configuration.</li>
+<li>QA-Lab: add <code>qa coverage --match <query></code> so focused proof selection can discover matching scenarios from existing metadata before running live or remote lanes.</li>
+<li>Discord/model picker: surface an alpha-bucket select (e.g. <code>A–G (12) · H–N (18) · O–Z (5)</code>) when the provider list or a provider's model list exceeds 25 items, so configs with <code>provider/*</code> wildcards stay one click from the right page instead of paginating through prev/next; falls back to numeric chunks when every item shares the same first letter.</li>
+<li>Control UI: add an ephemeral Activity tab for sanitized live tool activity summaries without persisting raw telemetry. Fixes #12831. Thanks @BunsDev.</li>
+<li>Build: include <code>ui:build</code> in the <code>full</code> and <code>ciArtifacts</code> profiles of <code>scripts/build-all.mjs</code> so <code>pnpm build</code> always rebuilds <code>dist/control-ui</code> after <code>tsdown</code> cleans <code>dist</code>, removing the second-command requirement and the missing-asset failure mode for source/runtime installs and CI artifact uploads. (#85206)</li>
+<li>iOS: improve Talk mode with direct realtime voice sessions, compact toolbar status, and responsive voice waveform feedback. (#86355) Thanks @ngutman.</li>
+<li>Media: replace the Sharp image backend with Rastermill for metadata, resizing, EXIF orientation, and PNG alpha-preserving optimization so OpenClaw no longer installs Sharp or the WhatsApp Jimp fallback for image processing. (#86437)</li>
+<li>Codex: update the bundled Codex CLI to 0.134.0 and keep native compaction disabled for budget-triggered app-server turns so OpenClaw owns the recovery boundary. (#86772)</li>
+</ul>
+<h3>Fixes</h3>
+<ul>
+<li>Memory/security: reject prompt-like text submitted through the explicit <code>memory_store</code> tool before embedding or storage, matching the existing auto-capture prompt-injection filter. (#87142)</li>
+<li>Gateway/security: enable the default auth rate limiter for remote non-browser and HTTP gateway auth failures when <code>gateway.auth.rateLimit</code> is unset, while preserving the loopback exemption. (#87148)</li>
+<li>Security/content boundaries: validate Browser snapshot tab URLs against SSRF policy before ChromeMCP or direct CDP reads, sanitize queued system-event text so untrusted plugin/channel labels cannot spoof nested prompt markers, wrap fetched file text and metadata as external content, apply ClickClack <code>allowFrom</code> sender allowlists before agent dispatch, reject RPCs from invalidated device-token clients during rotation, require staged sandbox media refs, and scrub serialized tool-call text from replies. (#78526, #87094, #87062, #83741, #70707, #86924) Thanks @zsxsoft, @ttzero25, and @mmaps.</li>
+<li>Transcripts/user turns: persist CLI, WebChat, media, follow-up, hook, and Codex-mirror user turns to the admitted session target; keep cleaned transcript text, inline image routing, provenance metadata, replay hooks, and fallback paths idempotent when runtimes fail or restart.</li>
+<li>TUI/status/onboarding/UI: queue busy TUI prompts instead of dropping them, preserve the configured default model during onboarding, show failed tool results as errors, show config-open failures in Control UI, keep status JSON plugin scans healthy, preserve xAI usage-limit errors locally, and expose explicit fast-mode/systemd state. (#86722, #87000, #85786, #87108, #87001, #86614, #87115, #86976)</li>
+<li>Plugin commands/SDK: preserve plugin LLM command auth, bind native plugin command dispatch to the host agent's LLM auth, keep <code>onDiagnosticEvent</code> exports discoverable through <code>Function.name</code>, stabilize diagnostic event root aliases, correlate pathless read diagnostics, suppress transient runner failures in channel command paths, and repair local approval resolution. (#85936, #87084, #86977, #87069, #86771)</li>
+<li>Codex/providers: keep WebChat delivery hints out of user prompts, avoid false queued-terminal idle timeouts, share the native hook relay registry, quarantine unsupported dynamic tool schemas, preserve Claude resumed-session system prompts, normalize greedy Ollama <code>top_p</code>, preserve per-agent thinking defaults for ingress runs, and avoid native compaction takeover on budget-triggered Codex turns. (#87096, #73950, #87049, #86689, #86772)</li>
+<li>Gateway/perf/release: reuse startup-warning metadata and prepared auth stores, avoid cloning live-switch and lifecycle session caches on read paths, defer warning and scheduled-service fallback imports, trim Gateway session/startup/runtime CPU churn, skip duplicate turn session touches, stop chat timeout fallback cascades, drop stale subagent announce history, bound benchmark/watch/kitchen-sink teardown waits, bound macOS/package/onboarding/plugin smoke commands, bound install finalization probes, resolve Parallels npm-update commands from guest <code>PATH</code>, and bootstrap raw AWS macOS Node/pnpm commands through <code>/usr/bin/env</code>. (#86997)</li>
+<li>Reply/perf: reduce visible reply delivery latency by preserving Telegram typing/progress context, lazy-loading slash-command startup metadata, avoiding hot-path model hydration, flag-gating Codex profiler timing, deferring context compaction maintenance, and tracking delivery timing. (#86989, #86990, #86991, #86992, #86993, #86994) Thanks @keshavbotagent.</li>
+<li>Reply/source delivery: keep TUI, Control UI, media, TTS, transcript, and Codex source-reply finals live without duplicate terminal events or stale replay artifacts.</li>
+<li>Agents/replay: repair legacy tool results before replay, preserve <code>sessions_spawn</code> transcript payloads, restore current guard checks, stage sandboxed workspace media, and keep duplicate transcripts tool display metadata from reappearing. (#82203, #86934, #87025) Thanks @martingarramon, @vincentkoc, and @joshavant.</li>
+<li>Agents/sessions: handle active-fallback failures in <code>sessions_send</code> so fallback routing reports the real failure and does not leave callers with an ambiguous dropped send. (#86638)</li>
+<li>Agents/hooks/subagents: enforce default hook agent allowlists, recover failed subagent lifecycle completions, and keep node task lifecycle cleanup from closing the Gateway listener. (#86101)</li>
+<li>Codex: project newer OpenClaw chat history into resumed app-server threads and keep Codex turn timeouts inside the Codex runtime boundary so timeouts do not poison shared app-server clients or fall through to unrelated provider fallback. (#86677, #86476) Thanks @TurboTheTurtle and @pashpashpash.</li>
+<li>Config/doctor/update: narrow profiled tool-section doctor repair, keep runtime-injected legacy web-search provider config out of user-authored config validation, and keep prerelease tags excluded from stable updater resolution. (#87030, #86818, #86559) Thanks @joshavant, @luoyanglang, and @stevenepalmer.</li>
+<li>CLI/Windows: add a Windows-only stack-size respawn for stack-heavy startup paths, default CLI logs to local timestamps, and validate timeout/banner TTY state more strictly. (#87031, #85387) Thanks @giodl73-repo and @vincentkoc.</li>
+<li>Locking/security: require owner identity proof before stale plugin lock removal, memoize session lock owner arguments, and avoid writing default exec approval stores unless policy state actually changed. (#86814, #86964) Thanks @Alix-007 and @vincentkoc.</li>
+<li>Install/release: bound Docker package build, inventory, pack, and tarball preparation with process-group timeouts; pin shrinkwrap patch drift to the pnpm lock; harden macOS restart and dSYM packaging; and run release Docker/live timeout wrappers in the foreground so child processes cannot wedge gates.</li>
+<li>Telegram/network: treat <code>ENETDOWN</code> as a transient pre-connect network failure so Telegram sends, gateway unhandled-rejection handling, and cron network retries follow the same recovery path as sibling network outages. (#86762) Thanks @TurboTheTurtle.</li>
+<li>Telegram: preserve inbound text entities, overlapping DM replies, account topic cache sidecars, outbound reply context, targeted bot-command mentions, durable group retry targets, forum topic names, and native progress callbacks. (#83873, #85361, #85555, #85656, #85709, #86299, #86553) Thanks @SebTardif, @luoyanglang, and @neeravmakwana.</li>
+<li>iMessage: read image attachments from local Messages attachment roots, dedupe duplicate local Messages-source accounts, seed direct DM history, fix image/group media attachment commands, advance catchup cursors after live handling, and keep slash-command acknowledgements in the source conversation. (#82642, #85475, #86569, #86705, #86706, #86770) Thanks @homer-byte, @TurboTheTurtle, @swang430, and @OmarShahine.</li>
+<li>WhatsApp/QQ/Twitch/IRC/Slack: restore WhatsApp ack identity and group-drop warnings, make QQ Bot media respect <code>OPENCLAW_HOME</code>, serialize Twitch auth disconnects, store IRC channel routes canonically, and keep Slack downloaded files out of reply media. (#83833, #85309, #85777, #85794, #85906, #86318, #86697) Thanks @sliverp, @neeravmakwana, and @Kailigithub.</li>
+<li>Discord/voice: improve voice playback and wake replies, bucket large model picker menus, merge media captions into one message, route metadata through configured proxies, restore numeric channel sends, suppress self-reply echoes, and tighten wake matching without breaking fuzzy wake phrases. (#80227, #86238, #86487, #86571, #86595, #86601)</li>
+<li>Codex: preserve native web-search metadata, keep oversized native thread reuse, bridge CLI API-key auth into the app server, preserve sandbox bootstrap path style, recover context-window prompt errors, honor yolo approval policy, disable native thread personality, and route compaction through Codex auth. (#85378, #85542, #85891, #85909, #86408)</li>
+<li>Agents/runtime: enforce session lock max-hold reclaim, release embedded-attempt locks on all exits, treat aborted subagent runs as terminal, avoid runtime model hydration on hot paths, disclose scoped session list counts, derive overflow budgets from provider errors, and keep fallback errors scoped to the active model candidate. (#70473, #85764, #86014, #86134, #86427, #86944) Thanks @openperf, @fuller-stack-dev, @zhangguiping-xydt, and @ferminquant.</li>
+<li>Config/update/doctor: retry config recovery after failed backup restore, skip shell env fallback on Windows, exclude prerelease tags from the stable git channel, support deep config edits, warn instead of aborting on unreadable cron stores, prune stale bundled plugin paths, and avoid duplicate restart prompts when the Gateway is already healthy. (#85739, #85787, #86060, #86260, #86384, #86533) Thanks @liaoyl830.</li>
+<li>Install/release: support Alpine CLI installs and runtime floors, prefer trusted startup argv runtime fallback roots, reject stale CLI node runtimes, avoid npm <code>min-release-age</code> installer failures, bound npm/package/Docker install phases, restore config parent ownership in Docker, seed Docker lockfile package tarballs before prune, make release/plugin prerelease checks fail closed instead of hanging or false-greening, and use host-visible Crabbox local work roots for Docker-backed proof. (#85491)</li>
+<li>Windows daemon: keep Scheduled Task gateway launches running on battery power and avoid workgroup-machine prompts for a domain user during task installation. (#59299)</li>
+<li>Security: avoid printing Gateway tokens in Docker, validate plugin model-pattern regexes safely, escape transcript metadata field names, harden session allowlist glob matching, audit Claude permission overrides under YOLO, and require explicit allow for ACP auto approvals. (#85849, #85934, #86046, #86557)</li>
+<li>Media/images: replace Sharp with Rastermill, keep EXIF normalization best-effort, normalize HEIC/HEIF before image descriptions, route Codex image API keys through OpenAI, preserve image compression metadata, and auto-scale live tool result caps. (#85776, #86037, #86437, #86857, #86923)</li>
+<li>Memory: prevent semantic vector indexes from silently degrading when embeddings are unavailable, stop doctor OOMs on large session stores, preserve sidecar hooks/artifacts, write fallback dream diaries, use CJK-aware dreaming dedupe, and avoid per-file watcher FD fan-out. (#80613, #82928, #85060, #85704, #85967, #86701) Thanks @brokemac79, @openperf, and @yaaboo-gif.</li>
+<li>Agents/sessions: include visibility metadata on restricted <code>sessions_list</code> results so scoped counts are clearly reported without widening access or exposing hidden-session counts. (#86944) Thanks @ferminquant.</li>
+<li>Gateway/DNS: validate wide-area discovery domains before deriving zone paths or writing zone files, so invalid <code>discovery.wideArea.domain</code> and <code>dns setup --domain</code> values fail with a DNS-name diagnostic instead of falling through to unrelated configuration errors. Thanks @mmaps.</li>
+<li>Agents/BTW: route fallback side-question streams through the embedded stream resolver so Anthropic-compatible MiniMax requests use the same capped transport as normal chat. (#86312) Thanks @neeravmakwana.</li>
+<li>Telegram: treat <code>/command@TargetBot</code> bot-command entities as explicit mentions for the addressed bot so <code>requireMention</code> groups no longer drop targeted commands or captions. Fixes #84462. (#86553) Thanks @luoyanglang.</li>
+<li>CI: bound Docker/Bash E2E tarball npm installs with <code>OPENCLAW_E2E_NPM_INSTALL_TIMEOUT</code> so package, onboarding, plugin, and upgrade lanes fail instead of hanging on a stuck npm install.</li>
+<li>CI: fail Parallels npm-update smoke jobs after the guest command timeout and cleanup backstop instead of only logging a timeout line.</li>
+<li>CI: bound kitchen-sink RPC HTTP probes so stalled gateway readiness or response bodies fail and retry instead of wedging the walker.</li>
+<li>CI: keep <code>OPENCLAW_TESTBOX=1 pnpm check:changed</code> delegating to Blacksmith Testbox through Crabbox without forwarding local Testbox or worker env into the remote command.</li>
+<li>CI: send KILL after the TERM grace period for manual checkout fetch timeouts so stuck Testbox and workflow checkout retries cannot hang behind a wedged <code>git fetch</code>.</li>
+<li>CI: send KILL after the TERM grace period for Bun global install smoke command timeouts so trapped <code>openclaw</code> child processes cannot wedge the scheduled install smoke.</li>
+<li>iMessage: thread current channel/account inbound attachment roots into the image tool so iMessage-saved attachments under <code>~/Library/Messages/Attachments</code> (including the wildcard <code>/Users/*/Library/Messages/Attachments</code> root) are read through the existing inbound path policy instead of being rejected as <code>path-not-allowed</code>. Literal <code>localRoots</code> stays workspace-scoped. Fixes #30170. (#86569)</li>
+<li>QQ Bot: respect <code>OPENCLAW_HOME</code> for outbound media path resolution so <code><qqmedia></code> sends no longer silently fail when <code>HOME</code> and <code>OPENCLAW_HOME</code> differ (Docker / multi-user hosts). Persisted QQ Bot data (sessions, known users, refs) stays anchored on the OS home for upgrade compatibility. Fixes #83562. Thanks @sliverp.</li>
+<li>Update: report the primary malformed <code>openclaw.extensions</code> payload error without adding a duplicate missing-main diagnostic. (#86596) Thanks @ferminquant.</li>
+<li>Control UI: keep host-local Markdown file paths inert while preserving app-relative links. (#86620) Thanks @BryanTegomoh.</li>
+<li>Gateway: dampen repeated unauthenticated device-required probes per URL while preserving explicit-auth and paired recovery paths. (#86575) Thanks @ferminquant.</li>
