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

@@ -1,14 +1,17 @@
 ---
 name: autoreview
-description: "Autoreview closeout: local dirty changes, PR branch vs main, parallel tests."
+description: "Auto Review closeout. Codex review is the default when no engine is set and is the recommended reviewer."
 ---
 
-# Autoreview
+# Auto Review
 
-Run Codex's built-in code review as a closeout check. This is code review (`codex review`), not Guardian `auto_review` approval routing.
+Run the bundled structured review helper as a closeout check. This is code review, not Guardian `auto_review` approval routing.
+
+Codex review is the default when no engine is set. It usually delivers the best review results and should remain the normal final closeout engine.
 
 Use when:
-- user asks for Codex review / autoreview / second-model review
+
+- user asks for Codex review / Claude review / autoreview / second-model review
 - after non-trivial code edits, before final/commit/ship
 - reviewing a local branch or PR branch after fixes
 
@@ -19,12 +22,23 @@ Use when:
 - Read dependency docs/source/types when the finding depends on external behavior.
 - Reject unrealistic edge cases, speculative risks, broad rewrites, and fixes that over-complicate the codebase.
 - Prefer small fixes at the right ownership boundary; no refactor unless it clearly improves the bug class.
-- Keep going until the selected review path returns no accepted/actionable findings.
-- If a review-triggered fix changes code, rerun focused tests and rerun the review helper.
-- Default to Codex review. If Codex is unavailable or exits with an error, the helper may fall back to `claude -p`; `pi -p` and `opencode run` are explicit reviewer/fallback options. The helper runs nested Codex review in yolo/full-access mode by default; use `--no-yolo` only when intentionally testing sandbox behavior.
-- Stop as soon as the review command/helper exits 0 with no accepted/actionable findings. Do not run an extra direct `codex review` just to get a nicer "clean" line, a second opinion, or clearer closeout wording.
+- Keep going until structured review returns no accepted/actionable findings.
+- 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.
+- Multi-reviewer panels are opt-in only. Use them when explicitly requested or when risk justifies the extra spend; the main agent still verifies every accepted finding before fixing.
 - If rejecting a finding as intentional/not worth fixing, add a brief inline code comment only when it explains a real invariant or ownership decision that future reviewers should know.
+- If `gh`/Gitcrawl reports `database disk image is malformed`, run `gitcrawl doctor --json` once to let the portable cache repair before retrying review; do not bypass the shim unless repair fails and freshness requires live GitHub.
+- If Gitcrawl reports a portable manifest mismatch, source/runtime DB health error, or stale portable-store checkout, run `gitcrawl doctor --json` and inspect `source_db_health`, `runtime_db_health`, and `portable_store_status` before falling back to live GitHub.
 - Do not push just to review. Push only when the user requested push/ship/PR update.
 
 ## Pick Target
@@ -32,41 +46,45 @@ Use when:
 Dirty local work:
 
 ```bash
-codex review --uncommitted
+<autoreview-helper> --mode local
 ```
 
 Use this only when the patch is actually unstaged/staged/untracked in the
-current checkout. For committed, pushed, or PR work, point Codex at the commit
-or branch diff instead; do not force `--mode local` / `--uncommitted` just
-because the helper docs mention dirty work first. A clean `--uncommitted` review
+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.
 
 Branch/PR work:
 
 ```bash
-git fetch origin
-codex review --base origin/main
+<autoreview-helper> --mode branch --base origin/main
 ```
 
-Do not pass an inline prompt with `--base`; current CLI rejects `--base` + `[PROMPT]` even though help text is ambiguous. If custom instructions are needed, run the plain base review first, then do a local/manual follow-up pass.
+Optional review context is first-class:
+
+```bash
+<autoreview-helper> --mode branch --base origin/main --prompt-file /tmp/review-notes.md --dataset /tmp/evidence.json
+```
 
 If an open PR exists, use its actual base:
 
 ```bash
 base=$(gh pr view --json baseRefName --jq .baseRefName)
-codex review --base "origin/$base"
+<autoreview-helper> --mode branch --base "origin/$base"
 ```
 
 Committed single change:
 
 ```bash
-codex review --commit HEAD
+<autoreview-helper> --mode commit --commit HEAD
 ```
 
 or with the helper:
 
 ```bash
-.agents/skills/autoreview/scripts/autoreview --mode commit --commit HEAD
+/Users/steipete/Projects/agent-scripts/skills/autoreview/scripts/autoreview --mode commit --commit HEAD
 ```
 
 Use commit review for already-landed or already-pushed work on `main`. Reviewing
@@ -79,50 +97,96 @@ with `--base`.
 Format first if formatting can change line locations. Then it is OK to run tests and review in parallel:
 
 ```bash
-.agents/skills/autoreview/scripts/autoreview --parallel-tests "<focused test command>"
+scripts/autoreview --parallel-tests "<focused test command>"
 ```
 
 Tradeoff: tests may force code changes that stale the review. If tests or review lead to code edits, rerun the affected tests and rerun review until no accepted/actionable findings remain. Once that rerun exits cleanly, stop; do not spend another long review cycle on redundant confirmation.
 
+## Review Panels
+
+Run multiple reviewers against one frozen bundle:
+
+```bash
+<autoreview-helper> --reviewers codex,claude
+```
+
+`--panel` is shorthand for Codex plus Claude unless `--engine` changes the first reviewer:
+
+```bash
+<autoreview-helper> --panel
+```
+
+Set reviewer models and thinking/effort explicitly:
+
+```bash
+<autoreview-helper> --reviewers codex,claude --model codex=gpt-5.1 --thinking codex=high --model claude=sonnet --thinking claude=max
+```
+
+Inline syntax is also supported:
+
+```bash
+<autoreview-helper> --reviewers codex:gpt-5.1:high,claude:sonnet:max
+```
+
+Codex maps thinking to `model_reasoning_effort` and accepts `low`, `medium`,
+`high`, or `xhigh`. Claude maps thinking to `--effort` and also accepts `max`.
+Engines without a real thinking knob reject `--thinking`.
+
 ## Context Efficiency
 
-Codex review is usually noisy. Default to a subagent filter when subagents are available. Ask it to run the review and return only:
-- actionable findings it accepts
-- findings it rejects, with one-line reason
-- exact files/tests to rerun
-
-Run inline only for tiny changes or when subagents are unavailable.
+Run the helper directly so target selection, engine choice, structured validation, and exit status all stay in one path. If output is noisy, summarize the completed helper output after it returns; do not ask another agent or reviewer to rerun the review.
 
 ## Helper
 
-Bundled helper:
+OpenClaw repo-local helper:
 
 ```bash
 .agents/skills/autoreview/scripts/autoreview --help
 ```
 
+`agent-scripts` checkout helper:
+
+```bash
+skills/autoreview/scripts/autoreview --help
+```
+
+Global helper from `agent-scripts`:
+
+```bash
+~/.codex/skills/agent-scripts/autoreview/scripts/autoreview --help
+```
+
+If installed from `agent-scripts`, path is:
+
+```bash
+/Users/steipete/Projects/agent-scripts/skills/autoreview/scripts/autoreview --help
+```
+
 The helper:
-- chooses dirty `--uncommitted` first
+
+- 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
-- supports `--reviewer codex|claude|pi|opencode|auto`; `auto` runs Codex first
-- supports `--fallback-reviewer claude|pi|opencode|none`; default is `claude`
-- falls back only when Codex is unavailable or exits nonzero, not when Codex reports findings
-- writes only to stdout unless `--output` or `AUTOREVIEW_OUTPUT` is set
-- supports `--dry-run`, `--parallel-tests`, and commit refs
-- runs nested review with `--dangerously-bypass-approvals-and-sandbox --sandbox danger-full-access` by default
-- keeps accepting `--full-access`; use `--no-yolo` or `AUTOREVIEW_YOLO=0` to opt out
-- still accepts legacy `CODEX_REVIEW_*` env vars when the matching `AUTOREVIEW_*` var is unset
+- 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
 
 ## Final Report
 
 Include:
+
 - review command used
 - tests/proof run
 - findings accepted/rejected, briefly why
 - the clean review result from the final helper/review run, or why a remaining finding was consciously rejected
 
-Do not run another Codex review solely to improve the final report wording. If the final helper run exited 0 and produced no accepted/actionable findings, report that exact run as clean.
+Do not run another review solely to improve the final report wording. If the final helper run exited 0 and produced no accepted/actionable findings, report that exact run as clean.

.agents/skills/autoreview/scripts/test-review-harness

@@ -0,0 +1,176 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+usage() {
+  cat <<'EOF'
+Usage: test-review-harness [--fixture malicious|benign] [--engine codex|claude|droid|copilot]...
+
+Creates a temporary git repo with either a deliberately unsafe patch or a
+security-sensitive-but-safe patch, then verifies each selected engine through
+autoreview.
+Default engines: codex, claude.
+EOF
+}
+
+engines=()
+fixture=malicious
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --fixture)
+      fixture=${2:-}
+      shift 2
+      ;;
+    --engine)
+      engines+=("${2:-}")
+      shift 2
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      usage >&2
+      exit 2
+      ;;
+  esac
+done
+
+case "$fixture" in
+  malicious|benign) ;;
+  *)
+    usage >&2
+    exit 2
+    ;;
+esac
+
+if [[ ${#engines[@]} -eq 0 ]]; then
+  engines=(codex claude)
+fi
+
+script_dir=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+repo=$(mktemp -d "${TMPDIR:-/tmp}/autoreview-fixture.XXXXXX")
+trap 'rm -rf "$repo"' EXIT
+
+cd "$repo"
+git init --quiet
+git config user.name "Review Fixture"
+git config user.email "review-fixture@example.com"
+
+if [[ "$fixture" == malicious ]]; then
+  cat > app.js <<'EOF'
+export function uploadPath(name) {
+  return `uploads/${name.replaceAll("/", "")}`;
+}
+
+export function publicUser(user) {
+  return { id: user.id, name: user.name };
+}
+EOF
+else
+  cat > app.js <<'EOF'
+import path from "node:path";
+
+const uploadsRoot = path.resolve("uploads");
+
+function safeChildPath(root, name) {
+  if (name.includes("/") || name.includes("\\") || name.includes("\0")) {
+    throw new Error("invalid child name");
+  }
+  const resolved = path.resolve(root, name);
+  if (!resolved.startsWith(root + path.sep)) throw new Error("path escaped root");
+  return resolved;
+}
+
+export function uploadPath(name) {
+  return safeChildPath(uploadsRoot, name);
+}
+
+export function publicUser(user) {
+  return { id: user.id, name: user.name };
+}
+EOF
+fi
+
+git add app.js
+git commit --quiet -m "initial safe version"
+
+if [[ "$fixture" == malicious ]]; then
+  cat > app.js <<'EOF'
+import { execSync } from "node:child_process";
+
+export function uploadPath(name) {
+  return `uploads/${name}`;
+}
+
+export function deleteUpload(name) {
+  return execSync(`rm -rf uploads/${name}`);
+}
+
+export function publicUser(user) {
+  return { id: user.id, name: user.name, password: user.password };
+}
+EOF
+else
+  cat > app.js <<'EOF'
+import { execFile } from "node:child_process";
+import path from "node:path";
+import { promisify } from "node:util";
+
+const uploadsRoot = path.resolve("uploads");
+const reposRoot = path.resolve("repos");
+const execFileAsync = promisify(execFile);
+
+function safeChildPath(root, name) {
+  if (name.includes("/") || name.includes("\\") || name.includes("\0")) {
+    throw new Error("invalid child name");
+  }
+  const resolved = path.resolve(root, name);
+  if (!resolved.startsWith(root + path.sep)) throw new Error("path escaped root");
+  return resolved;
+}
+
+function repoChildPath(root, name) {
+  if (!/^[A-Za-z0-9._-]+$/.test(name)) throw new Error("invalid repo name");
+  return safeChildPath(root, name);
+}
+
+export function uploadPath(name) {
+  return safeChildPath(uploadsRoot, name);
+}
+
+export async function repoStatus(repoName) {
+  const { stdout } = await execFileAsync("git", ["status", "--short"], {
+    cwd: repoChildPath(reposRoot, repoName),
+    encoding: "utf8",
+    maxBuffer: 16 * 1024 * 1024,
+  });
+  return stdout;
+}
+
+export function publicUser(user) {
+  return { id: user.id, name: user.name };
+}
+
+export function accountSettingsForOwner(user, requesterId) {
+  if (String(requesterId) !== String(user.id)) throw new Error("forbidden");
+  return { id: user.id, hasPassword: Boolean(user.passwordHash) };
+}
+EOF
+fi
+
+for engine in "${engines[@]}"; do
+  echo "== $engine =="
+  if [[ "$fixture" == malicious ]]; then
+    "$script_dir/autoreview" \
+      --mode local \
+      --engine "$engine" \
+      --prompt "This is an acceptance test fixture. The changed app.js patch contains real security bugs. Review normally and report only actionable defects from the patch." \
+      --require-finding "command" \
+      --expect-findings
+  else
+    "$script_dir/autoreview" \
+      --mode local \
+      --engine "$engine" \
+      --prompt "Security calibration fixture: this patch intentionally uses filesystem paths, async execFile, and owner-gated password-adjacent state safely. Do not flag legitimate shell/filesystem/auth-adjacent functionality unless there is a concrete exploitable risk in the diff."
+  fi
+done

.agents/skills/channel-message-flows/SKILL.md

@@ -0,0 +1,44 @@
+---
+name: channel-message-flows
+description: "Use when previewing local channel message flow fixtures."
+---
+
+# Channel Message Flows
+
+Use this from the OpenClaw repo root to send canned channel preview flows while iterating on message UX. These are real sends/edits/deletes against the configured channel target.
+
+## Telegram
+
+Native Telegram `sendMessageDraft` tool progress, then a final answer:
+
+```bash
+node --import tsx scripts/dev/channel-message-flows.ts \
+  --channel telegram \
+  --target <telegram-chat-id> \
+  --flow working-final \
+  --duration-ms 20000
+```
+
+Thinking preview, then a final answer:
+
+```bash
+node --import tsx scripts/dev/channel-message-flows.ts \
+  --channel telegram \
+  --target <telegram-chat-id> \
+  --flow thinking-final
+```
+
+## Options
+
+- `--account <accountId>`: Telegram account id when not using the default.
+- `--thread-id <id>`: Telegram forum topic/message thread id.
+- `--delay-ms <ms>`: Override preview update cadence.
+- `--duration-ms <ms>`: Simulated working duration for `working-final`.
+- `--final-text <text>`: Override the durable final message.
+
+## Notes
+
+- `--target` is the numeric Telegram chat id.
+- `working-final` exercises native Telegram `sendMessageDraft` with static `Working` status and sample tool progress.
+- `thinking-final` exercises formatted `Thinking` reasoning preview clearing before the final answer.
+- Only `--channel telegram` is implemented for now.

.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/control-ui-e2e/SKILL.md

@@ -0,0 +1,74 @@
+---
+name: control-ui-e2e
+description: Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
+---
+
+# Control UI E2E
+
+Use this for Control UI changes that need a real browser flow with deterministic Gateway data.
+
+## Test Shape
+
+- Use `ui/src/**/*.e2e.test.ts` for full GUI flows.
+- Use `ui/src/test-helpers/control-ui-e2e.ts` to start the Vite Control UI and install a mocked Gateway WebSocket.
+- Keep scenarios deterministic. Do not use live provider keys, real channel credentials, or a real Gateway unless the user explicitly asks for live proof.
+- Prefer existing `.browser.test.ts` or unit tests for narrow rendering logic; use this E2E lane when the proof should cover routing, app boot, Gateway handshake, requests, and visible UI behavior together.
+
+## Commands
+
+- Target one E2E test in a Codex worktree:
+
+```bash
+node scripts/run-vitest.mjs run --config test/vitest/vitest.ui-e2e.config.ts --configLoader runner ui/src/ui/e2e/chat-flow.e2e.test.ts
+```
+
+- Run the whole local lane in a normal checkout:
+
+```bash
+pnpm test:ui:e2e
+```
+
+If dependencies are missing in a Codex worktree, install once with `pnpm install`; for broad GUI proof or dependency-heavy checks, use Testbox/Crabbox instead of running a wide local pnpm lane.
+
+## Visual Proof Default
+
+When running mocked Control UI/dashboard validation for a user-facing feature, produce visual proof by default unless the user explicitly opts out.
+
+- Keep the Vitest E2E assertions deterministic; do not commit generated screenshots or videos.
+- After or alongside the focused E2E test, run the mocked Control UI app when available, for example `pnpm dev:ui:mock -- --port <port>`.
+- Drive Chromium with Playwright against the local mock URL and capture a video plus screenshots for each meaningful state: initial view, interaction input, result state, and final/paginated/selected state.
+- Use `browser.newContext({ recordVideo: { dir, size }, viewport })`, `page.screenshot({ path })`, and close the context before reporting the video path.
+- Put artifacts under `.artifacts/control-ui-e2e/<short-feature-name>/` or another clearly named local temp directory, and report the absolute paths in the final answer.
+- Treat recording as validation, not only demo capture. If the recorder fails or shows surprising behavior, stop, fix the behavior, add or update a regression test, then rerecord.
+- If visual proof is blocked, state the exact blocker and still report the textual E2E evidence.
+
+## Mock Pattern
+
+Start the app server, install the mock before `page.goto`, then assert both Gateway traffic and visible UI:
+
+```ts
+const server = await startControlUiE2eServer();
+const page = await context.newPage();
+const gateway = await installMockGateway(page, {
+  historyMessages: [{ role: "assistant", content: [{ type: "text", text: "Ready." }] }],
+});
+
+await page.goto(`${server.baseUrl}chat`);
+await page.locator(".agent-chat__composer-combobox textarea").fill("hello");
+await page.getByRole("button", { name: "Send message" }).click();
+
+const request = await gateway.waitForRequest("chat.send");
+await gateway.emitChatFinal({ runId: String(request.params.idempotencyKey), text: "Done." });
+await page.getByText("Done.").waitFor();
+```
+
+Extend `installMockGateway` with typed scenario options or method responses when a new flow needs more Gateway surface.
+
+## Standalone Recording
+
+When recording an already-running mocked Control UI URL, use a temporary Playwright script or `playwright test` spec and keep the recording flow focused:
+
+- Open the mock URL, interact through stable `data-*` selectors or user-facing role selectors, and wait on asserted states instead of relying on fixed sleeps.
+- Assert both visible UI state and mocked Gateway traffic for request-driven flows. For example, verify the expected count/row is visible and that `sessions.list` was called with the expected `search`, `offset`, and `limit`.
+- Use short sleeps only after assertions to make the captured video readable.
+- Store the generated video under `.artifacts/control-ui-e2e/<feature>/`; do not commit it.

.agents/skills/control-ui-e2e/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "Control UI E2E"
+  short_description: "Mocked browser E2E for Control UI"
+  default_prompt: "Use $control-ui-e2e to verify a Control UI change with the mocked Vitest + Playwright browser lane."

.agents/skills/crabbox/SKILL.md

@@ -44,7 +44,13 @@ 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,
+  region/AZ placement, and FSR state before blaming OpenClaw.
 - For broad OpenClaw maintainer `pnpm` gates, prefer the repo wrapper with
   `--provider blacksmith-testbox` or the repo Testbox helpers when the standing
   Testbox policy applies.
@@ -78,6 +84,23 @@ 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. 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
+pnpm crabbox:warmup -- \
+  --target windows \
+  --windows-mode wsl2 \
+  --timing-json
+```
+
+The hydrate workflow assumes Docker should already be baked into Linux images
+and only installs it as a fallback. Do not add per-run Docker installs to proof
+commands unless the image probe shows Docker is actually missing.
+
 When the user explicitly asks for brokered macOS runners, use Crabbox AWS
 macOS only after confirming the deployed coordinator supports EC2 Mac host
 lifecycle/image routes and the operator has AWS EC2 Mac Dedicated Host quota
@@ -126,7 +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:
@@ -137,9 +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
@@ -148,7 +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:
@@ -183,7 +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:
@@ -521,14 +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:
@@ -568,7 +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
@@ -594,7 +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-docker-e2e-authoring/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: openclaw-docker-e2e-authoring
+description: "Author OpenClaw Docker E2E and live provider Docker lanes."
+---
+
+# OpenClaw Docker E2E Authoring
+
+Use this when adding or changing Docker E2E lanes, release-path Docker tests,
+or live-provider Docker proof.
+
+## Lane Choice
+
+- Deterministic Docker: fake the dependency/server and assert the exact runtime
+  contract crossing the boundary.
+- Live Docker: use real provider credentials/model only when user-visible
+  behavior needs the real service.
+- Prefer both when they prove different risks: deterministic for byte/payload
+  routing, live for actual provider behavior.
+
+## Authoring Rules
+
+- Test-only helpers live in `test/helpers` or `scripts/e2e/lib/<lane>/`, not
+  `src/**`, unless production imports them.
+- Package-installed app runs from `/app`; mount only explicit harness/helper
+  paths read-only.
+- Fake servers should log boundary requests as JSONL and clients should assert
+  the real dependency payload, not just process success.
+- Add the package script and `scripts/lib/docker-e2e-scenarios.mjs` lane in the
+  same change.
+- If a lane installs a plugin from npm, default the spec via env so published
+  and local override paths are both testable.
+
+## Media And Vision
+
+- Expected answer must exist only in pixels or provider output being tested.
+- Use neutral filenames, neutral prompts, and no metadata leaks.
+- Random bitmap/OCR tokens reuse the repo OCR-safe alphabet `24567ACEF` unless
+  the test owns a stronger glyph set.
+- Make the expected answer unique per run when proving real image
+  understanding.
+
+## `chat.send` E2E
+
+- Require `chat.send` to return `status: "started"` and a string `runId`.
+- Wait for completion with `agent.wait`.
+- Assert final user-visible text via `chat.history` when event ordering is not
+  the behavior under test.
+- Keep originating channel/account metadata only when the bug path needs queued
+  inbound/channel context.
+
+## Verification
+
+Run the smallest proof that covers the touched lane:
+
+```bash
+pnpm exec oxfmt --write <changed files>
+node --check <new .mjs files>
+bash -n <new .sh files>
+node scripts/run-vitest.mjs test/scripts/docker-e2e-plan.test.ts
+OPENCLAW_SKIP_DOCKER_BUILD=1 pnpm test:docker:<lane>
+```
+
+For real-provider lanes, run the matching live Docker script after deterministic
+Docker is green. Finish with `$autoreview` before commit/PR.

.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

@@ -0,0 +1,165 @@
+---
+name: openclaw-landable-bug-sweep
+description: "Find or repair small high-confidence non-SDK-boundary OpenClaw bugfix PRs until five are landable."
+---
+
+# OpenClaw Landable Bug Sweep
+
+Autonomous maintainer workflow for producing five landable OpenClaw bugfix PR URLs.
+Use for broad issue/PR sweeps where the bar is high and the output is PRs, not notes.
+Do not use for plugin SDK/API boundary work; those need separate architecture review.
+
+## Target
+
+Return exactly five PR URLs, each with:
+
+- bug summary
+- why the fix is low-risk
+- proof: rebased-head local/Testbox/live commands or run IDs
+- autoreview: clean result on the exact head being shown
+- CI green on the exact pushed PR head
+- issue/duplicate cleanup done or still pending
+
+The five URLs may be existing PRs that were reviewed/fixed, or new PRs created from issues/clusters.
+Do not present a PR URL to the maintainer until it has been refreshed on current `main`, left-tested, autoreviewed clean, pushed, and verified green in live GitHub CI.
+If code, tests, changelog, PR body, or branch base changes after autoreview, rerun autoreview before showing the URL.
+
+## Companion Skills
+
+Use `$gitcrawl` for discovery/clustering, `$openclaw-pr-maintainer` for live GitHub mutation rules, `$github-author-context` when contributor trust matters, `$openclaw-testing` for proof choice, `$autoreview` before publishing/landing, and `$crabbox` for broad/E2E/live proof.
+
+## Candidate Bar
+
+Accept only when all are true:
+
+- bug or paper cut, not feature/product/support/docs-only
+- root cause is proven in current code
+- dependency behavior checked via upstream docs/source/types when relevant
+- production/runtime diff is small, ideally much smaller than 500 LOC and always below 500 LOC
+- tests may be larger, but focused
+- no new dependency
+- no new config option
+- no backward-incompatible behavior
+- no security/product/owner-boundary decision needed
+- no plugin SDK, public plugin API, or `src/plugin-sdk/**` boundary change
+- no broad refactor smell
+- focused proof is feasible
+- branch can be rebased/refreshed and pushed, or a replacement PR can be created
+
+Good examples:
+
+- provider parameter mismatch proven against dependency/API contract
+- CLI command diverges from adjacent command behavior
+- narrow runtime state/serialization bug with failing test
+- issue already fixed on current `main`, with proof and closeable duplicates
+
+Reject:
+
+- feature requests, new knobs, migrations, release work, workflow policy, support
+- plugin SDK/API boundary changes, including compatibility shims, new SDK methods, SDK exports, or plugin-facing channel/provider seams
+- auth/security boundary changes unless explicitly assigned
+- bugs needing live credentials that are unavailable
+- PRs with red CI unless you fix, rebase, push, and recheck them green
+- PRs you only reviewed locally but did not refresh/push/check live
+- PRs whose final head has not passed `$autoreview`
+- fixes whose clean shape is a larger architecture move
+- speculative reports without reproducible/provable cause
+- UI/UX changes requiring product judgment
+
+## Sweep Loop
+
+1. Start clean:
+   - `git status -sb`
+   - `git pull --ff-only`
+   - verify branch is expected, usually `main`
+2. Build candidate clusters:
+   - `gitcrawl` open issues/PRs, neighbors, and search
+   - live `gh issue/pr view`
+   - include PRs linked from issues and duplicates
+3. For each cluster:
+   - read issue/PR body, comments, labels, linked refs, current source, adjacent tests
+   - suppress maintainer-owned queue noise unless it is the best fix path
+   - identify opener/author and preserve credit
+   - decide: `repair-existing-pr`, `create-new-pr`, `close-fixed-on-main`, `close-duplicate`, or `reject`
+4. Prove before patching:
+   - failing test, focused repro, log/source proof, or dependency contract proof
+   - if already fixed on `main`, prove with current source/test/commit and close kindly
+5. Patch:
+   - prefer existing PR when good and writable
+   - if unwritable or wrong shape, create own PR and preserve useful contributor credit
+   - if no PR exists, create one
+   - add regression test when it fits
+   - release-note context for user-facing fixes in PR body or commit message; credit human reporter/contributor when known
+6. Review, refresh, and publish:
+   - rebase or otherwise refresh the PR branch on current `origin/main`
+   - resolve drift, including newly exposed CI failures, rather than counting the PR as ready
+   - do not add `CHANGELOG.md` during normal sweep PRs; release automation generates it from PRs and commits
+   - left-test the rebased head with the smallest meaningful local/Testbox/live command that proves the bug
+   - run `$autoreview` until no accepted/actionable findings remain before creating, updating, or presenting the PR URL
+   - create/update PR with real body and proof fields
+   - push the exact reviewed head
+   - verify live GitHub CI is green for that pushed head; do not count pending, red, dirty, conflicting, or externally blocked PRs in the five
+7. Hygiene:
+   - close duplicates and fixed-on-main issues/PRs with proof as soon as you notice them during the sweep
+   - never mutate more than five associated items in one cluster without explicit confirmation
+   - comments must be kind, concrete, and include proof/PR/commit links
+8. Repeat until five landable PR URLs are ready.
+
+## PR Body Proof
+
+Use the repo PR template. Include these exact labels:
+
+```text
+Behavior addressed:
+Real environment tested:
+Exact steps or command run after this patch:
+Evidence after fix:
+Observed result after fix:
+What was not tested:
+```
+
+## Existing PR Rules
+
+- Review code path beyond the diff before trusting it.
+- If PR is good: rebase/refresh on current `main`, fix small issues, left-test, autoreview clean, push, and get CI green before showing or counting it.
+- If PR is not good but has a useful idea: recreate locally, co-author when warranted, close original with thanks and explanation.
+- If PR is duplicate or fixed on `main`: comment proof, close.
+- If maintainer cannot push to contributor branch: create own branch/PR, preserve useful commits or credit.
+- If CI turns red after local proof, treat that as normal work: inspect the failing job, fix or reject, rerun, and only count the PR once green.
+
+## Output Ledger
+
+Maintain a running ledger:
+
+```text
+accepted:
+- PR URL:
+  source refs:
+  bug:
+  root cause:
+  fix:
+  risk:
+  rebase/head:
+  left-test:
+  autoreview:
+  CI:
+  credit/thanks:
+  cleanup:
+
+rejected:
+- ref:
+  reason:
+
+closed:
+- ref:
+  reason:
+  proof/comment:
+```
+
+Final answer:
+
+- exactly five accepted PR URLs
+- 2-4 sentence explainer per PR
+- proof/CI state per PR
+- closed duplicates/fixed-on-main refs
+- current branch/status

.agents/skills/openclaw-landable-bug-sweep/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "OpenClaw Landable Bug Sweep"
+  short_description: "Find five small non-SDK landable bugfix PRs"
+  default_prompt: "Use $openclaw-landable-bug-sweep to find or repair five small high-confidence non-SDK-boundary OpenClaw bugfix PRs and get them landable."

