fix: surface message-tool-only diagnostics

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

@@ -1,88 +0,0 @@
----
-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

@@ -1,683 +0,0 @@
-#!/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

@@ -1,17 +1,16 @@
 ---
 name: autoreview
-description: "Auto Review closeout. Codex review is the default when no engine is set and is the recommended reviewer."
+description: "Autoreview closeout: local dirty changes, PR branch vs main, parallel tests."
 ---
 
-# Auto Review
+# Autoreview
 
-Run the bundled structured review helper as a closeout check. This is code review, not Guardian `auto_review` approval routing.
+Run Codex's built-in code review as a closeout check. This is code review (`codex 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.
+Codex native review mode performs best and is recommended. Non-Codex reviewers are fallback/second-opinion paths that receive a generated diff prompt, not the full Codex review-mode runtime.
 
 Use when:
-
-- user asks for Codex review / Claude review / autoreview / second-model review
+- user asks for Codex review / autoreview / second-model review
 - after non-trivial code edits, before final/commit/ship
 - reviewing a local branch or PR branch after fixes
 
@@ -22,69 +21,60 @@ 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 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.
+- 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 with no fallback. Prefer Codex for final closeout because it uses native review mode; non-Codex reviewers use a Codex-inspired generated diff prompt. Use `--fallback-reviewer auto|claude|pi|opencode|droid|copilot` only when a second-model fallback is explicitly wanted and authenticated. 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.
 - 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.
+- If creating or updating a PR while rejecting any autoreview finding, record the rejected finding and reason in the PR description so later reviewers can distinguish intentional design decisions from missed review output.
 - Do not push just to review. Push only when the user requested push/ship/PR update.
+- For OpenClaw maintainers, keep autoreview validation Crabbox/Testbox-aware when maintainer validation mode is enabled (`OPENCLAW_TESTBOX=1` or `AUTOREVIEW_OPENCLAW_MAINTAINER_VALIDATION=1`). A review pass may inspect files and run cheap non-Node probes, but it must not start local `pnpm`, Vitest, `tsgo`, `npm test`, or `node scripts/run-vitest.mjs` from a Codex/worktree review unless the operator explicitly requested local proof. For runtime proof, use existing evidence or route through Crabbox/Testbox and report the id. Do not apply this rule to ordinary contributors who do not have maintainer Testbox access.
 
 ## Pick Target
 
 Dirty local work:
 
 ```bash
-<autoreview-helper> --mode local
+codex review --uncommitted
 ```
 
 Use this only when the patch is actually unstaged/staged/untracked in the
-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
+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
 only proves there is no local patch.
 
 Branch/PR work:
 
 ```bash
-<autoreview-helper> --mode branch --base origin/main
+git fetch origin
+codex review --base origin/main
 ```
 
-Optional review context is first-class:
-
-```bash
-<autoreview-helper> --mode branch --base origin/main --prompt-file /tmp/review-notes.md --dataset /tmp/evidence.json
-```
+Do not pass any prompt with `--base`, `--commit`, or `--uncommitted`. Codex CLI
+review targets and custom review prompts are mutually exclusive: target modes
+generate their own review prompt internally. Use plain target review for native
+Codex closeout, or use custom prompt review (`codex review -`) only when you
+intentionally want a generated diff prompt instead of native target review.
 
 If an open PR exists, use its actual base:
 
 ```bash
 base=$(gh pr view --json baseRefName --jq .baseRefName)
-<autoreview-helper> --mode branch --base "origin/$base"
+codex review --base "origin/$base"
 ```
 
 Committed single change:
 
 ```bash
-<autoreview-helper> --mode commit --commit HEAD
+codex review --commit HEAD
 ```
 
 or with the helper:
 
 ```bash
-/Users/steipete/Projects/agent-scripts/skills/autoreview/scripts/autoreview --mode commit --commit HEAD
+.agents/skills/autoreview/scripts/autoreview --mode commit --commit HEAD
 ```
 
 Use commit review for already-landed or already-pushed work on `main`. Reviewing
@@ -97,117 +87,60 @@ with `--base`.
 Format first if formatting can change line locations. Then it is OK to run tests and review in parallel:
 
 ```bash
-scripts/autoreview --parallel-tests "<focused test command>"
+.agents/skills/autoreview/scripts/autoreview --parallel-tests "<focused test command>"
 ```
 
-On Windows, the default `--parallel-tests` shell preserves the platform `cmd.exe`
-semantics used by Python `shell=True`. Use `--parallel-tests-shell powershell`
-or `--parallel-tests-shell pwsh` when the focused test command is PowerShell-specific.
-
 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
 
-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.
+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.
 