+<li>IRC: store inbound channel routes with the canonical <code>channel:#name</code> target and join transient channel sends before writing. (#85906) Thanks @Kailigithub.</li>
+<li>Usage: surface unknown all-zero model pricing as missing cost entries instead of a confident <code>$0</code> total. (#85882) Thanks @MichaelZelbel.</li>
+<li>Agents/Codex: honor yolo app-server approval policy only for the full <code>never</code> plus <code>danger-full-access</code> case. (#85909) Thanks @earlvanze.</li>
+<li>Gateway/Gmail: clear Gmail watcher renewal intervals on re-entry so hot reloads do not leak lifecycle timers. (#82947) Thanks @SebTardif.</li>
+<li>Logging: exit cleanly on broken stdout/stderr pipes without masking existing failure exit codes. (#80059) Thanks @pavelzak.</li>
+<li>Gateway/security: escape transcript metadata field names while extracting oversized session line prefixes. (#85934) Thanks @SebTardif.</li>
+<li>Plugins/security: validate manifest model pattern regexes with the safe-regex compiler so unsafe patterns are ignored before matching. (#86046) Thanks @SebTardif.</li>
+<li>Discord: route gateway metadata REST lookups through the configured Discord proxy so proxied accounts do not fall back to direct <code>discord.com</code> connections before opening the WebSocket. Fixes #80227. Thanks @Clivilwalker.</li>
+<li>Agents/media: hydrate current-turn image attachments from filename-derived MIME types so active vision can see generated or forwarded images whose source omitted an image content type. (#84812) Thanks @marchpure.</li>
+<li>Agents/fs: point workspace-only scratch-path guidance at in-workspace temp directories while keeping host-root writes rejected by the tool guard. (#86501) Thanks @tianxiaochannel-oss88.</li>
+<li>Agents/media: keep async cron media completions scoped to their run session while preserving direct delivery for stale generated-media success and failure notifications. (#86529) Thanks @ai-hpc.</li>
+<li>Gateway: emit plugin <code>session_end</code>/<code>session_start</code> hooks when <code>agent.send</code> rotates or replaces a session id, keeping hook lifecycle state aligned with <code>sessions.changed</code> notifications. Fixes #83507. (#85875) Thanks @brokemac79.</li>
+<li>OpenShell/SSH: reject malformed generated exec commands before sandbox/session setup so unresolved workflow placeholders fail fast instead of reaching the remote shell. Fixes #72373. Thanks @brokemac79.</li>
+<li>Google: stop normalizing <code>gemini-3.1-flash-lite</code> to the retired preview endpoint and update Flash Lite alias guidance to the GA model id. Fixes #86151. (#86240) Thanks @SebTardif.</li>
+<li>Installer: make Alpine apk installs cover Git, verify the Node runtime floor, try <code>nodejs-current</code>, and report Alpine version guidance when repositories only provide older Node packages.</li>
+<li>Agents/status: prefer the active Claude CLI OAuth auth label over an unused Anthropic env API-key label for equivalent runtime aliases. Fixes #80184. (#86570) Thanks @brokemac79.</li>
+<li>Agents/media: send direct fallback for generated media still missing after an active requester wake fails. (#85489) Thanks @fuller-stack-dev.</li>
+<li>Agents: derive overflow compaction budgets from provider-reported and synthetic over-budget token counts so confirmed context overflows compact before retrying. (#70473) Thanks @fuller-stack-dev.</li>
+<li>Agents/Codex: recover Codex context-window prompt errors through overflow compaction and surface reset guidance when recovery is exhausted. (#85542) Thanks @fuller-stack-dev.</li>
+<li>Agents/Codex: allow Codex app-server runs to bootstrap from <code>CODEX_API_KEY</code> or <code>OPENAI_API_KEY</code> when no Codex auth profile is configured.</li>
+<li>Agents/Codex: keep selected Codex runtime routing on OpenAI-Codex while preserving direct OpenAI API-key compaction fallback. (#86408) Thanks @funmerlin and @VACInc.</li>
+<li>Agent transcript: include OpenClaw agent session logs when finding local transcript candidates.</li>
+<li>Crabbox: bootstrap raw AWS macOS shell commands wrapped in absolute <code>time</code> paths so RSS probes can run Node and pnpm on fresh macOS runners.</li>
+<li>Crabbox: bootstrap raw AWS macOS shell commands even when setup statements precede Node or pnpm usage.</li>
+<li>TUI/local: skip unnecessary secret resolution, gateway model catalog loading, bootstrap, and skill scans in explicit local-model runs so startup reaches the model request faster.</li>
+<li>Sessions/doctor: load large session stores without clone amplification during read-only doctor checks and reclaim stale <code>sessions.json.*.tmp</code> sidecars. Fixes #56827. Thanks @openperf.</li>
+<li>Tests: clean successful plugin gateway gauntlet isolated temp roots while keeping an explicit preservation switch for failed/debug runs.</li>
+<li>Plugins/perf: reuse derived plugin metadata snapshots for the lifetime of the process so reply-time skill setup no longer rescans plugin metadata on every turn.</li>
+<li>Discord/OpenAI voice: keep wake-name master consults using the current speaker context after ignored ambient transcripts and shorten the default capture silence grace.</li>
+<li>Doctor: skip redundant Gateway restart prompts when a recent supervisor restart leaves the Gateway healthy. Fixes #86518. (#86533) Thanks @liaoyl830.</li>
+<li>Cron: restore suspended cron lanes to the configured/default concurrency instead of falling back to one after quota or circuit-breaker auto-resume.</li>
+<li>Gateway: keep session-only Control UI tool-start mirrors flowing during diagnostic queue pressure instead of silently dropping non-terminal tool updates.</li>
+<li>Agents/memory: return optional not-found context for missing date-only daily memory reads instead of logging benign first-run <code>ENOENT</code> failures. Fixes #82928. Thanks @galiniliev.</li>
+<li>Discord: merge streamed text captions into following media block replies so captions and attachments send as one message. (#86487) Thanks @neeravmakwana.</li>
+<li>Gateway: avoid sending duplicate tool-event frames to Control UI connections that are subscribed by both run and session.</li>
+<li>Discord/OpenAI voice: accept broader edge-position fuzzy wake-name transcripts while keeping ambient speech gated.</li>
+<li>Discord/OpenAI voice: accept longer leading wake-name mistranscripts such as "Open Club" for OpenClaw.</li>
+<li>Agents/OpenAI-compatible: stop ModelStudio-compatible chat requests before sending system/tool-only payloads that have no usable user or assistant turn. (#86177) Thanks @TurboTheTurtle.</li>
+<li>Gateway/plugins: reuse plugin package realpath checks while building installed plugin indexes so startup avoids repeated filesystem resolution work.</li>
+<li>Kilo Gateway: send string <code>stop</code> sequences as arrays so Kilo accepts OpenAI-compatible chat completions. (#86461) Thanks @SebTardif.</li>
+<li>Discord/OpenAI voice: accept leading fuzzy wake-name transcripts such as "Monty" or "Moti" for a Molty agent while keeping ambient speech gated.</li>
+<li>Media understanding: convert HEIC and HEIF images to JPEG before image description providers run so iPhone photos work in direct and configured image-description flows. (#86037)</li>
+<li>Agents: release embedded-attempt session locks from outer teardown so post-prompt exceptions cannot wedge later requests behind <code>SessionWriteLockTimeoutError</code>. Fixes #86014. Thanks @openperf.</li>
+<li>Discord/OpenAI voice: rotate Realtime sessions at provider max duration without logging the expected session-expiry event as an error.</li>
+<li>Sessions: skip metadata-only entries during QMD-slugified session lookup so one incomplete row does not block transcript hit resolution. (#86327) Thanks @abnershang.</li>
+<li>Agents/media: derive bundled plugin local-media trust from plugin tool metadata instead of importing the full plugin registry on subscription paths. (#84409) Thanks @samzong.</li>
+<li>Image tool: keep config-backed custom-provider API keys usable for auto-discovered vision models, including deferred image-tool execution without env keys or auth profiles. (#85733)</li>
+<li>Memory/local embeddings: run local GGUF embeddings in an isolated worker sidecar and degrade to configured fallback or keyword search on worker failure so native embedding crashes do not take down the Gateway. (#85348) Thanks @osolmaz.</li>
+<li>Gateway: clear the runtime config snapshot before <code>SIGUSR1</code> in-process restarts so config changes survive the next gateway loop. (#86388) Thanks @XuZehan-iCenter.</li>
+<li>Models: show OAuth delegation markers as configured <code>models.json</code> auth while keeping runtime route usability checks strict. (#86378) Thanks @rohitjavvadi.</li>
+<li>Cron: seed active scheduled and manual cron task rows with a progress summary so status surfaces do not look blank while jobs run. (#86313) Thanks @ferminquant.</li>
+<li>Cron: preserve unsupported persisted cron payload rows during routine store writes while keeping those rows non-runnable. Fixes #84922. (#86415) Thanks @IWhatsskill.</li>
+<li>Updater: exclude prerelease git tags from stable channel resolution so source updates do not check out newer alpha/rc/preview/canary tags. (#86260) Thanks @stevenepalmer.</li>
+<li>Security/Audit: flag webhook <code>hooks.token</code> reuse of active Gateway password auth in <code>openclaw security audit</code> while keeping password-mode startup compatibility. (#84338) Thanks @coygeek.</li>
+<li>QQBot: derive the outbound reply watchdog from configured agent and provider timeouts so slow local model replies are not cut off at five minutes. Fixes #85267. (#85271) Thanks @SymbolStar.</li>
+<li>Agents/heartbeat: stop heartbeat turns after the first valid <code>heartbeat_respond</code> so repeated response loops do not burn tokens. (#86357) Thanks @udaymanish6.</li>
+<li>Tasks: keep retained lost tasks out of default status health counts, explain their cleanup window during maintenance, and prune lost task records after 24 hours instead of the general 7-day terminal retention.</li>
+<li>Memory-core: keep REM dreaming focused on live light-staged memories and mark staged entries as considered so old recall history no longer dominates fresh candidates. (#86302) Thanks @SebTardif.</li>
+<li>Memory: abort sync instead of downgrading an existing semantic vector index to FTS-only when the configured embedding provider is temporarily unavailable. (#85704) Thanks @yaaboo-gif.</li>
+<li>Telegram: propagate forum topic names through the account-scoped topic cache for native command context and topic create/edit actions. (#86299) Thanks @SebTardif.</li>
+<li>Slack: keep downloaded read-only files out of reply media so Slack file reads do not echo files back to the conversation. (#86318) Thanks @neeravmakwana.</li>
+<li>Cron: accept leading-plus relative durations such as <code>+5m</code> for one-shot <code>--at</code> schedules. (#86341) Thanks @mushuiyu886.</li>
+<li>Agents/media: preserve async-started media tool metadata so background generation starts no longer surface generic incomplete-turn warnings while replay stays unsafe. (#85933) Thanks @fuller-stack-dev.</li>
+<li>Docker E2E: dedupe scheduler lane resources so npm/service package lanes are not over-counted and serialized unnecessarily.</li>
+<li>QA/diagnostics: add a collector-backed OpenTelemetry smoke lane, make the OTLP payload leak check scenario-aware, and keep source QA builds from failing on optional dependency imports resolved through pnpm's temp module path.</li>
+<li>Crabbox: bootstrap Git metadata for sparse remote changed gates so raw synced workspaces can run <code>pnpm check:changed</code> from the intended diff.</li>
+<li>xAI/LM Studio: avoid buffering ordinary bracketed or <code>final</code> prose until stream completion while watching for plain-text tool-call fallbacks.</li>
+<li>Doctor: warn and continue when the cron job store exists but cannot be read so later health checks still run. Fixes #86102. (#86384) Thanks @1052326311.</li>
+<li>Discord: suppress a bot's previous reply body and referenced media from prompt context when a user replies to that bot message, while keeping reply metadata for routing. (#86238) Thanks @fuller-stack-dev.</li>
+<li>Discord: restore bare numeric channel IDs for outbound message-tool sends while keeping explicit DM targets unambiguous. (#86571) Thanks @joshavant.</li>
+<li>Docker E2E: avoid rebuilding the Control UI twice while preparing the shared OpenClaw package tarball for package-backed scenario runs.</li>
+<li>Tests: avoid rebuilding the Control UI twice during the installer Docker smoke now that <code>pnpm build</code> includes <code>ui:build</code>.</li>
+<li>Tests: give QA config mutation RPCs enough native Windows budget to finish gateway config writes and restart settle after hot scenario runs.</li>
+<li>Tests: keep the gateway restart-inflight QA scenario focused on restart recovery on native Windows by allowing expected embedded prompt handoff errors and using the Windows-safe timeout budget.</li>
+<li>QA-Lab: make the synthetic OpenAI provider honor generic <code>reply exactly:</code> directives after required kickoff reads so restart-recovery scenarios do not fall through to generic repo-summary prose.</li>
+<li>Gateway: abort active <code>agent</code> RPC runs during forced restart shutdown so stale in-process turns cannot keep writing a session after the Gateway lifecycle restarts.</li>
+<li>Crabbox: sync clean sparse worktrees through a temporary full checkout even when reusing an existing lease so tracked build-time files are not omitted.</li>
+<li>Build: route <code>scripts/ui.js</code> through the shared pnpm runner and keep Control UI chunking helpers in sparse-included source so native Windows Corepack builds can produce <code>dist/control-ui</code>.</li>
+<li>Tests: give the memory fallback QA scenario enough turn budget to exercise native Windows gateway runs instead of failing on the client timeout while the mock agent is still dispatching.</li>
+<li>Tests: collect QA gateway CPU/RSS metrics on native Windows and give the channel baseline enough turn budget to report slow gateway runs instead of timing out before proof.</li>
+<li>Install/update: bypass npm <code>min-release-age</code> policies with <code>--min-release-age=0</code> instead of <code>--before</code> so hosted installers keep working on npm versions that reject the combined config. (#84749) Thanks @TeodoroRodrigo.</li>
+<li>Diagnostics: reclaim wedged session lanes when stale active-run bookkeeping blocks queued work despite no forward progress. Fixes #85639. Thanks @openperf.</li>
+<li>WebChat: keep message-tool replies visible in the chat while still summarizing internal tool results for the model. Fixes #86347. Thanks @shakkernerd.</li>
+<li>Gateway/perf: fail startup benchmark samples when the Gateway process exits before benchmark teardown, including signal deaths after readiness probes.</li>
+<li>Gateway/perf: fail restart benchmark samples when the Gateway exits before benchmark teardown, including clean exits and signal deaths after successful restart probes.</li>
+<li>Agents/tests: keep model catalog visibility on static selection helpers so catalog visibility checks avoid the broad model-selection barrel import.</li>
+<li>Agents/commitments: serialize commitment store load-modify-save writes so concurrent heartbeat and CLI updates no longer lose dismissal, sent, or attempt state. (#81153) Thanks @ai-hpc.</li>
+<li>xAI/LM Studio: promote plain-text tool-call fallbacks into structured tool calls and strip leaked internal tool syntax before user-facing delivery. (#86222) Thanks @fuller-stack-dev.</li>