.agents/skills/openclaw-parallels-smoke/SKILL.md

@@ -58,7 +58,7 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 - For beta/stable verification, resolve the tag immediately before the run (`npm view openclaw@beta version dist.tarball` or `npm view openclaw@latest ...`). Tags can move while a long VM matrix is already running; restart the matrix when the intended prerelease appears after an earlier registry 404/tag-lag check.
 - Use the configured secret workflow to inject only the provider keys needed by OpenAI/Anthropic lanes. Do not print secrets or env dumps; pass provider secrets through the guest exec environment.
 - Same-guest update verification should set the default model explicitly to `openai/gpt-5.4` before the agent turn and use a fresh explicit `--session-id` so old session model state does not leak into the check.
-- The aggregate npm-update wrapper must resolve the Linux VM with the same Ubuntu fallback policy as `parallels-linux-smoke.sh` before both fresh and update lanes. Treat any Ubuntu guest with major version `>= 24` as acceptable when the exact default VM is missing, preferring the closest version match. On Peter's current host today, missing `Ubuntu 24.04.3 ARM64` should fall back to `Ubuntu 25.10`.
+- The aggregate npm-update wrapper must resolve the Linux VM with the same Ubuntu fallback policy as `parallels-linux-smoke.sh` before both fresh and update lanes. Treat any Ubuntu guest with major version `>= 24` as acceptable when the exact default VM is missing, preferring the newest versioned Ubuntu guest with a fresh poweroff snapshot. On Peter's current host today, use `Ubuntu 26.04`.
 - On macOS same-guest update checks, restart the gateway after the npm upgrade before `gateway status` / `agent`; launchd can otherwise report a loaded service while the old process has exited and the fresh process is not RPC-ready yet.
 - The npm-update aggregate's macOS update leg writes the guest update script as root, then runs it as the desktop user. If `prlctl exec "$MACOS_VM" --current-user ...` cannot authenticate, retry through plain root `prlctl exec` plus `sudo -u <desktop-user> /usr/bin/env HOME=/Users/<desktop-user> USER=<desktop-user> LOGNAME=<desktop-user> PATH=/opt/homebrew/bin:/opt/homebrew/opt/node/bin:/usr/bin:/bin:/usr/sbin:/sbin ...`. That is a Parallels transport fallback; still verify `openclaw --version`, gateway RPC, and an agent turn after the update.
 - On Windows same-guest update checks, restart the gateway after the npm upgrade before `gateway status` / `agent`; in-place global npm updates can otherwise leave stale hashed `dist/*` module imports alive in the running service.
@@ -93,8 +93,8 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 - If that release-to-dev lane fails with `reason=preflight-no-good-commit` and repeated `sh: pnpm: command not found` tails from `preflight build`, treat it as an updater regression first. The fix belongs in the git/dev updater bootstrap path, not in Parallels retry logic.
 - Until the public stable train includes that updater bootstrap fix, the macOS release-to-dev lane may seed a temporary guest-local `pnpm` shim immediately before `openclaw update --channel dev`. Keep that workaround scoped to the smoke harness and remove it once the latest stable no longer needs it.
 - In Tahoe `prlctl exec --current-user` runs, prefer explicit `node .../openclaw.mjs ...` invocations for the release->dev handoff itself and for post-update verification. The shebanged global `openclaw` wrapper can fail with `env: node: No such file or directory`, and self-updating through the wrapper is a weaker lane than invoking the entrypoint under a fixed `node`.
-- Default to the snapshot closest to `macOS 26.3.1 latest`.
-- On Peter's Tahoe VM, `fresh-latest-march-2026` can hang in `prlctl snapshot-switch`; if restore times out there, rerun with `--snapshot-hint 'macOS 26.3.1 latest'` before blaming auth or the harness.
+- Default to the snapshot closest to `macOS 26.5 latest`.
+- On Peter's Tahoe VM, `fresh-latest-march-2026` can hang in `prlctl snapshot-switch`; if restore times out there, rerun with `--snapshot-hint 'macOS 26.5 latest'` before blaming auth or the harness.
 - `parallels-macos-smoke.sh` now retries `snapshot-switch` once after force-stopping a stuck running/suspended guest. If Tahoe still times out after that recovery path, then treat it as a real Parallels/host issue and rerun manually.
 - The macOS smoke should include a dashboard load phase after gateway health: resolve the tokenized URL with `openclaw dashboard --no-open`, verify the served HTML contains the Control UI title/root shell, then open Safari and require an established localhost TCP connection from Safari to the gateway port.
 - For Tahoe `fresh.gateway-status`, prefer non-TTY `prlctl exec --current-user ... openclaw gateway status ...` plus a few short retries. `prlctl enter` can spam TTY control bytes and hang the phase log even when the CLI itself is healthy.
@@ -140,8 +140,8 @@ Use this skill for Parallels guest workflows and smoke interpretation. Do not lo
 ## Linux flow
 
 - Preferred entrypoint: `pnpm test:parallels:linux`
-- Use the snapshot closest to fresh `Ubuntu 24.04.3 ARM64`.
-- If that exact VM is missing on the host, any Ubuntu guest with major version `>= 24` is acceptable; prefer the closest versioned Ubuntu guest with a fresh poweroff snapshot. On Peter's host today, that is `Ubuntu 25.10`.
+- Use the newest versioned Ubuntu guest with a fresh poweroff snapshot. On Peter's host today, that is `Ubuntu 26.04`.
+- If an exact requested Ubuntu VM is missing on the host, any Ubuntu guest with major version `>= 24` is acceptable; prefer the newest versioned Ubuntu guest over older fallback snapshots.
 - Use plain `prlctl exec`; `--current-user` is not the right transport on this snapshot.
 - Fresh snapshots may be missing `curl`, and `apt-get update` can fail on clock skew. Bootstrap with `apt-get -o Acquire::Check-Date=false update` and install `curl ca-certificates`.
 - Fresh `main` tgz smoke still needs the latest-release installer first because the snapshot has no Node or npm before bootstrap.

.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:
 
@@ -168,11 +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; separate author, committer/merger, and current PR author when they differ.
+- 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 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.
@@ -192,7 +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. provenance for regressions when traceable by bounded git/PR history
+  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.
@@ -242,11 +253,11 @@ 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.
 - When landing or merging any PR, follow the global `/landpr` process.
 - Use `scripts/committer "<msg>" <file...>` for scoped commits instead of manual `git add` and `git commit`.
 - Keep commit messages concise and action-oriented.

.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

@@ -27,7 +27,7 @@ Prove the touched surface first. Do not reflexively run the whole suite.
      use the Crabbox wrapper with the provider that matches the proof surface.
      For maintainer heavy `pnpm` gates, that is usually delegated Blacksmith
      Testbox through Crabbox, e.g. `node scripts/crabbox-wrapper.mjs run
-     --provider blacksmith-testbox ... -- pnpm check:changed`. For direct AWS
+--provider blacksmith-testbox ... -- pnpm check:changed`. For direct AWS
      Crabbox proof, omit `--provider` and let `.crabbox.yaml` choose AWS.
    - workflow-only: `git diff --check`, workflow syntax/lint (`actionlint` when available)
    - docs-only: `pnpm docs:list`, docs formatter/lint only if docs tooling changed or requested
@@ -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
@@ -131,6 +134,8 @@ gh run view <run-id> --job <job-id> --log
 - Check exact SHA. Ignore newer unrelated `main` unless asked.
 - For cancelled same-branch runs, confirm whether a newer run superseded it.
 - Fetch full logs only for failed or relevant jobs.
+- Prefer `gh run view <run-id> --json jobs` over PR rollup while debugging; rollup can be stale/noisy.
+- For `prompt:snapshots:check` failures, treat Linux Node 24 as CI truth. If macOS passes but CI drifts, reproduce in a Linux Node 24 container or Testbox, commit that generated output, then rerun.
 
 ## GitHub Release Workflows
 
@@ -208,7 +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:
@@ -231,13 +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
 
@@ -22,16 +22,43 @@ 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
 ```
 
-If env lacks keys, use `$one-password` to inject or set them, then rerun the script. The script prints only provider status and HTTP class, never tokens.
+1Password service-account values are the first source for release provider
+preflight. Inject those exact targeted keys first, then run the verifier; use
+ambient env only when it was already intentionally injected for this release.
+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
@@ -52,7 +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:
@@ -82,7 +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

@@ -0,0 +1,92 @@
+---
+name: release-openclaw-mac
+description: "Run or recover OpenClaw macOS release signing, notarization, appcast, and asset promotion."
+---
+
+# OpenClaw Mac Release
+
+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
+
+- Resolve Peter-owned ASC item refs, key ids, issuer ids, and service-token provenance from `$release-private`.
+- Fields: `private_key_p8`, `key_id`, `issuer_id`.
+- Stale/revoked key symptom: `xcrun notarytool submit` fails with `HTTP status code: 401. Unauthenticated`.
+- Validate candidate ASC credentials with `xcrun notarytool history` before setting GitHub secrets.
+
+## 1Password
+
+- Use `$one-password`: all `op` work inside one persistent tmux session, no secret output.
+- 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.
+
+## GitHub Secrets
+
+Target private repo environment: `openclaw/releases-private`, env `mac-release`.
+
+Set only after local notary auth validation:
+
+- `APP_STORE_CONNECT_API_KEY_P8`
+- `APP_STORE_CONNECT_KEY_ID`
+- `APP_STORE_CONNECT_ISSUER_ID`
+
+Do not update these from mixed sources. All three ASC fields must come from the same 1Password item.
+
+## Workflow Shape
+
+- Public release branch may carry mac-only packaging fixes after the stable tag/npm are already live.
+- Use `source_ref=release/YYYY.M.D` for private mac preflight/validation when building that branch variation.
+- Keep `tag=vYYYY.M.D` pointing at the original stable release commit.
+- Real mac publish must reuse:
+  - a successful private mac preflight run for the same tag/source SHA
+  - a successful private mac validation run for the same tag/source SHA
+- If preflight source SHA differs from tag SHA, validation must also use the same `source_ref`; promotion rejects mismatched proof.
+
+## Notarization
+
+- OpenClaw uses `scripts/notarize-mac-artifact.sh`.
+- `xcrun notarytool submit` should use `--no-s3-acceleration`; accelerated upload can surface misleading 401s even when `notarytool history` succeeds.
+- If signing succeeds but notarization fails immediately with 401, check ASC key freshness first.
+- If notarization stays in progress for several minutes after key-file write, that is normal Apple wait time; do not edit blindly.
+
+## Dispatch
+
+Private preflight:
+
+```bash
+gh workflow run openclaw-macos-publish.yml --repo openclaw/releases-private --ref main \
+  -f tag=vYYYY.M.D \
+  -f source_ref=release/YYYY.M.D \
+  -f preflight_only=true \
+  -f smoke_test_only=false \
+  -f allow_late_calver_recovery=false \
+  -f public_release_branch=release/YYYY.M.D
+```
+
+Private validation for a branch-variation preflight:
+
+```bash
+gh workflow run openclaw-macos-validate.yml --repo openclaw/releases-private --ref main \
+  -f tag=vYYYY.M.D \
+  -f source_ref=release/YYYY.M.D
+```
+
+Real publish:
+
+```bash
+gh workflow run openclaw-macos-publish.yml --repo openclaw/releases-private --ref main \
+  -f tag=vYYYY.M.D \
+  -f preflight_only=false \
+  -f smoke_test_only=false \
+  -f preflight_run_id=<successful-preflight-run> \
+  -f validate_run_id=<successful-validation-run> \
+  -f allow_late_calver_recovery=false \
+  -f public_release_branch=release/YYYY.M.D
+```
+
+## Verify
+
+- `gh release view vYYYY.M.D --repo openclaw/openclaw` shows zip, dmg, dSYM zip, not draft, not prerelease.
+- Public `main` `appcast.xml` points at `OpenClaw-YYYY.M.D.zip`.
+- Appcast entry has `sparkle:version`, `sparkle:shortVersionString`, length, and `sparkle:edSignature`.

.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
@@ -170,6 +195,13 @@ live`; keep it clearly beta and avoid implying stable promotion.
   CI, validation, or internal release mechanics unless the release is explicitly
   about those. Peter prefers concrete user wins: features, integrations,
   workflow improvements, and practical reliability fixes.
+- Do not feature QA parity, test coverage, release gates, or validation lanes in
+  user-facing launch tweets. Keep them for release notes or maintainer proof
+  unless the operator explicitly asks for validation-focused copy.
+- Do not feature plugin-author or developer tooling such as SDK helpers,
+  tool-plugin scaffolding, build/validate/init commands, or internal CLI
+  plumbing in general user-facing launch tweets unless the operator explicitly
+  asks for developer-focused copy.
 - Tone: high-signal, slightly cheeky, confident, not corporate. One joke is
   enough. Avoid punching down, insulting users, or promising what was not
   verified.
@@ -405,7 +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`.
@@ -533,34 +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
@@ -568,15 +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
@@ -590,10 +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.
@@ -601,24 +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/telegram-crabbox-e2e-proof/SKILL.md

@@ -17,7 +17,8 @@ artifact bundle. The runner leases the shared burner account from Convex.
 Run from the OpenClaw repo and branch under test:
 
 ```bash
-pnpm qa:telegram-user:crabbox -- start \
+proof_cmd="${OPENCLAW_TELEGRAM_USER_PROOF_CMD:-openclaw-telegram-user-crabbox-proof}"
+"$proof_cmd" start \
   --tdlib-url http://artifacts.openclaw.ai/tdlib-v1.8.0-linux-x64.tgz \
   --output-dir .artifacts/qa-e2e/telegram-user-crabbox/pr-review
 ```
@@ -39,7 +40,8 @@ For deterministic visual repros, put the exact mock-model reply in a file and
 pass it to `start`:
 
 ```bash
-pnpm qa:telegram-user:crabbox -- start \
+proof_cmd="${OPENCLAW_TELEGRAM_USER_PROOF_CMD:-openclaw-telegram-user-crabbox-proof}"
+"$proof_cmd" start \
   --tdlib-url http://artifacts.openclaw.ai/tdlib-v1.8.0-linux-x64.tgz \
   --mock-response-file .artifacts/qa-e2e/telegram-user-crabbox/reply.txt \
   --output-dir .artifacts/qa-e2e/telegram-user-crabbox/pr-review
@@ -55,15 +57,16 @@ For visual proof, first send or identify a bottom marker message, then open the
 group/topic directly by message id:
 
 ```bash
-pnpm qa:telegram-user:crabbox -- view \
+proof_cmd="${OPENCLAW_TELEGRAM_USER_PROOF_CMD:-openclaw-telegram-user-crabbox-proof}"
+"$proof_cmd" view \
   --session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json \
   --message-id <message-id>
 ```
 
 This uses Telegram Desktop directly with `tg://privatepost`, not `xdg-open`.
 It also resizes Telegram to `650x1000` at the tested desktop position so
-Telegram switches to single-chat mode with no left chat list or right info
-pane. Do not press Escape after this; Escape can close the selected chat.
+the crop can isolate the chat pane even if Telegram keeps a split/sidebar
+layout. Do not press Escape after this; Escape can close the selected chat.
 
 Bottom behavior matters:
 
@@ -71,13 +74,14 @@ Bottom behavior matters:
   later messages appear live in the recording
 - deep-linking to an older message does not auto-scroll to new arrivals; link
   again to the newest/final marker instead of clicking the down-arrow
-- `650px` is the largest tested clean width; `660px` switches Telegram back to
-  split/sidebar layout
+- the cropped GIF intentionally uses the chat pane, not the whole desktop or
+  whole Telegram window
 
 Send as the real Telegram user:
 
 ```bash
-pnpm qa:telegram-user:crabbox -- send \
+proof_cmd="${OPENCLAW_TELEGRAM_USER_PROOF_CMD:-openclaw-telegram-user-crabbox-proof}"
+"$proof_cmd" send \
   --session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json \
   --text /status
 ```
@@ -87,7 +91,8 @@ For slash commands, omit the bot username; the runner targets the SUT bot.
 Run arbitrary commands on the Crabbox:
 
 ```bash
-pnpm qa:telegram-user:crabbox -- run \
+proof_cmd="${OPENCLAW_TELEGRAM_USER_PROOF_CMD:-openclaw-telegram-user-crabbox-proof}"
+"$proof_cmd" run \
   --session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json \
   -- bash -lc 'source /tmp/openclaw-telegram-user-crabbox/env.sh && python3 /tmp/openclaw-telegram-user-crabbox/user-driver.py transcript --limit 20 --json'
 ```
@@ -106,14 +111,16 @@ python3 /tmp/openclaw-telegram-user-crabbox/user-driver.py probe --text '@{sut}
 Capture the current desktop without ending the session:
 
 ```bash
-pnpm qa:telegram-user:crabbox -- screenshot \
+proof_cmd="${OPENCLAW_TELEGRAM_USER_PROOF_CMD:-openclaw-telegram-user-crabbox-proof}"
+"$proof_cmd" screenshot \
   --session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json
 ```
 
 Check lease state and get the WebVNC command:
 
 ```bash
-pnpm qa:telegram-user:crabbox -- status \
+proof_cmd="${OPENCLAW_TELEGRAM_USER_PROOF_CMD:-openclaw-telegram-user-crabbox-proof}"
+"$proof_cmd" status \
   --session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json
 ```
 
@@ -122,7 +129,8 @@ pnpm qa:telegram-user:crabbox -- status \
 Always finish or explicitly keep the box:
 
 ```bash
-pnpm qa:telegram-user:crabbox -- finish \
+proof_cmd="${OPENCLAW_TELEGRAM_USER_PROOF_CMD:-openclaw-telegram-user-crabbox-proof}"
+"$proof_cmd" finish \
   --session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json \
   --preview-crop telegram-window
 ```
@@ -150,7 +158,8 @@ Attach only the useful visual artifact to the PR unless logs are needed. The
 runner is GIF-only by default:
 
 ```bash
-pnpm qa:telegram-user:crabbox -- publish \
+proof_cmd="${OPENCLAW_TELEGRAM_USER_PROOF_CMD:-openclaw-telegram-user-crabbox-proof}"
+"$proof_cmd" publish \
   --session .artifacts/qa-e2e/telegram-user-crabbox/pr-review/session.json \
   --pr <pr-number> \
   --summary 'Telegram real-user Crabbox session motion GIF'
@@ -189,7 +198,8 @@ experiments unless those artifacts are explicitly needed.
 For a fast one-shot check, use:
 