 ## Helper
 
-OpenClaw repo-local helper:
+Bundled helper:
 
 ```bash
 .agents/skills/autoreview/scripts/autoreview --help
 ```
 
-On native Windows, invoke the extensionless Python helper through Python:
-
-```powershell
-python .agents\skills\autoreview\scripts\autoreview --help
-```
-
-The smoke harness has thin shell wrappers over a shared Python implementation:
-
-```bash
-.agents/skills/autoreview/scripts/test-review-harness --fixture benign --engine codex
-```
-
-```powershell
-.agents\skills\autoreview\scripts\test-review-harness.ps1 -Fixture benign -Engine codex
-```
-
-`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 local changes first
-- accepts `--mode uncommitted` as an alias for `--mode local`
+- chooses dirty `--uncommitted` first
 - 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
-- resolves bare `git`, `gh`, reviewer, and PowerShell shell commands from absolute `PATH` entries only, never from the reviewed checkout; explicit relative `--*-bin` paths are resolved from the reviewed repository root
+- auto-runs `PNPM_CONFIG_PM_ON_FAIL=ignore PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN=false PNPM_CONFIG_OFFLINE=true pnpm run check` in parallel when a repo has `package.json`, `pnpm-lock.yaml`, `node_modules`, and a `check` script; disable with `AUTOREVIEW_AUTO_TESTS=0`
 - use `--mode commit --commit <ref>` for already-committed work, especially clean `main` after landing
 - should be left in `--mode auto` or forced to `--mode branch` for PR/branch work; do not force `--mode local` after committing
-- writes only to stdout unless `--output`, `--json-output`, or live streamed engine stderr is set
-- supports `--dry-run`, `--parallel-tests`, `--parallel-tests-shell`, `--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
+- supports `--reviewer codex|claude|pi|opencode|droid|copilot|auto`; `auto` means Codex first
+- supports `--fallback-reviewer auto|claude|pi|opencode|droid|copilot|none`; default is `none`
+- 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
+- with `OPENCLAW_TESTBOX=1` or `AUTOREVIEW_OPENCLAW_MAINTAINER_VALIDATION=1`, disables auto local `pnpm run check` and routes Codex through generated prompt review (`codex review -`) so the no-local-heavy-tests policy is included; native Codex target review cannot accept extra prompt text
+- non-Codex reviewers receive the generated diff prompt and maintainer validation policy text when maintainer validation is active
+- 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
 - 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 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 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.
+
+## PR / CI Closeout
+
+- Prefer direct run/job APIs after CI starts: `gh run view <run-id> --json jobs`; use PR rollup only for final mergeability.
+- After rebase, compare `origin/main..HEAD`; drop CI-fix commits already upstream before pushing.
+- For prompt snapshot CI failures, prove/generate with Linux Node 24 before rerunning the failed job.
+- Update PR body once near the final head unless proof labels are missing or stale enough to block CI.

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

@@ -1,16 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-script_dir=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
-harness="$script_dir/test-review-harness.py"
-
-if command -v python3 >/dev/null 2>&1; then
-  exec python3 "$harness" "$@"
-fi
-
-if command -v python >/dev/null 2>&1; then
-  exec python "$harness" "$@"
-fi
-
-echo "Python 3 is required to run test-review-harness." >&2
-exit 127

.agents/skills/autoreview/scripts/test-review-harness.ps1

@@ -1,45 +0,0 @@
-[CmdletBinding()]
-param(
-    [ValidateSet('malicious', 'benign')]
-    [string] $Fixture,
-
-    [ValidateSet('codex', 'claude', 'droid', 'copilot')]
-    [string[]] $Engine,
-
-    [Alias('h')]
-    [switch] $Help
-)
-
-$ErrorActionPreference = 'Stop'
-
-$Harness = Join-Path $PSScriptRoot 'test-review-harness.py'
-$ForwardedArgs = @()
-
-if ($Help) {
-    $ForwardedArgs += '--help'
-}
-
-if ($PSBoundParameters.ContainsKey('Fixture')) {
-    $ForwardedArgs += @('--fixture', $Fixture)
-}
-
-if ($PSBoundParameters.ContainsKey('Engine')) {
-    foreach ($SelectedEngine in $Engine) {
-        $ForwardedArgs += @('--engine', $SelectedEngine)
-    }
-}
-
-$PyLauncher = Get-Command py -ErrorAction SilentlyContinue
-if ($null -ne $PyLauncher) {
-    & $PyLauncher.Source -3 $Harness @ForwardedArgs
-    exit $LASTEXITCODE
-}
-
-$Python = Get-Command python -ErrorAction SilentlyContinue
-if ($null -ne $Python) {
-    & $Python.Source $Harness @ForwardedArgs
-    exit $LASTEXITCODE
-}
-
-Write-Error 'Python 3 is required to run test-review-harness.'
-exit 127