+<li>CLI: suppress benign self-update version-skew warnings during package post-update finalization.</li>
+<li>Gateway/perf: tighten restart and startup benchmark failure handling so long profiling runs, failed probes, and fresh Linux runners no longer produce false passing or <code>n/a</code> results.</li>
+<li>Checks: keep intentional Knip unused-file findings optional so full CI and sparse proof workspaces stay aligned.</li>
+<li>Docker: restore writable <code>~/.config</code> in runtime images. Fixes #85968. Thanks @hkoessler and @Bartok9.</li>
+<li>Plugin SDK: keep legacy root diagnostic subscriptions connected when built plugin SDK aliases resolve diagnostic helpers through a separate module graph.</li>
+<li>Diagnostics: export alertable OTel and Prometheus signals for blocked tools, model failover, stale sessions, liveness warnings, oversized payloads, and webhook ingress while fixing shared OTLP endpoints with query strings.</li>
+<li>Tests: normalize macOS canonical temp paths in exec allowlists, fs-safe trash assertions, installed plugin matching, Telegram topic-name stores, and built ACPX MCP server expectations so native macOS proof runners cover the intended behavior.</li>
+<li>Codex/app-server: preserve message-tool-only source reply delivery mode on active runs so sub-agent completion wakeups can steer the active Codex turn instead of being rejected. (#86287) Thanks @ferminquant.</li>
+<li>Tests: sample the Windows kitchen-sink RPC gateway directly and serialize RSS probes so native runs keep the memory guard active.</li>
+<li>Tests: normalize bundled plugin lifecycle probe paths and state-root lookup so native Windows release sweeps accept valid packaged plugin installs.</li>
+<li>Agents/Claude CLI: route live native Bash permission requests through OpenClaw exec policy so Claude turns no longer stall on <code>control_request</code>, and document that OpenClaw exec policy is authoritative. Fixes #80819. (#86330, from #81971) Thanks @guthirry and @sallyom.</li>
+<li>Security audit: warn when YOLO OpenClaw exec policy overrides a restrictive raw Claude <code>--permission-mode</code> for managed live sessions. (#86557) Thanks @sallyom.</li>
+<li>Config: keep benign legacy metadata write anomalies out of default doctor and config command output while preserving explicit anomaly logging for diagnostics.</li>
+<li>Codex: log when implicit app-server <code>never</code> approvals are promoted for OpenClaw tool policy, including whether the trigger was a <code>before_tool_call</code> hook or trusted tool policy.</li>
+<li>Codex harness: make subscription usage-limit errors without reset times explain that OpenClaw cannot determine the reset and point users to wait until Codex is available, use another Codex account, or switch to another configured model/provider. Thanks @amknight.</li>
+<li>Google Vertex: support production ADC modes such as Workload Identity Federation, service-account credentials, and metadata-server ADC for the native Vertex transport. (#83971) Thanks @damianFelixPago.</li>
+<li>Telegram: route normal <code>[telegram][diag]</code> polling diagnostics through <code>runtime.log</code> while keeping non-diag warnings and persistence failures on <code>runtime.error</code>, so healthy polling startup no longer looks like an error. Fixes #82957. (#82958) Thanks @galiniliev.</li>
+<li>Providers/Ollama: strip inline Kimi cloud reasoning prefixes from streamed and final visible replies while keeping ordinary Kimi answers append-only. (#86286) Thanks @jason-allen-oneal.</li>
+</ul>
+<ul>
+<li>Gateway: require Talk secret authority before setup-code handoff can include Talk secrets. (#85690) Thanks @ngutman.</li>
+<li>Agents: keep fallback error reporting scoped to the active model candidate so stale prior-provider quota/auth text is not reported for later fallback attempts. (#86134) Thanks @zhangguiping-xydt.</li>
+<li>iMessage: dedupe watcher startup when <code>channels.imessage.accounts</code> lists both <code>default</code> and a named account that point at the same local Messages source, so the gateway no longer spawns two <code>imsg rpc</code> processes or doubles inbound replies; the dedupe is scoped to watcher startup, leaving duplicate accounts addressable for outbound sends, status, and capability listings, and <code>openclaw doctor</code> flags the redundant account with a rebinding hint. Fixes #65141. (#86705) Thanks @swang430.</li>
+</ul>
+<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
+]]></description>
+            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.5.26/OpenClaw-2026.5.26.zip" length="54484748" type="application/octet-stream" sparkle:edSignature="y4WXG7JT8ktJ+K7YDgllY7u5Z9BSKR/SwGiwEh0gikOJ/SWqwcQd+z2tWa2zgwvCJKWsAUFwJs1ATor880SUBg=="/>
+        </item>
         <item>
             <title>2026.5.22</title>
             <pubDate>Sun, 24 May 2026 01:41:27 +0000</pubDate>
@@ -281,397 +537,5 @@
 ]]></description>
             <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.5.22/OpenClaw-2026.5.22.zip" length="54409357" type="application/octet-stream" sparkle:edSignature="am1mwLOmUHor9QuQWtxSsKoBOCySUBo4fB+0Qdcrz0E3wf6ESIMTfOC0k+dKJSh9gtLZw5jzpWVqTBzEdU36Aw=="/>
         </item>
-        <item>
-            <title>2026.5.20</title>
-            <pubDate>Thu, 21 May 2026 21:19:52 +0000</pubDate>
-            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
-            <sparkle:version>2026052090</sparkle:version>
-            <sparkle:shortVersionString>2026.5.20</sparkle:shortVersionString>
-            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
-            <description><![CDATA[<h2>OpenClaw 2026.5.20</h2>
-<h3>Changes</h3>
-<ul>
-<li>Exec approvals: remove the old <code>cat SKILL.md && printf ... && <skill-wrapper></code> allowlist compatibility path so skill files must be loaded with the read tool and only the real skill executable is auto-allowed.</li>
-<li>Discord: let voice sessions follow configured Discord users into voice channels, with allowed-channel checks, multi-user handoff, bounded reconciliation, and DAVE recovery preservation. (#84264) Thanks @fuller-stack-dev.</li>
-<li>Discord/voice: include bounded <code>IDENTITY.md</code>, <code>USER.md</code>, and <code>SOUL.md</code> profile context in realtime voice session instructions by default, with <code>voice.realtime.bootstrapContextFiles: []</code> available to disable it. (#84499) Thanks @fuller-stack-dev.</li>
-<li>Dependencies: bump the bundled Codex harness to <code>@openai/codex</code> <code>0.132.0</code> and refresh the app-server model-list docs for the new catalog.</li>
-<li>CLI/policy: add the bundled Policy plugin for policy-backed channel conformance checks, doctor lint findings, and opt-in workspace repair. (#80407) Thanks @giodl73-repo.</li>
-<li>Agents/config: allow <code>agents.list[].experimental.localModelLean</code> so lean local-model mode can be enabled for one configured agent instead of globally.</li>
-<li>Providers/xAI: add device-code OAuth login so remote and headless setups can authorize xAI without a localhost browser callback. (#84005) Thanks @fuller-stack-dev.</li>
-<li>Providers/OpenRouter: honor provider-level <code>params.provider</code> routing policy for OpenRouter requests, with model and agent params overriding the defaults. Thanks @amknight.</li>
-</ul>
-<h3>Fixes</h3>
-<ul>
-<li>CLI/tasks: include stale-running task maintenance decisions in <code>openclaw tasks maintenance --json</code> so retained and reconcile candidates explain backing-session, cron, CLI, and wedged-subagent state. (#84691) Thanks @efpiva.</li>
-<li>Codex app-server: keep system-prompt reports working when bootstrap hooks provide workspace files with only a path and content, so hook-supplied SOUL/IDENTITY/TOOLS/USER context still reports injected characters correctly. (#84736) Thanks @JARVIS-Glasses.</li>
-<li>Providers/MiniMax music: stop advertising <code>durationSeconds</code> control and remove prompt-injected duration hints, so <code>music_generate</code> reports MiniMax duration as an unsupported override instead of suggesting MiniMax can enforce track length. Fixes #84508. Thanks @neeravmakwana.</li>
-<li>Doctor: warn when sandbox tool policy hides configured MCP server tools before provider requests. (#84699) Thanks @nxmxbbd.</li>
-<li>WhatsApp: update Baileys to <code>7.0.0-rc12</code>.</li>
-<li>Build: suppress per-locale <code>rolldown-plugin-dts:fake-js</code> CommonJS dts warnings emitted while bundling the intentionally-inlined <code>zod/v4/locales/*.d.cts</code> files, so <code>pnpm build</code> output stays readable after the 0.25.1 plugin bump. Thanks @romneyda.</li>
-<li>CLI/nodes: route lazy plugin-registration logs to stderr for JSON-mode <code>openclaw nodes</code> commands so stdout stays parseable. (#84684) Thanks @TurboTheTurtle.</li>
-<li>Approvals: route manual <code>/approve</code> decisions through the trusted approval runtime so active exec and plugin approvals no longer look unknown or expired.</li>
-<li>Mac app: update the About settings copyright year to 2026. (#84385) Thanks @pejmanjohn.</li>
-<li>Dependencies: update <code>@openclaw/fs-safe</code> to <code>0.2.7</code> so OpenClaw's default Python-helper-off policy keeps best-effort Node write fallbacks for private stores, secret writes, run logs, and media attachments on Linux/macOS.</li>
-<li>Infra/secrets: restore the fail-closed contract for <code>tryReadSecretFileSync</code> so credential loaders that pass <code>rejectSymlink: true</code> (Telegram, LINE, Zalo, IRC, Nextcloud Talk tokens) refuse symlinked credential files instead of silently accepting them, and the infra-state CI shard's secret-file symlink test passes again. Thanks @romneyda.</li>
-<li>Browser: honor the configured image sanitization limit for screenshots and labeled snapshots so browser-captured images follow the same resize policy as other image results. (#84595)</li>
-<li>Doctor: remove unrecognized <code>models.providers.*.models[*].compat.thinkingFormat</code> values during <code>doctor --fix</code> so stale provider model config can validate after upgrade. Fixes #77803.</li>
-<li>Doctor: warn when <code>openclaw.json</code> stores plaintext secret-bearing config fields, including model provider API keys and sensitive provider headers. (#84718) Thanks @lukaIvanic.</li>
-<li>Status: show the configured default, session-selected model, reason, clear hint, and docs link when a session remains pinned to a model that differs from <code>agents.defaults.model.primary</code>.</li>
-<li>WebChat: clear stale typing indicators when session change events mark the active chat run complete.</li>
-<li>Mac app: keep local packaging signed with a stable app identity for permission testing and fix Control UI production builds under current Vite/Highlight.js exports.</li>
-<li>macOS app: update the embedded Peekaboo bridge to 3.2.1 so OpenClaw-hosted UI automation works with current Peekaboo CLI capture flows.</li>
-<li>Cron: deliver preferred final assistant output for successful scheduled runs when trailing plain tool warnings remain in diagnostics instead of marking the run failed.</li>
-<li>fix(mattermost): fail closed on missing channel type [AI]. (#84091) Thanks @pgondhi987.</li>
-<li>Recheck rebuilt system.run argv [AI]. (#84090) Thanks @pgondhi987.</li>
-<li>CLI: keep the private QA subcommand out of exported command descriptors unless <code>OPENCLAW_ENABLE_PRIVATE_QA_CLI=1</code>, so root help and subcommand markers match runtime registration. (#84519)</li>
-<li>CLI/cron: bound <code>openclaw cron show</code> job lookup pagination so non-advancing or unbounded <code>cron.list</code> responses fail instead of hanging the command. Fixes #83856. (#83989)</li>
-<li>Agents/messages: stop message-tool-only turns after a successful source-channel <code>message</code> send while keeping transcript mirrors under the session write lock. (#84289)</li>
-<li>Agents: filter silent heartbeat response-tool transcript artifacts out of embedded context snapshots so later user turns are not polluted by heartbeat no-op messages. (#83477) Thanks @fuller-stack-dev.</li>
-<li>Agents/OpenAI: log repeated strict tool-schema downgrade diagnostics once per provider/model/tool signature, reducing duplicate debug noise while preserving <code>strict=false</code> fallback behavior. Fixes #82930. (#82933) Thanks @galiniliev.</li>
-<li>Agents/code mode: spell out the <code>exec</code> tool's JavaScript/TypeScript, no Node module, and catalog-bridge constraints in model-visible schema text so agents can use enabled tools without trial-and-error. (#84269) Thanks @Kaspre.</li>
-<li>Codex: give <code>image_generate</code> dynamic-tool calls a 120s default watchdog when no per-call or configured image timeout is set, so image generation no longer falls back to the generic 30s bridge timeout. (#84254) Thanks @moritzmmayerhofer.</li>
-<li>Codex: avoid duplicate dynamic tool terminal diagnostics while large diagnostic backlogs drain without blocking tool responses. (#82937) Thanks @galiniliev.</li>
-<li>CLI/message: include a stable top-level <code>messageId</code> in <code>openclaw message --json</code> output when channel sends return one. (#84191) Thanks @100menotu001.</li>
-<li>Cron: preserve legacy top-level array <code>jobs.json</code> stores when loading or adding scheduled jobs so old cron jobs are no longer treated as an empty store during upgrade. Fixes #60799. (#84433) Thanks @IWhatsskill.</li>
-<li>Gateway/agents: use an agent's <code>identity.name</code> in Gateway agent summaries when <code>agents.list[].name</code> is unset, so configured agent labels remain visible in clients. (#84355; refs #57835) Thanks @luoyanglang.</li>
-<li>Channels/replies: keep normal <code>/verbose</code> failed-tool progress compact in message-tool replies and prevent late text-only tool output from appearing after the final answer. (#84303) Thanks @VACInc.</li>
-<li>Plugins/hooks: apply a default 30-second timeout to <code>before_compaction</code> and <code>after_compaction</code> hooks so a hung plugin handler no longer blocks compaction completion. (#84153)</li>
-<li>Discord: preserve disabled presentation buttons when adapting and rendering Discord message controls. (#84188) Thanks @100menotu001.</li>
-<li>Twitch: add a test-only client-manager registry reset helper so non-isolated Twitch tests can clear cached managers between cases. Fixes #83887. (#84244) Thanks @hclsys.</li>
-<li>Cron: run main-session scheduled work on a cron-owned wake lane while preserving reply delivery context, so background cron turns no longer block human main-session chat. Fixes #82766. (#82767) Thanks @galiniliev.</li>
-<li>Cron: use structured embedded-run denial metadata for isolated scheduled tasks so blocked exec requests fail the job without treating ordinary assistant prose as a denial. (#84067) Thanks @abnershang.</li>
-<li>Cron: keep recovered tool warnings diagnostic for successful scheduled runs so final cron output is delivered instead of being replaced by a post-processing warning. (#84045) Thanks @abnershang.</li>
-<li>Plugins/perf: thread explicit plugin discovery results through <code>loadBundledCapabilityRuntimeRegistry</code>, <code>resolveBundledPluginSources</code>, and <code>listChannelCatalogEntries</code> so callers that already hold a discovery result skip redundant filesystem walks. Thanks @SebTardif.</li>
-<li>harden update restart script creation [AI]. (#84088) Thanks @pgondhi987.</li>
-<li>Docker: keep the bundled Codex plugin in official release image keep lists so the default OpenAI agent harness remains available after Docker pruning. Fixes #83613. (#83626) Thanks @YuanHanzhong.</li>
-<li>CLI/channels: preserve the first line of <code>openclaw channels logs</code> output when the rolling tail window starts exactly on a line boundary, mirroring the already-fixed <code>readLogSlice</code> behavior in <code>src/logging/log-tail.ts</code>.</li>