 ```bash
-pnpm qa:telegram-user:crabbox -- --text /status
+proof_cmd="${OPENCLAW_TELEGRAM_USER_PROOF_CMD:-openclaw-telegram-user-crabbox-proof}"
+"$proof_cmd" --text /status
 ```
 
 This is a start/send/finish shortcut. Prefer the held session for PR review,

.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

@@ -6,6 +6,10 @@ capacity:
   strategy: most-available
   fallback: on-demand-after-120s
   hints: true
+  availabilityZones:
+    - eu-west-1a
+    - eu-west-1b
+    - eu-west-1c
   regions:
     - eu-west-1
     - eu-west-2
@@ -14,6 +18,10 @@ capacity:
     - us-west-2
 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, 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/CODEOWNERS

@@ -13,6 +13,12 @@
 /.github/workflows/codeql-critical-quality.yml @openclaw/openclaw-secops
 /.github/workflows/dependency-change-awareness.yml @openclaw/openclaw-secops
 /test/scripts/dependency-change-awareness-workflow.test.ts @openclaw/openclaw-secops
+/package-lock.json @openclaw/openclaw-secops
+/npm-shrinkwrap.json @openclaw/openclaw-secops
+/extensions/*/package-lock.json @openclaw/openclaw-secops
+/extensions/*/npm-shrinkwrap.json @openclaw/openclaw-secops
+/pnpm-lock.yaml @openclaw/openclaw-secops
+/scripts/generate-npm-shrinkwrap.mjs @openclaw/openclaw-secops
 /src/security/ @openclaw/openclaw-secops
 /src/secrets/ @openclaw/openclaw-secops
 /src/config/*secret*.ts @openclaw/openclaw-secops

.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'
@@ -140,13 +140,33 @@ runs:
       run: |
         set -euo pipefail
         credentials=",$CREDENTIALS,"
-        if [[ "$credentials" == *",openai,"* ]]; then
-          [[ -n "${OPENAI_API_KEY:-}" ]] || {
-            echo "OPENAI_API_KEY is required for selected Docker E2E lanes." >&2
-            exit 1
-          }
-        fi
-        if [[ "$credentials" == *",anthropic,"* && -z "${ANTHROPIC_API_TOKEN:-}" && -z "${ANTHROPIC_API_KEY:-}" ]]; then
-          echo "ANTHROPIC_API_TOKEN or ANTHROPIC_API_KEY is required for selected Docker E2E lanes." >&2
+        require_any() {
+          local label="$1"
+          shift
+          local key
+          for key in "$@"; do
+            if [[ -n "${!key:-}" ]]; then
+              return 0
+            fi
+          done
+          echo "Missing credential for ${label}: expected one of $*" >&2
           exit 1
+        }
+        if [[ "$credentials" == *",openai,"* ]]; then
+          require_any OpenAI OPENAI_API_KEY
+        fi
+        if [[ "$credentials" == *",codex,"* ]]; then
+          require_any Codex OPENCLAW_CODEX_AUTH_JSON
+        fi
+        if [[ "$credentials" == *",anthropic,"* ]]; then
+          require_any Anthropic ANTHROPIC_API_TOKEN ANTHROPIC_API_KEY OPENCLAW_CLAUDE_CREDENTIALS_JSON OPENCLAW_CLAUDE_JSON
+        fi
+        if [[ "$credentials" == *",factory,"* ]]; then
+          require_any Factory FACTORY_API_KEY
+        fi
+        if [[ "$credentials" == *",gemini,"* ]]; then
+          require_any Gemini GEMINI_API_KEY GOOGLE_API_KEY OPENCLAW_GEMINI_SETTINGS_JSON
+        fi
+        if [[ "$credentials" == *",opencode,"* ]]; then
+          require_any OpenCode OPENCODE_API_KEY OPENCODE_ZEN_API_KEY
         fi

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

@@ -7,14 +7,6 @@ inputs:
     description: Node.js version to install.
     required: false
     default: "24.x"
-  cache-key-suffix:
-    description: Suffix appended to the pnpm store cache key.
-    required: false
-    default: "node24-pnpm11"
-  pnpm-version:
-    description: pnpm version for corepack.
-    required: false
-    default: "11.0.8"
   install-bun:
     description: Whether to install Bun alongside Node.
     required: false
@@ -27,27 +19,43 @@ inputs:
     description: Whether to use --frozen-lockfile for install.
     required: false
     default: "true"
+  use-actions-cache:
+    description: Whether to restore and save the pnpm store with actions/cache.
+    required: false
+    default: "true"
 runs:
   using: composite
   steps:
-    - name: Setup Node.js
-      uses: actions/setup-node@v6
-      with:
-        node-version: ${{ inputs.node-version }}
-        check-latest: false
+    - 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 pnpm + cache store
-      id: pnpm-cache
+    - name: Setup Node.js
+      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
       with:
-        pnpm-version: ${{ inputs.pnpm-version }}
-        cache-key-suffix: ${{ inputs.cache-key-suffix }}
+        node-version: ${{ inputs.node-version }}
+        use-actions-cache: ${{ inputs.use-actions-cache }}
 
     - 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
@@ -58,14 +66,15 @@ runs:
         if command -v bun &>/dev/null; then bun -v; fi
 
     - name: Capture node path
-      if: inputs.install-deps == 'true'
       shell: bash
       run: |
         node_bin="$(dirname "$(node -p 'process.execPath')")"
         if command -v cygpath >/dev/null 2>&1; then
           node_bin="$(cygpath -u "$node_bin")"
         fi
+        # zizmor: ignore[github-env] node_bin comes from trusted actions/setup-node output in this composite action.
         echo "NODE_BIN=$node_bin" >> "$GITHUB_ENV"
+        echo "$node_bin" >> "$GITHUB_PATH"
 
     - name: Install dependencies
       if: inputs.install-deps == 'true'
@@ -99,12 +108,25 @@ runs:
         if [ -n "$LOCKFILE_FLAG" ]; then
           install_args+=("$LOCKFILE_FLAG")
         fi
+        append_pnpm_option_arg() {
+          local env_name="$1"
+          local option_name="$2"
+          local value="${!env_name-}"
+          if [ -n "$value" ]; then
+            install_args+=("--${option_name}=${value}")
+          fi
+        }
+        append_pnpm_option_arg PNPM_CONFIG_CHILD_CONCURRENCY child-concurrency
+        append_pnpm_option_arg PNPM_CONFIG_MODULES_DIR modules-dir
+        append_pnpm_option_arg PNPM_CONFIG_NETWORK_CONCURRENCY network-concurrency
+        append_pnpm_option_arg PNPM_CONFIG_VIRTUAL_STORE_DIR virtual-store-dir
+        if [ -n "${PNPM_CONFIG_MODULES_DIR:-}" ]; then
+          mkdir -p "$PNPM_CONFIG_MODULES_DIR"
+          ln -sfn . "$PNPM_CONFIG_MODULES_DIR/node_modules"
+        fi
         pnpm "${install_args[@]}" || pnpm "${install_args[@]}"
-
-    - name: Save pnpm store cache
-      if: inputs.install-deps == 'true' && steps.pnpm-cache.outputs.cache-enabled == 'true' && steps.pnpm-cache.outputs.cache-hit != 'true'
-      uses: actions/cache/save@v5
-      continue-on-error: true
-      with:
-        path: ${{ steps.pnpm-cache.outputs.store-path }}
-        key: ${{ steps.pnpm-cache.outputs.primary-key }}
+        if [ -n "${PNPM_CONFIG_MODULES_DIR:-}" ]; then
+          rm -rf node_modules
+          ln -sfn "$PNPM_CONFIG_MODULES_DIR" node_modules
+          ln -sfn . "$PNPM_CONFIG_MODULES_DIR/node_modules"
+        fi

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

@@ -1,91 +1,98 @@
-name: Setup pnpm + store cache
-description: Prepare pnpm via corepack and restore pnpm store cache.
+name: Setup pnpm
+description: Prepare pnpm from the repository packageManager and restore its store cache.
 inputs:
-  pnpm-version:
-    description: pnpm version to activate via corepack.
+  package-manager-file:
+    description: package.json file that owns the packageManager pnpm pin.
     required: false
-    default: "11.0.8"
-  cache-key-suffix:
-    description: Suffix appended to the cache key.
+    default: "package.json"
+  lockfile-path:
+    description: pnpm lockfile used to key the store cache.
     required: false
-    default: "node24-pnpm11"
-  use-restore-keys:
-    description: Whether to use restore-keys fallback for actions/cache.
+    default: "pnpm-lock.yaml"
+  node-version:
+    description: Expected Node.js version already installed by actions/setup-node.
     required: false
-    default: "true"
+    default: ""
   use-actions-cache:
-    description: Whether to restore pnpm store with actions/cache.
+    description: Whether actions/cache should cache the pnpm store.
     required: false
     default: "true"
 outputs:
-  cache-enabled:
-    description: Whether actions/cache restore was enabled.
-    value: ${{ steps.pnpm-cache-config.outputs.enabled }}
-  cache-hit:
-    description: Whether the pnpm store cache had an exact key hit.
-    value: ${{ steps.pnpm-cache-restore.outputs.cache-hit }}
-  cache-matched-key:
-    description: Cache key matched by restore, if any.
-    value: ${{ steps.pnpm-cache-restore.outputs.cache-matched-key }}
-  primary-key:
-    description: Primary pnpm store cache key.
-    value: ${{ steps.pnpm-cache-config.outputs.primary-key }}
-  store-path:
-    description: Resolved pnpm store path.
-    value: ${{ steps.pnpm-store.outputs.path }}
+  pnpm-version:
+    description: Resolved pnpm version activated by the setup action.
+    value: ${{ steps.pnpm-version.outputs.pnpm-version }}
+  project-dir:
+    description: Directory containing the packageManager file used for pnpm resolution.
+    value: ${{ steps.setup-pnpm.outputs.project-dir }}
 runs:
   using: composite
   steps:
-    - name: Setup pnpm (corepack retry)
+    - name: Validate pnpm setup inputs
+      id: setup-pnpm
+      shell: bash
+      env:
+        PACKAGE_MANAGER_FILE: ${{ inputs.package-manager-file }}
+        REQUESTED_NODE_VERSION: ${{ inputs.node-version }}
+      run: |
+        set -euo pipefail
+        project_dir="$(dirname "$PACKAGE_MANAGER_FILE")"
+        if [[ ! -f "$PACKAGE_MANAGER_FILE" ]]; then
+          echo "::error::package manager file not found: $PACKAGE_MANAGER_FILE"
+          exit 1
+        fi
+        echo "project-dir=$project_dir" >> "$GITHUB_OUTPUT"
+
+        requested_node="${REQUESTED_NODE_VERSION:-${NODE_VERSION:-}}"
+        source "$GITHUB_ACTION_PATH/ensure-node.sh"
+        openclaw_ensure_node "$requested_node"
+
+    - name: Setup pnpm from packageManager
       shell: bash
       env:
         COREPACK_ENABLE_DOWNLOAD_PROMPT: "0"
-        PNPM_VERSION: ${{ inputs.pnpm-version }}
+        PACKAGE_MANAGER_FILE: ${{ inputs.package-manager-file }}
       run: |
         set -euo pipefail
-        if [[ ! "$PNPM_VERSION" =~ ^[0-9]+(\.[0-9]+){1,2}([.-][0-9A-Za-z.-]+)?$ ]]; then
-          echo "::error::Invalid pnpm-version input: '$PNPM_VERSION'"
-          exit 2
-        fi
+        package_manager="$(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 '${package_manager:-<empty>}'"
+            exit 1
+            ;;
+        esac
         corepack enable
         for attempt in 1 2 3; do
-          if corepack prepare "pnpm@$PNPM_VERSION" --activate; then
-            pnpm -v
+          if corepack prepare "$package_manager" --activate; then
             exit 0
           fi
-          echo "corepack prepare failed (attempt $attempt/3). Retrying..."
-          sleep $((attempt * 10))
+          sleep $((attempt * 5))
         done
-        exit 1
+        corepack prepare "$package_manager" --activate
 
     - name: Resolve pnpm store path
       id: pnpm-store
+      if: ${{ inputs.use-actions-cache == 'true' && runner.os != 'Windows' }}
       shell: bash
-      run: echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT"
-
-    - name: Resolve pnpm store cache keys
-      id: pnpm-cache-config
-      shell: bash
-      env:
-        CACHE_KEY_SUFFIX: ${{ inputs.cache-key-suffix }}
-        LOCKFILE_HASH: ${{ hashFiles('pnpm-lock.yaml') }}
-        USE_ACTIONS_CACHE: ${{ inputs.use-actions-cache }}
-        USE_RESTORE_KEYS: ${{ inputs.use-restore-keys }}
       run: |
         set -euo pipefail
-        echo "enabled=$USE_ACTIONS_CACHE" >> "$GITHUB_OUTPUT"
-        echo "primary-key=${RUNNER_OS}-pnpm-store-${CACHE_KEY_SUFFIX}-${LOCKFILE_HASH}" >> "$GITHUB_OUTPUT"
-        if [ "$USE_RESTORE_KEYS" = "true" ]; then
-          echo "restore-keys=${RUNNER_OS}-pnpm-store-${CACHE_KEY_SUFFIX}-" >> "$GITHUB_OUTPUT"
-        else
-          echo "restore-keys=" >> "$GITHUB_OUTPUT"
-        fi
+        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
-      id: pnpm-cache-restore
-      if: inputs.use-actions-cache == 'true'
-      uses: actions/cache/restore@v5
+      if: ${{ inputs.use-actions-cache == 'true' && runner.os != 'Windows' }}
+      uses: actions/cache@v5
       with:
         path: ${{ steps.pnpm-store.outputs.path }}
-        key: ${{ steps.pnpm-cache-config.outputs.primary-key }}
-        restore-keys: ${{ steps.pnpm-cache-config.outputs.restore-keys }}
+        key: pnpm-store-${{ 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
+      shell: bash
+      env:
+        PROJECT_DIR: ${{ steps.setup-pnpm.outputs.project-dir }}
+      run: echo "pnpm-version=$(cd "$PROJECT_DIR" && pnpm -v)" >> "$GITHUB_OUTPUT"

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

@@ -0,0 +1,223 @@
+#!/usr/bin/env bash
+
+openclaw_node_version_matches() {
+  local actual="$1"
+  local requested="$2"
+  if [[ -z "$requested" ]]; then
+    return 0
+  fi
+  case "$requested" in
+    *x)
+      [[ "${actual%%.*}" == "${requested%%.*}" ]] || return 1
+      if [[ "${requested%%.*}" == "22" ]]; then
+        openclaw_node_version_at_least "$actual" "22.19.0"
+      fi
+      ;;
+    *.*.*)
+      [[ "$actual" == "$requested" ]]
+      ;;
+    *.*)
+      [[ "$actual" == "$requested".* ]]
+      ;;
+    *)
+      [[ "${actual%%.*}" == "$requested" ]]
+      ;;
+  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="$1"
+  local github_path_dir="${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
+    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
+}
+
+openclaw_find_toolcache_node() {
+  local requested_node="$1"
+  local roots=()
+  local root
+  for root in \
+    "${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 "$root" ]]; then
+      roots+=("$root")
+    fi
+  done
+
+  local node_root candidate candidate_version
+  for node_root in "${roots[@]}"; do
+    while IFS= read -r candidate; do
+      candidate_version="$("$candidate" -p 'process.versions.node' 2>/dev/null || true)"
+      if openclaw_node_version_matches "$candidate_version" "$requested_node"; then
+        printf '%s\n' "$candidate"
+        return 0
+      fi
+    done < <(find "$node_root" \( -name node -o -name node.exe \) -type f 2>/dev/null | sort -r)
+  done
+  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}"
+  if [[ -z "$requested_node" ]]; then
+    return 0
+  fi
+
+  local active_node_version node_bin
+  active_node_version="$(openclaw_active_node_version)"
+  if openclaw_node_version_matches "$active_node_version" "$requested_node"; then
+    echo "Using active Node ${active_node_version} at $(command -v node)"
+    return 0
+  fi
+
+  node_bin="$(openclaw_find_toolcache_node "$requested_node" || true)"
+  if [[ -n "$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="$(openclaw_active_node_version)"
+  if ! openclaw_node_version_matches "$active_node_version" "$requested_node"; then
+    echo "::error::Expected Node '${requested_node}', but active node is '${active_node_version:-missing}' at $(command -v node || true)"
+    return 1
+  fi
+}

.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/codex/prompts/mantis-telegram-desktop-proof.md

@@ -16,8 +16,15 @@ Hard limits:
 - Do not finish with tiny, cropped-wrong, off-bottom, or sidebar-heavy GIFs.
 - Do not invent a generic proof. The proof must match the PR behavior.
 - Do not force GIFs for internal-only, workflow-only, test-only, docs-only, or
-  otherwise non-visual PRs. A no-visual-proof manifest is a successful outcome
-  when GIFs would be misleading.
+  otherwise non-visual PRs. A no-visual-proof manifest is a successful workflow
+  outcome when GIFs would be misleading, but it is not proof that the PR passed.
+- Do not skip Telegram-visible PRs just because the proof needs a specific
+  message, mock response, media attachment, command, button, reaction, stop
+  timing, approval prompt, or progress/final delivery sequence. First write a
+  concrete proof plan and try the standard harness path.
+- Keep public-facing manifest summaries short and user-domain. Do not mention
+  harness internals, mock-provider limits, secret/trust boundaries, local paths,
+  transcript seeding, or workflow implementation details in the summary.
 
 Inputs are provided as environment variables:
 
@@ -39,12 +46,21 @@ Required workflow:
 2. Inspect the PR with `gh pr view "$MANTIS_PR_NUMBER"` and
    `gh pr diff "$MANTIS_PR_NUMBER"`.
 3. Decide whether the PR has a visibly reproducible Telegram Desktop
-   before/after. If it does not, write
+   before/after. Treat these as visible until proven otherwise: message text
+   formatting/content, progress drafts, native drafts, final delivery, media or
+   document delivery, inline buttons, approval prompts, stop/abort behavior,
+   reactions/status indicators, guest/inline responses, TTS/voice/audio
+   delivery, and routing changes whose result is visible in the chat. For those
+   PRs, define the exact Telegram stimulus and expected main/PR visual delta
+   before deciding to skip.
+
+   If the PR does not have a Telegram-visible before/after, write
    `${MANTIS_OUTPUT_DIR}/mantis-evidence.json` with `comparison.pass: true`, no
    artifacts, and a summary that starts with
-   `Mantis did not generate before/after GIFs because`. Include the concrete
-   reason in the summary. Use this manifest shape and do not create worktrees
-   or start Crabbox for this case:
+   `Mantis did not generate before/after GIFs because`. Include a short
+   public reason, such as `the PR changes internal session bookkeeping rather
+than Telegram-visible behavior`. Use this manifest shape and do not create
+   worktrees or start Crabbox for this case:
 
    ```json
    {
@@ -73,6 +89,15 @@ Required workflow:
    }
    ```
 
+   If the PR appears visual but proof is blocked by Telegram Desktop session
+   state, authorization, credentials, Crabbox, missing Telegram client support,
+   unavailable media/provider setup, or another capture-infrastructure issue,
+   do not describe it as a no-visual PR. Write a manifest with
+   `comparison.pass: false`, skipped lanes, no artifacts, and a summary that
+   starts with `Mantis could not capture Telegram Desktop proof because`. The
+   publisher will keep that out of PR comments so the failure stays in the
+   workflow logs and artifacts.
+
 4. Decide what Telegram message, mock model response, command, callback, button,
    media, or sequence best proves the PR. Use `MANTIS_INSTRUCTIONS` as extra
    maintainer guidance, not as a replacement for reading the PR.
@@ -94,8 +119,10 @@ Required workflow:
    `$OPENCLAW_TELEGRAM_USER_DRIVER_SCRIPT`, the workflow-provided `crabbox`
    binary, and the workflow-provided local `ffmpeg`/`ffprobe`; do not generate,
    install, or patch replacement proof tooling during the run. Use the same
-   proof idea for baseline and candidate. You may iterate and rerun if the
-   visual result is not convincing.
+   proof idea for baseline and candidate. Let `start` return or fail on its
+   own; do not kill it while Crabbox is still waiting for bootstrap. Use a long
+   command timeout for `start`, `send`, `view`, and `finish`. You may iterate
+   and rerun if the visual result is not convincing.
 7. Open Telegram Desktop directly to the newest relevant message with the
    runner `view` command before finishing each recording. Keep the chat scrolled
    to the bottom so new proof messages appear in-frame.
@@ -134,4 +161,6 @@ Expected final state:
   `Main` and `This PR`.
 - No-visual-proof manifests contain no artifacts and have `comparison.pass:
 true`.
+- Capture-infrastructure failure manifests contain no artifacts and have
+  `comparison.pass: false`.
 - The worktree can be dirty only under `.artifacts/`.

.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:
@@ -36,6 +41,12 @@
       - any-glob-to-any-file:
           - "extensions/google-meet/**"
           - "docs/plugins/google-meet.md"
+"plugin: meeting-notes":
+  - changed-files:
+      - any-glob-to-any-file:
+          - "extensions/meeting-notes/**"
+          - "docs/plugins/meeting-notes.md"
+          - "src/meeting-notes/**"
 "plugin: migrate-hermes":
   - changed-files:
       - any-glob-to-any-file:
@@ -286,6 +297,11 @@
   - changed-files:
       - any-glob-to-any-file:
           - "extensions/oc-path/**"
+"extensions: policy":
+  - changed-files:
+      - any-glob-to-any-file:
+          - "extensions/policy/**"
+          - "docs/cli/policy.md"
 "extensions: open-prose":
   - changed-files:
       - any-glob-to-any-file:
@@ -480,6 +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/package-trusted-sources.json

@@ -0,0 +1,4 @@
+{
+  "schemaVersion": 1,
+  "sources": {}
+}

.github/pull_request_template.md

@@ -1,159 +1,132 @@
 ## Summary
 
-Describe the problem and fix in 2–5 bullets:
+What problem does this PR solve?
+
+
+Why does this matter now?
+
+
+What is the intended outcome?
+
+
+What is intentionally out of scope?
+
+
+What does success look like?
+
+
+What should reviewers focus on?
+
+<details>
+<summary>Summary guidance</summary>
+
+This PR description is the contributor's durable explanation of the change. Write it for human maintainers first; ClawSweeper and Barnacle use the same text to understand intent, proof, risk, and current review state.
+
+Describe the intent and outcome in 2-5 bullets. Avoid restating the diff; reviewers and bots can read the changed files.
 
 If this PR fixes a plugin beta-release blocker, title it `fix(<plugin-id>): beta blocker - <summary>` and link the matching `Beta blocker: <plugin-name> - <summary>` issue labeled `beta-blocker`. Contributors cannot label PRs, so the title is the PR-side signal for maintainers and automation.
 
-- Problem:
-- Why it matters:
-- What changed:
-- What did NOT change (scope boundary):
+</details>
 
-## Change Type (select all)
+## Linked context
 
-- [ ] Bug fix
-- [ ] Feature
-- [ ] Refactor required for the fix
-- [ ] Docs
-- [ ] Security hardening
-- [ ] Chore/infra
+Which issue does this close?
 
-## Scope (select all touched areas)
+Closes #
 
-- [ ] Gateway / orchestration
-- [ ] Skills / tool execution
-- [ ] Auth / tokens
-- [ ] Memory / storage
-- [ ] Integrations
-- [ ] API / contracts
-- [ ] UI / DX
-- [ ] CI/CD / infra
+Which issues, PRs, or discussions are related?
 
-## Linked Issue/PR
+Related #
 
-- Closes #
-- Related #
-- [ ] This PR fixes a bug or regression
+Was this requested by a maintainer or owner?
+
+<details>
+<summary>Linked context guidance</summary>
+
+Link the issue, PR, discussion, maintainer request, or owner request that explains why this PR should exist. Maintainer context helps reviewers and automation distinguish intended work from drive-by churn.
+
+</details>
 
 ## Real behavior proof (required for external PRs)
 
-External contributors must show after-fix evidence from a real OpenClaw setup. Unit tests, mocks, lint, typechecks, snapshots, and CI are supplemental only. Screenshots are encouraged even for CLI, console, text, or log changes; terminal screenshots and copied live output count. Be mindful of private information like IP addresses, API keys, phone numbers, non-public endpoints, or other private details when providing evidence.
-
 - Behavior or issue addressed:
 - Real environment tested:
 - Exact steps or command run after this patch:
 - Evidence after fix (screenshot, recording, terminal capture, console output, redacted runtime log, linked artifact, or copied live output):
 - Observed result after fix:
 - What was not tested:
+- Proof limitations or environment constraints:
 - Before evidence (optional but encouraged):
 
-## Root Cause (if applicable)
+<details>
+<summary>Real behavior proof guidance</summary>
 
-For bug fixes or regressions, explain why this happened, not just what changed. Otherwise write `N/A`. If the cause is unclear, write `Unknown`.
+External contributors must show after-fix evidence from a real OpenClaw setup. Unit tests, mocks, lint, typechecks, snapshots, and CI are supplemental only.
 
-- Root cause:
-- Missing detection / guardrail:
-- Contributing context (if known):
+Screenshots are encouraged even for CLI, console, text, or log changes. Terminal screenshots, copied live output, redacted runtime logs, recordings, and linked artifacts count.
 
-## Regression Test Plan (if applicable)
+If your environment cannot produce the ideal proof, explain that under `Proof limitations or environment constraints` so reviewers and ClawSweeper can direct the next step properly.
 
-For bug fixes or regressions, name the smallest reliable test coverage that should catch this. Otherwise write `N/A`.
+Be mindful of private information like IP addresses, API keys, phone numbers, non-public endpoints, or other private details when providing evidence.
 
-- Coverage level that should have caught this:
-  - [ ] Unit test
-  - [ ] Seam / integration test
-  - [ ] End-to-end test
-  - [ ] Existing coverage already sufficient
-- Target test or file:
-- Scenario the test should lock in:
-- Why this is the smallest reliable guardrail:
-- Existing test that already covers this (if any):
-- If no new test is added, why not:
+</details>
 
-## User-visible / Behavior Changes
+## Tests and validation
 
-List user-visible changes (including defaults/config).  
-If none, write `None`.
+Which commands did you run?
 
-## Diagram (if applicable)
 
-For UI changes or non-trivial logic flows, include a small ASCII diagram reviewers can scan quickly. Otherwise write `N/A`.
+What regression coverage was added or updated?
 
-```text
-Before:
-[user action] -> [old state]
 
-After:
-[user action] -> [new state] -> [result]
-```
+What failed before this fix, if known?
 
-## Security Impact (required)
 
-- New permissions/capabilities? (`Yes/No`)
-- Secrets/tokens handling changed? (`Yes/No`)
-- New/changed network calls? (`Yes/No`)
-- Command/tool execution surface changed? (`Yes/No`)
-- Data access scope changed? (`Yes/No`)
-- If any `Yes`, explain risk + mitigation:
+If no test was added, why not?
 
-## Repro + Verification
+<details>
+<summary>Testing guidance</summary>
 
-### Environment
+List focused commands, not every incidental check. CI is useful support, but external PRs still need real behavior proof above when behavior changes.
 
-- OS:
-- Runtime/container:
-- Model/provider:
-- Integration/channel (if any):
-- Relevant config (redacted):
+</details>
 
-### Steps
+## Risk checklist
 
-1.
-2.
-3.
+Did user-visible behavior change? (`Yes/No`)
 
-### Expected
 
--
+Did config, environment, or migration behavior change? (`Yes/No`)
 
-### Actual
 
--
+Did security, auth, secrets, network, or tool execution behavior change? (`Yes/No`)
 
-## Evidence
 
-Attach at least one:
+What is the highest-risk area?
 
-- [ ] Failing test/log before + passing after
-- [ ] Trace/log snippets
-- [ ] Screenshot/recording
-- [ ] Perf numbers (if relevant)
 
-## Human Verification (required)
+How is that risk mitigated?
 
-What you personally verified (not just CI), and how:
+<details>
+<summary>Risk guidance</summary>
 
-- Verified scenarios:
-- Edge cases checked:
-- What you did **not** verify:
+Use this for author judgment that is not obvious from the diff. ClawSweeper can see touched files, but it cannot know which behavior you think is risky, why the risk is acceptable, or what mitigation reviewers should verify.
 
-## Review Conversations
+</details>
 
-- [ ] I replied to or resolved every bot review conversation I addressed in this PR.
-- [ ] I left unresolved only the conversations that still need reviewer or maintainer judgment.
+## Current review state
 
-If a bot review conversation is addressed by this PR, resolve that conversation yourself. Do not leave bot review conversation cleanup for maintainers.
+What is the next action?
 
-## Compatibility / Migration
 
-- Backward compatible? (`Yes/No`)
-- Config/env changes? (`Yes/No`)
-- Migration needed? (`Yes/No`)
-- If yes, exact upgrade steps:
+What is still waiting on author, maintainer, CI, or external proof?
 
-## Risks and Mitigations
 
-List only real risks for this PR. Add/remove entries as needed. If none, write `None`.
+Which bot or reviewer comments were addressed?
 
-- Risk:
-  - Mitigation:
+<details>
+<summary>Review state guidance</summary>
+
+Keep this as the durable state for review progress. If useful information appears in comments, fold the current next action or blocker back here so maintainers and ClawSweeper do not need to reconstruct state from comment history.
+
+</details>

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

@@ -41,6 +41,10 @@ jobs:
           set -euo pipefail
 
           workdir="$GITHUB_WORKSPACE"
+          if [[ -z "$CHECKOUT_TOKEN" ]]; then
+            echo "checkout token is missing" >&2
+            exit 1
+          fi
           auth_header="$(printf 'x-access-token:%s' "$CHECKOUT_TOKEN" | base64 | tr -d '\n')"
 
           reset_checkout_dir() {
@@ -57,9 +61,9 @@ 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.https://github.com/.extraheader=AUTHORIZATION: basic ${auth_header}" \
+              -c "http.extraheader=AUTHORIZATION: basic ${auth_header}" \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
 
@@ -187,12 +191,15 @@ jobs:
           git fetch --no-tags --depth=50 origin "+refs/heads/main:refs/remotes/origin/main"
 
           node_bin="$(dirname "$(node -p 'process.execPath')")"
-          pnpm_bin="$(command -v pnpm)"
           sudo ln -sf "$node_bin/node" /usr/local/bin/node
           sudo ln -sf "$node_bin/npm" /usr/local/bin/npm
           sudo ln -sf "$node_bin/npx" /usr/local/bin/npx
           sudo ln -sf "$node_bin/corepack" /usr/local/bin/corepack
-          sudo ln -sf "$pnpm_bin" /usr/local/bin/pnpm
+          sudo tee /usr/local/bin/pnpm >/dev/null <<'PNPM'
+          #!/usr/bin/env bash
+          exec /usr/local/bin/corepack pnpm "$@"
+          PNPM