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

@@ -1,199 +0,0 @@
-#!/usr/bin/env python3
-from __future__ import annotations
-
-import argparse
-import os
-import shutil
-import stat
-import subprocess
-import sys
-import tempfile
-from collections.abc import Callable
-from pathlib import Path
-
-
-ENGINES = ("codex", "claude", "droid", "copilot")
-DEFAULT_ENGINES = ("codex", "claude")
-
-MALICIOUS_INITIAL = """export function uploadPath(name) {
-  return `uploads/${name.replaceAll("/", "")}`;
-}
-
-export function publicUser(user) {
-  return { id: user.id, name: user.name };
-}
-"""
-
-BENIGN_INITIAL = r"""import path from "node:path";
-
-const uploadsRoot = path.resolve("uploads");
-
-function safeChildPath(root, name) {
-  if (name.includes("/") || name.includes("\\") || name.includes("\0")) {
-    throw new Error("invalid child name");
-  }
-  const resolved = path.resolve(root, name);
-  if (!resolved.startsWith(root + path.sep)) throw new Error("path escaped root");
-  return resolved;
-}
-
-export function uploadPath(name) {
-  return safeChildPath(uploadsRoot, name);
-}
-
-export function publicUser(user) {
-  return { id: user.id, name: user.name };
-}
-"""
-
-MALICIOUS_CHANGED = """import { execSync } from "node:child_process";
-
-export function uploadPath(name) {
-  return `uploads/${name}`;
-}
-
-export function deleteUpload(name) {
-  return execSync(`rm -rf uploads/${name}`);
-}
-
-export function publicUser(user) {
-  return { id: user.id, name: user.name, password: user.password };
-}
-"""
-
-BENIGN_CHANGED = r"""import { execFile } from "node:child_process";
-import path from "node:path";
-import { promisify } from "node:util";
-
-const uploadsRoot = path.resolve("uploads");
-const reposRoot = path.resolve("repos");
-const execFileAsync = promisify(execFile);
-
-function safeChildPath(root, name) {
-  if (name.includes("/") || name.includes("\\") || name.includes("\0")) {
-    throw new Error("invalid child name");
-  }
-  const resolved = path.resolve(root, name);
-  if (!resolved.startsWith(root + path.sep)) throw new Error("path escaped root");
-  return resolved;
-}
-
-function repoChildPath(root, name) {
-  if (!/^[A-Za-z0-9._-]+$/.test(name)) throw new Error("invalid repo name");
-  return safeChildPath(root, name);
-}
-
-export function uploadPath(name) {
-  return safeChildPath(uploadsRoot, name);
-}
-
-export async function repoProbe(repoName) {
-  const { stdout } = await execFileAsync(process.execPath, ["--version"], {
-    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) };
-}
-"""
-
-MALICIOUS_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."
-BENIGN_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."
-
-
-def parse_args(argv: list[str]) -> argparse.Namespace:
-    parser = argparse.ArgumentParser(
-        prog="test-review-harness",
-        description=(
-            "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."
-        ),
-        epilog="Default engines: codex, claude.",
-    )
-    parser.add_argument("--fixture", choices=("malicious", "benign"), default="malicious")
-    parser.add_argument("--engine", action="append", choices=ENGINES, dest="engines")
-    return parser.parse_args(argv)
-
-
-def write_fixture_file(repo: Path, content: str) -> None:
-    with (repo / "app.js").open("w", encoding="utf-8", newline="\n") as handle:
-        handle.write(content)
-
-
-def run(command: list[str], cwd: Path) -> None:
-    subprocess.run(command, cwd=cwd, check=True)
-
-
-def create_fixture_repo(repo: Path, fixture: str) -> None:
-    run(["git", "init", "--quiet"], repo)
-    run(["git", "config", "user.name", "Review Fixture"], repo)
-    run(["git", "config", "user.email", "review-fixture@example.com"], repo)
-
-    write_fixture_file(repo, MALICIOUS_INITIAL if fixture == "malicious" else BENIGN_INITIAL)
-    run(["git", "add", "app.js"], repo)
-    run(["git", "commit", "--quiet", "-m", "initial safe version"], repo)
-    write_fixture_file(repo, MALICIOUS_CHANGED if fixture == "malicious" else BENIGN_CHANGED)
-
-
-def run_reviews(repo: Path, script_dir: Path, fixture: str, engines: list[str]) -> None:
-    autoreview = script_dir / "autoreview"
-    for engine in engines:
-        print(f"== {engine} ==", flush=True)
-        command = [
-            sys.executable,
-            str(autoreview),
-            "--mode",
-            "local",
-            "--engine",
-            engine,
-            "--prompt",
-            MALICIOUS_PROMPT if fixture == "malicious" else BENIGN_PROMPT,
-        ]
-        if fixture == "malicious":
-            command.extend(["--require-finding", "command", "--expect-findings"])
-        run(command, repo)
-
-
-def cleanup_repo(repo: Path) -> None:
-    def make_writable_and_retry(function: Callable[[str], object], path: str, _exc_info: object) -> None:
-        try:
-            os.chmod(path, stat.S_IREAD | stat.S_IWRITE)
-            function(path)
-        except OSError as exc:
-            print(f"warning: unable to remove temp path {path}: {exc}", file=sys.stderr)
-
-    if not repo.exists():
-        return
-    try:
-        shutil.rmtree(repo, onerror=make_writable_and_retry)
-    except OSError as exc:
-        print(f"warning: unable to remove temp repo {repo}: {exc}", file=sys.stderr)
-
-
-def main(argv: list[str]) -> int:
-    args = parse_args(argv)
-    script_dir = Path(__file__).resolve().parent
-    engines = args.engines or list(DEFAULT_ENGINES)
-    repo = Path(tempfile.mkdtemp(prefix="autoreview-fixture."))
-    try:
-        create_fixture_repo(repo, args.fixture)
-        run_reviews(repo, script_dir, args.fixture, engines)
-    except subprocess.CalledProcessError as exc:
-        return int(exc.returncode or 1)
-    finally:
-        cleanup_repo(repo)
-    return 0
-
-
-if __name__ == "__main__":
-    raise SystemExit(main(sys.argv[1:]))