-<li>Control UI: treat terminal session status as authoritative over stale active-run flags so completed terminal runs stop showing abort/live UI. (#84057)</li>
-<li>CLI: preserve embedded equals signs in inline root option values instead of truncating after the second separator. (#83995) Thanks @ThiagoCAltoe.</li>
-<li>Matrix/config: accept <code>messages.queue.byChannel.matrix</code> queue overrides and keep queue provider schema/type keys aligned for Matrix, Google Chat, and Mattermost. Thanks @bdjben.</li>
-<li>CLI: format <code>openclaw acp client</code> failures through the shared error formatter so object-shaped errors stay readable instead of printing <code>[object Object]</code>. Fixes #83904. (#84080)</li>
-<li>Providers/Ollama: default unknown-capabilities models to tool-capable so discovered native Ollama models can use tools when <code>/api/show</code> omits capabilities. (#84055) Thanks @dutifulbob.</li>
-<li>Installer/Windows: launch <code>install.ps1</code> onboarding as an attached child process so fresh native Windows installs do not freeze visibly at <code>Starting setup...</code> or corrupt the wizard's terminal rendering.</li>
-<li>CLI/update: keep restart health checks working across one-version CLI/Gateway protocol skew and use the managed Gateway service Node for all follow-up commands even when the package root is unchanged, so <code>openclaw update</code> no longer silently switches the gateway to a different Node binary when multiple Node installations are present. Thanks @amknight.</li>
-<li>CLI/gateway: include the running Gateway version in <code>gateway status</code> JSON output, preserving existing server metadata while falling back to status RPC data for read probes. Fixes #56222. Thanks @galiniliev.</li>
-<li>Memory/search: close local embedding providers when active-memory searches time out so pending local model loads and embedding contexts are aborted and released. (#83858) Thanks @brokemac79.</li>
-<li>CLI/nodes: request pending node surface approval scopes before <code>openclaw nodes approve</code> so exec-capable node approval can use admin-scoped Gateway credentials instead of failing with <code>missing scope: operator.admin</code>. (#84392) Thanks @joshavant.</li>
-<li>Gateway: reject slow node event sends before outbound buffers grow unbounded and log the rejected payload diagnostic. (#84387) Thanks @samzong.</li>
-<li>Agents: include bounded trajectory queued-writer diagnostics in <code>pi-trajectory-flush</code> timeout warnings so flush stalls show pending writes, queued bytes, and append state. Fixes #82961. (#82962) Thanks @galiniliev.</li>
-<li>Agents/subagents: recover stale completion announces by retrying unsupported transcript-wait wakes without transcript waiting and forcing a message-tool handoff when the requester run is already stale. Fixes #83699. (#83700) Thanks @galiniliev.</li>
-<li>Agents/subagents: constrain wildcard subagent target allowlists to configured agents while preserving explicitly listed compatibility targets. Fixes #84040. (#84357) Thanks @joshavant.</li>
-<li>Providers/Anthropic: route Anthropic model refs selected with Claude CLI auth through the Claude CLI runtime so shorthand refs such as <code>anthropic/opus-4.7</code> no longer fall back to embedded Anthropic billing. Fixes #84222. (#84374) Thanks @joshavant.</li>
-<li>Agents: honor explicit <code>models.providers.<id>.timeoutSeconds</code> values above the default idle watchdog for cloud and self-hosted providers, so long first-token waits no longer fall back at ~120s when the provider timeout is higher. (#83979) Thanks @yujiawei.</li>
-<li>Agents/Codex: keep encrypted Responses reasoning replay provenance-bound so stale mirrored Codex transcripts drop invalid encrypted content before request assembly while preserving matching same-session replay. Fixes #83836. (#84367) Thanks @joshavant.</li>
-<li>Agents/subagents: skip stale embedded-run wake probes for dormant completion requesters, so late subagent completions go straight to requester-agent/direct handoff instead of producing <code>reason=no_active_run</code> queue noise. (#82964) Thanks @galiniliev.</li>
-<li>CLI: retry config snapshot reads after a transient failure so one rejected read no longer poisons later commands in the same process. (#83931) Thanks @honor2030.</li>
-<li>Media: decode URL path basenames before using them as remote media fallback filenames, so files like <code>My%20Report.pdf</code> are surfaced as <code>My Report.pdf</code>. Fixes #84050. (#84052) Thanks @jbetala7.</li>
-<li>WhatsApp: clarify inbound group diagnostics so observed but unregistered groups point to <code>channels.whatsapp.groups</code> without changing routing or sender authorization. (#83846) Thanks @neeravmakwana.</li>
-<li>WhatsApp: drain pending outbound deliveries on a 30s periodic timer in addition to the reconnect handler, so messages enqueued while the provider is already connected no longer wait for the next reconnect to send. (#79083) Thanks @Oviemudiaga.</li>
-<li>CLI/TUI: include gateway plugin slash commands in TUI autocomplete, so connected sessions can suggest plugin-owned commands exposed by the running Gateway. (#83640) Thanks @se7en-agent.</li>
-<li>Gateway/mobile: restore QR setup-code handoff of bounded operator tokens for iOS and Android onboarding while keeping admin and pairing scopes out of bootstrap. (#83684) Thanks @ngutman.</li>
-<li>iOS: repair Release archive compilation for the TestFlight build. (#84255) Thanks @ngutman.</li>
-<li>Agents/compaction: bound plugin-owned CLI transcript compaction with the host safety timeout so a hung context engine can no longer stall post-turn cleanup. (#84083) Thanks @100yenadmin.</li>
-<li>Control UI/usage: truncate long context skill, tool, and file names in the usage panel while keeping the full name available on hover. (#42197) Thanks @Rain120.</li>
-<li>Codex: respect explicit <code>models auth order set</code> and <code>config.auth.order</code> precedence over stale <code>lastGood</code> in <code>/codex account</code>, and show <code>no working credential</code> when every explicit-order profile is ineligible instead of marking a lower-ranked profile as active. Fixes #84386. (#84412) Thanks @openperf.</li>
-<li>Agents: honor <code>messages.suppressToolErrors</code> for mutating tool failures so configured chat surfaces do not receive separate warning payloads. (#81561) Thanks @moeedahmed.</li>
-<li>Agents/fallback: surface billing guidance for mixed rate-limit plus billing fallback exhaustion instead of generic failure copy. Fixes #79396. (#79489) Thanks @aayushprsingh.</li>
-</ul>
-<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
-]]></description>
-            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.5.20/OpenClaw-2026.5.20.zip" length="54396392" type="application/octet-stream" sparkle:edSignature="Ufz+twYjgj5NDg29tG3Ttx/JNyT3/a3EKLciBGvsa38C6Dwqp4yFYC5jSBiSlubwBXhrq8OQDMgavMKtSsclBQ=="/>
-        </item>
-        <item>
-            <title>2026.5.19</title>
-            <pubDate>Wed, 20 May 2026 21:27:21 +0000</pubDate>
-            <link>https://raw.githubusercontent.com/openclaw/openclaw/main/appcast.xml</link>
-            <sparkle:version>2026051990</sparkle:version>
-            <sparkle:shortVersionString>2026.5.19</sparkle:shortVersionString>
-            <sparkle:minimumSystemVersion>15.0</sparkle:minimumSystemVersion>
-            <description><![CDATA[<h2>OpenClaw 2026.5.19</h2>
-<h3>Changes</h3>
-<ul>
-<li>Agents: clarify that fixes should default to clean bounded refactors, lean internals, and explicit plugin SDK/API deprecation paths.</li>
-<li>Dependencies: update <code>@openclaw/proxyline</code> to 0.3.3.</li>
-<li>Dependencies: update Pi packages to 0.75.1 and raise the minimum supported Node.js 22 line to 22.19.</li>
-<li>Docker/Podman: add <code>OPENCLAW_IMAGE_APT_PACKAGES</code> as the runtime-neutral image build arg for extra apt packages while keeping <code>OPENCLAW_DOCKER_APT_PACKAGES</code> as a legacy fallback. (#62431) Thanks @urtabajev.</li>
-<li>Gateway/ACPX: attribute startup probe, config, runtime, and resource-count costs in restart traces without changing readiness behavior. (#83300) Thanks @samzong.</li>
-<li>Gateway: overlap startup logging and plugin-service startup with channel sidecars to reduce restart ready latency while preserving <code>/readyz</code> sidecar gating. (#83301) Thanks @samzong.</li>
-<li>Plugins/admin-http-rpc: allow trusted admin HTTP RPC clients to start and wait for web QR login flows. (#83259) Thanks @liorb-mountapps.</li>
-<li>Mac app: redesign Settings pages with consistent card layouts, cached navigation, cleaner permissions/voice/skills/cron/exec/debug panes, and steadier spacing around the native sidebar.</li>
-<li>Mac app: refine Voice & Talk recognition-language and wake-phrase settings so they use the same compact card rows as the rest of Settings.</li>
-<li>Skills: rename the repo-local Codex closeout review skill and helper to <code>autoreview</code> while preserving the Codex-first fallback behavior.</li>
-<li>Skills: add a meme-maker skill for curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.</li>
-<li>Skills CLI: allow <code>openclaw skills install</code> and <code>openclaw skills update</code> to target shared managed skills with <code>--global</code>. (#74466) Thanks @Marvae.</li>
-<li>Browser: surface pending and recently handled modal dialogs in snapshots, return <code>blockedByDialog</code> when an action opens a modal, and allow <code>browser dialog --dialog-id</code> to answer pending dialogs.</li>
-<li>Browser CLI: add <code>openclaw browser evaluate --timeout-ms</code> so long-running page functions can extend both the evaluate action and request timeout budgets. (#83447) Thanks @eefreenyc.</li>
-<li>Codex app-server: scope OpenClaw prompt guidance by runtime surface so native Codex keeps Codex-owned base/personality instructions while OpenClaw contributes only runtime context, delivery guidance, and explicitly scoped command hints. (#83454) Thanks @100yenadmin.</li>
-<li>Docker/Podman: add <code>OPENCLAW_IMAGE_PIP_PACKAGES</code> for opt-in Python package installation in local image builds. (#83771) Thanks @stephenredmond-straiteis.</li>
-<li>Agents/tools: shorten built-in tool descriptions and schema hints across media, messaging, sessions, cron, Gateway, web, image/PDF, TTS, nodes, and plan tools while preserving routing guardrails.</li>
-<li>Skills: add node inspector debugging, fused diagram generation, and throwaway spike workflow skills.</li>
-<li>CLI/plugins: add <code>defineToolPlugin</code> plus <code>openclaw plugins build</code>, <code>validate</code>, and <code>init</code> for typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories.</li>
-<li>Agents/skills: tighten bundled skill prompts and metadata, quote skill descriptions, refresh current CLI/API guidance, and update embedded sherpa-onnx runtime downloads.</li>
-<li>Skills: update the Obsidian skill to target the official <code>obsidian</code> CLI and require its registered binary instead of the third-party <code>obsidian-cli</code>.</li>
-<li>Skills: add a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.</li>
-<li>Codex: add <code>/codex plugins list</code>, <code>enable</code>, and <code>disable</code> for managing configured native Codex plugins from chat without editing config by hand.</li>
-<li>Plugins/messages: add presentation capability limits for channel renderers, adapt rich message controls before native rendering, and mark legacy <code>interactive</code>/Slack directive producer APIs as deprecated.</li>
-<li>Plugins/subagents: store channel delivery routes as canonical session metadata and deprecate ad hoc subagent hook delivery-origin fields in favor of core route projection.</li>
-<li>Proxy: support HTTPS managed forward-proxy endpoints and scoped <code>proxy.tls.caFile</code> CA trust for proxy endpoint TLS. (#79171) Thanks @jesse-merhi.</li>
-<li>QA-Lab: add first-hour 20-turn and optional 100-turn runtime parity scenarios, with tier metadata for standard and soak QA gates. Fixes #80338; refs #80337. Thanks @100yenadmin.</li>
-<li>QA-Lab: add <code>openclaw qa suite --runtime-parity-tier</code> and wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes. Fixes #80337. Thanks @100yenadmin.</li>
-<li>QA-Lab: add a live-only Codex Pi-shaped Read vocabulary canary so runtime parity catches native workspace-read prompt compatibility drift. (#80323) Thanks @100yenadmin.</li>
-<li>QA-Lab: add live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing. (#80323) Thanks @100yenadmin.</li>
-<li>QA-Lab: add runtime tool fixture scenarios and coverage reporting for Codex-native workspace tools, OpenClaw dynamic tools, and optional plugin-backed tools. Fixes #80173. Thanks @100yenadmin.</li>
-<li>QA-Lab: expose runtime tool fixture coverage through <code>openclaw qa coverage --tools</code>, with optional suite-summary evaluation for parity gate artifacts. Thanks @100yenadmin.</li>
-<li>QA-Lab: schedule a live-frontier Codex-vs-Pi runtime token-efficiency artifact lane in the all-lanes QA workflow. Fixes #80175. Thanks @100yenadmin.</li>
-<li>QA-Lab: hard-gate required OpenClaw dynamic runtime-tool drift in the standard Codex-vs-Pi tier with a blocking release-check verifier and publish the tool coverage report artifact. Fixes #80339; refs #80319. Thanks @100yenadmin.</li>
-<li>QA-Lab: add the personal-agent approval-denial scenario so the benchmark pack verifies denied local reads stop cleanly without tool progress or fixture leaks. (#83150) Thanks @iFiras-Max1.</li>
-<li>QA-Lab: extend the personal-agent benchmark pack with a local task followthrough scenario for proof-backed pending, blocked, and done status reporting. Thanks @iFiras-Max1.</li>
-<li>QA-Lab: add a report-only dreaming shadow-trial scenario so candidate memory promotion can be evaluated without mutating <code>MEMORY.md</code>. Thanks @iFiras-Max1.</li>
-<li>Gateway/performance: add <code>pnpm test:restart:gateway</code> benchmark tooling for repeated restart readiness, downtime, trace, and resource-slope evidence. (#83299) Thanks @samzong.</li>
-<li>Android: switch Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts. (#83130) Thanks @sliekens.</li>
-<li>Gateway/config: expose config lookup reload metadata so tools can distinguish restart-required, hot-reloadable, and no-op fields before applying config edits. Fixes #81409. (#81612) Thanks @LLagoon3.</li>
-<li>Telegram: add allowlisted native DM draft previews for transient tool progress while keeping final answers on the normal persistent delivery path. (#83622) Thanks @akrimm702.</li>
-<li>QA-Lab: add a personal-agent share-safe diagnostics artifact scenario so support handoffs keep useful status while omitting raw personal content. Thanks @iFiras-Max1.</li>
-<li>QA-Lab: add a personal-agent no-fake-progress scenario so completion claims stay tied to local evidence instead of unsupported external progress. (#83824) Thanks @iFiras-Max1.</li>
-</ul>
-<h3>Fixes</h3>
-<ul>
-<li>CLI: reject explicit port numbers above 65535 before they reach Gateway or Node bind paths. Fixes #83900. (#84008) Thanks @hclsys.</li>
-<li>Codex app-server: preserve plugin tool auth profiles when Codex owns model transport so OpenClaw dynamic tools can resolve their provider credentials. (#83603) Thanks @rubencu.</li>
-<li>Memory/search: scan the JS-side fallback vector path (used when the sqlite-vec index is unavailable or has a mismatched dimension) in bounded rowid batches and yield to the event loop between batches so large chunk tables can no longer pin the Node.js main thread for multi-second windows. Also keeps the SQL prepared statement rooted in a local so node:sqlite cannot finalize it mid-scan under heap pressure. Fixes #81172. Thanks @dev23xyz-oss.</li>