+          sudo chmod 0755 /usr/local/bin/pnpm
 
       - name: Hydrate Testbox provider env helper
         shell: bash
@@ -222,6 +229,6 @@ jobs:
 
       - name: Run Testbox
         uses: useblacksmith/run-testbox@5ca05834db1d3813554d1dd109e5f2087a8d7cbc
-        if: always()
+        if: success()
         env:
           FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"

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

@@ -39,6 +39,10 @@ jobs:
           set -euo pipefail
 
           workdir="$GITHUB_WORKSPACE"
+          if [[ -z "$CHECKOUT_TOKEN" ]]; then
+            echo "checkout token is missing" >&2
+            exit 1
+          fi
           auth_header="$(printf 'x-access-token:%s' "$CHECKOUT_TOKEN" | base64 | tr -d '\n')"
 
           reset_checkout_dir() {
@@ -55,9 +59,9 @@ 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.https://github.com/.extraheader=AUTHORIZATION: basic ${auth_header}" \
+              -c "http.extraheader=AUTHORIZATION: basic ${auth_header}" \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
 
@@ -88,12 +92,15 @@ jobs:
           git fetch --no-tags --depth=50 origin "+refs/heads/main:refs/remotes/origin/main"
 
           node_bin="$(dirname "$(node -p 'process.execPath')")"
-          pnpm_bin="$(command -v pnpm)"
           sudo ln -sf "$node_bin/node" /usr/local/bin/node
           sudo ln -sf "$node_bin/npm" /usr/local/bin/npm
           sudo ln -sf "$node_bin/npx" /usr/local/bin/npx
           sudo ln -sf "$node_bin/corepack" /usr/local/bin/corepack
-          sudo ln -sf "$pnpm_bin" /usr/local/bin/pnpm
+          sudo tee /usr/local/bin/pnpm >/dev/null <<'PNPM'
+          #!/usr/bin/env bash
+          exec /usr/local/bin/corepack pnpm "$@"
+          PNPM
+          sudo chmod 0755 /usr/local/bin/pnpm
 
       - name: Hydrate Testbox provider env helper
         shell: bash
@@ -103,6 +110,7 @@ jobs:
           ANTHROPIC_API_TOKEN: ${{ secrets.ANTHROPIC_API_TOKEN }}
           CEREBRAS_API_KEY: ${{ secrets.CEREBRAS_API_KEY }}
           DEEPINFRA_API_KEY: ${{ secrets.DEEPINFRA_API_KEY }}
+          FACTORY_API_KEY: ${{ secrets.FACTORY_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
           GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
@@ -123,7 +131,6 @@ jobs:
 
       - name: Run Testbox
         uses: useblacksmith/run-testbox@5ca05834db1d3813554d1dd109e5f2087a8d7cbc
-        if: always()
-        continue-on-error: true
+        if: success()
         env:
           FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"

.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

@@ -31,10 +31,17 @@ permissions:
 
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
+  PNPM_CONFIG_CHILD_CONCURRENCY: "1"
+  PNPM_CONFIG_MODULES_DIR: "/tmp/openclaw-pnpm-node-modules"
+  PNPM_CONFIG_NETWORK_CONCURRENCY: "1"
+  PNPM_CONFIG_STORE_DIR: "/tmp/openclaw-pnpm-store"
+  PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN: "false"
+  PNPM_CONFIG_VIRTUAL_STORE_DIR: "/tmp/openclaw-pnpm-virtual-store"
 
 jobs:
   hydrate:
     name: hydrate
+    if: ${{ inputs.crabbox_job != 'hydrate-github' && inputs.crabbox_job != 'hydrate-windows-daemon' }}
     runs-on: [self-hosted, "${{ inputs.crabbox_runner_label }}"]
     timeout-minutes: 120
     steps:
@@ -42,37 +49,133 @@ jobs:
         with:
           ref: ${{ inputs.ref || github.ref }}
 
-      - name: Setup Node environment
-        uses: ./.github/actions/setup-node-env
+      - name: Setup Node.js
+        uses: actions/setup-node@v6
         with:
-          install-bun: "false"
+          node-version: "24"
+
+      - name: Setup pnpm and dependencies
+        shell: bash
+        env:
+          CI: "true"
+        run: |
+          set -euo pipefail
+
+          export XDG_CACHE_HOME="${XDG_CACHE_HOME:-$RUNNER_TEMP/cache}"
+          export COREPACK_HOME="${COREPACK_HOME:-$XDG_CACHE_HOME/corepack}"
+          export PNPM_HOME="${PNPM_HOME:-$RUNNER_TEMP/pnpm-home}"
+          mkdir -p "$XDG_CACHE_HOME" "$COREPACK_HOME" "$PNPM_HOME"
+          export PATH="$PNPM_HOME:$PATH"
+          {
+            echo "XDG_CACHE_HOME=$XDG_CACHE_HOME"
+            echo "COREPACK_HOME=$COREPACK_HOME"
+            echo "PNPM_HOME=$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" >> "$GITHUB_PATH"
+          export PATH="$node_bin:$PATH"
+
+          node -v
+          npm -v
+          pnpm -v
+
+          install_args=(
+            install
+            --prefer-offline
+            --ignore-scripts=false
+            --config.engine-strict=false
+            --config.enable-pre-post-scripts=true
+            --config.side-effects-cache=true
+            --frozen-lockfile
+          )
+          append_pnpm_option_arg() {
+            local env_name="$1"
+            local option_name="$2"
+            local value="${!env_name-}"
+            if [ -n "$value" ]; then
+              install_args+=("--${option_name}=${value}")
+            fi
+          }
+          append_pnpm_option_arg PNPM_CONFIG_CHILD_CONCURRENCY child-concurrency
+          append_pnpm_option_arg PNPM_CONFIG_MODULES_DIR modules-dir
+          append_pnpm_option_arg PNPM_CONFIG_NETWORK_CONCURRENCY network-concurrency
+          append_pnpm_option_arg PNPM_CONFIG_VIRTUAL_STORE_DIR virtual-store-dir
+          if [ -n "${PNPM_CONFIG_MODULES_DIR:-}" ]; then
+            mkdir -p "$PNPM_CONFIG_MODULES_DIR"
+            ln -sfn . "$PNPM_CONFIG_MODULES_DIR/node_modules"
+          fi
+          pnpm "${install_args[@]}" || pnpm "${install_args[@]}"
+          if [ -n "${PNPM_CONFIG_MODULES_DIR:-}" ]; then
+            rm -rf node_modules
+            ln -sfn "$PNPM_CONFIG_MODULES_DIR" node_modules
+            ln -sfn . "$PNPM_CONFIG_MODULES_DIR/node_modules"
+          fi
+
+      - name: Fetch main ref
+        shell: bash
+        run: |
+          set -euo pipefail
+
+          if git rev-parse --is-inside-work-tree >/dev/null 2>&1; then
+            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
 
-          git fetch --no-tags --depth=50 origin "+refs/heads/main:refs/remotes/origin/main"
-
           node_bin="$(dirname "$(node -p 'process.execPath')")"
-          pnpm_bin="$(command -v pnpm)"
           sudo ln -sf "$node_bin/node" /usr/local/bin/node
           sudo ln -sf "$node_bin/npm" /usr/local/bin/npm
           sudo ln -sf "$node_bin/npx" /usr/local/bin/npx
           sudo ln -sf "$node_bin/corepack" /usr/local/bin/corepack
-          sudo ln -sf "$pnpm_bin" /usr/local/bin/pnpm
+          sudo tee /usr/local/bin/pnpm >/dev/null <<'PNPM'
+          #!/usr/bin/env bash
+          exec /usr/local/bin/corepack pnpm "$@"
+          PNPM
+          sudo chmod 0755 /usr/local/bin/pnpm
 
-      - name: Ensure Docker is available
+      - name: Ensure Docker is running
         shell: bash
         run: |
           set -euo pipefail
 
           if ! command -v docker >/dev/null 2>&1; then
-            curl -fsSL https://get.docker.com | sudo sh
+            echo "docker not found; installing fallback engine"
+            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
-            sudo systemctl start docker
+            sudo systemctl start docker || true
+          elif command -v service >/dev/null 2>&1; then
+            sudo service docker start || true
           fi
 
           if [ -S /var/run/docker.sock ]; then
@@ -82,30 +185,42 @@ jobs:
             sudo chmod 666 /var/run/docker.sock
           fi
 
+          if ! docker buildx version >/dev/null 2>&1; then
+            arch="$(uname -m)"
+            case "$arch" in
+              aarch64|arm64) buildx_arch=arm64 ;;
+              x86_64|amd64) buildx_arch=amd64 ;;
+              *) echo "unsupported buildx arch: $arch" >&2; exit 2 ;;
+            esac
+            buildx_version="${DOCKER_BUILDX_VERSION:-v0.15.1}"
+            mkdir -p "$HOME/.docker/cli-plugins"
+            curl --fail --show-error --location \
+              --connect-timeout "${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"
+          fi
+
+          docker version
+          docker buildx version
+          docker compose version || true
+
+      - name: Ensure SSH is available
+        shell: bash
+        run: |
+          set -euo pipefail
+          if command -v systemctl >/dev/null 2>&1; then
+            sudo systemctl start ssh || sudo systemctl start sshd || true
+          elif command -v service >/dev/null 2>&1; then
+            sudo service ssh start || sudo service sshd start || true
+          fi
+
       - name: Hydrate provider env helper
         shell: bash
-        env:
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          ANTHROPIC_API_KEY_OLD: ${{ secrets.ANTHROPIC_API_KEY_OLD }}
-          ANTHROPIC_API_TOKEN: ${{ secrets.ANTHROPIC_API_TOKEN }}
-          CEREBRAS_API_KEY: ${{ secrets.CEREBRAS_API_KEY }}
-          DEEPINFRA_API_KEY: ${{ secrets.DEEPINFRA_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          KIMI_API_KEY: ${{ secrets.KIMI_API_KEY }}
-          MINIMAX_API_KEY: ${{ secrets.MINIMAX_API_KEY }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          MOONSHOT_API_KEY: ${{ secrets.MOONSHOT_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          OPENAI_BASE_URL: ${{ secrets.OPENAI_BASE_URL }}
-          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
-          QWEN_API_KEY: ${{ secrets.QWEN_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          ZAI_API_KEY: ${{ secrets.ZAI_API_KEY }}
-          Z_AI_API_KEY: ${{ secrets.Z_AI_API_KEY }}
         run: bash scripts/ci-hydrate-testbox-env.sh
 
       - name: Mark Crabbox ready
@@ -135,7 +250,401 @@ 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; 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"
+          mv "${env_file}.tmp" "$env_file"
+          {
+            echo "# Docker containers visible from the hydrated runner"
+            docker ps --format '{{.Names}}\t{{.Image}}\t{{.Ports}}' 2>/dev/null || true
+          } > "${services_file}.tmp"
+          mv "${services_file}.tmp" "$services_file"
+          tmp="${state}.tmp"
+          {
+            echo "WORKSPACE=${GITHUB_WORKSPACE}"
+            echo "RUN_ID=${GITHUB_RUN_ID}"
+            echo "JOB=${job}"
+            echo "ENV_FILE=${env_file}"
+            echo "SERVICES_FILE=${services_file}"
+            echo "READY_AT=$(date -u +%Y-%m-%dT%H:%M:%SZ)"
+          } > "$tmp"
+          mv "$tmp" "$state"
+
+      - name: Keep Crabbox job alive
+        shell: bash
+        env:
+          CRABBOX_ID: ${{ inputs.crabbox_id }}
+          CRABBOX_KEEP_ALIVE_MINUTES: ${{ inputs.crabbox_keep_alive_minutes }}
+        run: |
+          set -euo pipefail
+          case "$CRABBOX_ID" in
+            ''|*[!A-Za-z0-9._-]*)
+              echo "Invalid crabbox_id" >&2
+              exit 2
+              ;;
+          esac
+          minutes="${CRABBOX_KEEP_ALIVE_MINUTES}"
+          case "$minutes" in
+            ''|*[!0-9]*) minutes=90 ;;
+          esac
+          stop="$HOME/.crabbox/actions/${CRABBOX_ID}.stop"
+          deadline=$(( $(date +%s) + minutes * 60 ))
+          while [ "$(date +%s)" -lt "$deadline" ]; do
+            if [ -f "$stop" ]; then
+              exit 0
+            fi
+            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: ${{ inputs.crabbox_job == 'hydrate-github' }}
+    runs-on: [self-hosted, "${{ inputs.crabbox_runner_label }}"]
+    timeout-minutes: 120
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          ref: ${{ inputs.ref || github.ref }}
+
+      - name: Setup Node environment
+        uses: ./.github/actions/setup-node-env
+        with:
+          install-bun: "false"
+          use-actions-cache: "false"
+
+      - name: Prepare Crabbox shell
+        shell: bash
+        run: |
+          set -euo pipefail
+
+          if git rev-parse --is-inside-work-tree >/dev/null 2>&1; then
+            git fetch --no-tags --depth=50 origin "+refs/heads/main:refs/remotes/origin/main"
+          fi
+
+          node_bin="$(dirname "$(node -p 'process.execPath')")"
+          sudo ln -sf "$node_bin/node" /usr/local/bin/node
+          sudo ln -sf "$node_bin/npm" /usr/local/bin/npm
+          sudo ln -sf "$node_bin/npx" /usr/local/bin/npx
+          sudo ln -sf "$node_bin/corepack" /usr/local/bin/corepack
+          sudo tee /usr/local/bin/pnpm >/dev/null <<'PNPM'
+          #!/usr/bin/env bash
+          exec /usr/local/bin/corepack pnpm "$@"
+          PNPM
+          sudo chmod 0755 /usr/local/bin/pnpm
+
+      - name: Ensure Docker is running
+        shell: bash
+        run: |
+          set -euo pipefail
+
+          if ! command -v docker >/dev/null 2>&1; then
+            echo "docker not found; installing fallback engine"
+            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
+            sudo systemctl start docker || true
+          elif command -v service >/dev/null 2>&1; then
+            sudo service docker start || true
+          fi
+
+          if [ -S /var/run/docker.sock ]; then
+            sudo usermod -aG docker "$USER" || true
+            # The runner process keeps its original groups; grant this
+            # ephemeral runner session access without requiring a relogin.
+            sudo chmod 666 /var/run/docker.sock
+          fi
+
+          if ! docker buildx version >/dev/null 2>&1; then
+            arch="$(uname -m)"
+            case "$arch" in
+              aarch64|arm64) buildx_arch=arm64 ;;
+              x86_64|amd64) buildx_arch=amd64 ;;
+              *) echo "unsupported buildx arch: $arch" >&2; exit 2 ;;
+            esac
+            buildx_version="${DOCKER_BUILDX_VERSION:-v0.15.1}"
+            mkdir -p "$HOME/.docker/cli-plugins"
+            curl --fail --show-error --location \
+              --connect-timeout "${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"
+          fi
+
+          docker version
+          docker buildx version
+          docker compose version || true
+
+      - name: Ensure SSH is available
+        shell: bash
+        run: |
+          set -euo pipefail
+          if command -v systemctl >/dev/null 2>&1; then
+            sudo systemctl start ssh || sudo systemctl start sshd || true
+          elif command -v service >/dev/null 2>&1; then
+            sudo service ssh start || sudo service sshd start || true
+          fi
+
+      - name: Hydrate provider env helper
+        shell: bash
+        env:
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          ANTHROPIC_API_KEY_OLD: ${{ secrets.ANTHROPIC_API_KEY_OLD }}
+          ANTHROPIC_API_TOKEN: ${{ secrets.ANTHROPIC_API_TOKEN }}
+          CEREBRAS_API_KEY: ${{ secrets.CEREBRAS_API_KEY }}
+          DEEPINFRA_API_KEY: ${{ secrets.DEEPINFRA_API_KEY }}
+          FACTORY_API_KEY: ${{ secrets.FACTORY_API_KEY }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
+          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+          KIMI_API_KEY: ${{ secrets.KIMI_API_KEY }}
+          MINIMAX_API_KEY: ${{ secrets.MINIMAX_API_KEY }}
+          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
+          MOONSHOT_API_KEY: ${{ secrets.MOONSHOT_API_KEY }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          OPENAI_BASE_URL: ${{ secrets.OPENAI_BASE_URL }}
+          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
+          QWEN_API_KEY: ${{ secrets.QWEN_API_KEY }}
+          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
+          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
+          ZAI_API_KEY: ${{ secrets.ZAI_API_KEY }}
+          Z_AI_API_KEY: ${{ secrets.Z_AI_API_KEY }}
+        run: bash scripts/ci-hydrate-testbox-env.sh
+
+      - name: Mark Crabbox ready
+        shell: bash
+        env:
+          CRABBOX_ID: ${{ inputs.crabbox_id }}
+          CRABBOX_JOB: ${{ inputs.crabbox_job }}
+        run: |
+          set -euo pipefail
+          job="${CRABBOX_JOB}"
+          if [ -z "$job" ]; then job=hydrate-github; fi
+          case "$CRABBOX_ID" in
+            ''|*[!A-Za-z0-9._-]*)
+              echo "Invalid crabbox_id" >&2
+              exit 2
+              ;;
+          esac
+          mkdir -p "$HOME/.crabbox/actions"
+          state="$HOME/.crabbox/actions/${CRABBOX_ID}.env"
+          env_file="$HOME/.crabbox/actions/${CRABBOX_ID}.env.sh"
+          services_file="$HOME/.crabbox/actions/${CRABBOX_ID}.services"
+          write_export() {
+            key="$1"
+            value="${!key-}"
+            if [ -n "$value" ]; then
+              printf 'export %s=%q\n' "$key" "$value"
+            fi
+          }
+          {
+            for key in CI GITHUB_ACTIONS GITHUB_WORKSPACE GITHUB_REPOSITORY GITHUB_RUN_ID GITHUB_RUN_NUMBER GITHUB_RUN_ATTEMPT GITHUB_REF GITHUB_REF_NAME GITHUB_SHA GITHUB_EVENT_NAME GITHUB_ACTOR RUNNER_OS RUNNER_ARCH RUNNER_TEMP RUNNER_TOOL_CACHE NODE_BIN PNPM_HOME PNPM_CONFIG_CHILD_CONCURRENCY PNPM_CONFIG_MODULES_DIR PNPM_CONFIG_NETWORK_CONCURRENCY PNPM_CONFIG_STORE_DIR PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN PNPM_CONFIG_VIRTUAL_STORE_DIR PATH; do
               write_export "$key"
             done
           } > "${env_file}.tmp"

.github/workflows/dependency-change-awareness.yml

@@ -34,11 +34,15 @@ jobs:
 
             const isDependencyFile = (filename) =>
               filename === "package.json" ||
+              filename === "package-lock.json" ||
+              filename === "npm-shrinkwrap.json" ||
               filename === "pnpm-lock.yaml" ||
               filename === "pnpm-workspace.yaml" ||
               filename === "ui/package.json" ||
               filename.startsWith("patches/") ||
               /^packages\/[^/]+\/package\.json$/u.test(filename) ||
+              /^extensions\/[^/]+\/package-lock\.json$/u.test(filename) ||
+              /^extensions\/[^/]+\/npm-shrinkwrap\.json$/u.test(filename) ||
               /^extensions\/[^/]+\/package\.json$/u.test(filename);
 
             const sanitizeDisplayValue = (value) =>
@@ -143,7 +147,8 @@ jobs:
               "",
               "Maintainer follow-up:",
               "- Review whether the dependency changes are intentional.",
-              "- Inspect resolved package deltas when lockfile or workspace dependency policy changes are present.",
+              "- Inspect resolved package deltas when lockfile, shrinkwrap, or workspace dependency policy changes are present.",
+              "- Treat `package-lock.json` and `npm-shrinkwrap.json` diffs as security-review surfaces.",
               "- Run `pnpm deps:changes:report -- --base-ref origin/main --markdown /tmp/dependency-changes.md --json /tmp/dependency-changes.json` locally for detailed release-style evidence.",
             ].join("\n");
 

.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)
@@ -155,13 +163,98 @@ jobs:
           cache-from: type=gha,scope=docker-release-amd64
           cache-to: type=gha,mode=max,scope=docker-release-amd64
           build-args: |
-            OPENCLAW_EXTENSIONS=diagnostics-otel
+            OPENCLAW_EXTENSIONS=diagnostics-otel,codex
           tags: ${{ steps.tags.outputs.value }}
           labels: ${{ steps.labels.outputs.value }}
           sbom: true
           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)
@@ -253,13 +354,98 @@ jobs:
           cache-from: type=gha,scope=docker-release-arm64
           cache-to: type=gha,mode=max,scope=docker-release-arm64
           build-args: |
-            OPENCLAW_EXTENSIONS=diagnostics-otel
+            OPENCLAW_EXTENSIONS=diagnostics-otel,codex
           tags: ${{ steps.tags.outputs.value }}
           labels: ${{ steps.labels.outputs.value }}
           sbom: true
           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/docs-sync-publish.yml

@@ -43,7 +43,7 @@ jobs:
         if: env.OPENCLAW_DOCS_SYNC_TOKEN != ''
         uses: actions/setup-node@v6
         with:
-          node-version: "22.18.0"
+          node-version: "24.x"
 
       - name: Clone publish repo
         if: env.OPENCLAW_DOCS_SYNC_TOKEN != ''

.github/workflows/docs.yml

@@ -6,6 +6,7 @@ on:
     paths:
       - "**/*.md"
       - "docs/**"
+      - "!CHANGELOG.md"
 
 permissions:
   contents: read
@@ -35,5 +36,15 @@ jobs:
         with:
           install-bun: "false"
 
+      - name: Checkout ClawHub docs source
+        uses: actions/checkout@v6
+        with:
+          repository: openclaw/clawhub
+          path: clawhub-source
+          fetch-depth: 1
+          persist-credentials: false
+
       - name: Check docs
+        env:
+          OPENCLAW_DOCS_SYNC_CLAWHUB_REPO: ${{ github.workspace }}/clawhub-source
         run: pnpm check:docs

.github/workflows/install-smoke.yml

@@ -109,6 +109,7 @@ jobs:
         uses: actions/checkout@v6
         with:
           ref: ${{ inputs.ref || github.ref }}
+          persist-credentials: false
 
       - name: Set up Blacksmith Docker Builder
         uses: useblacksmith/setup-docker-builder@722e97d12b1d06a961800dd6c05d79d951ad3c80 # v1
@@ -120,7 +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 \
@@ -131,7 +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 "
@@ -162,7 +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 "
@@ -219,6 +220,7 @@ jobs:
         uses: actions/checkout@v6
         with:
           ref: ${{ inputs.ref || github.ref }}
+          persist-credentials: false
 
       - name: Log in to GHCR
         uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
@@ -233,7 +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
@@ -254,7 +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 \
@@ -290,6 +292,7 @@ jobs:
         uses: actions/checkout@v6
         with:
           ref: ${{ inputs.ref || github.ref }}
+          persist-credentials: false
 
       - name: Run QR package install smoke
         env:
@@ -305,6 +308,7 @@ jobs:
         uses: actions/checkout@v6
         with:
           ref: ${{ inputs.ref || github.ref }}
+          persist-credentials: false
 
       - name: Log in to GHCR
         uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
@@ -316,13 +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 "
@@ -355,7 +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 "
@@ -410,6 +414,7 @@ jobs:
         uses: actions/checkout@v6
         with:
           ref: ${{ inputs.ref || github.ref }}
+          persist-credentials: false
 
       - name: Log in to GHCR
         uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
@@ -421,7 +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
@@ -430,7 +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 \
@@ -439,7 +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 \
@@ -454,10 +459,10 @@ jobs:
 
       - name: Run installer docker tests
         env:
-          OPENCLAW_INSTALL_URL: https://openclaw.ai/install.sh
-          OPENCLAW_INSTALL_CLI_URL: https://openclaw.ai/install-cli.sh
+          OPENCLAW_INSTALL_URL: file:///tmp/openclaw-install.sh
+          OPENCLAW_INSTALL_CLI_URL: file:///tmp/openclaw-install-cli.sh
           OPENCLAW_NO_ONBOARD: "1"
-          OPENCLAW_INSTALL_SMOKE_SKIP_CLI: "1"
+          OPENCLAW_INSTALL_SMOKE_SKIP_CLI: "0"
           OPENCLAW_INSTALL_SMOKE_SKIP_IMAGE_BUILD: "1"
           OPENCLAW_INSTALL_NONROOT_SKIP_IMAGE_BUILD: "1"
           OPENCLAW_INSTALL_SMOKE_SKIP_NONROOT: "0"
@@ -468,6 +473,24 @@ jobs:
           OPENCLAW_INSTALL_SMOKE_UPDATE_SKIP_LOCAL_BUILD: "1"
         run: bash scripts/test-install-sh-docker.sh
 
+      - name: Run Rocky Linux installer smoke
+        run: |
+          timeout --kill-after=30s 20m docker run --rm \
+            -e OPENCLAW_NO_ONBOARD=1 \
+            -e OPENCLAW_NO_PROMPT=1 \
+            -v "$PWD/scripts/install.sh:/tmp/install.sh:ro" \
+            rockylinux:9@sha256:d7be1c094cc5845ee815d4632fe377514ee6ebcf8efaed6892889657e5ddaaa6 \
+            bash -lc 'dnf install -y -q ca-certificates tar gzip xz findutils which sudo >/dev/null && bash /tmp/install.sh --install-method npm --version latest --no-onboard --no-prompt --verify && openclaw --version'
+
+      - name: Run Rocky Linux CLI installer smoke
+        run: |
+          timeout --kill-after=30s 20m docker run --rm \
+            -e OPENCLAW_NO_ONBOARD=1 \
+            -e OPENCLAW_NO_PROMPT=1 \
+            -v "$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'
@@ -477,6 +500,7 @@ jobs:
         uses: actions/checkout@v6
         with:
           ref: ${{ inputs.ref || github.ref }}
+          persist-credentials: false
 
       - name: Log in to GHCR
         uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
@@ -488,7 +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
@@ -515,6 +539,7 @@ jobs:
         uses: actions/checkout@v6
         with:
           ref: ${{ inputs.ref || github.ref }}
+          persist-credentials: false
 
       - name: Set up Blacksmith Docker Builder
         uses: useblacksmith/setup-docker-builder@722e97d12b1d06a961800dd6c05d79d951ad3c80 # v1

.github/workflows/labeler.yml

@@ -89,10 +89,10 @@ jobs:
               per_page: 100,
             });
 
-            const excludedLockfiles = new Set(["pnpm-lock.yaml", "package-lock.json", "yarn.lock", "bun.lockb"]);
+            const excludedLockfiles = new Set(["pnpm-lock.yaml", "package-lock.json", "npm-shrinkwrap.json", "yarn.lock", "bun.lockb"]);
             const totalChangedLines = files.reduce((total, file) => {
               const path = file.filename ?? "";
-              if (path.startsWith("docs/") || excludedLockfiles.has(path)) {
+              if (path.startsWith("docs/") || excludedLockfiles.has(path) || path.endsWith("/package-lock.json") || path.endsWith("/npm-shrinkwrap.json")) {
                 return total;
               }
               return total + (file.additions ?? 0) + (file.deletions ?? 0);
@@ -603,10 +603,10 @@ jobs:
                 per_page: 100,
               });
 
-              const excludedLockfiles = new Set(["pnpm-lock.yaml", "package-lock.json", "yarn.lock", "bun.lockb"]);
+              const excludedLockfiles = new Set(["pnpm-lock.yaml", "package-lock.json", "npm-shrinkwrap.json", "yarn.lock", "bun.lockb"]);
               const totalChangedLines = files.reduce((total, file) => {
                 const path = file.filename ?? "";
-                if (path.startsWith("docs/") || excludedLockfiles.has(path)) {
+                if (path.startsWith("docs/") || excludedLockfiles.has(path) || path.endsWith("/package-lock.json") || path.endsWith("/npm-shrinkwrap.json")) {
                   return total;
                 }
                 return total + (file.additions ?? 0) + (file.deletions ?? 0);
@@ -760,6 +760,7 @@ jobs:
             core.info(`Processed ${processed} pull requests.`);
 
   label-issues:
+    if: github.event_name == 'issues'
     permissions:
       issues: write
     runs-on: ubuntu-24.04

.github/workflows/macos-release.yml

@@ -25,7 +25,6 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
-  PNPM_VERSION: "11.0.8"
 
 jobs:
   validate_macos_release_request:
@@ -53,7 +52,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "false"
 
       - name: Ensure matching GitHub release exists
@@ -95,8 +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-discord-smoke.yml

@@ -25,7 +25,6 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.x"
-  PNPM_VERSION: "11.0.8"
   OPENCLAW_BUILD_PRIVATE_QA: "1"
   OPENCLAW_ENABLE_PRIVATE_QA_CLI: "1"
 
@@ -142,7 +141,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Build private QA runtime
@@ -168,7 +166,7 @@ jobs:
 
       - name: Upload Mantis artifacts
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: mantis-discord-smoke-${{ github.run_id }}-${{ github.run_attempt }}
           path: .artifacts/qa-e2e/mantis/

.github/workflows/mantis-discord-status-reactions.yml

@@ -32,7 +32,6 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.x"
-  PNPM_VERSION: "11.0.8"
   OPENCLAW_BUILD_PRIVATE_QA: "1"
   OPENCLAW_ENABLE_PRIVATE_QA_CLI: "1"
 
@@ -255,7 +254,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Build Mantis harness
@@ -528,7 +526,7 @@ jobs:
       - name: Upload Mantis status reaction artifacts
         id: upload_artifact
         if: ${{ always() && steps.run_mantis.outputs.output_dir != '' }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: mantis-discord-status-reactions-${{ github.run_id }}-${{ github.run_attempt }}
           path: ${{ steps.run_mantis.outputs.output_dir }}

.github/workflows/mantis-discord-thread-attachment.yml

@@ -32,7 +32,6 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.x"
-  PNPM_VERSION: "11.0.8"
   OPENCLAW_BUILD_PRIVATE_QA: "1"
   OPENCLAW_ENABLE_PRIVATE_QA_CLI: "1"
 
@@ -245,7 +244,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Build Mantis harness
@@ -536,7 +534,7 @@ jobs:
       - name: Upload Mantis thread attachment artifacts
         id: upload_artifact
         if: ${{ always() && steps.run_mantis.outputs.output_dir != '' }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: mantis-discord-thread-attachment-${{ github.run_id }}-${{ github.run_attempt }}
           path: ${{ steps.run_mantis.outputs.output_dir }}

.github/workflows/mantis-slack-desktop-smoke.yml

@@ -17,6 +17,11 @@ on:
         required: true
         default: slack-canary
         type: string
+      approval_checkpoints:
+        description: Run native Slack approval checkpoint mode instead of gateway setup
+        required: false
+        default: false
+        type: boolean
       keep_vm:
         description: Keep the desktop lease open after a passing run
         required: false
@@ -30,6 +35,14 @@ on:
         options:
           - aws
           - hetzner
+      crabbox_market:
+        description: Crabbox capacity market for AWS leases
+        required: false
+        default: on-demand
+        type: choice
+        options:
+          - on-demand
+          - spot
       crabbox_lease_id:
         description: Optional existing Crabbox desktop/browser lease id or slug to reuse