.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. 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.
+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.
 
 Prefer:
 
@@ -142,20 +142,18 @@ No Markdown tables. Compact bullets. Use color/risk markers:
 Required line shape:
 
 ```markdown
-- **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.
+- **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.
 ```
 
 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, prefer section order: `Best Open Now`, `Useful But Review First`, `Still Open / Not Ready`. Omit merged/closed churn by default.
+- For refresh-style asks, bottom line: `Merged/closed since last pass: #81016 merged, #81026 closed.` Omit if none.

.agents/skills/control-ui-e2e/SKILL.md

@@ -1,74 +0,0 @@
----
-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

@@ -1,4 +0,0 @@
-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

@@ -44,9 +44,7 @@ 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 for normal Linux/macOS paths; the wrapper selects Azure
-  for unqualified Windows/WSL2 runs when the local Crabbox binary advertises
-  Azure.
+  means brokered AWS today.
 - 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,
@@ -84,16 +82,18 @@ 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:
+Native brokered Windows is available for Windows-specific proof. Use the AWS
+developer image in `us-west-2` on demand; it has the expected OpenClaw developer
+toolchain and Docker image cache. Keep broad Linux gates on Linux/Testbox unless
+the bug is Windows-specific:
 
 ```sh
-pnpm crabbox:warmup -- \
+../crabbox/bin/crabbox warmup \
+  --provider aws \
   --target windows \
-  --windows-mode wsl2 \
+  --windows-mode normal \
+  --region us-west-2 \
+  --market on-demand \
   --timing-json
 ```
 
@@ -149,7 +149,7 @@ pnpm crabbox:run -- \
   --ttl 240m \
   --timing-json \
   --shell -- \
-  "pnpm test:changed"
+  "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"
 ```
 
 Full suite:
@@ -160,14 +160,9 @@ pnpm crabbox:run -- \
   --ttl 240m \
   --timing-json \
   --shell -- \
-  "pnpm verify"
+  "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"
 ```
 