-<li>Memory Wiki: preserve fs-safe diagnostics when bridge source page writes fail for non-symlink filesystem safety reasons, so directory collisions are reported with the underlying error code. (#83776) Thanks @TurboTheTurtle.</li>
-<li>Telegram: keep forum topics from blocking sibling topic traffic by routing inbound serialization, media/text buffers, and account API queues on topic-aware lanes. (#83829)</li>
-<li>Telegram: keep queued forum-topic follow-up messages from inheriting superseded source abort signals, so later same-topic user turns can still run and reply after an active turn is replaced. (#83827) Thanks @VACInc.</li>
-<li>CLI/update: bypass npm freshness filters consistently during managed package and plugin installs so freshly published release plugins remain installable. Thanks @jalehman.</li>
-<li>CLI/update: guide root-owned npm install EACCES recovery by stopping the managed Gateway before manual package replacement, then reinstalling and restarting the service. Fixes #83747. (#83757) Thanks @brokemac79.</li>
-<li>Twitch: register refreshing chat tokens with Twurple's chat intent so automatic token refresh keeps chat access available. (#83750) Thanks @TurboTheTurtle.</li>
-<li>Agents/subagents: keep collect-mode announce queues batching unresolved-origin items with compatible same-route messages and resume collection after a true cross-channel drain when a later compatible batch remains. Fixes #83577.</li>
-<li>Skills: refresh existing session skill snapshots when watched skill roots change, so changed extra skill directories take effect without starting a new session. Fixes #83782. (#83800) Thanks @hclsys.</li>
-<li>Providers/Anthropic: preserve native image input for current Claude model rows when stale local catalog data marks them text-only. (#83756) Thanks @TurboTheTurtle.</li>
-<li>Providers/Anthropic: preserve Claude 4 image capability when configured model refs resolve through a stale local catalog row. (#83756) Thanks @TurboTheTurtle.</li>
-<li>Providers/DeepSeek: normalize MCP tool schemas with <code>anyOf</code>/<code>oneOf</code> unions before normal and compaction requests reach DeepSeek, preventing union-shaped parameters from being rejected. (#83766) Thanks @TurboTheTurtle.</li>
-<li>Control UI: render live tool progress from session-scoped <code>session.tool</code> Gateway events so externally started runs show their tool cards in the active session. (#83734) Thanks @TurboTheTurtle.</li>
-<li>Outbound: resolve send-capable channel plugins from the active runtime registry when the pinned startup registry only has setup metadata. (#83733) Thanks @TurboTheTurtle.</li>
-<li>Discord: preserve streamed reply previews when recovered tool-warning finals are delivered before or after the assistant's final reply. (#84169) Thanks @neeravmakwana.</li>
-<li>Control UI: keep the chat delete confirmation popover clamped inside the visible viewport on small screens. (#83804) Thanks @ThiagoCAltoe.</li>
-<li>Browser: enforce current-tab URL allowlist checks for <code>/act</code> evaluate/batch actions and <code>/highlight</code> routes while leaving tab-management actions unblocked. (#78523)</li>
-<li>CI: require real-behavior-proof verdict markers to come from the ClawSweeper GitHub App before accepting exact-head proof. (#83692)</li>
-<li>Models: show the effective OpenAI/Codex auth profile in <code>/models</code> provider headers instead of falling back to the OpenAI env-key label. (#83697) Thanks @yu-xin-c.</li>
-<li>CLI: include active bundled loopback MCP tools in CLI system prompts and reset provider-side CLI sessions when that prompt-visible tool surface changes. (#83785) Thanks @TurboTheTurtle.</li>
-<li>Browser: keep a profile <code>cdpPort</code> when its <code>cdpUrl</code> omits a port, while still letting explicitly written URL ports win. (#82166) Thanks @Marvae.</li>
-<li>Agents/image generation: allow distinct <code>image_generate</code> prompts to start separate session-backed background tasks while same-prompt retries still return the active task status. (#83614) Thanks @Elarwei001.</li>
-<li>Gateway/WebChat: honor configured <code>channels.webchat.textChunkLimit</code> and <code>chunkMode</code> overrides when chunking WebChat replies. (#83713)</li>
-<li>Control UI: stop the chat reading indicator from sticking after an assistant response finishes. (#83515) Thanks @njuboy11.</li>
-<li>Skills: reject empty or whitespace-only skill names and descriptions during quick validation. (#27061)</li>
-<li>Sessions: skip trailing custom transcript entries when checking tail assistant replies so embedded CLI gap-fill does not duplicate canonical assistant output. (#83635) Thanks @yaoyi1222.</li>
-<li>Memory Wiki: keep <code>wiki_lint</code> tool output path-safe by reporting vault-internal lint reports as relative paths in tool text and details while preserving absolute report paths for CLI/file callers. (#83439) Thanks @LLagoon3.</li>
-<li>Telegram: keep verbose tool progress visible without mirroring non-final progress into active session transcripts, preventing embedded provider replies from aborting mid-run. (#83631) Thanks @kurplunkin.</li>
-<li>Telegram: log successful outbound text and media deliveries with account, chat, message, operation, thread, reply, silent, and chunk metadata while keeping message bodies out of logs. Fixes #83196. (#83247) Thanks @jrwrest.</li>
-<li>Cron: link isolated scheduled task runs to their stable cron session so task status and cleanup can follow the backing agent run. (#83606) Thanks @jai.</li>
-<li>Codex app-server: mark Codex-native subagent task mirrors terminal when blocked or failed spawn-agent calls arrive with stale initializing child state, preventing task registry entries from staying running. Fixes #83852. (#83945) Thanks @joshavant.</li>
-<li>CLI: enforce the documented Node.js 22.19 runtime floor in the source launcher.</li>
-<li>Release stability: repair broad-gate regressions in requester-agent completion handoff, QA-Lab mock spawn attribution, Slack monitor test isolation, plugin uninstall peer fixtures, and Node-floor launcher contract coverage.</li>
-<li>Agents/replies: persist queued follow-up user messages and assistant error stubs only once across model-fallback retries, preventing repeated provider rejections from corrupted same-role session transcripts. Fixes #83404. (#83417) Thanks @yetval.</li>
-<li>Telegram: preserve reply-target context for bare mention replies on runtime-only turns so the model sees the replied-to message body. Fixes #83767. (#83953) Thanks @joshavant.</li>
-<li>ClawHub: preserve configured base URL path prefixes when building API request URLs, so self-hosted ClawHub instances mounted under a subpath keep routing correctly. (#83982) Thanks @ThiagoCAltoe.</li>
-<li>Slack: persist delivered inbound message IDs and fail closed when same-channel thread replies lose their thread context, preventing delayed duplicate replies and accidental channel-root posts. Fixes #83521. Thanks @shannon0430.</li>
-<li>Codex app-server: complete OpenClaw dynamic tool diagnostics at the request boundary so successful, failed, timed out, aborted, and blocked tool calls do not leave active tool state behind. Fixes #83474. Thanks @rozmiarD.</li>
-<li>Gateway/config: keep config writes from failing on unrelated unresolved auth-profile SecretRefs while preserving live auth-profile runtime snapshots.</li>
-<li>Gateway/sessions: clear stored CLI provider resume bindings on non-subagent <code>/reset</code> so the next turn starts a fresh provider-side CLI conversation instead of resuming old context. (#83448) Thanks @jasonyliu.</li>
-<li>Doctor: preserve legacy whole-agent Claude CLI intent by moving matching Anthropic model selections to model-scoped runtime policy before removing stale runtime pins. Fixes #83491. Thanks @danielcrick.</li>
-<li>Discord/OpenAI: keep realtime Discord voice sessions hearing follow-up turns with OpenAI realtime and prebuffer assistant playback to avoid choppy starts. (#80505) Thanks @Solvely-Colin.</li>
-<li>LM Studio: resolve env-template API keys like <code>${LMSTUDIO_API_KEY}</code> through the standard SecretInput path instead of sending the raw template as the bearer token, and preserve header-auth and discovery-key precedence when the template is unset. Fixes #80495. (#80568) Thanks @MonkeyLeeT.</li>
-<li>Discord/subagents: route the initial reply from thread-bound delegated sessions into the bound Discord thread instead of the parent channel. Fixes #83170. (#83172) Thanks @100menotu001.</li>
-<li>Gateway/sessions: rotate failed agent sessions when their transcript file is missing instead of wedging per-channel lanes. Fixes #83488. (#83553) Thanks @LLagoon3.</li>
-<li>Agents: refresh final-delivery routing from fresh session state before declaring a no-send failure, keeping recovered runs on the normal durable delivery path. (#83835) Thanks @joshavant.</li>
-<li>Agents: guard final-delivery fresh session routing against mismatched logical sessions before reusing recovered delivery context. (#83928) Thanks @joshavant.</li>
-<li>Media: prevent image metadata probing from invoking external decoder delegates on unrecognized image bytes, and stop fallback chaining after real processing errors.</li>
-<li>Media: install Sharp with the root package and fall back to sips, Windows native imaging, ImageMagick, GraphicsMagick, or ffmpeg for image resizing/conversion when Sharp is unavailable. Fixes #83401. Thanks @scotthuang.</li>
-<li>Telegram: deliver generated media completions back into forum topics by preserving topic IDs across requester-agent handoff. (#83556) Thanks @fuller-stack-dev.</li>
-<li>Gateway: defer update-check startup until after readiness so package update checks no longer block sidecar-ready startup, while preserving update broadcasts and shutdown cleanup. (#83520) Thanks @samzong.</li>
-<li>Telegram: keep <code>/btw</code> and read-only status commands from aborting active runs, and avoid retaining raw update payloads in timed-out spool tombstones. Refs #83272.</li>
-<li>Agents: log strict-agentic execution contract diagnostics only when the planning-only retry path actually triggers.</li>
-<li>Agents: stop embedded session takeover and session write-lock errors from consuming model fallbacks while preserving provider fallback metadata. Fixes #83510. Thanks @luyao618.</li>
-<li>Agents/video: hide <code>video_generate</code> reference-audio parameters unless a registered video provider supports audio inputs.</li>
-<li>Plugins: fall back to npm for official ClawHub updates when artifact downloads are unavailable, including beta-to-default fallback and dry-run version reporting.</li>
-<li>Plugins/xAI: echo PKCE challenge fields during OAuth authorization-code token exchange for xAI token-endpoint compatibility. (#83499) Thanks @fuller-stack-dev.</li>
-<li>Codex app-server: hydrate current inbound image attachments before queued runs so Responses-backed agents receive Discord and other channel images as native vision input. Fixes #83466. Thanks @iannwu.</li>
-<li>Codex app-server: keep native code mode available without forcing code-mode-only so OpenClaw dynamic tool turns complete through the app-server tool bridge. Fixes #83109. Thanks @daswass.</li>
-<li>Codex app-server: expose OpenClaw's sandbox-routed shell as <code>sandbox_exec</code>/<code>sandbox_process</code> for non-Docker sandbox backends so SSH sandbox agents keep a correctly routed shell path without shadowing Codex native shell. Fixes #80322. Thanks @keramblock.</li>
-<li>Release stability: recover stale session diagnostics and Codex OAuth fallback state so stuck runs and reused refresh tokens clear without blocking follow-up work. (#83503) Thanks @100yenadmin.</li>
-<li>Messages/TTS: apply TTS directives before message-tool sends reach core, gateway, or plugin delivery so opt-in message-tool rooms and proactive sends attach voice notes instead of leaking raw tags. Fixes #81598. Thanks @CG-Intelligence-Agent-Jack and @CoronovirusG10.</li>
-<li>Messages/Codex: keep Codex direct/source chats on message-tool visible delivery by default while documenting and testing <code>messages.visibleReplies: "automatic"</code> as the old-mode opt-out; channel wildcard model overrides now apply to direct chats before harness delivery defaults.</li>
-<li>Memory/QMD: keep archived session transcript hits visible after QMD export while preserving normal <code>.md</code> session ids that only resemble archive names. (#83518; fixes #83506) Thanks @tanshanshan.</li>
-<li>Codex app-server: preserve network access for sandboxed Codex code-mode turns when the OpenClaw sandbox allows outbound egress. Fixes #83347. Thanks @YusukeIt0.</li>
-<li>Codex app-server: honor writable Docker bind mounts for sandboxed workspace-write turns while disabling native Code Mode when container-path aliases or read-only bind shadows cannot be represented safely host-side. Fixes #83737. (#83849) Thanks @joshavant.</li>
-<li>QA-Lab: keep the OTLP smoke decoder independent of removed OpenTelemetry generated-root internals.</li>
-<li>Messages: default group/channel visible replies to automatic final delivery again, keeping <code>message_tool</code> opt-in for ambient/shared rooms and tool-reliable models.</li>
-<li>CLI/TUI: force standalone <code>/exit</code> runs to terminate after <code>runTui</code> returns so onboarding-launched TUI children do not stay alive invisibly. (#83501) Thanks @fuller-stack-dev.</li>
-<li>Agents/code mode: honor per-agent code-mode config in schema, runtime catalog activation, and model payload filtering. Fixes #83388. Thanks @Kaspre.</li>
-<li>Agents/code mode: preserve agent, session, run, and channel context in <code>before_tool_call</code> hooks for top-level <code>exec</code>/<code>wait</code> dispatches. Fixes #83387.</li>
-<li>QQBot: shorten C2C typing indicators to a 10-second window renewed every 5 seconds, capped to keep a final passive-reply slot available. (#83469)</li>
-<li>Replies: keep final payload delivery after live preview updates so channels can finalize or send the completed answer instead of losing preview-only drafts. (#83468)</li>
-<li>Discord: deliver final replies in progress-mode preview streams instead of deduplicating the final visible message. (#83443) Thanks @compoodment.</li>
-<li>Providers/Xiaomi: replay MiMo Anthropic-compatible <code>reasoning_content</code> as provider-required thinking blocks even when OpenClaw thinking is disabled, fixing follow-up tool turns for <code>mimo-v2-flash</code>. Fixes #83407. Thanks @Xgenious7.</li>
-<li>Agents/exec approvals: forward approval-runtime credentials on agent-owned Gateway approval calls so approved async commands complete through the existing runtime path instead of stalling on unauthenticated follow-up calls. Thanks @IWhatsskill, @Patrick-Erichsen, and @jesse-merhi.</li>
-<li>Gateway/skills: preflight remote macOS skill-bin refreshes with a WebSocket connectivity check so stale node sessions skip quickly instead of logging slow <code>system.which</code> timeout warnings.</li>
-<li>CLI/config: keep broken discovered plugins that are not referenced by active config from failing <code>openclaw config validate</code>, while preserving fatal errors for explicitly configured plugin entries.</li>
-<li>GitHub Copilot: drop unsafe native Responses reasoning replay items with non-replayable IDs before dispatch, preventing affected Copilot sessions from failing with <code>invalid_request_body</code>. Fixes #83220. Thanks @galiniliev.</li>
-<li>Agents/Codex: fail closed when an explicitly requested Codex harness is not registered instead of silently trying configured model fallbacks. Fixes #83349. Thanks @r2-vibes.</li>