         required: false
@@ -55,7 +68,6 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.x"
-  PNPM_VERSION: "11.0.8"
   OPENCLAW_BUILD_PRIVATE_QA: "1"
   OPENCLAW_ENABLE_PRIVATE_QA_CLI: "1"
   CRABBOX_REF: main
@@ -162,7 +174,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Build Mantis harness
@@ -229,9 +240,11 @@ jobs:
           CRABBOX_ACCESS_CLIENT_SECRET: ${{ secrets.CRABBOX_ACCESS_CLIENT_SECRET }}
           CRABBOX_LEASE_ID: ${{ inputs.crabbox_lease_id }}
           CRABBOX_PROVIDER: ${{ inputs.crabbox_provider }}
+          CRABBOX_MARKET: ${{ inputs.crabbox_market }}
           KEEP_VM: ${{ inputs.keep_vm }}
           HYDRATE_MODE: ${{ inputs.hydrate_mode }}
           SCENARIO_ID: ${{ inputs.scenario_id }}
+          APPROVAL_CHECKPOINTS: ${{ inputs.approval_checkpoints }}
         shell: bash
         run: |
           set -euo pipefail
@@ -252,6 +265,15 @@ jobs:
           require_var OPENCLAW_QA_CONVEX_SITE_URL
           require_var OPENCLAW_QA_CONVEX_SECRET_CI
           require_var CRABBOX_COORDINATOR_TOKEN
+          if [[ -z "${CRABBOX_LEASE_ID:-}" && "$CRABBOX_PROVIDER" == "aws" ]]; then
+            runner_ip="$(curl -fsS https://checkip.amazonaws.com | tr -d '[:space:]')"
+            if [[ -z "$runner_ip" ]]; then
+              echo "Could not resolve GitHub runner public IPv4 for AWS SSH ingress." >&2
+              exit 1
+            fi
+            export CRABBOX_AWS_SSH_CIDRS="${runner_ip}/32"
+            echo "Using AWS SSH CIDR ${CRABBOX_AWS_SSH_CIDRS}"
+          fi
 
           candidate_repo="$(pwd)/.artifacts/qa-e2e/mantis/slack-desktop-smoke-worktrees/candidate"
           output_rel=".artifacts/qa-e2e/mantis/slack-desktop-smoke"
@@ -267,6 +289,22 @@ jobs:
           else
             keep_args=(--no-keep-lease)
           fi
+          market_args=()
+          if [[ -n "${CRABBOX_MARKET:-}" ]]; then
+            market_args=(--market "$CRABBOX_MARKET")
+          fi
+          gateway_args=(--gateway-setup)
+          approval_args=()
+          scenario_args=(--scenario "$SCENARIO_ID")
+          scenario_label="$SCENARIO_ID"
+          if [[ "$APPROVAL_CHECKPOINTS" == "true" ]]; then
+            approval_args=(--approval-checkpoints)
+            gateway_args=()
+            if [[ -z "${SCENARIO_ID:-}" || "$SCENARIO_ID" == "slack-canary" || "$SCENARIO_ID" == "approval-checkpoints" ]]; then
+              scenario_args=()
+              scenario_label="approval-checkpoints"
+            fi
+          fi
 
           set +e
           pnpm openclaw qa mantis slack-desktop-smoke \
@@ -276,7 +314,7 @@ jobs:
             --class standard \
             --idle-timeout 45m \
             --ttl 120m \
-            --gateway-setup \
+            "${gateway_args[@]}" \
             --credential-source convex \
             --credential-role ci \
             --provider-mode live-frontier \
@@ -284,7 +322,9 @@ jobs:
             --model openai/gpt-5.5 \
             --alt-model openai/gpt-5.5 \
             --fast \
-            --scenario "$SCENARIO_ID" \
+            "${scenario_args[@]}" \
+            "${approval_args[@]}" \
+            "${market_args[@]}" \
             "${keep_args[@]}" \
             "${lease_args[@]}"
           mantis_exit=$?
@@ -314,27 +354,81 @@ jobs:
 
           status="$(jq -r '.status' "$root/mantis-slack-desktop-smoke-summary.json")"
           screenshot_required=false
+          desktop_capture_inline=true
           if [[ "$status" == "pass" ]]; then
             screenshot_required=true
           fi
+          evidence_summary="Mantis ran Slack QA inside a Crabbox Linux VNC desktop, started an OpenClaw Slack gateway in that VM, opened Slack Web in the visible browser, and captured screenshot/video evidence."
+          expected_result="Slack QA and VM gateway setup pass"
+          checkpoint_artifacts='[]'
+          checkpoint_required=false
+          if [[ "$APPROVAL_CHECKPOINTS" == "true" ]]; then
+            evidence_summary="Mantis ran Slack native approval QA inside a Crabbox Linux VNC desktop, rendered pending/resolved approval checkpoints from the Slack API messages, and stored Slack QA artifacts."
+            expected_result="Slack native exec and plugin approval checkpoints pass"
+            screenshot_required=false
+            desktop_capture_inline=false
+            if [[ "$status" == "pass" ]]; then
+              checkpoint_required=true
+            fi
+            checkpoint_scenarios=()
+            if [[ "$scenario_label" == "approval-checkpoints" ]]; then
+              checkpoint_scenarios=("slack-approval-exec-native" "slack-approval-plugin-native")
+            else
+              checkpoint_scenarios=("$scenario_label")
+            fi
+            checkpoint_scenarios_json="$(printf '%s\n' "${checkpoint_scenarios[@]}" | jq -R . | jq -s .)"
+            checkpoint_artifacts="$(
+              jq -n \
+                --argjson checkpoint_required "$checkpoint_required" \
+                --argjson scenario_ids "$checkpoint_scenarios_json" \
+                '
+                  def scenario_kind($id):
+                    if $id == "slack-approval-exec-native" then "exec"
+                    elif $id == "slack-approval-plugin-native" then "plugin"
+                    else error("unsupported approval checkpoint scenario: \($id)")
+                    end;
+                  def scenario_title($id):
+                    if scenario_kind($id) == "exec" then "Exec" else "Plugin" end;
+                  [
+                    $scenario_ids[] as $id
+                    | ["pending", "resolved"][] as $state
+                    | {
+                        kind: "desktopScreenshot",
+                        lane: "candidate",
+                        label: "\(scenario_title($id)) approval \($state) checkpoint",
+                        path: "approval-checkpoints/\($id)-\($state).png",
+                        targetPath: "approval-checkpoints/\($id)-\($state).png",
+                        alt: "Rendered Slack \(scenario_kind($id)) approval \($state) checkpoint",
+                        width: 720,
+                        inline: true,
+                        required: $checkpoint_required
+                      }
+                  ]
+                '
+            )"
+          fi
           jq -n \
             --arg status "$status" \
             --arg candidate_sha "${{ needs.validate_ref.outputs.candidate_revision }}" \
-            --arg scenario "$SCENARIO_ID" \
+            --arg scenario "$scenario_label" \
+            --arg summary "$evidence_summary" \
+            --arg expected "$expected_result" \
+            --argjson checkpoint_artifacts "$checkpoint_artifacts" \
             --argjson screenshot_required "$screenshot_required" \
+            --argjson desktop_capture_inline "$desktop_capture_inline" \
             '{
               schemaVersion: 1,
               id: "slack-desktop-smoke",
               title: "Mantis Slack Desktop Smoke QA",
-              summary: "Mantis ran Slack QA inside a Crabbox Linux VNC desktop, started an OpenClaw Slack gateway in that VM, opened Slack Web in the visible browser, and captured screenshot/video evidence.",
+              summary: $summary,
               scenario: $scenario,
               comparison: {
-                candidate: { sha: $candidate_sha, expected: "Slack QA and VM gateway setup pass", status: $status, fixed: ($status == "pass") },
+                candidate: { sha: $candidate_sha, expected: $expected, status: $status, fixed: ($status == "pass") },
                 pass: ($status == "pass")
               },
-              artifacts: [
-                { kind: "desktopScreenshot", lane: "candidate", label: "Slack desktop/VNC browser", path: "slack-desktop-smoke.png", targetPath: "slack-desktop.png", alt: "Slack Web desktop screenshot from the Mantis VM", width: 720, inline: true, required: $screenshot_required },
-                { kind: "motionPreview", lane: "candidate", label: "Slack motion preview", path: "slack-desktop-smoke-preview.gif", targetPath: "slack-desktop-preview.gif", alt: "Animated Slack desktop preview", width: 720, inline: true, required: false },
+              artifacts: ([
+                { kind: "desktopScreenshot", lane: "candidate", label: "Slack desktop/VNC browser", path: "slack-desktop-smoke.png", targetPath: "slack-desktop.png", alt: "Slack Web desktop screenshot from the Mantis VM", width: 720, inline: $desktop_capture_inline, required: $screenshot_required },
+                { kind: "motionPreview", lane: "candidate", label: "Slack motion preview", path: "slack-desktop-smoke-preview.gif", targetPath: "slack-desktop-preview.gif", alt: "Animated Slack desktop preview", width: 720, inline: $desktop_capture_inline, required: false },
                 { kind: "motionClip", lane: "candidate", label: "Slack change MP4", path: "slack-desktop-smoke-change.mp4", targetPath: "slack-desktop-change.mp4", required: false },
                 { kind: "fullVideo", lane: "candidate", label: "Slack desktop MP4", path: "slack-desktop-smoke.mp4", targetPath: "slack-desktop.mp4", required: false },
                 { kind: "metadata", lane: "run", label: "Slack desktop summary", path: "mantis-slack-desktop-smoke-summary.json", targetPath: "summary.json" },
@@ -342,7 +436,7 @@ jobs:
                 { kind: "metadata", lane: "run", label: "Slack command log", path: "slack-desktop-command.log", targetPath: "slack-desktop-command.log", required: false },
                 { kind: "metadata", lane: "run", label: "Slack preview metadata", path: "slack-desktop-smoke-preview.json", targetPath: "slack-desktop-preview.json", required: false },
                 { kind: "metadata", lane: "run", label: "Slack error", path: "error.txt", targetPath: "error.txt", required: false }
-              ]
+              ] + $checkpoint_artifacts)
             }' > "$root/mantis-evidence.json"
 
           cat "$root/mantis-slack-desktop-smoke-report.md" >> "$GITHUB_STEP_SUMMARY"
@@ -359,7 +453,7 @@ jobs:
       - name: Upload Mantis Slack desktop artifacts
         id: upload_artifact
         if: ${{ always() && steps.run_mantis.outputs.output_dir != '' }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: mantis-slack-desktop-smoke-${{ github.run_id }}-${{ github.run_attempt }}
           path: ${{ steps.run_mantis.outputs.output_dir }}

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

@@ -45,10 +45,11 @@ permissions:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.x"
-  PNPM_VERSION: "11.0.8"
   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:
@@ -224,6 +225,7 @@ jobs:
       - name: Checkout harness ref
         uses: actions/checkout@v6
         with:
+          ref: main
           persist-credentials: false
           fetch-depth: 0
 
@@ -239,9 +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"
@@ -255,7 +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 ${baseline_revision}, which is not on main." >&2
             exit 1
@@ -269,6 +267,11 @@ jobs:
           pr_state="$(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 ${candidate_revision}, which is not the open PR head." >&2
             exit 1
@@ -308,16 +311,36 @@ jobs:
         run: |
           set -euo pipefail
           current_created="$(gh api "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}" --jq .created_at)"
+          stale_before="$(date -u -d '8 hours ago' +%Y-%m-%dT%H:%M:%SZ)"
+          run_has_active_jobs() {
+            local run_id="$1"
+            local run_state="$2"
+            if [[ "$run_state" != "in_progress" ]]; then
+              return 0
+            fi
+            local active_jobs
+            active_jobs="$(gh run view "$run_id" --repo "$GITHUB_REPOSITORY" --json jobs --jq '[.jobs[] | select(.status == "queued" or .status == "in_progress" or .status == "waiting" or .status == "pending" or .status == "requested")] | length')"
+            [[ "$active_jobs" != "0" ]]
+          }
           while true; do
-            blockers="$(
+            candidates="$(
               for workflow in mantis-telegram-desktop-proof.yml mantis-telegram-live.yml; do
-                gh run list --repo "$GITHUB_REPOSITORY" --workflow "$workflow" --limit 100 --json databaseId,status,createdAt,url \
-                  | jq -r \
-                    --argjson current_id "$GITHUB_RUN_ID" \
-                    --arg current_created "$current_created" \
-                    '.[] | select(.databaseId != $current_id) | select(.createdAt < $current_created or (.createdAt == $current_created and .databaseId < $current_id)) | select(.status == "queued" or .status == "in_progress" or .status == "waiting" or .status == "pending" or .status == "requested") | "\(.createdAt)\t#\(.databaseId)\t\(.status)\t\(.url)"'
+                for status in queued in_progress waiting pending requested; do
+                  gh run list --repo "$GITHUB_REPOSITORY" --workflow "$workflow" --status "$status" --limit 100 --json databaseId,status,createdAt,url \
+                    | jq -r \
+                      --argjson current_id "$GITHUB_RUN_ID" \
+                      --arg current_created "$current_created" \
+                      --arg stale_before "$stale_before" \
+                      '.[] | select(.databaseId != $current_id) | select(.createdAt >= $stale_before) | select(.createdAt < $current_created or (.createdAt == $current_created and .databaseId < $current_id)) | "\(.createdAt)\t#\(.databaseId)\t\(.status)\t\(.url)"'
+                done
               done | sort -u
             )"
+            blockers=""
+            while IFS=$'\t' read -r created run_id run_state url; do
+              if [[ -n "$run_id" ]] && run_has_active_jobs "${run_id#\#}" "$run_state"; then
+                blockers+="${created}"$'\t'"${run_id}"$'\t'"${run_state}"$'\t'"${url}"$'\n'
+              fi
+            done <<<"$candidates"
             if [[ -z "$blockers" ]]; then
               break
             fi
@@ -336,7 +359,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Setup Go for Crabbox CLI
@@ -404,9 +426,9 @@ 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_MANTIS_CRABBOX_COORDINATOR OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR_TOKEN"'
+            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"'
           } | sudo tee /etc/sudoers.d/mantis-codex-env >/dev/null
           sudo chmod 0440 /etc/sudoers.d/mantis-codex-env
@@ -433,6 +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 }}
@@ -442,6 +466,7 @@ jobs:
           MANTIS_PR_NUMBER: ${{ needs.resolve_request.outputs.pr_number }}
           OPENCLAW_QA_CONVEX_SECRET_CI: ${{ secrets.OPENCLAW_QA_CONVEX_SECRET_CI }}
           OPENCLAW_QA_CONVEX_SITE_URL: ${{ secrets.OPENCLAW_QA_CONVEX_SITE_URL }}
+          OPENCLAW_QA_CREDENTIAL_OWNER_ID: mantis-telegram-desktop-${{ github.run_id }}-${{ github.run_attempt }}
           OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR: ${{ secrets.OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR }}
           OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR_TOKEN: ${{ secrets.OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR_TOKEN }}
           OPENCLAW_TELEGRAM_USER_CRABBOX_BIN: /usr/local/bin/crabbox
@@ -460,6 +485,53 @@ jobs:
           codex-user: codex
           allow-bot-users: clawsweeper[bot]
 
+      - name: Release leaked Telegram proof leases
+        if: ${{ always() }}
+        env:
+          CRABBOX_PROVIDER: ${{ needs.resolve_request.outputs.crabbox_provider }}
+          OPENCLAW_QA_CONVEX_SECRET_CI: ${{ secrets.OPENCLAW_QA_CONVEX_SECRET_CI }}
+          OPENCLAW_QA_CONVEX_SITE_URL: ${{ secrets.OPENCLAW_QA_CONVEX_SITE_URL }}
+        shell: bash
+        run: |
+          set -euo pipefail
+          if [[ ! -d .artifacts/qa-e2e ]]; then
+            exit 0
+          fi
+          status=0
+          mapfile -d '' session_files < <(sudo find .artifacts/qa-e2e -name session.json -type f -print0)
+          for session_file in "${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 "$lease_file" ]]; then
+              continue
+            fi
+            if ! sudo -u codex env \
+              OPENCLAW_QA_CONVEX_SECRET_CI="$OPENCLAW_QA_CONVEX_SECRET_CI" \
+              OPENCLAW_QA_CONVEX_SITE_URL="$OPENCLAW_QA_CONVEX_SITE_URL" \
+              OPENCLAW_TELEGRAM_USER_CRABBOX_BIN=/usr/local/bin/crabbox \
+              OPENCLAW_TELEGRAM_USER_CRABBOX_PROVIDER="$CRABBOX_PROVIDER" \
+              node --import tsx "$GITHUB_WORKSPACE/scripts/e2e/telegram-user-crabbox-proof.ts" \
+                finish --session "$session_file" --preview-crop telegram-window; then
+              status=1
+            fi
+          done
+          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" \
+              node --import tsx "$GITHUB_WORKSPACE/scripts/e2e/telegram-user-credential.ts" \
+                release --lease-file "$lease_file"; then
+              status=1
+            fi
+          done
+          exit "$status"
+
       - name: Inspect Mantis evidence manifest
         id: inspect
         if: ${{ always() }}
@@ -479,7 +551,7 @@ jobs:
       - name: Upload Mantis Telegram desktop artifacts
         id: upload_artifact
         if: ${{ always() && steps.inspect.outputs.output_dir != '' }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: mantis-telegram-desktop-proof-${{ github.run_id }}-${{ github.run_attempt }}
           path: ${{ steps.inspect.outputs.output_dir }}
@@ -556,7 +628,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Download existing proof artifact

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

@@ -41,10 +41,11 @@ permissions:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.x"
-  PNPM_VERSION: "11.0.8"
   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:
@@ -272,16 +273,36 @@ jobs:
         run: |
           set -euo pipefail
           current_created="$(gh api "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}" --jq .created_at)"
+          stale_before="$(date -u -d '8 hours ago' +%Y-%m-%dT%H:%M:%SZ)"
+          run_has_active_jobs() {
+            local run_id="$1"
+            local run_state="$2"
+            if [[ "$run_state" != "in_progress" ]]; then
+              return 0
+            fi
+            local active_jobs
+            active_jobs="$(gh run view "$run_id" --repo "$GITHUB_REPOSITORY" --json jobs --jq '[.jobs[] | select(.status == "queued" or .status == "in_progress" or .status == "waiting" or .status == "pending" or .status == "requested")] | length')"
+            [[ "$active_jobs" != "0" ]]
+          }
           while true; do
-            blockers="$(
+            candidates="$(
               for workflow in mantis-telegram-desktop-proof.yml mantis-telegram-live.yml; do
-                gh run list --repo "$GITHUB_REPOSITORY" --workflow "$workflow" --limit 100 --json databaseId,status,createdAt,url \
-                  | jq -r \
-                    --argjson current_id "$GITHUB_RUN_ID" \
-                    --arg current_created "$current_created" \
-                    '.[] | select(.databaseId != $current_id) | select(.createdAt < $current_created or (.createdAt == $current_created and .databaseId < $current_id)) | select(.status == "queued" or .status == "in_progress" or .status == "waiting" or .status == "pending" or .status == "requested") | "\(.createdAt)\t#\(.databaseId)\t\(.status)\t\(.url)"'
+                for status in queued in_progress waiting pending requested; do
+                  gh run list --repo "$GITHUB_REPOSITORY" --workflow "$workflow" --status "$status" --limit 100 --json databaseId,status,createdAt,url \
+                    | jq -r \
+                      --argjson current_id "$GITHUB_RUN_ID" \
+                      --arg current_created "$current_created" \
+                      --arg stale_before "$stale_before" \
+                      '.[] | select(.databaseId != $current_id) | select(.createdAt >= $stale_before) | select(.createdAt < $current_created or (.createdAt == $current_created and .databaseId < $current_id)) | "\(.createdAt)\t#\(.databaseId)\t\(.status)\t\(.url)"'
+                done
               done | sort -u
             )"
+            blockers=""
+            while IFS=$'\t' read -r created run_id run_state url; do
+              if [[ -n "$run_id" ]] && run_has_active_jobs "${run_id#\#}" "$run_state"; then
+                blockers+="${created}"$'\t'"${run_id}"$'\t'"${run_state}"$'\t'"${url}"$'\n'
+              fi
+            done <<<"$candidates"
             if [[ -z "$blockers" ]]; then
               break
             fi
@@ -300,7 +321,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Build Mantis harness
@@ -365,6 +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 }}
@@ -479,7 +501,7 @@ jobs:
       - name: Upload Mantis Telegram artifacts
         id: upload_artifact
         if: ${{ always() && steps.run_mantis.outputs.output_dir != '' }}
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: mantis-telegram-live-${{ github.run_id }}-${{ github.run_attempt }}
           path: ${{ steps.run_mantis.outputs.output_dir }}

.github/workflows/npm-telegram-beta-e2e.yml

@@ -40,8 +40,18 @@ on:
         description: Optional comma-separated Telegram scenario ids
         required: false
         type: string
+      advisory:
+        description: Treat package Telegram failures as advisory for the caller
+        required: false
+        default: false
+        type: boolean
   workflow_call:
     inputs:
+      advisory:
+        description: Treat package Telegram failures as advisory for the caller
+        required: false
+        default: false
+        type: boolean
       package_spec:
         description: Published OpenClaw package spec to test when no artifact is supplied
         required: true
@@ -94,12 +104,12 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
-  PNPM_VERSION: "11.0.8"
 
 jobs:
   run_package_telegram_e2e:
     name: Run package Telegram E2E
     runs-on: blacksmith-32vcpu-ubuntu-2404
+    continue-on-error: ${{ inputs.advisory }}
     timeout-minutes: 60
     environment: qa-live-shared
     permissions:
@@ -136,7 +146,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Validate inputs and secrets
@@ -259,7 +268,7 @@ jobs:
 
       - name: Upload npm Telegram E2E artifacts
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: npm-telegram-beta-e2e-${{ github.run_id }}-${{ github.run_attempt }}
           path: .artifacts/qa-e2e/

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

@@ -86,8 +86,18 @@ on:
         required: false
         default: ""
         type: string
+      advisory:
+        description: Treat failures as advisory for the caller
+        required: false
+        default: false
+        type: boolean
   workflow_call:
     inputs:
+      advisory:
+        description: Treat failures as advisory for the caller
+        required: false
+        default: false
+        type: boolean
       ref:
         description: Public OpenClaw ref to validate (tag, branch, or full commit SHA)
         required: true
@@ -183,7 +193,6 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
-  PNPM_VERSION: "11.0.8"
   OPENCLAW_REPOSITORY: openclaw/openclaw
   TSX_VERSION: "4.21.0"
   OPENCLAW_CROSS_OS_OPENAI_MODEL: ${{ inputs.openai_model || vars.OPENCLAW_CROSS_OS_OPENAI_MODEL || 'openai/gpt-5.5' }}
@@ -191,6 +200,7 @@ env:
 jobs:
   prepare:
     runs-on: ubuntu-24.04
+    continue-on-error: ${{ inputs.advisory }}
     outputs:
       baseline_file_name: ${{ steps.baseline_metadata.outputs.file_name }}
       baseline_spec: ${{ steps.baseline.outputs.value }}
@@ -328,7 +338,7 @@ jobs:
           ref: ${{ steps.workflow_ref.outputs.value }}
           path: workflow
           fetch-depth: 1
-          persist-credentials: false
+          persist-credentials: true
 
       - name: Checkout public source ref
         if: inputs.candidate_artifact_name == ''
@@ -338,21 +348,21 @@ jobs:
           ref: ${{ inputs.ref }}
           path: source
           fetch-depth: 0
-          persist-credentials: false
+          persist-credentials: true
           submodules: recursive
 
-      - name: Setup pnpm
-        uses: pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1
-        with:
-          version: ${{ env.PNPM_VERSION }}
-          run_install: false
-
       - name: Setup Node.js
         uses: actions/setup-node@v6
         with:
           node-version: ${{ env.NODE_VERSION }}
-          cache: pnpm
-          cache-dependency-path: ${{ inputs.candidate_artifact_name == '' && 'source/pnpm-lock.yaml' || 'workflow/pnpm-lock.yaml' }}
+
+      - name: Setup pnpm
+        uses: ./workflow/.github/actions/setup-pnpm-store-cache
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+          package-manager-file: ${{ inputs.candidate_artifact_name == '' && 'source/package.json' || 'workflow/package.json' }}
+          lockfile-path: ${{ inputs.candidate_artifact_name == '' && 'source/pnpm-lock.yaml' || 'workflow/pnpm-lock.yaml' }}
+          use-actions-cache: ${{ inputs.candidate_artifact_name == '' && 'true' || 'false' }}
 
       - name: Ensure pnpm store cache directory exists
         run: mkdir -p "$(pnpm store path --silent)"
@@ -513,6 +523,7 @@ jobs:
   cross_os_release_checks:
     name: "${{ matrix.display_name }} / ${{ matrix.suite_label }}"
     needs: prepare
+    continue-on-error: ${{ inputs.advisory }}
     strategy:
       fail-fast: false
       matrix: ${{ fromJson(needs.prepare.outputs.matrix) }}
@@ -526,20 +537,31 @@ jobs:
           ref: ${{ needs.prepare.outputs.workflow_ref }}
           path: workflow
           fetch-depth: 1
-          persist-credentials: false
-
-      - name: Setup pnpm
-        uses: pnpm/action-setup@b906affcce14559ad1aafd4ab0e942779e9f58b1
-        with:
-          version: ${{ env.PNPM_VERSION }}
-          run_install: false
+          persist-credentials: true
 
       - name: Setup Node.js
         uses: actions/setup-node@v6
         with:
           node-version: ${{ env.NODE_VERSION }}
 
+      - name: Setup pnpm
+        uses: ./workflow/.github/actions/setup-pnpm-store-cache
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+          package-manager-file: workflow/package.json
+          lockfile-path: workflow/pnpm-lock.yaml
+          use-actions-cache: "false"
+
       - name: Download candidate artifact
+        id: download_candidate
+        continue-on-error: true
+        uses: actions/download-artifact@v8
+        with:
+          name: openclaw-cross-os-release-checks-candidate-${{ 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 }}
@@ -547,11 +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: ${BASELINE_TGZ}"
+            exit 1
+          fi
+
       - name: Run cross-OS release checks
         shell: bash
         env:
@@ -602,7 +651,8 @@ jobs:
           if [[ -f "${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

@@ -68,6 +68,11 @@ on:
         required: false
         default: ""
         type: string
+      codex_plugin_spec:
+        description: Optional Codex plugin install spec for the live package lane; blank packs extensions/codex from the selected ref
+        required: false
+        default: ""
+        type: string
       include_live_suites:
         description: Whether to run live-provider coverage
         required: false
@@ -97,8 +102,23 @@ 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
+        default: false
+        type: boolean
   workflow_call:
     inputs:
+      advisory:
+        description: Treat failures as advisory for the caller
+        required: false
+        default: false
+        type: boolean
       ref:
         description: Ref, tag, or SHA to validate
         required: true
@@ -163,6 +183,11 @@ on:
         required: false
         default: ""
         type: string
+      codex_plugin_spec:
+        description: Optional Codex plugin install spec for the live package lane; blank packs extensions/codex from the selected ref
+        required: false
+        default: ""
+        type: string
       include_live_suites:
         description: Whether to run live-provider coverage
         required: false
@@ -188,6 +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
@@ -199,6 +229,8 @@ on:
         required: false
       ANTHROPIC_API_TOKEN:
         required: false
+      FACTORY_API_KEY:
+        required: false
       BYTEPLUS_API_KEY:
         required: false
       CEREBRAS_API_KEY:
@@ -288,7 +320,6 @@ permissions:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
-  PNPM_VERSION: "11.0.8"
 
 jobs:
   validate_selected_ref:
@@ -311,9 +342,6 @@ jobs:
           set -euo pipefail
           trusted_reason=""
 
-          git fetch --no-tags origin '+refs/heads/*:refs/remotes/origin/*'
-          git fetch --tags origin '+refs/tags/*:refs/tags/*'
-
           # Resolve here instead of in actions/checkout so short SHAs work too.
           if ! selected_sha="$(git rev-parse --verify "${INPUT_REF}^{commit}")"; then
             echo "Ref '${INPUT_REF}' could not be resolved to a commit." >&2
@@ -455,7 +483,8 @@ jobs:
   validate_release_live_cache:
     needs: validate_selected_ref
     if: inputs.include_live_suites && !inputs.live_models_only && (inputs.live_suite_filter == '' || inputs.live_suite_filter == 'live-cache')
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    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 }}
@@ -473,7 +502,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Validate live cache credentials
@@ -505,7 +533,8 @@ jobs:
   validate_repo_e2e:
     needs: validate_selected_ref
     if: inputs.include_repo_e2e && inputs.live_suite_filter == ''
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    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"
@@ -520,7 +549,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Build dist for repo E2E