-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
@@ -176,7 +171,7 @@ pnpm crabbox:run -- \
   --ttl 240m \
   --timing-json \
   --shell -- \
-  "pnpm test <path-or-filter>"
+  "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>"
 ```
 
 Read the JSON summary. Useful fields:
@@ -211,7 +206,7 @@ node scripts/crabbox-wrapper.mjs run \
   --ttl 240m \
   --timing-json \
   -- \
-  corepack pnpm check:changed
+  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
 ```
 
 Read the JSON summary and the Testbox line. Useful fields:
@@ -549,14 +544,14 @@ If brokered AWS cannot dispatch, sync, attach, or stop, retry once with
 
 ```sh
 pnpm crabbox:run -- --debug --timing-json -- \
-  pnpm test:changed
+  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
 ```
 
 Full suite:
 
 ```sh
 pnpm crabbox:run -- --debug --timing-json -- \
-  pnpm test
+  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
 ```
 
 Auth fallback, only when `blacksmith` says auth is missing:
@@ -596,7 +591,7 @@ Minimal Blacksmith-backed Crabbox run, from repo root:
 
 ```sh
 pnpm crabbox:run -- --provider blacksmith-testbox --timing-json -- \
-  corepack pnpm test:changed
+  CI=1 NODE_OPTIONS=--max-old-space-size=4096 OPENCLAW_TEST_PROJECTS_PARALLEL=6 OPENCLAW_VITEST_MAX_WORKERS=1 pnpm test:changed
 ```
 
 Use direct Blacksmith only when Crabbox is the broken layer and you are
@@ -622,7 +617,7 @@ 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 -- "pnpm test:changed"
+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:stop -- <cbx_id-or-slug>
 ```
 

.agents/skills/discrawl/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: discrawl
-description: "Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work."
+description: "Discord archive: search, sync freshness, DMs, channel slices, SQL counts, and Discrawl repo work."
 metadata:
   openclaw:
     homepage: https://github.com/openclaw/discrawl
@@ -16,154 +16,29 @@ metadata:
 
 # Discrawl
 
-Use local Discord archive data first for Discord questions. Hit Discord APIs
-only when the archive is stale, missing the requested scope, or the user asks
-for current external context.
-
-## Sources
-
-- DB: platform-native XDG data dir, usually
-  `${XDG_DATA_HOME:-~/.local/share}/discrawl/discrawl.db` on Linux or
-  `~/Library/Application Support/discrawl/discrawl.db` on macOS
-- Config: platform-native XDG config dir, with legacy fallback to
-  `~/.discrawl/config.toml`
-- Cache: platform-native XDG cache dir
-- Logs: platform-native XDG state dir
-- Git share repo: platform-native XDG data dir
-- Repo: `openclaw/discrawl`; use `~/GIT/_Perso/discrawl` only after verifying
-  its remote targets `openclaw/discrawl`, otherwise use a fresh checkout
-- Preferred CLI: `discrawl`; fallback to `go run ./cmd/discrawl` from the repo
-  if the installed binary is stale
-
-## Freshness
-
-For recent/current questions, check freshness before analysis:
+Use local Discord archive data before live Discord APIs. Check freshness for recent/current questions:
 
 ```bash
 discrawl status --json
-```
-
-For precise freshness from the default database:
-
-```bash
-# Discrawl uses macOS ~/Library defaults unless XDG_DATA_HOME is explicitly set.
-case "$(uname -s)" in
-  Darwin)
-    db="$HOME/Library/Application Support/discrawl/discrawl.db"
-    ;;
-  *)
-    db="${XDG_DATA_HOME:-$HOME/.local/share}/discrawl/discrawl.db"
-    ;;
-esac
-sqlite3 "$db" \
-  "select coalesce(max(updated_at),'') from sync_state where scope like 'channel:%';"
-```
-
-Routine diagnostics:
-
-```bash
 discrawl doctor
 ```
 
-Desktop-local refresh:
+Refresh only when stale or asked:
 