-<li>QA-Lab: make runtime tool coverage fail on missing required tool exercise instead of treating pass/pass parity envelope drift as missing coverage.</li>
-<li>Core/plugins: harden clawpatch-reported edge cases across gateway auth cleanup, Claude session id paths, plugin activation policy, apply-patch hunk handling, diagnostic redaction, and plugin metadata validation.</li>
-<li>UI: show reasoning choices as plain labels instead of leaking internal override wording in session and chat pickers.</li>
-<li>Mac app: avoid repeating the Configuration heading inside channel quick settings.</li>
-<li>Mac app: keep the Settings sidebar always visible and remove the redundant titlebar hide/show control.</li>
-<li>Mac app: normalize Settings pane content margins so pages share the same left and right rail.</li>
-<li>Mac app: prefer explicit private/Tailscale/LAN Gateway endpoints over SSH tunnels, preserve legacy loopback tunnel configs, persist transport choices, and show captured SSH stderr when tunneling really fails.</li>
-<li>Gateway/sessions: keep ACP/acpx and runtime child sessions visible in configured-only session lists when their owner or parent session belongs to a configured agent.</li>
-<li>Mac app: keep app-level menu commands and Dashboard failure states reachable when the remote Gateway is disconnected.</li>
-<li>Mac app: allow longer Gateway and Context errors to wrap in the menu instead of truncating the useful failure detail.</li>
-<li>Mac app: tighten remote Gateway fields in Settings so the Connection pane keeps readable labels and full action button text.</li>
-<li>Mac app: keep custom Settings card rows left-aligned and full-width so Discovery and status sections no longer appear centered or detached.</li>
-<li>Mac app: align Location permission controls to the same trailing column as the rest of Settings.</li>
-<li>Mac app: add Dashboard, Chat, Canvas, and Settings shortcuts to the Dock icon menu.</li>
-<li>Mac app: replace the Settings window's native split-view sidebar with an explicit layout so page content keeps its leading gutter when the sidebar is shown or hidden.</li>
-<li>Mac app: render channel quick config as aligned Settings rows and hide schema-only variants that cannot be edited safely from the quick pane.</li>
-<li>Gateway/webchat: hide internal runtime-context and other <code>display: false</code> transcript messages from Chat history and live message events. Fixes #83216. Thanks @EmpireCreator.</li>
-<li>CLI/help: keep <code>gateway</code>, <code>doctor</code>, <code>status</code>, and <code>health</code> help registration out of action/runtime imports so subcommand <code>--help</code> stays lightweight in constrained terminals. Fixes #83228. Thanks @dfguerrerom.</li>
-<li>CLI/help: show plugin-owned command help based on the active memory slot so LanceDB memory users see <code>ltm</code> instead of unavailable <code>memory</code> commands. Fixes #83745. (#83841) Thanks @joshavant.</li>
-<li>Cron/Discord: keep explicit announce runs in message-tool-only source-reply mode so scheduled agent turns post once instead of also echoing through automatic visible replies. Fixes #83261. Thanks @Theralley.</li>
-<li>Telegram: preserve forum-topic origin targets in inbound, audio-preflight, and skipped-message hook contexts so follow-up delivery stays bound to the originating topic. Fixes #83302. Thanks @M00zyx.</li>
-<li>Telegram: retry HTTP 421 Misdirected Request send failures on a fresh fallback transport so transient edge-node routing errors no longer drop outbound replies. Fixes #48892. (#48908) Thanks @MarsDoge.</li>
-<li>Telegram: fail topic sends closed when Telegram reports <code>message thread not found</code> instead of retrying without <code>message_thread_id</code> into the base chat. Refs #83302.</li>
-<li>Config/subagents: remove ignored agent-model <code>timeoutMs</code> keys, keep subagent model config to primary/fallback selection, and clean shipped stale config through doctor. Fixes #83291. Thanks @giodl73-repo.</li>
-<li>Mac app: align the Sessions settings pane with the standard Settings page gutter and row spacing.</li>
-<li>OpenAI/Codex: stop rejecting available <code>openai-codex</code> GPT-5.1, GPT-5.2, and GPT-5.3 model refs during config validation, while keeping removed Spark aliases suppressed. Fixes #83303.</li>
-<li>Plugins/xAI: complete OAuth-backed xAI login and sidecar auth fixes, including guarded loopback callback CORS handling, video generation polling/defaults, and native-host User-Agent attribution. (#83322) Thanks @Jaaneek.</li>
-<li>Codex app-server: preserve streamed native command output in mirrored transcripts and trajectory exports when final snapshots omit aggregated output. (#83200) Thanks @rozmiarD.</li>
-<li>Codex app-server: fail closed when chat or sender policy denies tools, disabling native code, app, environment, and user MCP surfaces for restricted turns. (#82374) Thanks @VACInc.</li>
-<li>Codex app-server: keep recent context-engine messages when oversized projected history is truncated, so short follow-ups in long channel sessions do not fall back to stale earlier turns. (#83127) Thanks @VACInc.</li>
-<li>Codex app-server: keep OpenClaw session spawning searchable while steering Codex-native delegation through native subagents, avoiding duplicate direct subagent surfaces. (#83329) Thanks @fuller-stack-dev.</li>
-<li>Codex app-server: recover stale childless Codex-native subagent task mirrors during maintenance and allow their registry rows to be cancelled without an OpenClaw child session. (#82836) Thanks @yshimadahrs-ship-it and @joshavant.</li>
-<li>Feishu: return bound subagent delivery origins from session thread setup so Feishu subagent completions route back to the same DM or topic. (#83190) Thanks @100menotu001.</li>
-<li>CLI/update: tailor post-update Gateway recovery hints by platform, showing systemd, LaunchAgent, Scheduled Task, or generic service-manager guidance instead of macOS-only recovery text. (#83096) Thanks @rubencu.</li>
-<li>Plugins: apply a default 15-second timeout to legacy <code>before_agent_start</code> hooks so hung plugin handlers no longer block agent startup. Fixes #48534. (#83136) Thanks @therahul-yo.</li>
-<li>Feishu: refresh inbound session delivery context for DM, group, and broadcast turns so later replies do not inherit stale WebChat routing. Fixes #78274.</li>
-<li>Agents/subagents: require the initial subagent registry save before reporting spawn accepted, returning a spawn error instead of losing an untracked run when the registry write fails. (#83146) Thanks @yetval.</li>
-<li>QA-Lab/qa-channel: attach redacted agent tool-start traces to outbound <code>QaBusMessage</code> records so scenarios can assert actual tool use instead of relying only on reply text. Fixes #67637. Thanks @100yenadmin.</li>
-<li>QA-Lab: fail live runtime parity reports when assistant-message usage is missing, preventing <code>0 vs 0</code> live token rows from being reported as passing proof. Fixes #80411. Thanks @100yenadmin.</li>
-<li>QA-Lab: add a runtime token-efficiency sidecar report that classifies Codex savings separately from regressions and fails only positive Codex-over-Pi live token deltas above threshold. Fixes #81093. Thanks @100yenadmin.</li>
-<li>QA-Lab: fail Codex-backed OpenAI live runtime-pair runs before launching isolated workers when no portable Codex auth is available, while staging API-key fallbacks and configured Codex keys for isolated QA agents. Fixes #80412. Thanks @100yenadmin.</li>
-<li>QA-Lab: refresh parity gates, mock frontier fixtures, model scenarios, and workflow artifact lanes to compare GPT-5.5 against Claude Opus 4.7. Fixes #74262. Thanks @100yenadmin.</li>
-<li>QA-Lab: make mock parity dispatch provider-aware for source discovery and subagent scenarios so OpenAI and Anthropic lanes no longer share identical canned plans. Fixes #64879. Thanks @100yenadmin.</li>
-<li>QA-Lab: stop returning Control UI bearer tokens from unauthenticated bootstrap payloads and bind Docker harness ports to loopback-only host addresses. (#66355) Thanks @pgondhi987.</li>
-<li>Mac app: avoid a SwiftUI metadata crash when rendering the Cron Jobs settings pane.</li>
-<li>Agents/subagents: preserve run-mode keep subagent registry entries past the session sweep TTL, so kept subagent runs remain visible after cleanup completes. Fixes #83132. (#83168) Thanks @yetval.</li>
-<li>Agents/OpenAI streams: yield via <code>setTimeout(0)</code> instead of <code>setImmediate</code> between bursty Responses chunks so abort timers can fire during the yield, keeping cancel-on-timeout responsive on hot streams. Refs #82462.</li>
-<li>Agents/Codex: keep legacy <code>oauthRef</code>-backed OAuth profiles usable while <code>openclaw doctor --fix</code> migrates them back to inline credentials, without creating new sidecar credentials. (#83312) Thanks @joshavant.</li>
-<li>Agents/Codex: load the selected provider owner alongside the Codex harness runtime so <code>openai-codex</code> models resolve when plugin allowlists scope runtime loading. Fixes #83380. (#83519) Thanks @joshavant.</li>
-<li>Telegram: fail stalled isolated-ingress handlers into tombstones and abort same-lane reply work before restarting, so later same-chat updates drain after a hung turn. Fixes #83272. (#83505) Thanks @joshavant.</li>
-<li>CLI/config: send SecretRef diagnostics to stderr so JSON command stdout remains parseable.</li>
-<li>CLI/doctor: seed Control UI allowed origins when migrating legacy non-loopback gateway bind host aliases like <code>0.0.0.0</code>. Fixes #83286. Thanks @giodl73-repo.</li>
-<li>CLI/plugins: ship the bundled memory CLI as a package entry so package-installed <code>openclaw memory</code> commands register correctly.</li>
-<li>CLI/update: defer doctor-time plugin package installs during package swaps and seed post-core repair from the updated install registry, preventing duplicate reinstall failures.</li>
-<li>CLI/update: preserve old-parent-readable config metadata during legacy package handoffs, fall back only to official <code>@openclaw/*</code> npm plugin packages when ClawHub plugin artifacts are unavailable, and keep managed service package roots authoritative during updates.</li>
-<li>Feishu: detect SecretRef top-level credentials as a configured default account instead of treating object-backed app secrets as missing.</li>
-<li>Gateway/restart: keep ordinary unmanaged SIGUSR1/config restarts in-process instead of detach-spawning an orphaned child, preserving custom supervisor PID tracking while leaving update restarts on the fresh-process path. Fixes #65668.</li>
-<li>CLI/completion: resolve concrete PowerShell profile paths and reload commands during setup and doctor completion installation. Fixes #44296. (#83059) Thanks @yu-xin-c.</li>
-<li>Telegram: keep isolated long polling below the hard <code>getUpdates</code> request guard so idle bot accounts with high <code>timeoutSeconds</code> do not false-disconnect and restart-loop. Fixes #83264. Thanks @riccodecarvalho.</li>
-<li>Providers/Google: preserve and recover Gemini 3 tool-call thought signatures during native replay so function-calling turns no longer fail with missing <code>thought_signature</code> 400s. Fixes #72879. (#80358) Thanks @abnershang.</li>
-<li>Telegram: skip transcript-only delivery mirrors and gateway-injected rows when resolving latest assistant text, preventing retained previews from replacing final replies with stale fragments. Fixes #83159. (#83362) Thanks @joshavant.</li>
-<li>Memory/QMD: keep lexical search on raw hyphenated queries while normalizing semantic QMD sub-searches, avoiding fallback to the builtin index for dashed identifiers and dates. Fixes #81328.</li>
-<li>Memory-core: distinguish sqlite-vec load failures from missing semantic vector embeddings in degraded <code>memory index</code> warnings, so vector recall diagnostics point at unresolved dimensions instead of blaming sqlite-vec when the store is ready. Fixes #75624. (#83056) Thanks @xuruiray and @Noah3521.</li>
-<li>Agents/subagents: preserve sandbox-peer controller ownership while routing completion announcements back to the originating run session, keeping subagent control and completion delivery scoped correctly. Fixes #80201. (#80242) Thanks @Jerry-Xin.</li>
-<li>Gateway: continue restarting remaining channels when one hot-reload channel restart fails, while still reporting aggregate reload failure and rolling back plugin pre-replace stops. Fixes #83054. Thanks @zqchris.</li>
-<li>Gateway/plugins: bind admin HTTP RPC dispatch to the accepting gateway instance so multi-gateway processes cannot execute plugin HTTP control-plane calls against another live gateway. Fixes #83486. (#83487) Thanks @coygeek.</li>
-<li>Telegram: keep hot-reload restarts from marking polling accounts manually stopped and restart isolated ingress cleanly after worker shutdown, preserving Telegram replies across config reloads. Fixes #83008. (#83410) Thanks @joshavant.</li>
-<li>Telegram/Ollama: pass current Telegram image attachments into native PI/Ollama vision turns so live photo prompts reach Ollama as native images. Fixes #83023. (#83516) Thanks @joshavant.</li>
-<li>Gateway/secrets: split the lightweight secrets runtime state and auth-store cache from the full secrets runtime and take a startup fast path when the gateway startup config has no SecretRef values, speeding up secrets startup while preserving cleanup and refresh semantics.</li>
-<li>Codex app-server: rotate oversized native Codex threads before resume and cap dynamic tool-result text entering native Codex sessions, preventing stale oversized context from surviving OpenClaw compaction. (#82981) Thanks @hansolo949.</li>
-<li>Gateway/restart: drain pending replies and active chat runs during restart shutdown before sockets and channels close, aborting timed-out chat runs through the normal cleanup path. (#69121) Thanks @alexlomt.</li>
-<li>Agents/Codex: use the Codex runtime context window for OpenAI-model preflight compaction and memory flush checks, so GPT-5.5 Codex sessions compact before hitting the smaller native context limit. Fixes #82982. Thanks @vliuyt.</li>
-<li>QA-Lab: clean orphaned gateway temp roots when a suite parent exits and wait on gateway plus transport readiness after config restarts, reducing stale <code>qa-channel</code> noise from interrupted runs. Fixes #65506. Thanks @100yenadmin.</li>
-<li>QA-Lab: wake qa-bus long polls that arrive with stale future cursors after a bus restart, preserving reconnect readiness for harness clients. (#67142) Thanks @hxy91819.</li>
-<li>QA-Lab: stage Multipass transfer scripts under OpenClaw's preferred temp root instead of raw OS temp paths, keeping the VM runner inside temp-path guardrails. (#64098) Thanks @ImLukeF.</li>
-<li>Agents/replies: keep surviving reply media and append a warning when other media references fail, so partial media normalization no longer drops failures silently. Thanks @Jerry-Xin.</li>
-<li>Config/models: accept <code>thinkingFormat: "together"</code> in model compat config so Together routes can opt into the Together-specific thinking response shape.</li>
-<li>Plugins/tokenjuice: bump the bundled tokenjuice runtime to 0.7.1, bringing Codex hook approval compatibility, pre-tool command wrapping fixes, and Rolldown/Vitest output compaction improvements into the OpenClaw plugin.</li>
-<li>Agents/OpenAI: stop post-processing GPT-5 final replies with hardcoded brevity caps, preserving full channel responses instead of appending synthetic ellipses, and log when strict-agentic GPT-5 execution activates. Fixes #82910.</li>
-<li>Mac app: refine the Settings General and Connection panes with cleaner status panels, card rows, and a single native titlebar sidebar toggle.</li>