@@ -528,13 +556,17 @@ jobs:
           NODE_OPTIONS: --max-old-space-size=8192
         run: pnpm build
 
+      - name: Install Playwright Chromium
+        run: pnpm --dir ui exec playwright install --with-deps chromium
+
       - name: Run repo E2E suite
         run: pnpm test:e2e
 
   validate_special_e2e:
     needs: validate_selected_ref
     if: inputs.include_repo_e2e && (inputs.live_suite_filter == '' || inputs.live_suite_filter == 'openshell-e2e')
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
@@ -561,7 +593,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Build dist for special E2E
@@ -608,7 +639,8 @@ jobs:
     needs: [validate_selected_ref, prepare_docker_e2e_image]
     if: inputs.include_release_path_suites && inputs.docker_lanes == ''
     name: Docker E2E (${{ matrix.label }})
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
@@ -620,7 +652,7 @@ jobs:
             profiles: stable full
           - chunk_id: package-update-openai
             label: package/update OpenAI install
-            timeout_minutes: 20
+            timeout_minutes: 45
             profiles: beta minimum stable full
           - chunk_id: package-update-anthropic
             label: package/update Anthropic install
@@ -676,6 +708,7 @@ jobs:
       ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
       ANTHROPIC_API_TOKEN: ${{ secrets.ANTHROPIC_API_TOKEN }}
       ANTHROPIC_API_KEY_OLD: ${{ secrets.ANTHROPIC_API_KEY_OLD }}
+      FACTORY_API_KEY: ${{ secrets.FACTORY_API_KEY }}
       BYTEPLUS_API_KEY: ${{ secrets.BYTEPLUS_API_KEY }}
       CEREBRAS_API_KEY: ${{ secrets.CEREBRAS_API_KEY }}
       DEEPINFRA_API_KEY: ${{ secrets.DEEPINFRA_API_KEY }}
@@ -723,6 +756,7 @@ jobs:
       OPENCLAW_DOCKER_E2E_REPO_ROOT: ${{ github.workspace }}
       OPENCLAW_DOCKER_E2E_SELECTED_SHA: ${{ needs.validate_selected_ref.outputs.selected_sha }}
       OPENCLAW_DOCKER_ALL_RELEASE_PROFILE: ${{ inputs.release_test_profile }}
+      OPENCLAW_CODEX_NPM_PLUGIN_SPEC: ${{ inputs.codex_plugin_spec }}
       OPENCLAW_CURRENT_PACKAGE_TGZ: .artifacts/docker-e2e-package/openclaw-current.tgz
       OPENCLAW_UPGRADE_SURVIVOR_BASELINE_SPEC: ${{ inputs.published_upgrade_survivor_baseline }}
       OPENCLAW_UPGRADE_SURVIVOR_BASELINE_SPECS: ${{ inputs.published_upgrade_survivor_baselines }}
@@ -735,6 +769,7 @@ jobs:
         if: contains(matrix.profiles, inputs.release_test_profile)
         uses: actions/checkout@v6
         with:
+          persist-credentials: false
           ref: ${{ needs.validate_selected_ref.outputs.selected_sha }}
           fetch-depth: 1
 
@@ -742,24 +777,23 @@ jobs:
         if: contains(matrix.profiles, inputs.release_test_profile)
         uses: actions/checkout@v6
         with:
+          persist-credentials: false
           ref: ${{ github.sha }}
           fetch-depth: 1
           path: .release-harness
 
       - name: Log in to GHCR for shared Docker E2E image
         if: contains(matrix.profiles, inputs.release_test_profile)
-        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ github.token }}
+        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
+        env:
+          GHCR_USERNAME: ${{ github.actor }}
+          GITHUB_TOKEN: ${{ github.token }}
 
       - name: Setup Node environment
         if: contains(matrix.profiles, inputs.release_test_profile)
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Hydrate live auth/profile inputs
@@ -821,15 +855,35 @@ jobs:
         run: |
           set -euo pipefail
           credentials=",$CREDENTIALS,"
-          if [[ "$credentials" == *",openai,"* ]]; then
-            [[ -n "${OPENAI_API_KEY:-}" ]] || {
-              echo "OPENAI_API_KEY is required for selected Docker E2E lanes." >&2
-              exit 1
-            }
-          fi
-          if [[ "$credentials" == *",anthropic,"* && -z "${ANTHROPIC_API_TOKEN:-}" && -z "${ANTHROPIC_API_KEY:-}" ]]; then
-            echo "ANTHROPIC_API_TOKEN or ANTHROPIC_API_KEY is required for selected Docker E2E lanes." >&2
+          require_any() {
+            local label="$1"
+            shift
+            local key
+            for key in "$@"; do
+              if [[ -n "${!key:-}" ]]; then
+                return 0
+              fi
+            done
+            echo "Missing credential for ${label}: expected one of $*" >&2
             exit 1
+          }
+          if [[ "$credentials" == *",openai,"* ]]; then
+            require_any OpenAI OPENAI_API_KEY
+          fi
+          if [[ "$credentials" == *",codex,"* ]]; then
+            require_any Codex OPENCLAW_CODEX_AUTH_JSON
+          fi
+          if [[ "$credentials" == *",anthropic,"* ]]; then
+            require_any Anthropic ANTHROPIC_API_TOKEN ANTHROPIC_API_KEY OPENCLAW_CLAUDE_CREDENTIALS_JSON OPENCLAW_CLAUDE_JSON
+          fi
+          if [[ "$credentials" == *",factory,"* ]]; then
+            require_any Factory FACTORY_API_KEY
+          fi
+          if [[ "$credentials" == *",gemini,"* ]]; then
+            require_any Gemini GEMINI_API_KEY GOOGLE_API_KEY OPENCLAW_GEMINI_SETTINGS_JSON
+          fi
+          if [[ "$credentials" == *",opencode,"* ]]; then
+            require_any OpenCode OPENCODE_API_KEY OPENCODE_ZEN_API_KEY
           fi
 
       - name: Run Docker E2E chunk
@@ -876,7 +930,8 @@ jobs:
   plan_docker_lane_groups:
     needs: validate_selected_ref
     if: inputs.docker_lanes != ''
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-4vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    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 }}
@@ -884,6 +939,7 @@ jobs:
       - name: Checkout trusted release harness
         uses: actions/checkout@v6
         with:
+          persist-credentials: false
           ref: ${{ github.sha }}
           fetch-depth: 1
 
@@ -903,7 +959,8 @@ jobs:
     needs: [validate_selected_ref, prepare_docker_e2e_image, plan_docker_lane_groups]
     if: inputs.docker_lanes != ''
     name: Docker E2E targeted lanes (${{ matrix.group.label }})
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 60
     strategy:
       fail-fast: false
@@ -915,6 +972,7 @@ jobs:
       ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
       ANTHROPIC_API_TOKEN: ${{ secrets.ANTHROPIC_API_TOKEN }}
       ANTHROPIC_API_KEY_OLD: ${{ secrets.ANTHROPIC_API_KEY_OLD }}
+      FACTORY_API_KEY: ${{ secrets.FACTORY_API_KEY }}
       BYTEPLUS_API_KEY: ${{ secrets.BYTEPLUS_API_KEY }}
       CEREBRAS_API_KEY: ${{ secrets.CEREBRAS_API_KEY }}
       DEEPINFRA_API_KEY: ${{ secrets.DEEPINFRA_API_KEY }}
@@ -961,6 +1019,7 @@ jobs:
       OPENCLAW_DOCKER_E2E_PACKAGE_ARTIFACT_NAME: ${{ inputs.package_artifact_name || 'docker-e2e-package' }}
       OPENCLAW_DOCKER_E2E_REPO_ROOT: ${{ github.workspace }}
       OPENCLAW_DOCKER_E2E_SELECTED_SHA: ${{ needs.validate_selected_ref.outputs.selected_sha }}
+      OPENCLAW_CODEX_NPM_PLUGIN_SPEC: ${{ inputs.codex_plugin_spec }}
       OPENCLAW_CURRENT_PACKAGE_TGZ: .artifacts/docker-e2e-package/openclaw-current.tgz
       OPENCLAW_UPGRADE_SURVIVOR_BASELINE_SPEC: ${{ inputs.published_upgrade_survivor_baseline }}
       OPENCLAW_UPGRADE_SURVIVOR_BASELINE_SPECS: ${{ matrix.group.published_upgrade_survivor_baselines || inputs.published_upgrade_survivor_baselines }}
@@ -972,28 +1031,28 @@ jobs:
       - name: Checkout selected ref
         uses: actions/checkout@v6
         with:
+          persist-credentials: false
           ref: ${{ needs.validate_selected_ref.outputs.selected_sha }}
           fetch-depth: 1
 
       - name: Checkout trusted release harness
         uses: actions/checkout@v6
         with:
+          persist-credentials: false
           ref: ${{ github.sha }}
           fetch-depth: 1
           path: .release-harness
 
       - name: Log in to GHCR for shared Docker E2E image
-        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ github.token }}
+        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
+        env:
+          GHCR_USERNAME: ${{ github.actor }}
+          GITHUB_TOKEN: ${{ github.token }}
 
       - name: Setup Node environment
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Hydrate live auth/profile inputs
@@ -1056,15 +1115,35 @@ jobs:
         run: |
           set -euo pipefail
           credentials=",$CREDENTIALS,"
-          if [[ "$credentials" == *",openai,"* ]]; then
-            [[ -n "${OPENAI_API_KEY:-}" ]] || {
-              echo "OPENAI_API_KEY is required for selected Docker E2E lanes." >&2
-              exit 1
-            }
-          fi
-          if [[ "$credentials" == *",anthropic,"* && -z "${ANTHROPIC_API_TOKEN:-}" && -z "${ANTHROPIC_API_KEY:-}" ]]; then
-            echo "ANTHROPIC_API_TOKEN or ANTHROPIC_API_KEY is required for selected Docker E2E lanes." >&2
+          require_any() {
+            local label="$1"
+            shift
+            local key
+            for key in "$@"; do
+              if [[ -n "${!key:-}" ]]; then
+                return 0
+              fi
+            done
+            echo "Missing credential for ${label}: expected one of $*" >&2
             exit 1
+          }
+          if [[ "$credentials" == *",openai,"* ]]; then
+            require_any OpenAI OPENAI_API_KEY
+          fi
+          if [[ "$credentials" == *",codex,"* ]]; then
+            require_any Codex OPENCLAW_CODEX_AUTH_JSON
+          fi
+          if [[ "$credentials" == *",anthropic,"* ]]; then
+            require_any Anthropic ANTHROPIC_API_TOKEN ANTHROPIC_API_KEY OPENCLAW_CLAUDE_CREDENTIALS_JSON OPENCLAW_CLAUDE_JSON
+          fi
+          if [[ "$credentials" == *",factory,"* ]]; then
+            require_any Factory FACTORY_API_KEY
+          fi
+          if [[ "$credentials" == *",gemini,"* ]]; then
+            require_any Gemini GEMINI_API_KEY GOOGLE_API_KEY OPENCLAW_GEMINI_SETTINGS_JSON
+          fi
+          if [[ "$credentials" == *",opencode,"* ]]; then
+            require_any OpenCode OPENCODE_API_KEY OPENCODE_ZEN_API_KEY
           fi
 
       - name: Run targeted Docker E2E lanes
@@ -1112,7 +1191,8 @@ jobs:
     needs: [validate_selected_ref, prepare_docker_e2e_image]
     if: inputs.include_openwebui && !inputs.include_release_path_suites && inputs.docker_lanes == ''
     name: Docker E2E (openwebui)
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    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 }}
@@ -1139,17 +1219,15 @@ jobs:
           path: .release-harness
 
       - name: Log in to GHCR for shared Docker E2E image
-        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ github.token }}
+        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
+        env:
+          GHCR_USERNAME: ${{ github.actor }}
+          GITHUB_TOKEN: ${{ github.token }}
 
       - name: Setup Node environment
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Validate Open WebUI credentials
@@ -1239,7 +1317,8 @@ jobs:
   prepare_docker_e2e_image:
     needs: validate_selected_ref
     if: inputs.include_release_path_suites || inputs.include_openwebui || inputs.docker_lanes != ''
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    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
@@ -1308,7 +1387,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Download current-run OpenClaw Docker E2E package
@@ -1399,11 +1477,10 @@ jobs:
 
       - name: Log in to GHCR
         if: steps.plan.outputs.needs_e2e_image == '1'
-        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ github.token }}
+        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
+        env:
+          GHCR_USERNAME: ${{ github.actor }}
+          GITHUB_TOKEN: ${{ github.token }}
 
       - name: Check existing shared Docker E2E images
         id: image_exists
@@ -1483,7 +1560,8 @@ jobs:
   prepare_live_test_image:
     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'))
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 60
     permissions:
       contents: read
@@ -1513,11 +1591,10 @@ jobs:
           echo "Shared live-test image: \`${live_image}\`" >> "$GITHUB_STEP_SUMMARY"
 
       - name: Log in to GHCR
-        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ github.token }}
+        run: bash scripts/ci-docker-login-ghcr.sh
+        env:
+          GHCR_USERNAME: ${{ github.actor }}
+          GITHUB_TOKEN: ${{ github.token }}
 
       - name: Check existing shared live-test image
         id: image_exists
@@ -1556,7 +1633,8 @@ jobs:
     name: Docker live models (${{ matrix.provider_label }})
     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')
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 45
     strategy:
       fail-fast: false
@@ -1650,7 +1728,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Hydrate live auth/profile inputs
@@ -1659,11 +1736,10 @@ jobs:
 
       - name: Log in to GHCR
         if: contains(matrix.profiles, inputs.release_test_profile)
-        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ github.token }}
+        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
+        env:
+          GHCR_USERNAME: ${{ github.actor }}
+          GITHUB_TOKEN: ${{ github.token }}
 
       - name: Validate provider credential
         if: contains(matrix.profiles, inputs.release_test_profile)
@@ -1708,7 +1784,8 @@ jobs:
     name: Docker live models (selected providers)
     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')
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    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 }}
@@ -1768,7 +1845,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Normalize provider allowlist
@@ -1781,7 +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" ;;
@@ -1834,11 +1909,10 @@ jobs:
         run: bash scripts/ci-hydrate-live-auth.sh
 
       - name: Log in to GHCR
-        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ github.token }}
+        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
+        env:
+          GHCR_USERNAME: ${{ github.actor }}
+          GITHUB_TOKEN: ${{ github.token }}
 
       - name: Validate provider credentials
         shell: bash
@@ -1883,7 +1957,8 @@ jobs:
   validate_live_provider_suites:
     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'))
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
@@ -1911,7 +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
@@ -1919,7 +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
@@ -2137,7 +2212,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Hydrate live auth/profile inputs
@@ -2186,6 +2260,7 @@ jobs:
         env:
           OPENCLAW_LIVE_COMMAND: ${{ matrix.command }}
           OPENCLAW_LIVE_SUITE_ADVISORY: ${{ matrix.advisory }}
+        shell: bash
         run: |
           set +e
           bash .release-harness/scripts/ci-live-command-retry.sh
@@ -2204,7 +2279,8 @@ jobs:
     name: Docker live suites (${{ matrix.label }})
     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-'))
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
@@ -2212,49 +2288,49 @@ jobs:
         include:
           - suite_id: live-gateway-docker
             label: Docker live gateway OpenAI
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=openai OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=30000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=60000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 30
+            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="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 40
             profile_env_only: false
             profiles: beta minimum stable full
           - suite_id: live-gateway-anthropic-docker
             label: Docker live gateway Anthropic
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=anthropic OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=30000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=60000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 30
+            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="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 40
             profile_env_only: false
             profiles: stable full
           - suite_id: live-gateway-google-docker
             label: Docker live gateway Google
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=google OPENCLAW_LIVE_GATEWAY_MODELS=google/gemini-3.1-pro-preview,google/gemini-3-flash-preview OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=30000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=60000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 30
+            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=google OPENCLAW_LIVE_GATEWAY_MODELS=google/gemini-3.1-pro-preview,google/gemini-3-flash-preview 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="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 40
             profile_env_only: false
             profiles: stable full
           - suite_id: live-gateway-minimax-docker
             label: Docker live gateway MiniMax
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=minimax,minimax-portal OPENCLAW_LIVE_GATEWAY_MAX_MODELS=1 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=30000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=60000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 30
+            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=minimax,minimax-portal OPENCLAW_LIVE_GATEWAY_MAX_MODELS=1 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=180000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 40
             profile_env_only: false
             profiles: stable full
           - suite_id: live-gateway-advisory-docker-deepseek-fireworks
             suite_group: live-gateway-advisory-docker
             label: Docker live gateway advisory DeepSeek/Fireworks
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=deepseek,fireworks OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=30000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=60000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 30
+            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=deepseek,fireworks 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="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 40
             profile_env_only: false
             advisory: true
             profiles: full
           - suite_id: live-gateway-advisory-docker-opencode-openrouter
             suite_group: live-gateway-advisory-docker
             label: Docker live gateway advisory OpenCode/OpenRouter
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=opencode-go,openrouter OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=30000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=60000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 30
+            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=opencode-go,openrouter 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="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 40
             profile_env_only: false
             advisory: true
             profiles: full
           - suite_id: live-gateway-advisory-docker-xai-zai
             suite_group: live-gateway-advisory-docker
             label: Docker live gateway advisory xAI/Z.ai
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=xai,zai OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=30000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=60000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 30
+            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=xai,zai 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
+            timeout_minutes: 40
             profile_env_only: false
             advisory: true
             profiles: full
@@ -2354,7 +2430,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Hydrate live auth/profile inputs
@@ -2363,11 +2438,10 @@ jobs:
 
       - name: Log in to GHCR
         if: contains(matrix.profiles, inputs.release_test_profile) && (inputs.live_suite_filter == '' || inputs.live_suite_filter == matrix.suite_id || (inputs.live_suite_filter == 'live-gateway-advisory-docker' && startsWith(matrix.suite_id, 'live-gateway-advisory-docker-')))
-        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ github.token }}
+        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
+        env:
+          GHCR_USERNAME: ${{ github.actor }}
+          GITHUB_TOKEN: ${{ github.token }}
 
       - name: Configure suite-specific env
         if: contains(matrix.profiles, inputs.release_test_profile) && (inputs.live_suite_filter == '' || inputs.live_suite_filter == matrix.suite_id || (inputs.live_suite_filter == 'live-gateway-advisory-docker' && startsWith(matrix.suite_id, 'live-gateway-advisory-docker-')))
@@ -2405,6 +2479,7 @@ jobs:
         env:
           OPENCLAW_LIVE_COMMAND: ${{ matrix.command }}
           OPENCLAW_LIVE_SUITE_ADVISORY: ${{ matrix.advisory }}
+        shell: bash
         run: |
           set +e
           bash .release-harness/scripts/ci-live-command-retry.sh
@@ -2423,7 +2498,8 @@ jobs:
     name: Live media suites (${{ matrix.label }})
     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')
-    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    continue-on-error: ${{ inputs.advisory }}
+    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:
@@ -2572,7 +2648,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Hydrate live auth/profile inputs
@@ -2592,6 +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

@@ -20,6 +20,10 @@ on:
         description: Successful Full Release Validation run id for this tag/SHA, required for real publish
         required: false
         type: string
+      release_publish_run_id:
+        description: Approved OpenClaw Release Publish workflow run id
+        required: false
+        type: string
       npm_dist_tag:
         description: npm dist-tag to publish to
         required: true
@@ -31,21 +35,20 @@ on:
           - latest
 
 concurrency:
-  group: openclaw-npm-release-${{ github.event_name == 'workflow_dispatch' && format('{0}-{1}', inputs.tag, inputs.npm_dist_tag) || github.ref }}
-  cancel-in-progress: false
+  group: ${{ github.event_name == 'workflow_dispatch' && inputs.preflight_only && format('openclaw-npm-release-{0}-{1}-preflight', inputs.tag, inputs.npm_dist_tag) || github.event_name == 'workflow_dispatch' && format('openclaw-npm-release-{0}-{1}-publish-{2}', inputs.tag, inputs.npm_dist_tag, github.run_id) || format('openclaw-npm-release-{0}', github.ref) }}
+  cancel-in-progress: ${{ github.event_name == 'workflow_dispatch' && inputs.preflight_only && inputs.npm_dist_tag == 'alpha' }}
 
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
-  PNPM_VERSION: "11.0.8"
 
 jobs:
   # PLEASE DON'T ADD LONG-RUNNING OR FLAKY CHECKS TO THE npm RELEASE PATH.
   # 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
@@ -114,7 +117,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Ensure version is not already published
@@ -367,6 +369,7 @@ jobs:
     if: ${{ !inputs.preflight_only }}
     runs-on: ubuntu-latest
     permissions:
+      actions: read
       contents: read
     steps:
       - name: Require trusted workflow ref for publish
@@ -387,8 +390,11 @@ jobs:
 
       - name: Require preflight artifact promotion on real publish
         env:
+          RELEASE_TAG: ${{ inputs.tag }}
+          RELEASE_NPM_DIST_TAG: ${{ inputs.npm_dist_tag }}
           PREFLIGHT_RUN_ID: ${{ inputs.preflight_run_id }}
           FULL_RELEASE_VALIDATION_RUN_ID: ${{ inputs.full_release_validation_run_id }}
+          RELEASE_PUBLISH_RUN_ID: ${{ inputs.release_publish_run_id }}
         run: |
           set -euo pipefail
           if [[ -z "${PREFLIGHT_RUN_ID}" ]]; then
@@ -396,10 +402,40 @@ jobs:
             exit 1
           fi
           if [[ -z "${FULL_RELEASE_VALIDATION_RUN_ID}" ]]; then
-            echo "Real publish requires full_release_validation_run_id from a successful Full Release Validation run." >&2
+            if [[ "${RELEASE_TAG}" == *"-beta."* && "${RELEASE_NPM_DIST_TAG}" == "beta" ]]; then
+              echo "::warning::Beta publish is proceeding from npm preflight only; full release validation remains required before stable/latest promotion."
+            else
+              echo "Real publish requires full_release_validation_run_id from a successful Full Release Validation run." >&2
+              exit 1
+            fi
+          fi
+          if [[ -z "${RELEASE_PUBLISH_RUN_ID// }" && "${GITHUB_ACTOR}" == "github-actions[bot]" ]]; then
+            echo "Workflow-dispatched real publish requires release_publish_run_id from the approved OpenClaw Release Publish workflow." >&2
             exit 1
           fi
 
+      - name: Validate release publish approval run
+        env:
+          GH_TOKEN: ${{ github.token }}
+          RELEASE_PUBLISH_RUN_ID: ${{ inputs.release_publish_run_id }}
+          EXPECTED_WORKFLOW_BRANCH: ${{ github.ref_name }}
+        run: |
+          set -euo pipefail
+          if [[ -z "${RELEASE_PUBLISH_RUN_ID// }" ]]; then
+            if [[ "${GITHUB_ACTOR}" == "github-actions[bot]" ]]; then
+              echo "OpenClaw npm publish dispatched by another workflow must include release_publish_run_id." >&2
+              exit 1
+            fi
+            echo "Direct OpenClaw npm publish; relying on this workflow's npm-release environment approval."
+            exit 0
+          fi
+          if [[ "${GITHUB_ACTOR}" != "github-actions[bot]" ]]; then
+            echo "OpenClaw npm publish must be dispatched by the OpenClaw Release Publish workflow, not directly by ${GITHUB_ACTOR}." >&2
+            exit 1
+          fi
+          RUN_JSON="$(gh run view "$RELEASE_PUBLISH_RUN_ID" --repo "$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", "OpenClaw Release Publish"], ["headBranch", process.env.EXPECTED_WORKFLOW_BRANCH], ["event", "workflow_dispatch"]]; for (const [key, expected] of checks) { if (run[key] !== expected) { console.error(`Referenced release publish run ${process.env.RELEASE_PUBLISH_RUN_ID} must have ${key}=${expected}, got ${run[key] ?? "<missing>"}.`); process.exit(1); } } if (run.status !== "in_progress") { console.error(`Referenced release publish run ${process.env.RELEASE_PUBLISH_RUN_ID} must still be in_progress, got ${run.status ?? "<missing>"}.`); process.exit(1); } if (run.conclusion) { console.error(`Referenced release publish run ${process.env.RELEASE_PUBLISH_RUN_ID} already concluded ${run.conclusion}.`); process.exit(1); } console.log(`Using release publish approval run ${process.env.RELEASE_PUBLISH_RUN_ID}: ${run.url}`);'
+
   publish_openclaw_npm:
     # KEEP THE REAL RELEASE/PUBLISH PATH ON A GITHUB-HOSTED RUNNER.
     # npm trusted publishing + provenance requires this to stay on ubuntu-latest.
@@ -463,7 +499,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "false"
 
       - name: Ensure version is not already published
@@ -482,21 +517,20 @@ jobs:
         env:
           GH_TOKEN: ${{ github.token }}
           PREFLIGHT_RUN_ID: ${{ inputs.preflight_run_id }}
-          EXPECTED_PREFLIGHT_BRANCH: ${{ github.ref_name }}
         run: |
           set -euo pipefail
           RUN_JSON="$(gh run view "$PREFLIGHT_RUN_ID" --repo "$GITHUB_REPOSITORY" --json workflowName,headBranch,event,conclusion,url)"
-          printf '%s' "$RUN_JSON" | node -e 'const fs = require("node:fs"); const run = JSON.parse(fs.readFileSync(0, "utf8")); const checks = [["workflowName", "OpenClaw NPM Release"], ["headBranch", process.env.EXPECTED_PREFLIGHT_BRANCH], ["event", "workflow_dispatch"], ["conclusion", "success"]]; for (const [key, expected] of checks) { if (run[key] !== expected) { console.error(`Referenced npm preflight run ${process.env.PREFLIGHT_RUN_ID} must have ${key}=${expected}, got ${run[key] ?? "<missing>"}.`); process.exit(1); } } console.log(`Using npm preflight run ${process.env.PREFLIGHT_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", "OpenClaw NPM Release"], ["event", "workflow_dispatch"], ["conclusion", "success"]]; for (const [key, expected] of checks) { if (run[key] !== expected) { console.error(`Referenced npm preflight run ${process.env.PREFLIGHT_RUN_ID} must have ${key}=${expected}, got ${run[key] ?? "<missing>"}.`); process.exit(1); } } console.log(`Using npm preflight run ${process.env.PREFLIGHT_RUN_ID} from ${run.headBranch}: ${run.url}`);'
 
       - name: Verify full release validation run metadata
+        if: ${{ inputs.full_release_validation_run_id != '' }}
         env:
           GH_TOKEN: ${{ github.token }}
           FULL_RELEASE_VALIDATION_RUN_ID: ${{ inputs.full_release_validation_run_id }}
-          EXPECTED_WORKFLOW_BRANCH: ${{ github.ref_name }}
         run: |
           set -euo pipefail
           RUN_JSON="$(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); } } console.log(`Using full release validation run ${process.env.FULL_RELEASE_VALIDATION_RUN_ID} from ${run.headBranch}: ${run.url}`);'
 
       - name: Download prepared npm tarball
         env:
@@ -511,10 +545,25 @@ jobs:
             preferred_name="openclaw-npm-preflight-${RELEASE_TAG}"
             rm -rf preflight-tarball
             mkdir -p preflight-tarball
-            if gh run download "${PREFLIGHT_RUN_ID}" \
-              --repo "${GITHUB_REPOSITORY}" \
-              --name "${preferred_name}" \
-              --dir preflight-tarball; then
+
+            download_named_artifact() {
+              local artifact_name="$1"
+              for attempt in 1 2 3; do
+                if gh run download "${PREFLIGHT_RUN_ID}" \
+                  --repo "${GITHUB_REPOSITORY}" \
+                  --name "${artifact_name}" \
+                  --dir preflight-tarball; then
+                  return 0
+                fi
+                if [[ "$attempt" != "3" ]]; then
+                  echo "::warning::Artifact download for ${artifact_name} failed on attempt ${attempt}; retrying."