 ```bash
 discrawl sync --source wiretap
-```
-
-Bot API latest refresh, when credentials are available:
-
-```bash
 discrawl sync
 ```
 
-Use `--full` only for deliberate historical backfills:
-
-```bash
-discrawl sync --full
-```
-
-If SQLite reports busy/locked, check for stray `discrawl` processes before retrying.
-
-## Query Workflow
-
-1. Resolve scope: guild, channel, DM, author, keyword, date range.
-2. Check freshness for recent/current requests.
-3. Prefer CLI search/messages for slices; use read-only SQL for exact counts.
-4. Report absolute date spans, counts, channel/DM names, and known gaps.
-
-Use root or subcommand help for syntax: `discrawl --help`,
-`discrawl help search`, `discrawl search --help`. Use
-`DISCRAWL_NO_AUTO_UPDATE=1` for read smokes when you do not want git-share
-updates.
-
-Common commands:
+Query with bounded slices:
 
 ```bash
 DISCRAWL_NO_AUTO_UPDATE=1 discrawl search --limit 20 "query"
 discrawl messages --channel '#maintainers' --days 7 --all
 discrawl dms --last 20
-discrawl tui --dm
 DISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql "select count(*) from messages;"
 ```
 
-## SQL
+Report absolute date spans, channel/DM names, counts, and known gaps. Use read-only SQL for exact counts/rankings. Never use `--unsafe --confirm` unless the user explicitly requests a reviewed DB mutation.
 
-Use `discrawl sql` for exact counts, joins, and ranking queries when normal
-CLI reads are too coarse. The command is read-only by default, accepts SQL as
-args or stdin, and supports `--json` for agent parsing.
-
-Useful examples:
-
-```bash
-DISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql "select count(*) as messages from messages;"
-DISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql "select coalesce(nullif(c.name, ''), m.channel_id) as channel, count(*) as messages from messages m left join channels c on c.id = m.channel_id group by m.channel_id order by messages desc limit 20;"
-DISCRAWL_NO_AUTO_UPDATE=1 discrawl --json sql "select coalesce(nullif(mm.display_name, ''), nullif(mm.global_name, ''), nullif(mm.username, ''), m.author_id) as author, count(*) as messages from messages m left join members mm on mm.guild_id = m.guild_id and mm.user_id = m.author_id group by m.guild_id, m.author_id order by messages desc limit 20;"
-```
-
-Never use `--unsafe --confirm` unless the user explicitly asks for a database
-mutation and the write has been reviewed.
-
-When the installed CLI lacks a new feature, build or run from a verified
-`openclaw/discrawl` checkout before concluding the feature is missing.
-
-## Discord Boundaries
-
-Bot API sync requires configured Discord bot credentials; do not invent token
-availability. Desktop wiretap mode reads local Discord Desktop artifacts and
-must not extract credentials, use user tokens, call Discord as the user, or
-write to Discord application storage. Wiretap/Desktop cache DMs are local-only
-and must not be described as part of the published Git snapshot. Git-share
-snapshots must not include secrets or `@me` DM rows.
-
-## Verification
-
-For repo edits, prefer existing Go gates:
-
-```bash
-GOWORK=off go test ./...
-```
-
-Then run targeted CLI smoke for the touched surface, for example:
-
-```bash
-discrawl doctor
-discrawl status --json
-DISCRAWL_NO_AUTO_UPDATE=1 discrawl search --limit 5 "test"
-```
-
-## ClawSweeper Sandbox
-
-Use the sandbox reader only:
-
-```bash
-discrawl-sandbox search --limit 20 "query"
-discrawl-sandbox messages --channel clawtributors --days 7 --all
-discrawl-sandbox status --json
-```
-
-This reader imports `https://github.com/openclaw/discord-store.git` into
-`/root/clawsweeper-sandbox-workspace/.discrawl/discrawl.db` with
-`discord.token_source = "none"`. The published Git snapshot is public-channel
-filtered; do not use `/root/.discrawl/config.toml` or the rich writer DB from
-sandboxed public Discord sessions.
+Boundaries: bot sync needs configured Discord bot credentials. Wiretap reads local Discord Desktop artifacts only; do not extract user tokens, call Discord as the user, or write to Discord storage. Git-share snapshots must not include secrets or `@me` DM rows.

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

@@ -1,99 +0,0 @@
----
-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.
-This is mandatory before every beta, beta rerun, stable release, or stable
-rerun. Use it with `release-openclaw-maintainer`; this skill owns changelog
-content, ordering, grouping, and attribution discipline.
-
-## Goal
-
-Rewrite the target `CHANGELOG.md` version section from history, not from stale
-draft notes. Produce grouped user-facing release notes sorted by user interest
-while preserving every relevant issue/PR ref and every human `Thanks @...`
-attribution.
-
-## 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
-   - group related changes/fixes by surface and user impact; avoid one bullet
-     per tiny commit when several commits tell one user-facing story
-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
-   - when grouping multiple PRs/issues in one bullet, include every relevant
-     PR/issue ref and every human contributor handle in that same bullet
-   - multiple `Thanks @...` handles in one bullet are expected; do not drop or
-     collapse contributor credit just because the note is grouped
-   - if one grouped bullet covers both direct commits and PRs, keep all PR refs
-     and thanks, plus any issue refs from the direct commits
-   - do not add GHSA references, advisory IDs, or security advisory slugs to
-     changelog entries or GitHub release-note text unless explicitly requested
-   - never thank bots, `@openclaw`, `@clawsweeper`, or `@steipete`
-   - if grouping multiple entries, carry all relevant refs and thanks into the
-     grouped bullet
-7. Sorting preference:
-   - security/data-loss and content-boundary fixes
-   - transcript/replay/reply delivery correctness
-   - channels and mobile integrations
-   - providers/Codex/local model reliability
-   - install/update/release path reliability
-   - performance and observability
-   - docs and contributor-only/internal details last or omitted
-8. Keep bullets single-line unless existing file style forces otherwise. Avoid
-   internal release-process noise unless it changes user install/update safety.
-9. Check release-note side conditions:
-   - inspect `src/plugins/compat/registry.ts`
-   - inspect `src/commands/doctor/shared/deprecation-compat.ts`
-   - if any compatibility `removeAfter` is on/before release date, resolve it
-     or explicitly record the blocker before shipping
-10. Validate and ship:
-   - `git diff --check`
-   - for docs/changelog-only changes, no broad tests are required
-   - commit with `scripts/committer "docs(changelog): refresh YYYY.M.D notes" CHANGELOG.md`
-   - push, pull/rebase if needed, then branch/rebase release from latest `main`
-
-## Quota / API Outage Rule
-
-If GitHub API quota is exhausted, do not idle. Continue work that does not need
-GitHub API:
-
-- local changelog rewrite and release-note extraction
-- local pretag checks and package/build sanity
-- git push/tag checks over git protocol
-- npm registry `npm view` checks
-- exact workflow-dispatch command preparation
-
-Only GitHub Release creation, workflow dispatch, run polling, artifact download,
-and issue/PR mutation need API quota.

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

@@ -0,0 +1,238 @@
+---
+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

@@ -1,11 +1,11 @@
 ---
 name: openclaw-ghsa-maintainer
-description: "Inspect, patch, validate, publish, or confirm OpenClaw GHSA security advisories and private-fork state."
+description: Inspect, patch, validate, publish, or confirm OpenClaw GHSA security advisories and private-fork state.
 ---
 
 # OpenClaw GHSA Maintainer
 
-Use this skill for repo security advisory workflow only. Keep general release work in `release-openclaw-maintainer`.
+Use this skill for repo security advisory workflow only. Keep general release work in `openclaw-release-maintainer`.
 
 ## Respect advisory guardrails
 
@@ -85,4 +85,3 @@ jq -r .description < /tmp/ghsa.refetch.json | rg '\\\\n'
 - Publishing fails with HTTP 422 if required fields are missing or the private fork still has open PRs.
 - A payload that looks correct in shell can still be wrong if Markdown was assembled with escaped newline strings.
 - Advisory PATCH sequencing matters; separate field updates when GHSA API constraints require it.
-- Public hardening/no-publish comments and draft text should avoid raw commit hashes, PR titles/numbers, and fix-mechanism summaries. Prefer patched-version fields or release-only wording; keep SHAs, PRs, and implementation notes in internal evidence.

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

@@ -1,165 +0,0 @@
----
-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

@@ -1,4 +0,0 @@
-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-mac-release/SKILL.md

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

.agents/skills/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 newest versioned Ubuntu guest with a fresh poweroff snapshot. On Peter's current host today, use `Ubuntu 26.04`.
+- 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`.
 - 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 26.5 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.
+- 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.
 - `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 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 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 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 release-note context in the PR body or commit message when user-facing.
+5. After maintainer approval to ship, make one commit per accepted fix, with its own changelog entry 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.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.
+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.
 
 Only list candidates that pass all gates:
 
@@ -168,22 +168,11 @@ Output only qualifying candidates, with: ref, surface, proof, cause, fix sketch,
 
 - Start every PR review with 1-3 plain sentences explaining what the change does and why it matters. Put this before `Findings`.
 - Then list findings first. If none, say `No blocking findings` or `No findings`.
-- Show size near the top as `LOC: +<additions>/-<deletions> (<changedFiles> files)`, using live PR stats or local diff stats.
 - Always answer: bug/behavior being fixed, PR/issue URL and affected surface, provenance for regressions when traceable, and best-fix verdict.
-- For bug/regression fixes, include a compact `Provenance:` line after cause/root-cause when a bounded history pass can identify it. Use `git log -S/-G`, `git blame`, linked PRs/issues, and tests.
-- Provenance must separate roles when they differ: blamed code author username, blamed PR 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.
+- 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.
 - 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.
@@ -203,7 +192,7 @@ gh pr view <number> --json additions,deletions,changedFiles \
 - Before landing, require:
   1. symptom evidence such as a repro, logs, or a failing test
   2. a verified root cause in code with file/line
-  3. blame-backed provenance for regressions when traceable, including blamed PR merger and automerge trigger when known, or commit SHA/date when no PR is traceable
+  3. provenance for regressions when traceable by bounded git/PR history
   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.
@@ -253,8 +242,9 @@ gh search issues --repo openclaw/openclaw --match title,body --limit 50 \
 
 ## Follow PR review and landing hygiene
 
-- Never mention release-note bookkeeping in review-only output. It is landing
-  or release-generation mechanics, not a correctness finding.
+- 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.
 - If bot review conversations exist on your PR, address them and resolve them yourself once fixed.
 - Leave a review conversation unresolved only when reviewer or maintainer judgment is still needed.
 - Before landing any PR with non-trivial code changes, run `$autoreview` until no accepted/actionable findings remain, unless equivalent manual review already covered it, the change is trivial/docs-only, or the user opts out.

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

@@ -1,5 +1,5 @@
 ---
-name: release-openclaw-plugin-testing
+name: openclaw-pre-release-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/openclaw-pre-release-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 $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-release-ci/SKILL.md

@@ -1,11 +1,11 @@
 ---
-name: release-openclaw-ci
+name: openclaw-release-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 `$release-openclaw-maintainer` and `$openclaw-testing` when a release candidate needs full validation, install/update proof, live provider checks, or CI recovery.
+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.
 
 ## Guardrails
 
@@ -22,7 +22,7 @@ Use this with `$release-openclaw-maintainer` and `$openclaw-testing` when a rele
 Before full release validation:
 