-<li>Agents/media: deliver failed async image, music, and video generation completions directly when requester-session completion handoff fails, so channel users see provider errors instead of silent fallback stalls.</li>
-<li>Browser/CDP: keep loopback proxy bypass active across both <code>NO_PROXY</code> casings and redact home-relative Chrome MCP profile paths in attach-failure diagnostics.</li>
-<li>Agents/music: steer song, jingle, beat, anthem, and instrumental requests toward <code>music_generate</code> audio creation instead of lyric-only replies, and reserve <code>lyrics</code> for exact sung words.</li>
-<li>Codex app-server: record native Codex tool calls and results into trajectory artifacts so debug/trajectory exports capture the full Codex-native tool history, not just OpenClaw-bridged turns. Thanks @vyctorbrzezowski.</li>
-<li>Codex/app-server: keep bound conversation sessions on the owning agent runtime so native Codex control and follow-up turns do not fall back to the default agent client. Fixes #82954. (#82993)</li>
-<li>CLI/infer: run gateway model probes in fresh explicit sessions so one-shot provider checks do not inherit default agent transcript state. (#82861) Thanks @Kaspre.</li>
-<li>Providers/Together: send video-generation requests to Together's v2 video API even when shared text-model config still points at the v1 base URL. (#82992)</li>
-<li>Browser CLI: preserve browser-level options on nested commands, skip option values during lazy command registration, and keep long-running wait/download/dialog hooks open for their advertised wait window.</li>
-<li>CLI/sessions: accept <code>openclaw sessions list</code> as an alias for <code>openclaw sessions</code>, matching other list-style commands. Fixes #81139. (#81163) Thanks @YB0y.</li>
-<li>Channels/stream previews: widen compact progress draft lines and cut prose at word boundaries while preserving command/path suffixes, with <code>streaming.progress.maxLineChars</code> for channel-specific tuning.</li>
-<li>CLI/plugins: have <code>openclaw plugins doctor</code> warn when a configured runtime needs a missing owner plugin, sharing the same install mapping as <code>openclaw doctor --fix</code>. Fixes #81326. (#81674) Thanks @Zavianx.</li>
-<li>Agents/Codex: route OpenAI runs that resolve to <code>openai-codex</code> through the Codex provider and bootstrap OpenClaw's stored OAuth profile into the Codex harness when the harness owns transport, so <code>openai/*</code> model refs no longer fail with <code>No API key found for openai-codex</code> despite an existing Codex OAuth profile. (#82864) Thanks @ragesaq.</li>
-<li>Agents/ACP: distinguish prompt-submitted and runtime-active child stalls from true interactive waits, including redacted proxy-env diagnostics for Codex ACP no-output runs. Fixes #44810.</li>
-<li>Agents/memory: explain that memory-triggered compaction exposes only <code>read</code> and append-only <code>write</code> when configured core tools are unavailable in <code>tools.allow</code> warnings. Fixes #82941. Thanks @galiniliev.</li>
-<li>Agents/OpenAI: preserve deterministic tool payload ordering for prompt-cache reuse across OpenAI Responses and chat completions calls. (#82940) Thanks @galiniliev.</li>
-<li>ACP/Codex: honor terminal ACP turn results so failed Codex/acpx runs are not recorded as successful after only progress text. Fixes #79522. Thanks @dudaefj.</li>
-<li>Telegram: warn when a media group drops photos that fail to download, including albums where every photo is skipped. Fixes #55216. (#82987) Thanks @eldar702.</li>
-<li>Agents/diagnostics: treat repeated same-handle embedded-run cleanup as idempotent while preserving true replacement-handle mismatch diagnostics. Fixes #82959. (#82960) Thanks @galiniliev.</li>
-<li>Agents/subagents: preserve high-priority <code>AGENTS.md</code> policy in bootstrap context when oversized files are trimmed, and warn agents to read the full policy file before relying on scoped rules. Fixes #82920. (#82921) Thanks @galiniliev.</li>
-<li>Agents/skills: apply the full effective tool policy pipeline to inline <code>command-dispatch: tool</code> skill dispatch before owner-only filtering, preserving configured allow, deny, sandbox, sender, group, and subagent restrictions. (#78525)</li>
-<li>Codex: avoid spawning native hook relay subprocesses for post-tool/finalize events with no registered hook handlers while preserving pre-tool safety and approval relays. Fixes #76552. (#78004) Thanks @evgyur.</li>
-<li>Channel accounts: keep top-level default channel accounts visible when named accounts are added alongside default credential material, so mixed legacy/new account configs keep resolving <code>default</code> instead of silently dropping it.</li>
-<li>Agents/CLI: reject empty successful CLI subprocess replies as <code>empty_response</code> and keep them out of shared auth-profile health, so blank Claude CLI results no longer become green no-payload turns. Fixes #83231. (#83421) Thanks @joshavant.</li>
-<li>Codex/Telegram: synthesize native Codex tool progress from final turn snapshots so Telegram <code>/verbose</code> stays visible when command events arrive only at completion.</li>
-<li>Codex/Telegram: deliver Codex verbose tool summaries in direct message-tool-only turns while suppressing message-send and activity-log noise. (#83186) Thanks @kurplunkin.</li>
-<li>Mac app: make Channels settings open faster by deferring config-schema work, avoiding startup channel probes, caching decoded channel status rows, and showing only compact quick settings instead of the full generated channel schema.</li>
-<li>Control UI: include the Control UI and Gateway protocol versions in protocol-mismatch errors so stale app/dashboard pairings identify which side needs rebuilding or restarting.</li>
-<li>Gateway/protocol: restore Gateway WS protocol v4 and keep <code>message.action</code> room-event metadata on the existing <code>inboundTurnKind</code> wire field while preserving internal inbound-event classification.</li>
-<li>Agents/tools: prefer non-webchat session-key routes when the message tool has stale webchat context, so message-tool-only replies keep delivering to the originating channel. Fixes #82911. (#83004) Thanks @joshavant.</li>
-<li>Channels: keep direct-message last-route writes on isolated <code>per-channel-peer</code> sessions instead of contaminating the agent main session with channel delivery context. Fixes #36614. Thanks @aspenas.</li>
-<li>Mac app: move the Settings sidebar toggle into the native titlebar and tighten the General pane width.</li>
-<li>Mac app: keep visited Settings panes mounted so switching tabs no longer blanks and reloads their content.</li>
-<li>Mac app: make Config settings open from shallow schema lookups and load selected paths on demand instead of fetching and rendering the full generated config schema up front.</li>
-<li>Codex: sanitize inline image payloads before Codex app-server and OpenAI Responses replay, and clear poisoned Codex thread bindings after invalid image errors. Fixes #82878.</li>
-<li>Providers/GitHub Copilot: request identity-encoded Copilot API responses across token exchange, catalog, model calls, usage, and embeddings so compressed Business-account error payloads no longer reach JSON parsers as gzip bytes. Fixes #82871. Thanks @tonyfe01.</li>
-<li>Telegram: redact nested raw-update identifiers and user metadata before verbose raw update logging, preserving useful update/message ids without exposing chat, user, command, or profile details. (#82945) Thanks @galiniliev and @joshavant.</li>
-<li>Telegram: preserve replied-to bot messages, captions, and media metadata in group reply chains so follow-up replies understand what the user is reacting to. (#82863)</li>
-<li>Providers/Together: update PI runtime packages to 0.74.1 and emit Together-style <code>reasoning.enabled</code>/<code>max_tokens</code> controls for reasoning-capable OpenAI-completions models.</li>
-<li>Agents/diagnostics: split slow embedded-run <code>attempt-dispatch</code> startup summaries into workspace, prompt, runtime-plan, and final dispatch subspans so traces identify the delayed setup phase. Fixes #82782. (#82783) Thanks @galiniliev.</li>
-<li>Agents/Codex: flatten nested tool-result middleware blocks into bounded text so successful message sends are no longer replaced with <code>Tool output unavailable due to post-processing error</code>. Fixes #82912. Thanks @joeykrug.</li>
-<li>CLI/media: accept HTTP(S) URLs in <code>openclaw infer image describe --file</code>, fetching remote images through the guarded media path instead of treating URLs as local files. Fixes #82837. (#82854) Thanks @neeravmakwana.</li>
-<li>Agents/subagents: keep session-backed parent runs active when the child wait call times out before the child session has actually settled, so late subagent completions are reconciled instead of being lost. Fixes #82787. Thanks @ramitrkar-hash.</li>
-<li>Control UI: advertise shared Gateway protocol constants in browser connect frames, fixing protocol mismatch handshakes after protocol constant drift. Fixes #82882. Thanks @galiniliev.</li>
-<li>Gateway: add rollback protocol-mismatch diagnostics, including client protocol ranges in Gateway logs and deep status/doctor hints for stale client processes. Fixes #82841. (#82908)</li>
-<li>Agents/subagents: keep successful keep-mode completion payloads pending after final-delivery retry exhaustion, so requester recovery no longer loses final subagent results. Fixes #82583. (#82999) Thanks @joshavant.</li>
-<li>Gateway/auth: allow same-host trusted-proxy callers to use the documented local direct <code>gateway.auth.password</code> fallback after revisiting the #78684 fail-closed policy, while keeping token fallback rejected and forwarded-header requests on the trusted-proxy path. Fixes #82607. (#82953) Thanks @joshavant.</li>
-<li>Agents/subagents: wait for queued completion handoffs to reach the parent transcript before marking them announced, preventing busy parent runs from cleaning up before observing child results. Fixes #82913. (#83039) Thanks @joshavant.</li>
-<li>Agents/subagents: route group/channel subagent completions through message-tool-only handoffs when required and keep active-requester wake failures from dropping completion delivery. Fixes #82803. Thanks @galiniliev, @yozakura-ava, and @moeedahmed.</li>
-<li>Memory-core: scan persisted memory source sessions on startup, comparing on-disk transcripts against the index and marking only missing/newer/resized files dirty for incremental sync. Fixes #82341. (#82341) Thanks @giodl73-repo.</li>
-<li>Telegram: keep the top-level default account in the account list when named accounts or bindings are added alongside top-level credentials, preserving default polling while still letting named-only configs resolve to a single account. Fixes #82794. (#82794) Thanks @giodl73-repo.</li>
-<li>CLI/models: reuse command-scoped plugin metadata across model listing, provider catalog, auth, and synthetic-auth checks, restoring fast <code>openclaw models</code> runs for plugin-heavy installs. Fixes #82881. (#83033) Thanks @joshavant.</li>
-<li>CLI/channels: show configured official external channels such as Discord in <code>openclaw channels list</code> when their plugin package is missing, including the install and doctor repair command instead of reporting no configured channels. Fixes #82813.</li>
-<li>Signal: preserve mixed-case group IDs through routing and session persistence so group auto-replies keep delivering after updates. Fixes #82827.</li>
-<li>Agents/tools: keep the <code>message</code> tool available in embedded runs when it is explicitly allowed through <code>tools.alsoAllow</code> or runtime tool allowlists, so channel plugins with custom reply delivery can still use configured message sends. Fixes #82833. Thanks @cn1313113.</li>
-<li>WhatsApp: honor forced document delivery for outbound image, GIF, and video media so <code>forceDocument</code>/<code>asDocument</code> sends preserve original media bytes instead of using compressed media payloads. (#79272) Thanks @itsuzef.</li>
-<li>WhatsApp: name outbound document attachments from their MIME type when no filename is provided, so PDF and CSV sends arrive as <code>file.pdf</code> and <code>file.csv</code> instead of an extensionless <code>file</code>. Thanks @mcaxtr.</li>
-<li>Process/diagnostics: report active lane blockers in lane wait warnings so <code>queueAhead=0</code> no longer hides commands waiting behind active work. Fixes #82791. (#82792) Thanks @galiniliev.</li>
-<li>Process/diagnostics: stop counting the active processing turn as queued backlog in liveness warnings so transient max-only event-loop spikes do not surface as gateway warnings.</li>
-<li>Agents/replies: classify provider conversation-state rejections and return a clear message-channel error instead of auto-resetting or falling back to a generic runner failure. (#82616) Thanks @dutifulbob.</li>
-<li>Browser plugin: trust managed Chrome CDP diagnostics when launch HTTP probes race cold-start readiness, avoiding false startup failures. Fixes #82904. (#82986) Thanks @kmanan and @hclsys.</li>
-<li>Android: prompt before replacing a changed Gateway TLS thumbprint, showing the old and new SHA-256 fingerprints so users can accept expected certificate rotations instead of hard failing on pin mismatch. (#83077) Thanks @sliekens.</li>
-<li>CLI/status: render extra gateway-like service diagnostics as warning/info output instead of error output. Fixes #46930. (#82922) thanks @giodl73-repo.</li>
-<li>Agents/failover: classify Moonshot/Kimi exhausted-balance HTTP 429 payloads as billing instead of generic rate limits, preserving billing guidance and fallback behavior. Fixes #43447. (#83079) Thanks @leno23.</li>
-<li>Plugin SDK: bundle <code>openclaw/plugin-sdk/zod</code> into the published package artifact and verify the packed zod subpath stays self-contained, so pnpm global installs can register plugins without a package-local <code>zod</code> symlink. Fixes #78398. (#78515) Thanks @ggzeng.</li>
-<li>Providers/Google: drop compaction-truncated Gemini thought signatures before replay so malformed Base64 no longer aborts the next assistant turn. (#82995) Thanks @wAngByg.</li>
-<li>Gateway/mobile: allow paired iOS and Android clients to refresh same-family OS metadata on authenticated reconnect instead of requiring a new approval. (#83490) Thanks @ngutman.</li>
-<li>WhatsApp: treat <code>upload-file</code> as a supported media send intent by lowering path/URL uploads through the channel's normal send-media transport. (#81883) Thanks @ngutman.</li>
-<li>iOS: end Live Activities when OpenClaw is connected, idle, or disconnected, and show compact attention states for approval-required reconnects. (#83597) Thanks @ngutman.</li>
-<li>Control UI: hide child nav items when collapsing the active sidebar group. Fixes #42167. (#42223) Thanks @Aroool.</li>
-<li>CI/proof: skip the real-behavior-proof gate for private org maintainers by minting a least-privilege (<code>members: read</code>) GitHub App token and checking active membership in the <code>maintainer</code> team, instead of treating <code>author_association=CONTRIBUTOR</code> as definitively external. (#83418) Thanks @romneyda.</li>
-</ul>
-<p><a href="https://github.com/openclaw/openclaw/blob/main/CHANGELOG.md">View full changelog</a></p>
-]]></description>
-            <enclosure url="https://github.com/openclaw/openclaw/releases/download/v2026.5.19/OpenClaw-2026.5.19.zip" length="54062201" type="application/octet-stream" sparkle:edSignature="7bVi6rv+TjhrUfi32V62BW2VgyV17jm7x+H6p10PRClCdXKZjhM7AX6MyvAz2+e7kzXIknj1Y9X7q43/E9fBBw=="/>
-        </item>
     </channel>
 </rss>