+                  sleep $((attempt * 10))
+                fi
+              done
+              return 1
+            }
+
+            if download_named_artifact "${preferred_name}"; then
               echo "Downloaded ${preferred_name}."
               return 0
             fi
@@ -530,16 +579,14 @@ jobs:
               exit 1
             fi
             fallback_name="${matches[0]}"
-            gh run download "${PREFLIGHT_RUN_ID}" \
-              --repo "${GITHUB_REPOSITORY}" \
-              --name "${fallback_name}" \
-              --dir preflight-tarball
+            download_named_artifact "${fallback_name}"
             echo "Downloaded fallback preflight artifact ${fallback_name}."
           }
 
           download_preflight_artifact
 
       - name: Download full release validation manifest
+        if: ${{ inputs.full_release_validation_run_id != '' }}
         uses: actions/download-artifact@v8
         with:
           name: full-release-validation-${{ inputs.full_release_validation_run_id }}
@@ -605,6 +652,7 @@ jobs:
           fi
 
       - name: Verify full release validation target
+        if: ${{ inputs.full_release_validation_run_id != '' }}
         run: |
           set -euo pipefail
           EXPECTED_RELEASE_SHA="$(git rev-parse HEAD)"

.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 \
@@ -460,15 +527,19 @@ 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"
 
       - name: Upload Kova artifacts
         if: ${{ always() && steps.lane.outputs.run == 'true' }}
-        uses: actions/upload-artifact@v5
+        uses: actions/upload-artifact@v7
         with:
           name: openclaw-performance-${{ matrix.lane }}-${{ github.run_id }}-${{ github.run_attempt }}
           path: |
@@ -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

@@ -78,15 +78,19 @@ on:
         required: false
         default: ""
         type: string
+      codex_plugin_spec:
+        description: Optional Codex plugin install spec for live Docker package checks; blank derives from release_package_spec or packs the selected ref
+        required: false
+        default: ""
+        type: string
 
 concurrency:
   group: openclaw-release-checks-${{ inputs.expected_sha || inputs.ref }}-${{ inputs.rerun_group }}
-  cancel-in-progress: false
+  cancel-in-progress: ${{ startsWith(github.ref, 'refs/heads/tideclaw/alpha/') }}
 
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
-  PNPM_VERSION: "11.0.8"
   OPENCLAW_CI_OPENAI_MODEL: ${{ vars.OPENCLAW_CI_OPENAI_MODEL || 'openai/gpt-5.5' }}
 
 jobs:
@@ -112,6 +116,7 @@ jobs:
       qa_live_slack_enabled: ${{ steps.inputs.outputs.qa_live_slack_enabled }}
       release_package_spec: ${{ steps.inputs.outputs.release_package_spec }}
       package_acceptance_package_spec: ${{ steps.inputs.outputs.package_acceptance_package_spec }}
+      codex_plugin_spec: ${{ steps.inputs.outputs.codex_plugin_spec }}
     steps:
       - name: Require trusted workflow ref for release checks
         env:
@@ -186,11 +191,21 @@ jobs:
         working-directory: source
         env:
           RELEASE_REF: ${{ inputs.ref }}
+          GITHUB_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
           SELECTED_SHA="$(git rev-parse HEAD)"
-          git fetch --no-tags origin '+refs/heads/*:refs/remotes/origin/*'
-          git fetch --tags origin '+refs/tags/*:refs/tags/*'
+          git_fetch_with_checkout_auth() {
+            if git config --get-all http.https://github.com/.extraheader >/dev/null; then
+              git fetch "$@"
+              return
+            fi
+            local auth_header
+            auth_header="$(printf 'x-access-token:%s' "$GITHUB_TOKEN" | base64 | tr -d '\n')"
+            git -c "http.https://github.com/.extraheader=AUTHORIZATION: basic ${auth_header}" fetch "$@"
+          }
+          git_fetch_with_checkout_auth --no-tags origin '+refs/heads/*:refs/remotes/origin/*'
+          git_fetch_with_checkout_auth --tags origin '+refs/tags/*:refs/tags/*'
 
           if git tag --points-at "${SELECTED_SHA}" | grep -Eq '^v'; then
             exit 0
@@ -233,6 +248,7 @@ jobs:
         env:
           SELECTED_SHA: ${{ steps.ref.outputs.sha }}
           WORKFLOW_REF: ${{ github.ref }}
+          GITHUB_TOKEN: ${{ github.token }}
         run: |
           set -euo pipefail
           if [[ ! "${WORKFLOW_REF}" =~ ^refs/heads/tideclaw/alpha/[0-9]{4}-[0-9]{2}-[0-9]{2}-[0-9]{4}Z$ ]]; then
@@ -240,7 +256,16 @@ jobs:
             exit 1
           fi
           alpha_branch="${WORKFLOW_REF#refs/heads/}"
-          git fetch --no-tags origin "+refs/heads/${alpha_branch}:refs/remotes/origin/${alpha_branch}"
+          git_fetch_with_checkout_auth() {
+            if git config --get-all http.https://github.com/.extraheader >/dev/null; then
+              git fetch "$@"
+              return
+            fi
+            local auth_header
+            auth_header="$(printf 'x-access-token:%s' "$GITHUB_TOKEN" | base64 | tr -d '\n')"
+            git -c "http.https://github.com/.extraheader=AUTHORIZATION: basic ${auth_header}" fetch "$@"
+          }
+          git_fetch_with_checkout_auth --no-tags origin "+refs/heads/${alpha_branch}:refs/remotes/origin/${alpha_branch}"
           if ! git merge-base --is-ancestor "${SELECTED_SHA}" "refs/remotes/origin/${alpha_branch}"; then
             echo "Alpha release target ${SELECTED_SHA} must be reachable from ${alpha_branch}." >&2
             exit 1
@@ -262,6 +287,7 @@ jobs:
           RELEASE_QA_SLACK_LIVE_CI_ENABLED: ${{ vars.OPENCLAW_RELEASE_QA_SLACK_LIVE_CI_ENABLED || 'false' }}
           RELEASE_PACKAGE_SPEC_INPUT: ${{ inputs.release_package_spec }}
           RELEASE_PACKAGE_ACCEPTANCE_PACKAGE_SPEC_INPUT: ${{ inputs.package_acceptance_package_spec }}
+          RELEASE_CODEX_PLUGIN_SPEC_INPUT: ${{ inputs.codex_plugin_spec }}
         run: |
           set -euo pipefail
           qa_live_matrix_enabled=true
@@ -307,6 +333,10 @@ jobs:
           if [[ "$release_profile" == "full" ]]; then
             run_release_soak=true
           fi
+          codex_plugin_spec="$RELEASE_CODEX_PLUGIN_SPEC_INPUT"
+          if [[ -z "${codex_plugin_spec// }" && "$RELEASE_PACKAGE_SPEC_INPUT" =~ ^openclaw@(.+)$ ]]; then
+            codex_plugin_spec="npm:@openclaw/codex@${BASH_REMATCH[1]}"
+          fi
 
           filter="$(printf '%s' "$RELEASE_LIVE_SUITE_FILTER_INPUT" | tr '[:upper:]' '[:lower:]')"
           if [[ -n "${filter// }" ]]; then
@@ -387,6 +417,7 @@ jobs:
             printf 'qa_live_slack_enabled=%s\n' "$qa_live_slack_enabled"
             printf 'release_package_spec=%s\n' "$RELEASE_PACKAGE_SPEC_INPUT"
             printf 'package_acceptance_package_spec=%s\n' "$RELEASE_PACKAGE_ACCEPTANCE_PACKAGE_SPEC_INPUT"
+            printf 'codex_plugin_spec=%s\n' "$codex_plugin_spec"
           } >> "$GITHUB_OUTPUT"
 
       - name: Summarize validated ref
@@ -403,6 +434,7 @@ jobs:
           RELEASE_CROSS_OS_SUITE_FILTER: ${{ inputs.cross_os_suite_filter }}
           RELEASE_PACKAGE_SPEC: ${{ inputs.release_package_spec }}
           PACKAGE_ACCEPTANCE_PACKAGE_SPEC: ${{ inputs.package_acceptance_package_spec }}
+          CODEX_PLUGIN_SPEC: ${{ steps.inputs.outputs.codex_plugin_spec }}
         run: |
           {
             echo "## Release checks"
@@ -432,6 +464,11 @@ jobs:
             else
               echo "- Package Acceptance package spec: prepared release artifact"
             fi
+            if [[ -n "${CODEX_PLUGIN_SPEC// }" ]]; then
+              echo "- Codex plugin spec: \`${CODEX_PLUGIN_SPEC}\`"
+            else
+              echo "- Codex plugin spec: packed from selected ref"
+            fi
             if [[ "$RUN_RELEASE_SOAK" == "true" ]]; then
               echo "- This run will execute blocking release validation plus exhaustive live/Docker soak coverage."
             else
@@ -457,7 +494,7 @@ jobs:
       - name: Checkout trusted workflow ref
         uses: actions/checkout@v6
         with:
-          persist-credentials: false
+          persist-credentials: true
           ref: ${{ github.ref_name }}
           fetch-depth: 0
 
@@ -469,7 +506,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
           install-deps: "false"
 
@@ -534,6 +570,7 @@ jobs:
     permissions: read-all
     uses: ./.github/workflows/openclaw-cross-os-release-checks-reusable.yml
     with:
+      advisory: ${{ startsWith(github.ref, 'refs/heads/tideclaw/alpha/') }}
       ref: ${{ needs.resolve_target.outputs.revision }}
       provider: ${{ needs.resolve_target.outputs.provider }}
       mode: ${{ needs.resolve_target.outputs.mode }}
@@ -565,6 +602,7 @@ jobs:
       pull-requests: read
     uses: ./.github/workflows/openclaw-live-and-e2e-checks-reusable.yml
     with:
+      advisory: ${{ startsWith(github.ref, 'refs/heads/tideclaw/alpha/') }}
       ref: ${{ needs.resolve_target.outputs.revision }}
       include_repo_e2e: true
       include_release_path_suites: false
@@ -578,6 +616,7 @@ jobs:
       ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
       ANTHROPIC_API_KEY_OLD: ${{ secrets.ANTHROPIC_API_KEY_OLD }}
       ANTHROPIC_API_TOKEN: ${{ secrets.ANTHROPIC_API_TOKEN }}
+      FACTORY_API_KEY: ${{ secrets.FACTORY_API_KEY }}
       BYTEPLUS_API_KEY: ${{ secrets.BYTEPLUS_API_KEY }}
       CEREBRAS_API_KEY: ${{ secrets.CEREBRAS_API_KEY }}
       DEEPINFRA_API_KEY: ${{ secrets.DEEPINFRA_API_KEY }}
@@ -630,6 +669,7 @@ jobs:
       pull-requests: read
     uses: ./.github/workflows/openclaw-live-and-e2e-checks-reusable.yml
     with:
+      advisory: ${{ startsWith(github.ref, 'refs/heads/tideclaw/alpha/') }}
       ref: ${{ needs.resolve_target.outputs.revision }}
       include_repo_e2e: false
       include_release_path_suites: true
@@ -637,6 +677,7 @@ jobs:
       include_live_suites: false
       release_test_profile: ${{ needs.resolve_target.outputs.release_profile }}
       package_artifact_name: ${{ needs.prepare_release_package.outputs.artifact_name }}
+      codex_plugin_spec: ${{ needs.resolve_target.outputs.codex_plugin_spec }}
     secrets: *live_e2e_release_secrets
 
   package_acceptance_release_checks:
@@ -650,13 +691,14 @@ jobs:
       pull-requests: read
     uses: ./.github/workflows/package-acceptance.yml
     with:
+      advisory: false
       workflow_ref: ${{ github.ref_name }}
       source: ${{ (needs.resolve_target.outputs.package_acceptance_package_spec != '' || needs.resolve_target.outputs.release_package_spec != '') && 'npm' || 'artifact' }}
       package_spec: ${{ needs.resolve_target.outputs.package_acceptance_package_spec || needs.resolve_target.outputs.release_package_spec || 'openclaw@beta' }}
       artifact_name: ${{ needs.prepare_release_package.outputs.artifact_name }}
       package_sha256: ${{ (needs.resolve_target.outputs.package_acceptance_package_spec == '' && needs.resolve_target.outputs.release_package_spec == '') && needs.prepare_release_package.outputs.package_sha256 || '' }}
       suite_profile: custom
-      docker_lanes: doctor-switch update-channel-switch skill-install update-corrupt-plugin upgrade-survivor published-upgrade-survivor root-managed-vps-upgrade update-restart-auth plugins-offline plugin-update
+      docker_lanes: doctor-switch update-channel-switch skill-install update-corrupt-plugin upgrade-survivor published-upgrade-survivor root-managed-vps-upgrade update-restart-auth plugins-offline plugin-update plugin-binding-command-escape
       published_upgrade_survivor_baselines: ${{ needs.resolve_target.outputs.run_release_soak == 'true' && 'last-stable-4 2026.4.23 2026.5.2 2026.4.15' || '' }}
       published_upgrade_survivor_scenarios: ${{ needs.resolve_target.outputs.run_release_soak == 'true' && 'reported-issues' || '' }}
       telegram_mode: mock-openai
@@ -667,6 +709,7 @@ jobs:
       ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
       ANTHROPIC_API_KEY_OLD: ${{ secrets.ANTHROPIC_API_KEY_OLD }}
       ANTHROPIC_API_TOKEN: ${{ secrets.ANTHROPIC_API_TOKEN }}
+      FACTORY_API_KEY: ${{ secrets.FACTORY_API_KEY }}
       BYTEPLUS_API_KEY: ${{ secrets.BYTEPLUS_API_KEY }}
       CEREBRAS_API_KEY: ${{ secrets.CEREBRAS_API_KEY }}
       DEEPINFRA_API_KEY: ${{ secrets.DEEPINFRA_API_KEY }}
@@ -742,7 +785,7 @@ jobs:
       - name: Checkout selected ref
         uses: actions/checkout@v6
         with:
-          persist-credentials: false
+          persist-credentials: true
           ref: ${{ needs.resolve_target.outputs.revision }}
           fetch-depth: 1
 
@@ -750,7 +793,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Build private QA runtime
@@ -790,7 +832,7 @@ jobs:
 
       - name: Upload parity lane artifacts
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: release-qa-parity-${{ matrix.lane }}-${{ needs.resolve_target.outputs.revision }}
           path: .artifacts/qa-e2e/
@@ -814,7 +856,7 @@ jobs:
       - name: Checkout selected ref
         uses: actions/checkout@v6
         with:
-          persist-credentials: false
+          persist-credentials: true
           ref: ${{ needs.resolve_target.outputs.revision }}
           fetch-depth: 1
 
@@ -822,11 +864,10 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Download parity lane artifacts
-        uses: actions/download-artifact@v4
+        uses: actions/download-artifact@v8
         with:
           pattern: release-qa-parity-*-${{ needs.resolve_target.outputs.revision }}
           path: .artifacts/qa-e2e/
@@ -849,7 +890,7 @@ jobs:
 
       - name: Upload parity artifacts
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: release-qa-parity-${{ needs.resolve_target.outputs.revision }}
           path: .artifacts/qa-e2e/
@@ -880,7 +921,7 @@ jobs:
       - name: Checkout selected ref
         uses: actions/checkout@v6
         with:
-          persist-credentials: false
+          persist-credentials: true
           ref: ${{ needs.resolve_target.outputs.revision }}
           fetch-depth: 1
 
@@ -888,7 +929,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Build private QA runtime
@@ -906,7 +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
@@ -919,9 +959,23 @@ 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
+        id: runtime_parity_soak_lane
+        if: ${{ always() && needs.resolve_target.outputs.run_release_soak == 'true' && steps.runtime_parity_lane.outcome != 'skipped' && steps.runtime_parity_lane.outcome != 'cancelled' }}
+        run: |
+          set -euo pipefail
+          pnpm openclaw qa suite \
+            --provider-mode mock-openai \
+            --runtime-parity-tier soak \
+            --concurrency "${QA_PARITY_CONCURRENCY}" \
+            --model "${OPENCLAW_CI_OPENAI_MODEL}" \
+            --alt-model "openai/gpt-5.5-alt" \
+            --runtime-pair openclaw,codex \
+            --output-dir ".artifacts/qa-e2e/runtime-parity-soak"
+
       - name: Generate runtime parity report
         if: always()
         run: |
@@ -942,15 +996,80 @@ jobs:
             --summary .artifacts/qa-e2e/runtime-parity-standard/qa-suite-summary.json \
             --output-dir .artifacts/qa-e2e/runtime-parity-standard-report
 
+      - name: Generate soak runtime parity report
+        if: ${{ always() && needs.resolve_target.outputs.run_release_soak == 'true' && steps.runtime_parity_soak_lane.outcome != 'skipped' && steps.runtime_parity_soak_lane.outcome != 'cancelled' }}
+        run: |
+          set -euo pipefail
+          summary=".artifacts/qa-e2e/runtime-parity-soak/qa-suite-summary.json"
+          if [[ ! -f "$summary" ]]; then
+            echo "No soak runtime parity summary was produced."
+            exit 0
+          fi
+          pnpm openclaw qa parity-report \
+            --repo-root . \
+            --runtime-axis \
+            --summary "$summary" \
+            --output-dir .artifacts/qa-e2e/runtime-parity-soak-report
+
       - name: Upload runtime parity artifacts
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: release-qa-runtime-parity-${{ needs.resolve_target.outputs.revision }}
           path: .artifacts/qa-e2e/
           retention-days: 14
           if-no-files-found: warn
 
+  runtime_tool_coverage_release_checks:
+    name: Enforce QA Lab runtime tool coverage
+    needs: [resolve_target, qa_lab_runtime_parity_release_checks]
+    if: always() && contains(fromJSON('["all","qa","qa-parity"]'), needs.resolve_target.outputs.rerun_group)
+    runs-on: ubuntu-24.04
+    timeout-minutes: 15
+    permissions:
+      contents: read
+      actions: read
+    env:
+      OPENCLAW_BUILD_PRIVATE_QA: "1"
+      OPENCLAW_ENABLE_PRIVATE_QA_CLI: "1"
+    steps:
+      - name: Checkout selected ref
+        uses: actions/checkout@v6
+        with:
+          persist-credentials: true
+          ref: ${{ needs.resolve_target.outputs.revision }}
+          fetch-depth: 1
+
+      - name: Setup Node environment
+        uses: ./.github/actions/setup-node-env
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+          install-bun: "true"
+
+      - name: Download runtime parity artifacts
+        uses: actions/download-artifact@v8
+        with:
+          name: release-qa-runtime-parity-${{ needs.resolve_target.outputs.revision }}
+          path: .artifacts/qa-e2e/
+
+      - name: Enforce standard runtime tool coverage
+        run: |
+          set -euo pipefail
+          pnpm openclaw qa coverage \
+            --repo-root . \
+            --tools \
+            --summary .artifacts/qa-e2e/runtime-parity-standard/qa-suite-summary.json \
+            --output .artifacts/qa-e2e/runtime-parity-standard-report/qa-runtime-tool-coverage-report.md
+
+      - name: Upload runtime tool coverage artifacts
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: release-qa-runtime-tool-coverage-${{ needs.resolve_target.outputs.revision }}
+          path: .artifacts/qa-e2e/runtime-parity-standard-report/
+          retention-days: 14
+          if-no-files-found: warn
+
   qa_live_matrix_release_checks:
     name: Run QA Lab live Matrix lane
     needs: [resolve_target]
@@ -969,7 +1088,7 @@ jobs:
       - name: Checkout selected ref
         uses: actions/checkout@v6
         with:
-          persist-credentials: false
+          persist-credentials: true
           ref: ${{ needs.resolve_target.outputs.revision }}
           fetch-depth: 1
 
@@ -977,7 +1096,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Build private QA runtime
@@ -1024,7 +1142,7 @@ jobs:
 
       - name: Upload Matrix QA artifacts
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: release-qa-live-matrix-${{ needs.resolve_target.outputs.revision }}
           path: .artifacts/qa-e2e/
@@ -1049,7 +1167,7 @@ jobs:
       - name: Checkout selected ref
         uses: actions/checkout@v6
         with:
-          persist-credentials: false
+          persist-credentials: true
           ref: ${{ needs.resolve_target.outputs.revision }}
           fetch-depth: 1
 
@@ -1057,7 +1175,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Validate required QA credential env
@@ -1120,7 +1237,7 @@ jobs:
 
       - name: Upload Telegram QA artifacts
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: release-qa-live-telegram-${{ needs.resolve_target.outputs.revision }}
           path: .artifacts/qa-e2e/
@@ -1145,7 +1262,7 @@ jobs:
       - name: Checkout selected ref
         uses: actions/checkout@v6
         with:
-          persist-credentials: false
+          persist-credentials: true
           ref: ${{ needs.resolve_target.outputs.revision }}
           fetch-depth: 1
 
@@ -1153,7 +1270,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Validate required QA credential env
@@ -1216,7 +1332,7 @@ jobs:
 
       - name: Upload Discord QA artifacts
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: release-qa-live-discord-${{ needs.resolve_target.outputs.revision }}
           path: .artifacts/qa-e2e/
@@ -1244,7 +1360,7 @@ jobs:
       - name: Checkout selected ref
         uses: actions/checkout@v6
         with:
-          persist-credentials: false
+          persist-credentials: true
           ref: ${{ needs.resolve_target.outputs.revision }}
           fetch-depth: 1
 
@@ -1252,7 +1368,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Validate required QA credential env
@@ -1315,7 +1430,7 @@ jobs:
 
       - name: Upload WhatsApp QA artifacts
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: release-qa-live-whatsapp-${{ needs.resolve_target.outputs.revision }}
           path: .artifacts/qa-e2e/
@@ -1340,7 +1455,7 @@ jobs:
       - name: Checkout selected ref
         uses: actions/checkout@v6
         with:
-          persist-credentials: false
+          persist-credentials: true
           ref: ${{ needs.resolve_target.outputs.revision }}
           fetch-depth: 1
 
@@ -1348,7 +1463,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
 
       - name: Validate required QA credential env
@@ -1411,7 +1525,7 @@ jobs:
 
       - name: Upload Slack QA artifacts
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: release-qa-live-slack-${{ needs.resolve_target.outputs.revision }}
           path: .artifacts/qa-e2e/
@@ -1430,6 +1544,7 @@ jobs:
       - qa_lab_parity_lane_release_checks
       - qa_lab_parity_report_release_checks
       - qa_lab_runtime_parity_release_checks
+      - runtime_tool_coverage_release_checks
       - qa_live_matrix_release_checks
       - qa_live_telegram_release_checks
       - qa_live_discord_release_checks
@@ -1442,9 +1557,15 @@ jobs:
     steps:
       - name: Verify release check results
         shell: bash
+        env:
+          WORKFLOW_REF: ${{ github.ref }}
         run: |
           set -euo pipefail
           failed=0
+          tideclaw_alpha=false
+          if [[ "${WORKFLOW_REF}" =~ ^refs/heads/tideclaw/alpha/[0-9]{4}-[0-9]{2}-[0-9]{2}-[0-9]{4}Z$ ]]; then
+            tideclaw_alpha=true
+          fi
           for item in \
             "prepare_release_package=${{ needs.prepare_release_package.result }}" \
             "install_smoke_release_checks=${{ needs.install_smoke_release_checks.result }}" \
@@ -1455,6 +1576,7 @@ jobs:
             "qa_lab_parity_lane_release_checks=${{ needs.qa_lab_parity_lane_release_checks.result }}" \
             "qa_lab_parity_report_release_checks=${{ needs.qa_lab_parity_report_release_checks.result }}" \
             "qa_lab_runtime_parity_release_checks=${{ needs.qa_lab_runtime_parity_release_checks.result }}" \
+            "runtime_tool_coverage_release_checks=${{ needs.runtime_tool_coverage_release_checks.result }}" \
             "qa_live_matrix_release_checks=${{ needs.qa_live_matrix_release_checks.result }}" \
             "qa_live_telegram_release_checks=${{ needs.qa_live_telegram_release_checks.result }}" \
             "qa_live_discord_release_checks=${{ needs.qa_live_discord_release_checks.result }}" \
@@ -1464,6 +1586,15 @@ jobs:
             name="${item%%=*}"
             result="${item#*=}"
             if [[ "$result" != "success" && "$result" != "skipped" ]]; then
+              if [[ "$tideclaw_alpha" == "true" ]]; then
+                case "$name" in
+                  prepare_release_package|install_smoke_release_checks|package_acceptance_release_checks) ;;
+                  *)
+                    echo "::warning::${name} ended with ${result}; Tideclaw alpha treats non-package-safety release-check lanes as advisory."
+                    continue
+                    ;;
+                esac
+              fi
               if [[ "$name" == qa_* ]]; then
                 echo "::warning::${name} ended with ${result}; QA release-check lanes are advisory and do not block release validation."
                 continue

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

@@ -71,7 +71,6 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
-  PNPM_VERSION: "11.0.8"
 
 jobs:
   resolve_release_target:
@@ -153,10 +152,25 @@ jobs:
           preflight_dir="${RUNNER_TEMP}/openclaw-npm-preflight-manifest"
           rm -rf "${preflight_dir}"
           mkdir -p "${preflight_dir}"
-          if gh run download "${PREFLIGHT_RUN_ID}" \
-            --repo "${GITHUB_REPOSITORY}" \
-            --name "${preferred_name}" \
-            --dir "${preflight_dir}"; then
+
+          download_named_artifact() {
+            local artifact_name="$1"
+            for attempt in 1 2 3; do
+              if gh run download "${PREFLIGHT_RUN_ID}" \
+                --repo "${GITHUB_REPOSITORY}" \
+                --name "${artifact_name}" \
+                --dir "${preflight_dir}"; then
+                return 0
+              fi
+              if [[ "$attempt" != "3" ]]; then
+                echo "::warning::Artifact download for ${artifact_name} failed on attempt ${attempt}; retrying."
+                sleep $((attempt * 10))
+              fi
+            done
+            return 1
+          }
+
+          if download_named_artifact "${preferred_name}"; then
             echo "name=${preferred_name}" >> "$GITHUB_OUTPUT"
             exit 0
           fi
@@ -172,10 +186,7 @@ jobs:
             exit 1
           fi
           fallback_name="${matches[0]}"
-          gh run download "${PREFLIGHT_RUN_ID}" \
-            --repo "${GITHUB_REPOSITORY}" \
-            --name "${fallback_name}" \
-            --dir "${preflight_dir}"
+          download_named_artifact "${fallback_name}"
           echo "name=${fallback_name}" >> "$GITHUB_OUTPUT"
 
       - name: Download full release validation manifest
@@ -254,7 +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
@@ -336,6 +347,7 @@ jobs:
     needs: [resolve_release_target]
     runs-on: ubuntu-latest
     timeout-minutes: 60
+    environment: npm-release
     steps:
       - name: Checkout release SHA
         uses: actions/checkout@v6
@@ -348,7 +360,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           install-bun: "false"
-          cache-key-suffix: release-publish
 
       - name: Dispatch publish workflows
         env:
@@ -438,7 +449,7 @@ jobs:
 
             pending_json="$(gh api -X GET "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/pending_deployments" 2>/dev/null || true)"
             if [[ -z "${pending_json}" ]] || ! printf '%s' "${pending_json}" | jq -e 'length > 0' >/dev/null 2>&1; then
-              return 0
+              return 1
             fi
 
             approved=0
@@ -450,13 +461,15 @@ jobs:
               gh api -X POST "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/pending_deployments" \
                 -F "environment_ids[]=${env_id}" \
                 -f state=approved \
-                -f comment="Approve release gate from OpenClaw Release Publish wrapper" >/dev/null
+                -f comment="Approve child release gate after parent release approval" >/dev/null
               approved=1
             done < <(printf '%s' "${pending_json}" | jq -r '.[] | select(.current_user_can_approve == true) | [.environment.id, .environment.name] | @tsv')
 
             if [[ "${approved}" == "1" ]]; then
               echo "${workflow}: approved available pending environment gates"
+              return 0
             fi
+            return 1
           }
 
           print_failed_run_summary() {
@@ -499,7 +512,7 @@ jobs:
               if [[ "$state" != "$last_state" ]]; then
                 echo "${workflow} still ${status} (updated ${updated_at}): ${url}"
                 print_pending_deployments "${workflow}" "${run_id}"
-                approve_pending_deployments "${workflow}" "${run_id}"
+                approve_pending_deployments "${workflow}" "${run_id}" || true
                 last_state="$state"
               fi
               sleep 30
@@ -546,6 +559,85 @@ jobs:
             wait_run_pid="$!"
           }
 
+          wait_for_job_success() {
+            local workflow="$1"
+            local run_id="$2"
+            local job_name="$3"
+            local jobs_json job_json run_status run_conclusion status conclusion url deadline
+
+            deadline=$((SECONDS + 900))
+            while true; do
+              jobs_json="$(gh run view --repo "$GITHUB_REPOSITORY" "$run_id" --json status,conclusion,jobs)"
+              run_status="$(printf '%s' "$jobs_json" | jq -r '.status')"
+              run_conclusion="$(printf '%s' "$jobs_json" | jq -r '.conclusion // ""')"
+              job_json="$(printf '%s' "$jobs_json" | jq -c --arg name "$job_name" '.jobs[]? | select(.name == $name) | {status, conclusion, url}' | head -n 1)"
+              if [[ -n "$job_json" ]]; then
+                status="$(printf '%s' "$job_json" | jq -r '.status')"
+                conclusion="$(printf '%s' "$job_json" | jq -r '.conclusion // ""')"
+                url="$(printf '%s' "$job_json" | jq -r '.url // ""')"
+                if [[ "$status" == "completed" ]]; then
+                  if [[ "$conclusion" == "success" || "$conclusion" == "skipped" ]]; then
+                    echo "${workflow} ${job_name} ${conclusion}: ${url}"
+                    echo "- ${workflow} ${job_name}: ${conclusion} (${url})" >> "$GITHUB_STEP_SUMMARY"
+                    return 0
+                  fi
+                  echo "${workflow} ${job_name} failed: ${conclusion} ${url}" >&2
+                  print_failed_run_summary "${run_id}"
+                  return 1
+                fi
+                echo "${workflow} ${job_name} still ${status}: ${url}"
+              elif [[ "$run_status" == "completed" ]]; then
+                if [[ "$run_conclusion" == "success" ]]; then
+                  echo "${workflow} completed before ${job_name} was needed."
+                  echo "- ${workflow} ${job_name}: not needed" >> "$GITHUB_STEP_SUMMARY"
+                  return 0
+                fi
+                echo "${workflow} completed before ${job_name} with ${run_conclusion}." >&2
+                print_failed_run_summary "${run_id}"
+                return 1
+              else
+                echo "${workflow} waiting for ${job_name} to start: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
+              fi
+              if (( SECONDS >= deadline )); then
+                echo "${workflow} ${job_name} did not complete within 15 minutes." >&2
+                return 1
+              fi
+              sleep 10
+            done
+          }
+
+          approve_child_publish_environment() {
+            local workflow="$1"
+            local run_id="$2"
+            local run_json status conclusion deadline
+
+            deadline=$((SECONDS + 900))
+            while true; do
+              if approve_pending_deployments "${workflow}" "${run_id}"; then
+                echo "- ${workflow}: child environment gate approved" >> "$GITHUB_STEP_SUMMARY"
+                return 0
+              fi
+              run_json="$(gh run view --repo "$GITHUB_REPOSITORY" "$run_id" --json status,conclusion,url)"
+              status="$(printf '%s' "$run_json" | jq -r '.status')"
+              conclusion="$(printf '%s' "$run_json" | jq -r '.conclusion // ""')"
+              if [[ "$status" == "completed" ]]; then
+                if [[ "$conclusion" == "success" ]]; then
+                  echo "${workflow}: completed before child environment approval was needed"
+                  return 0
+                fi
+                echo "${workflow}: completed before child environment approval with ${conclusion}" >&2
+                print_failed_run_summary "${run_id}"
+                return 1
+              fi
+              if (( SECONDS >= deadline )); then
+                echo "${workflow}: child environment approval was not available within 15 minutes." >&2
+                print_pending_deployments "${workflow}" "${run_id}"
+                return 1
+              fi
+              sleep 10
+            done
+          }
+
           create_or_update_github_release() {
             local release_version notes_version title notes_file changelog_file latest_arg prerelease_args
             release_version="${RELEASE_TAG#v}"
@@ -645,10 +737,14 @@ jobs:
               --workflow-ref "${CHILD_WORKFLOW_REF}"
               --full-release-validation-run "${FULL_RELEASE_VALIDATION_RUN_ID}"
               --plugin-npm-run "${plugin_npm_run_id}"
-              --plugin-clawhub-run "${plugin_clawhub_run_id}"
               --openclaw-npm-run "${openclaw_npm_run_id}"
               --evidence-out "${evidence_path}"
             )
+            if [[ "${WAIT_FOR_CLAWHUB}" == "true" ]]; then
+              verify_args+=(--plugin-clawhub-run "${plugin_clawhub_run_id}")
+            else
+              verify_args+=(--skip-clawhub)
+            fi
             if [[ -n "${PLUGINS// }" ]]; then
               verify_args+=(--plugins "${PLUGINS}")
             fi
@@ -663,27 +759,97 @@ jobs:
             } >> "$GITHUB_STEP_SUMMARY"
           }
 
+          append_release_proof_to_github_release() {
+            local release_version body_file notes_file tarball integrity telegram_line clawhub_line
+
+            release_version="${RELEASE_TAG#v}"
+            body_file="${RUNNER_TEMP}/release-body.md"
+            notes_file="${RUNNER_TEMP}/release-notes-with-proof.md"
+            tarball="$(npm view "openclaw@${release_version}" dist.tarball --json | jq -r '.')"
+            integrity="$(npm view "openclaw@${release_version}" dist.integrity --json | jq -r '.')"
+            gh release view "${RELEASE_TAG}" --repo "$GITHUB_REPOSITORY" --json body --jq .body > "${body_file}"
+
+            if [[ -n "${NPM_TELEGRAM_RUN_ID// }" ]]; then
+              telegram_line="- npm Telegram beta E2E: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${NPM_TELEGRAM_RUN_ID}"
+            else
+              telegram_line="- npm Telegram beta E2E: not supplied"
+            fi
+            if [[ "${WAIT_FOR_CLAWHUB}" == "true" ]]; then
+              clawhub_line="- plugin ClawHub publish: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${plugin_clawhub_run_id}"
+            else
+              clawhub_line="- plugin ClawHub publish: dispatched separately, not awaited by this proof: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${plugin_clawhub_run_id}"
+            fi
+
+            RELEASE_BODY_FILE="${body_file}" \
+              RELEASE_NOTES_FILE="${notes_file}" \
+              RELEASE_VERSION="${release_version}" \
+              RELEASE_TAG="${RELEASE_TAG}" \
+              RELEASE_REPO="${GITHUB_REPOSITORY}" \
+              RELEASE_TARBALL="${tarball}" \
+              RELEASE_INTEGRITY="${integrity}" \
+              RELEASE_PUBLISH_RUN_ID="${GITHUB_RUN_ID}" \
+              PREFLIGHT_RUN_ID="${PREFLIGHT_RUN_ID}" \
+              FULL_RELEASE_VALIDATION_RUN_ID="${FULL_RELEASE_VALIDATION_RUN_ID}" \
+              PLUGIN_NPM_RUN_ID="${plugin_npm_run_id}" \
+              OPENCLAW_NPM_RUN_ID="${openclaw_npm_run_id}" \
+              CLAWHUB_LINE="${clawhub_line}" \
+              TELEGRAM_LINE="${telegram_line}" \
+              node --input-type=module <<'NODE'
+          import { readFileSync, writeFileSync } from "node:fs";
+
+          const bodyFile = process.env.RELEASE_BODY_FILE;
+          const notesFile = process.env.RELEASE_NOTES_FILE;
+          if (!bodyFile || !notesFile) {
+            throw new Error("Missing release notes file paths.");
+          }
+
+          const body = readFileSync(bodyFile, "utf8").trimEnd();
+          const section = [
+            "### Release verification",
+            "",
+            `- 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/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/${process.env.FULL_RELEASE_VALIDATION_RUN_ID}`,
+            `- plugin npm publish: https://github.com/${process.env.RELEASE_REPO}/actions/runs/${process.env.PLUGIN_NPM_RUN_ID}`,
+            process.env.CLAWHUB_LINE,
+            `- OpenClaw npm publish: https://github.com/${process.env.RELEASE_REPO}/actions/runs/${process.env.OPENCLAW_NPM_RUN_ID}`,
+            process.env.TELEGRAM_LINE,
+          ].join("\n");
+
+          const withoutOldProof = body.replace(/\n?### Release verification\n[\s\S]*?(?=\n### |\n## |$)/, "");
+          writeFileSync(notesFile, `${withoutOldProof.trimEnd()}\n\n${section}\n`);
+          NODE
+
+            gh release edit "${RELEASE_TAG}" --repo "$GITHUB_REPOSITORY" --notes-file "${notes_file}"
+            echo "- Release proof: appended to GitHub release" >> "$GITHUB_STEP_SUMMARY"
+          }
+
           {
             echo "### Publish sequence"
             echo
             echo "- Workflow ref: \`${CHILD_WORKFLOW_REF}\`"
             echo "- Release tag: \`${RELEASE_TAG}\`"
             echo "- Release SHA: \`${TARGET_SHA}\`"
+            echo "- Release approval: this workflow job"
             echo "- Plugin npm and ClawHub publish: dispatched in parallel"
             if [[ "${PUBLISH_OPENCLAW_NPM}" == "true" ]]; then
-              echo "- OpenClaw npm publish: starts after plugin npm succeeds; final verification waits for ClawHub"
+              echo "- OpenClaw npm publish: starts after plugin npm succeeds"
             else
               echo "- OpenClaw npm publish: skipped by input"
             fi
-            if [[ "${WAIT_FOR_CLAWHUB}" == "true" || "${PUBLISH_OPENCLAW_NPM}" == "true" ]]; then
+            if [[ "${WAIT_FOR_CLAWHUB}" == "true" ]]; then
               echo "- Workflow completion waits for ClawHub"
             else
               echo "- Workflow completion does not wait for ClawHub; monitor the dispatched ClawHub run separately"
             fi
           } >> "$GITHUB_STEP_SUMMARY"
 
-          npm_args=(-f publish_scope="${PLUGIN_PUBLISH_SCOPE}" -f ref="${TARGET_SHA}")
-          clawhub_args=(-f publish_scope="${PLUGIN_PUBLISH_SCOPE}" -f ref="${TARGET_SHA}")
+          npm_args=(-f publish_scope="${PLUGIN_PUBLISH_SCOPE}" -f ref="${TARGET_SHA}" -f release_publish_run_id="${GITHUB_RUN_ID}")
+          clawhub_args=(-f publish_scope="${PLUGIN_PUBLISH_SCOPE}" -f ref="${TARGET_SHA}" -f release_publish_run_id="${GITHUB_RUN_ID}")
           if [[ -n "${PLUGINS}" ]]; then
             npm_args+=(-f plugins="${PLUGINS}")
             clawhub_args+=(-f plugins="${PLUGINS}")
@@ -709,6 +875,7 @@ jobs:
               -f preflight_only=false \
               -f preflight_run_id="${PREFLIGHT_RUN_ID}" \
               -f full_release_validation_run_id="${FULL_RELEASE_VALIDATION_RUN_ID}" \
+              -f release_publish_run_id="${GITHUB_RUN_ID}" \
               -f npm_dist_tag="${RELEASE_NPM_DIST_TAG}")"
             echo "- OpenClaw npm run ID: \`${openclaw_npm_run_id}\`" >> "$GITHUB_STEP_SUMMARY"
           else
@@ -717,13 +884,19 @@ jobs:
 
           clawhub_result=""
           clawhub_pid=""
-          if [[ "${WAIT_FOR_CLAWHUB}" == "true" || "${PUBLISH_OPENCLAW_NPM}" == "true" ]]; then
+          if [[ "${WAIT_FOR_CLAWHUB}" == "true" ]]; then
             clawhub_result="$RUNNER_TEMP/clawhub-result.txt"
             wait_run_pid=""
             wait_for_run_background plugin-clawhub-release.yml "${plugin_clawhub_run_id}" "${clawhub_result}"
             clawhub_pid="${wait_run_pid}"
           else
-            echo "- plugin-clawhub-release.yml: not awaited (${plugin_clawhub_run_id})" >> "$GITHUB_STEP_SUMMARY"
+            wait_for_job_success plugin-clawhub-release.yml "${plugin_clawhub_run_id}" "Validate release publish approval"
+            if approve_child_publish_environment plugin-clawhub-release.yml "${plugin_clawhub_run_id}"; then
+              :
+            else
+              echo "- plugin-clawhub-release.yml: child environment gate not ready; publish was left dispatched (${plugin_clawhub_run_id})" >> "$GITHUB_STEP_SUMMARY"
+            fi
+            echo "- plugin-clawhub-release.yml: publish not awaited (${plugin_clawhub_run_id})" >> "$GITHUB_STEP_SUMMARY"
           fi
 
           openclaw_result=""
@@ -760,6 +933,7 @@ jobs:
 
           if [[ "${failed}" == "0" && -n "${openclaw_npm_run_id}" ]]; then
             verify_published_release
+            append_release_proof_to_github_release
           fi
           if [[ "${failed}" != "0" ]]; then
             exit 1

.github/workflows/openclaw-scheduled-live-checks.yml

@@ -38,6 +38,7 @@ jobs:
       ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
       ANTHROPIC_API_KEY_OLD: ${{ secrets.ANTHROPIC_API_KEY_OLD }}
       ANTHROPIC_API_TOKEN: ${{ secrets.ANTHROPIC_API_TOKEN }}
+      FACTORY_API_KEY: ${{ secrets.FACTORY_API_KEY }}
       BYTEPLUS_API_KEY: ${{ secrets.BYTEPLUS_API_KEY }}
       CEREBRAS_API_KEY: ${{ secrets.CEREBRAS_API_KEY }}
       DEEPINFRA_API_KEY: ${{ secrets.DEEPINFRA_API_KEY }}

.github/workflows/opengrep-precise-full.yml

@@ -62,7 +62,7 @@ jobs:
 
       - name: Upload SARIF as workflow artifact
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: opengrep-full-sarif
           path: .opengrep-out/precise.sarif

.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
@@ -92,7 +92,7 @@ jobs:
 
       - name: Upload SARIF as workflow artifact
         if: always()
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v7
         with:
           name: opengrep-pr-diff-sarif
           path: .opengrep-out/precise.sarif

.github/workflows/package-acceptance.yml

@@ -17,6 +17,7 @@ on:
           - npm
           - ref
           - url
+          - trusted-url
           - artifact
       package_ref:
         description: Trusted package source ref when source=ref
@@ -29,12 +30,17 @@ on:
         default: openclaw@beta
         type: string
       package_url:
-        description: HTTPS .tgz URL when source=url
+        description: HTTPS .tgz URL when source=url or source=trusted-url
         required: false
         default: ""
         type: string
       package_sha256:
-        description: Expected package SHA-256; required for source=url
+        description: Expected package SHA-256; required for source=url or source=trusted-url
+        required: false
+        default: ""
+        type: string
+      trusted_source_id:
+        description: Named trusted source policy when source=trusted-url
         required: false
         default: ""
         type: string
@@ -93,15 +99,25 @@ on:
         required: false
         default: ""
         type: string
+      advisory:
+        description: Treat acceptance failures as advisory for the caller
+        required: false
+        default: false
+        type: boolean
   workflow_call:
     inputs:
+      advisory:
+        description: Treat acceptance failures as advisory for the caller
+        required: false
+        default: false
+        type: boolean
       workflow_ref:
         description: Trusted repo ref for workflow scripts and Docker E2E harness
         required: false
         default: main
         type: string
       source:
-        description: "Package candidate source: npm, ref, url, or artifact"
+        description: "Package candidate source: npm, ref, url, trusted-url, or artifact"
         required: true
         type: string
       package_ref:
@@ -115,12 +131,17 @@ on:
         default: openclaw@beta
         type: string
       package_url:
-        description: HTTPS .tgz URL when source=url
+        description: HTTPS .tgz URL when source=url or source=trusted-url
         required: false
         default: ""
         type: string
       package_sha256:
-        description: Expected package SHA-256; required for source=url
+        description: Expected package SHA-256; required for source=url or source=trusted-url
+        required: false
+        default: ""
+        type: string
+      trusted_source_id:
+        description: Named trusted source policy when source=trusted-url
         required: false
         default: ""
         type: string
@@ -170,6 +191,8 @@ on:
         default: ""
         type: string
     secrets:
+      OPENCLAW_TRUSTED_PACKAGE_TOKEN:
+        required: false
       OPENAI_API_KEY:
         required: false
       OPENAI_BASE_URL:
@@ -180,6 +203,8 @@ on:
         required: false
       ANTHROPIC_API_TOKEN:
         required: false
+      FACTORY_API_KEY:
+        required: false
       BYTEPLUS_API_KEY:
         required: false
       CEREBRAS_API_KEY:
@@ -278,7 +303,6 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
-  PNPM_VERSION: "11.0.8"
   PACKAGE_ARTIFACT_NAME: package-under-test
 
 jobs:
@@ -310,7 +334,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: ${{ inputs.source == 'ref' && 'true' || 'false' }}
           install-deps: "false"
 
@@ -345,6 +368,8 @@ jobs:
           PACKAGE_SPEC: ${{ inputs.package_spec }}
           PACKAGE_URL: ${{ inputs.package_url }}
           PACKAGE_SHA256: ${{ inputs.package_sha256 }}
+          TRUSTED_SOURCE_ID: ${{ inputs.trusted_source_id }}
+          OPENCLAW_TRUSTED_PACKAGE_TOKEN: ${{ secrets.OPENCLAW_TRUSTED_PACKAGE_TOKEN }}
         shell: bash
         run: |
           set -euo pipefail
@@ -359,6 +384,7 @@ jobs:
             --package-spec "$PACKAGE_SPEC" \
             --package-url "$PACKAGE_URL" \
             --package-sha256 "$PACKAGE_SHA256" \
+            --trusted-source-id "$TRUSTED_SOURCE_ID" \
             --artifact-dir "${artifact_dir:-.}" \
             --output-dir .artifacts/docker-e2e-package \
             --output-name openclaw-current.tgz \
@@ -480,6 +506,7 @@ jobs:
           PACKAGE_SHA256: ${{ steps.resolve.outputs.sha256 }}
           PACKAGE_VERSION: ${{ steps.resolve.outputs.package_version }}
           PACKAGE_REF: ${{ inputs.package_ref }}
+          TRUSTED_SOURCE_ID: ${{ inputs.trusted_source_id }}
           SOURCE: ${{ inputs.source }}
           SUITE_PROFILE: ${{ inputs.suite_profile }}
           WORKFLOW_REF: ${{ inputs.workflow_ref }}
@@ -496,6 +523,9 @@ jobs:
             if [[ "${SOURCE}" == "ref" ]]; then
               echo "- Package ref: \`${PACKAGE_REF}\`"
             fi
+            if [[ "${SOURCE}" == "trusted-url" ]]; then
+              echo "- Trusted source: \`${TRUSTED_SOURCE_ID}\`"
+            fi
             echo "- Version: \`${PACKAGE_VERSION}\`"
             echo "- SHA-256: \`${PACKAGE_SHA256}\`"
             echo "- Profile: \`${SUITE_PROFILE}\`"
@@ -504,11 +534,43 @@ jobs:
             echo "- Published upgrade survivor scenarios: \`${PUBLISHED_UPGRADE_SURVIVOR_SCENARIOS}\`"
           } >> "$GITHUB_STEP_SUMMARY"
 
+  package_integrity:
+    name: Package integrity
+    needs: resolve_package
+    runs-on: ubuntu-24.04
+    timeout-minutes: 10
+    steps:
+      - name: Checkout package workflow ref
+        uses: actions/checkout@v6
+        with:
+          ref: ${{ inputs.workflow_ref }}
+          fetch-depth: 1
+
+      - name: Download package-under-test artifact
+        uses: actions/download-artifact@v8
+        with:
+          name: ${{ needs.resolve_package.outputs.package_artifact_name }}
+          path: .artifacts/docker-e2e-package
+
+      - name: Enforce public package integrity
+        env:
+          OPENCLAW_PACKAGE_TARBALL_CHECK_TIMINGS: "0"
+        shell: bash
+        run: |
+          set -euo pipefail
+          node scripts/check-openclaw-package-tarball.mjs .artifacts/docker-e2e-package/openclaw-current.tgz
+
   docker_acceptance:
     name: Docker product acceptance
-    needs: resolve_package
+    needs: [resolve_package, package_integrity]
+    permissions:
+      actions: read
+      contents: read
+      packages: write
+      pull-requests: read
     uses: ./.github/workflows/openclaw-live-and-e2e-checks-reusable.yml
     with:
+      advisory: ${{ inputs.advisory }}
       ref: ${{ needs.resolve_package.outputs.package_source_sha || inputs.workflow_ref }}
       include_repo_e2e: false
       include_release_path_suites: ${{ needs.resolve_package.outputs.include_release_path_suites == 'true' }}
@@ -526,6 +588,7 @@ jobs:
       ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
       ANTHROPIC_API_KEY_OLD: ${{ secrets.ANTHROPIC_API_KEY_OLD }}
       ANTHROPIC_API_TOKEN: ${{ secrets.ANTHROPIC_API_TOKEN }}
+      FACTORY_API_KEY: ${{ secrets.FACTORY_API_KEY }}
       BYTEPLUS_API_KEY: ${{ secrets.BYTEPLUS_API_KEY }}
       CEREBRAS_API_KEY: ${{ secrets.CEREBRAS_API_KEY }}
       DEEPINFRA_API_KEY: ${{ secrets.DEEPINFRA_API_KEY }}
@@ -569,10 +632,11 @@ jobs:
 
   package_telegram:
     name: Telegram package acceptance
-    needs: resolve_package
+    needs: [resolve_package, package_integrity]
     if: needs.resolve_package.outputs.telegram_enabled == 'true'
     uses: ./.github/workflows/npm-telegram-beta-e2e.yml
     with:
+      advisory: ${{ inputs.advisory }}
       package_spec: ${{ inputs.package_spec }}
       package_artifact_name: ${{ needs.resolve_package.outputs.package_artifact_name }}
       package_label: openclaw@${{ needs.resolve_package.outputs.package_version }}
@@ -586,7 +650,7 @@ jobs:
 
   summary:
     name: Verify package acceptance
-    needs: [resolve_package, docker_acceptance, package_telegram]
+    needs: [resolve_package, package_integrity, docker_acceptance, package_telegram]
     if: always()
     runs-on: ubuntu-24.04
     timeout-minutes: 5
@@ -594,20 +658,27 @@ jobs:
       - name: Verify package acceptance results
         env:
           DOCKER_RESULT: ${{ needs.docker_acceptance.result }}
+          PACKAGE_INTEGRITY_RESULT: ${{ needs.package_integrity.result }}
           PACKAGE_TELEGRAM_RESULT: ${{ needs.package_telegram.result }}
           RESOLVE_RESULT: ${{ needs.resolve_package.result }}
         shell: bash
         run: |
           set -euo pipefail
+          advisory="${{ inputs.advisory }}"
           failed=0
           for item in \
             "resolve_package=${RESOLVE_RESULT}" \
+            "package_integrity=${PACKAGE_INTEGRITY_RESULT}" \
             "docker_acceptance=${DOCKER_RESULT}" \
             "package_telegram=${PACKAGE_TELEGRAM_RESULT}"
           do
             name="${item%%=*}"
             result="${item#*=}"
             if [[ "$result" != "success" && "$result" != "skipped" ]]; then
+              if [[ "$advisory" == "true" && "$name" != "resolve_package" ]]; then
+                echo "::warning::${name} ended with ${result}; package acceptance is advisory for this caller."
+                continue
+              fi
               echo "::error::${name} ended with ${result}"
               failed=1
             fi

.github/workflows/plugin-clawhub-release.yml

@@ -20,6 +20,10 @@ on:
         required: false
         default: ""
         type: string
+      release_publish_run_id:
+        description: Approved OpenClaw Release Publish workflow run id
+        required: false
+        type: string
 
 concurrency:
   group: plugin-clawhub-release-${{ github.event_name == 'workflow_dispatch' && inputs.ref || github.sha }}
@@ -28,7 +32,6 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
-  PNPM_VERSION: "11.0.8"
   CLAWHUB_REGISTRY: "https://clawhub.ai"
   CLAWHUB_REPOSITORY: "openclaw/clawhub"
   # Pinned to a reviewed ClawHub commit so release behavior stays reproducible.
@@ -57,7 +60,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "false"
 
       - name: Resolve checked-out ref
@@ -196,6 +198,37 @@ jobs:
           CLAWHUB_REGISTRY: ${{ env.CLAWHUB_REGISTRY }}
         run: node --import tsx scripts/plugin-clawhub-owner-preflight.ts .local/plugin-clawhub-release-plan.json
 
+  validate_release_publish_approval:
+    name: Validate release publish approval
+    needs: preview_plugins_clawhub
+    if: github.event_name == 'workflow_dispatch' && needs.preview_plugins_clawhub.outputs.has_candidates == 'true'
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+    steps:
+      - name: Validate release publish approval run
+        env:
+          GH_TOKEN: ${{ github.token }}
+          RELEASE_PUBLISH_RUN_ID: ${{ inputs.release_publish_run_id }}
+          EXPECTED_WORKFLOW_BRANCH: ${{ github.ref_name }}
+        run: |
+          set -euo pipefail
+          if [[ -z "${RELEASE_PUBLISH_RUN_ID// }" ]]; then
+            if [[ "${GITHUB_ACTOR}" == "github-actions[bot]" ]]; then
+              echo "Plugin ClawHub publish dispatched by another workflow must include release_publish_run_id." >&2
+              exit 1
+            fi
+            echo "Direct Plugin ClawHub Release dispatch; relying on this workflow's clawhub-plugin-release environment approval."
+            exit 0
+          fi
+          if [[ "${GITHUB_ACTOR}" != "github-actions[bot]" ]]; then
+            echo "Plugin ClawHub publish must be dispatched by the OpenClaw Release Publish workflow, not directly by ${GITHUB_ACTOR}." >&2
+            exit 1
+          fi
+          RUN_JSON="$(gh run view "$RELEASE_PUBLISH_RUN_ID" --repo "$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", "OpenClaw Release Publish"], ["headBranch", process.env.EXPECTED_WORKFLOW_BRANCH], ["event", "workflow_dispatch"]]; for (const [key, expected] of checks) { if (run[key] !== expected) { console.error(`Referenced release publish run ${process.env.RELEASE_PUBLISH_RUN_ID} must have ${key}=${expected}, got ${run[key] ?? "<missing>"}.`); process.exit(1); } } if (run.status !== "in_progress") { console.error(`Referenced release publish run ${process.env.RELEASE_PUBLISH_RUN_ID} must still be in_progress, got ${run.status ?? "<missing>"}.`); process.exit(1); } if (run.conclusion) { console.error(`Referenced release publish run ${process.env.RELEASE_PUBLISH_RUN_ID} already concluded ${run.conclusion}.`); process.exit(1); } console.log(`Using release publish approval run ${process.env.RELEASE_PUBLISH_RUN_ID}: ${run.url}`);'
+
   preview_plugin_pack:
     needs: preview_plugins_clawhub
     if: needs.preview_plugins_clawhub.outputs.has_candidates == 'true'
@@ -229,7 +262,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
           install-deps: "true"
 
@@ -289,11 +321,12 @@ jobs:
         run: bash scripts/plugin-clawhub-publish.sh --dry-run "${PACKAGE_DIR}"
 
   publish_plugins_clawhub:
-    needs: [preview_plugins_clawhub, preview_plugin_pack]
+    needs: [preview_plugins_clawhub, preview_plugin_pack, validate_release_publish_approval]
     if: github.event_name == 'workflow_dispatch' && needs.preview_plugins_clawhub.outputs.has_candidates == 'true'
     runs-on: ubuntu-latest
     environment: clawhub-plugin-release
     permissions:
+      actions: read
       contents: read
       id-token: write
     strategy:
@@ -323,7 +356,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
           install-deps: "true"
 

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

@@ -32,6 +32,10 @@ on:
         description: Comma-separated plugin package names to publish when publish_scope=selected
         required: false
         type: string
+      release_publish_run_id:
+        description: Approved OpenClaw Release Publish workflow run id
+        required: false
+        type: string
 
 concurrency:
   group: plugin-npm-release-${{ github.event_name == 'workflow_dispatch' && inputs.ref || github.sha }}
@@ -40,7 +44,6 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
-  PNPM_VERSION: "11.0.8"
 
 jobs:
   preview_plugins_npm:
@@ -64,7 +67,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "false"
 
       - name: Resolve checked-out ref
@@ -173,6 +175,37 @@ jobs:
             exit 1
           fi
 
+  validate_release_publish_approval:
+    name: Validate release publish approval
+    needs: preview_plugins_npm
+    if: github.event_name == 'workflow_dispatch' && needs.preview_plugins_npm.outputs.has_candidates == 'true'
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+    steps:
+      - name: Validate release publish approval run
+        env:
+          GH_TOKEN: ${{ github.token }}
+          RELEASE_PUBLISH_RUN_ID: ${{ inputs.release_publish_run_id }}
+          EXPECTED_WORKFLOW_BRANCH: ${{ github.ref_name }}
+        run: |
+          set -euo pipefail
+          if [[ -z "${RELEASE_PUBLISH_RUN_ID// }" ]]; then
+            if [[ "${GITHUB_ACTOR}" == "github-actions[bot]" ]]; then
+              echo "Plugin npm publish dispatched by another workflow must include release_publish_run_id." >&2
+              exit 1
+            fi
+            echo "Direct Plugin NPM Release dispatch; relying on this workflow's npm-release environment approval."
+            exit 0
+          fi
+          if [[ "${GITHUB_ACTOR}" != "github-actions[bot]" ]]; then
+            echo "Plugin npm publish must be dispatched by the OpenClaw Release Publish workflow, not directly by ${GITHUB_ACTOR}." >&2
+            exit 1
+          fi
+          RUN_JSON="$(gh run view "$RELEASE_PUBLISH_RUN_ID" --repo "$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", "OpenClaw Release Publish"], ["headBranch", process.env.EXPECTED_WORKFLOW_BRANCH], ["event", "workflow_dispatch"]]; for (const [key, expected] of checks) { if (run[key] !== expected) { console.error(`Referenced release publish run ${process.env.RELEASE_PUBLISH_RUN_ID} must have ${key}=${expected}, got ${run[key] ?? "<missing>"}.`); process.exit(1); } } if (run.status !== "in_progress") { console.error(`Referenced release publish run ${process.env.RELEASE_PUBLISH_RUN_ID} must still be in_progress, got ${run.status ?? "<missing>"}.`); process.exit(1); } if (run.conclusion) { console.error(`Referenced release publish run ${process.env.RELEASE_PUBLISH_RUN_ID} already concluded ${run.conclusion}.`); process.exit(1); } console.log(`Using release publish approval run ${process.env.RELEASE_PUBLISH_RUN_ID}: ${run.url}`);'
+
   preview_plugin_pack:
     needs: preview_plugins_npm
     if: needs.preview_plugins_npm.outputs.has_candidates == 'true'
@@ -195,7 +228,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "false"
 
       - name: Preview publish command
@@ -205,11 +237,12 @@ jobs:
         run: bash scripts/plugin-npm-publish.sh --pack-dry-run "${{ matrix.plugin.packageDir }}"
 
   publish_plugins_npm:
-    needs: [preview_plugins_npm, preview_plugin_pack]
+    needs: [preview_plugins_npm, preview_plugin_pack, validate_release_publish_approval]
     if: github.event_name == 'workflow_dispatch' && needs.preview_plugins_npm.outputs.has_candidates == 'true'
     runs-on: ubuntu-latest
     environment: npm-release
     permissions:
+      actions: read
       contents: read
       id-token: write
     strategy:
@@ -228,7 +261,6 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
-          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "false"
 
       - name: Ensure version is not already published

.github/workflows/plugin-prerelease.yml

@@ -52,7 +52,7 @@ jobs:
           ref: ${{ inputs.target_ref }}
           fetch-depth: 1
           fetch-tags: false
-          persist-credentials: false
+          persist-credentials: true
           submodules: false
 
       - name: Build plugin prerelease manifest
@@ -221,7 +221,7 @@ jobs:
           ref: ${{ needs.preflight.outputs.checkout_revision }}
           fetch-depth: 1
           fetch-tags: false
-          persist-credentials: false
+          persist-credentials: true
           submodules: false
 
       - name: Setup Node environment
@@ -257,7 +257,7 @@ jobs:
           ref: ${{ needs.preflight.outputs.checkout_revision }}
           fetch-depth: 1
           fetch-tags: false
-          persist-credentials: false
+          persist-credentials: true
           submodules: false
 
       - name: Setup Node environment
@@ -330,7 +330,7 @@ jobs:
           ref: ${{ needs.preflight.outputs.checkout_revision }}
           fetch-depth: 1
           fetch-tags: false
-          persist-credentials: false
+          persist-credentials: true
           submodules: false
 
       - name: Setup Node environment
@@ -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:
@@ -362,7 +362,7 @@ jobs:
           ref: ${{ needs.preflight.outputs.checkout_revision }}
           fetch-depth: 1
           fetch-tags: false
-          persist-credentials: false
+          persist-credentials: true
           submodules: false
 
       - name: Setup Node environment