apps/android/app/build.gradle.kts

@@ -65,8 +65,8 @@ android {
     applicationId = "ai.openclaw.app"
     minSdk = 31
     targetSdk = 36
-    versionCode = 2026052500
-    versionName = "2026.5.25"
+    versionCode = 2026052801
+    versionName = "2026.5.28"
     ndk {
       // Support all major ABIs — native libs are tiny (~47 KB per ABI)
       abiFilters += listOf("armeabi-v7a", "arm64-v8a", "x86", "x86_64")

apps/android/app/src/debug/AndroidManifest.xml

@@ -0,0 +1,14 @@
+<manifest xmlns:android="http://schemas.android.com/apk/res/android">
+    <application>
+        <receiver
+            android:name=".VoiceE2eReceiver"
+            android:exported="true">
+            <intent-filter>
+                <action android:name="ai.openclaw.app.debug.RUN_VOICE_E2E" />
+            </intent-filter>
+        </receiver>
+        <service
+            android:name=".VoiceE2eService"
+            android:exported="false" />
+    </application>
+</manifest>

apps/android/app/src/debug/java/ai/openclaw/app/VoiceE2eReceiver.kt

@@ -0,0 +1,195 @@
+package ai.openclaw.app
+
+import android.app.Service
+import android.content.BroadcastReceiver
+import android.content.Context
+import android.content.Intent
+import android.os.IBinder
+import android.util.Base64
+import android.util.Log
+import kotlinx.coroutines.CoroutineScope
+import kotlinx.coroutines.Dispatchers
+import kotlinx.coroutines.SupervisorJob
+import kotlinx.coroutines.cancel
+import kotlinx.coroutines.delay
+import kotlinx.coroutines.launch
+import kotlinx.coroutines.withTimeout
+import kotlinx.serialization.json.JsonNull
+import kotlinx.serialization.json.JsonPrimitive
+import kotlinx.serialization.json.buildJsonObject
+import java.io.File
+
+private const val tag = "VoiceE2E"
+private const val resultFileName = "voice_e2e_result.json"
+
+class VoiceE2eReceiver : BroadcastReceiver() {
+  override fun onReceive(
+    context: Context,
+    intent: Intent,
+  ) {
+    context.startService(
+      Intent(context, VoiceE2eService::class.java)
+        .putExtras(intent),
+    )
+  }
+}
+
+class VoiceE2eService : Service() {
+  private val serviceScope = CoroutineScope(SupervisorJob() + Dispatchers.IO)
+
+  override fun onBind(intent: Intent?): IBinder? = null
+
+  override fun onStartCommand(
+    intent: Intent?,
+    flags: Int,
+    startId: Int,
+  ): Int {
+    val command = intent ?: return START_NOT_STICKY
+    serviceScope.launch {
+      try {
+        runCommand(command)
+      } finally {
+        stopSelf(startId)
+      }
+    }
+    return START_NOT_STICKY
+  }
+
+  override fun onDestroy() {
+    serviceScope.cancel()
+    super.onDestroy()
+  }
+
+  private suspend fun runCommand(intent: Intent) {
+    try {
+      val app = applicationContext as NodeApp
+      val runtime = app.ensureRuntime()
+      val mode =
+        intent
+          .getDecodedStringExtra("mode")
+          ?.trim()
+          .orEmpty()
+          .ifEmpty { "both" }
+      if (mode == "stop") {
+        runtime.cancelMicCapture()
+        runtime.setTalkModeEnabled(false)
+        writeResult("""{"ok":true,"mode":"stop"}""")
+        return
+      }
+
+      val connect = !intent.getBooleanExtra("noConnect", false)
+      val connectTimeoutMs = intent.getLongExtra("connectTimeoutMs", 20_000L)
+      if (connect) {
+        configureGateway(runtime = runtime, intent = intent)
+      }
+      if (connect || !runtime.isConnected.value) {
+        awaitGateway(runtime = runtime, timeoutMs = connectTimeoutMs)
+      }
+
+      startActivity(
+        Intent(actionOpenVoiceE2e)
+          .setClass(this, MainActivity::class.java)
+          .addFlags(Intent.FLAG_ACTIVITY_NEW_TASK or Intent.FLAG_ACTIVITY_SINGLE_TOP or Intent.FLAG_ACTIVITY_CLEAR_TOP),
+      )
+
+      if (mode == "connect") {
+        val resultJson = """{"ok":true,"mode":"connect","connected":true}"""
+        writeResult(resultJson)
+        Log.i(tag, "PASS $resultJson")
+        return
+      }
+
+      val transcript =
+        intent
+          .getDecodedStringExtra("transcript")
+          ?.trim()
+          .orEmpty()
+          .ifEmpty { "Reply exactly: Android voice e2e normal path ok." }
+      val realtimeReply =
+        intent
+          .getDecodedStringExtra("realtimeAssistant")
+          ?.trim()
+          .orEmpty()
+          .ifEmpty { "Android realtime voice e2e relay path ok." }
+      val timeoutMs = intent.getLongExtra("timeoutMs", 60_000L)
+      val result =
+        runtime.runVoiceE2e(
+          mode = mode,
+          transcript = transcript,
+          realtimeAssistantText = realtimeReply,
+          timeoutMs = timeoutMs,
+        )
+      val resultJson = encodeResult(result)
+      writeResult(resultJson)
+      Log.i(tag, "PASS $resultJson")
+    } catch (err: Throwable) {
+      val resultJson =
+        buildJsonObject {
+          put("ok", JsonPrimitive(false))
+          put("error", JsonPrimitive(err.message ?: err::class.java.simpleName))
+        }.toString()
+      writeResult(resultJson)
+      Log.e(tag, "FAIL $resultJson", err)
+    }
+  }
+
+  private fun configureGateway(
+    runtime: NodeRuntime,
+    intent: Intent,
+  ) {
+    val host =
+      intent
+        .getDecodedStringExtra("host")
+        ?.trim()
+        .orEmpty()
+        .ifEmpty { "127.0.0.1" }
+    val port = intent.getIntExtra("port", 18789)
+    runtime.setManualEnabled(true)
+    runtime.setManualHost(host)
+    runtime.setManualPort(port)
+    runtime.setManualTls(intent.getBooleanExtra("tls", false))
+    runtime.setGatewayToken(intent.getDecodedStringExtra("token").orEmpty())
+    runtime.setGatewayBootstrapToken(intent.getDecodedStringExtra("bootstrapToken").orEmpty())
+    runtime.setGatewayPassword(intent.getDecodedStringExtra("password").orEmpty())
+    runtime.setOnboardingCompleted(true)
+    runtime.connectManual()
+  }
+
+  private suspend fun awaitGateway(
+    runtime: NodeRuntime,
+    timeoutMs: Long,
+  ) {
+    withTimeout(timeoutMs) {
+      while (!runtime.isConnected.value) {
+        delay(100L)
+      }
+    }
+  }
+
+  private fun encodeResult(result: NodeRuntime.VoiceE2eResult): String =
+    buildJsonObject {
+      put("ok", JsonPrimitive(true))
+      put("normal", result.normal?.let(::encodeSlice) ?: JsonNull)
+      put("realtime", result.realtime?.let(::encodeSlice) ?: JsonNull)
+    }.toString()
+
+  private fun encodeSlice(slice: NodeRuntime.VoiceE2eSliceResult) =
+    buildJsonObject {
+      put("mode", JsonPrimitive(slice.mode))
+      put("status", JsonPrimitive(slice.status))
+      put("userText", slice.userText?.let(::JsonPrimitive) ?: JsonNull)
+      put("assistantText", slice.assistantText?.let(::JsonPrimitive) ?: JsonNull)
+    }
+
+  private fun writeResult(json: String) {
+    File(cacheDir, resultFileName).writeText(json)
+  }
+}
+
+private fun Intent.getDecodedStringExtra(name: String): String? {
+  val encoded = getStringExtra("${name}Base64")
+  if (!encoded.isNullOrBlank()) {
+    return String(Base64.decode(encoded, Base64.NO_WRAP), Charsets.UTF_8)
+  }
+  return getStringExtra(name)
+}

apps/android/app/src/main/java/ai/openclaw/app/AssistantLaunch.kt

@@ -3,6 +3,7 @@ package ai.openclaw.app
 import android.content.Intent
 
 const val actionAskOpenClaw = "ai.openclaw.app.action.ASK_OPENCLAW"
+const val actionOpenVoiceE2e = "ai.openclaw.app.debug.OPEN_VOICE_E2E"
 const val extraAssistantPrompt = "prompt"
 
 enum class HomeDestination {
@@ -19,6 +20,14 @@ data class AssistantLaunchRequest(
   val autoSend: Boolean,
 )
 
+fun parseHomeDestinationIntent(intent: Intent?): HomeDestination? {
+  val action = intent?.action ?: return null
+  return when {
+    BuildConfig.DEBUG && action == actionOpenVoiceE2e -> HomeDestination.Voice
+    else -> null
+  }
+}
+
 fun parseAssistantLaunchIntent(intent: Intent?): AssistantLaunchRequest? {
   val action = intent?.action ?: return null
   return when (action) {

apps/android/app/src/main/java/ai/openclaw/app/MainActivity.kt

@@ -79,6 +79,10 @@ class MainActivity : ComponentActivity() {
   }
 
   private fun handleAssistantIntent(intent: android.content.Intent?) {
+    parseHomeDestinationIntent(intent)?.let { destination ->
+      viewModel.requestHomeDestination(destination)
+      return
+    }
     val request = parseAssistantLaunchIntent(intent) ?: return
     viewModel.handleAssistantLaunch(request)
   }

apps/android/app/src/main/java/ai/openclaw/app/MainViewModel.kt

@@ -330,6 +330,10 @@ class MainViewModel(
     _requestedHomeDestination.value = null
   }
 
+  fun requestHomeDestination(destination: HomeDestination) {
+    _requestedHomeDestination.value = destination
+  }
+
   fun clearChatDraft() {
     _chatDraft.value = null
   }

apps/android/app/src/main/java/ai/openclaw/app/NodeRuntime.kt

@@ -47,6 +47,7 @@ import ai.openclaw.app.protocol.OpenClawCanvasA2UIAction
 import ai.openclaw.app.voice.MicCaptureManager
 import ai.openclaw.app.voice.TalkModeManager
 import ai.openclaw.app.voice.VoiceConversationEntry
+import ai.openclaw.app.voice.VoiceConversationRole
 import android.Manifest
 import android.content.Context
 import android.content.pm.PackageManager
@@ -64,6 +65,7 @@ import kotlinx.coroutines.flow.asStateFlow
 import kotlinx.coroutines.flow.combine
 import kotlinx.coroutines.flow.distinctUntilChanged
 import kotlinx.coroutines.launch
+import kotlinx.coroutines.withTimeout
 import kotlinx.serialization.Serializable
 import kotlinx.serialization.json.Json
 import kotlinx.serialization.json.JsonArray
@@ -256,6 +258,18 @@ class NodeRuntime(
     val previousFingerprintSha256: String? = null,
   )
 
+  data class VoiceE2eSliceResult(
+    val mode: String,
+    val status: String,
+    val userText: String?,
+    val assistantText: String?,
+  )
+
+  data class VoiceE2eResult(
+    val normal: VoiceE2eSliceResult?,
+    val realtime: VoiceE2eSliceResult?,
+  )
+
   private val _isConnected = MutableStateFlow(false)
   val isConnected: StateFlow<Boolean> = _isConnected.asStateFlow()
   private val _nodeConnected = MutableStateFlow(false)
@@ -501,7 +515,7 @@ class NodeRuntime(
         context = appContext,
         scope = scope,
         session = operatorSession,
-        isConnected = { operatorConnected },
+        isConnected = { _isConnected.value },
         onBeforeSpeak = { micCapture.pauseForTts() },
         onAfterSpeak = { micCapture.resumeAfterTts() },
       ).also { speaker ->
@@ -608,7 +622,7 @@ class NodeRuntime(
       context = appContext,
       scope = scope,
       session = operatorSession,
-      isConnected = { operatorConnected },
+      isConnected = { _isConnected.value },
       onBeforeSpeak = { micCapture.pauseForTts() },
       onAfterSpeak = { micCapture.resumeAfterTts() },
       onStoppedByRelay = { finishTalkModeAfterRelayClose() },
@@ -1187,6 +1201,115 @@ class NodeRuntime(
     talkMode.setPlaybackEnabled(value)
   }
 
+  suspend fun runVoiceE2e(
+    mode: String,
+    transcript: String,
+    realtimeAssistantText: String,
+    timeoutMs: Long,
+  ): VoiceE2eResult {
+    if (!BuildConfig.DEBUG) {
+      throw IllegalStateException("voice e2e is debug-only")
+    }
+    if (!_isConnected.value) {
+      throw IllegalStateException("gateway not connected")
+    }
+    if (!hasRecordAudioPermission()) {
+      throw IllegalStateException("microphone permission missing")
+    }
+
+    val normalizedMode = mode.trim().lowercase().ifEmpty { "both" }
+    val runNormal = normalizedMode == "both" || normalizedMode == "normal" || normalizedMode == "dictation"
+    val runRealtime = normalizedMode == "both" || normalizedMode == "realtime" || normalizedMode == "talk"
+    if (!runNormal && !runRealtime) {
+      throw IllegalArgumentException("unknown voice e2e mode: $mode")
+    }
+
+    val previousSpeakerEnabled = speakerEnabled.value
+    setSpeakerEnabled(false)
+    var completed = false
+    return try {
+      VoiceE2eResult(
+        normal =
+          if (runNormal) {
+            runNormalVoiceE2e(transcript = transcript, timeoutMs = timeoutMs)
+          } else {
+            null
+          },
+        realtime =
+          if (runRealtime) {
+            runRealtimeVoiceE2e(
+              transcript = transcript,
+              assistantText = realtimeAssistantText,
+              timeoutMs = timeoutMs,
+            )
+          } else {
+            null
+          },
+      ).also { completed = true }
+    } finally {
+      if (!completed) {
+        stopActiveVoiceSession()
+      }
+      setSpeakerEnabled(previousSpeakerEnabled)
+    }
+  }
+
+  private suspend fun runNormalVoiceE2e(
+    transcript: String,
+    timeoutMs: Long,
+  ): VoiceE2eSliceResult {
+    stopActiveVoiceSession()
+    setVoiceCaptureMode(VoiceCaptureMode.ManualMic)
+    micCapture.submitTranscribedMessage(transcript)
+    awaitVoiceConversation(timeoutMs = timeoutMs) {
+      micCapture.conversation.value.any { it.role == VoiceConversationRole.Assistant && !it.isStreaming }
+    }
+    val entries = micCapture.conversation.value
+    return VoiceE2eSliceResult(
+      mode = "normal",
+      status = micCapture.statusText.value,
+      userText = entries.lastOrNull { it.role == VoiceConversationRole.User }?.text,
+      assistantText = entries.lastOrNull { it.role == VoiceConversationRole.Assistant }?.text,
+    )
+  }
+
+  private suspend fun runRealtimeVoiceE2e(
+    transcript: String,
+    assistantText: String,
+    timeoutMs: Long,
+  ): VoiceE2eSliceResult {
+    stopActiveVoiceSession()
+    setVoiceCaptureMode(VoiceCaptureMode.TalkMode)
+    talkMode.runE2eRealtimeTurn(
+      userText = transcript,
+      assistantText = assistantText,
+      timeoutMs = timeoutMs,
+    )
+    awaitVoiceConversation(timeoutMs = timeoutMs) {
+      val entries = talkMode.conversation.value
+      entries.any { it.role == VoiceConversationRole.User && !it.isStreaming } &&
+        entries.any { it.role == VoiceConversationRole.Assistant && !it.isStreaming }
+    }
+    val entries = talkMode.conversation.value
+    return VoiceE2eSliceResult(
+      mode = "realtime",
+      status = talkMode.statusText.value,
+      userText = entries.lastOrNull { it.role == VoiceConversationRole.User }?.text,
+      assistantText = entries.lastOrNull { it.role == VoiceConversationRole.Assistant }?.text,
+    )
+  }
+
+  private suspend fun awaitVoiceConversation(
+    timeoutMs: Long,
+    ready: () -> Boolean,
+  ) {
+    withTimeout(timeoutMs) {
+      while (!ready()) {
+        delay(100L)
+      }
+    }
+  }
+
   private fun setVoiceCaptureMode(
     mode: VoiceCaptureMode,
     persistManualMic: Boolean = true,

apps/android/app/src/main/java/ai/openclaw/app/gateway/GatewayHostSecurity.kt

@@ -44,7 +44,7 @@ internal fun isLoopbackGatewayHost(
   return isMappedIpv4 && address[12] == 127.toByte()
 }
 
-internal fun isPrivateLanGatewayHost(
+internal fun isLocalCleartextGatewayHost(
   rawHost: String?,
   allowEmulatorBridgeAlias: Boolean = isAndroidEmulatorRuntime(),
 ): Boolean {