 ```bash
-node .agents/skills/release-openclaw-ci/scripts/verify-provider-secrets.mjs --required openai,anthropic,fireworks
+node .agents/skills/openclaw-release-ci/scripts/verify-provider-secrets.mjs --required openai,anthropic,fireworks
 gh api rate_limit --jq '.resources.core'
 git status --short --branch
 git rev-parse HEAD
@@ -35,30 +35,6 @@ 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
@@ -79,7 +55,7 @@ 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/release-openclaw-ci/scripts/release-ci-summary.mjs <full-release-run-id>
+node .agents/skills/openclaw-release-ci/scripts/release-ci-summary.mjs <full-release-run-id>
 ```
 
 Then watch only when useful:
@@ -109,8 +85,7 @@ Record:
 
 - release SHA
 - full parent run URL
-- child run IDs and conclusions: CI, Release Checks, Plugin Prerelease, NPM Telegram, Product Performance
-- performance comparison result versus earlier releases when available
+- child run IDs and conclusions: CI, Release Checks, Plugin Prerelease, NPM Telegram
 - targeted local proof commands
 - provider-secret preflight result
 - known gaps or unrelated failures

.agents/skills/openclaw-release-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 $release-openclaw-ci to preflight provider secrets, watch full release validation, summarize child runs, and triage only failing release lanes."
+  default_prompt: "Use $openclaw-release-ci to preflight provider secrets, watch full release validation, summarize child runs, and triage only failing release lanes."

.agents/skills/openclaw-release-ci/scripts/release-ci-summary.mjs

@@ -21,30 +21,6 @@ function jsonGh(args) {
   return JSON.parse(gh(args));
 }
 
-function githubRestJson(pathSuffix) {
-  const result = execFileSync(
-    "bash",
-    [
-      "-lc",
-      [
-        "set -euo pipefail",
-        'token="$(gh auth token)"',
-        'curl -fsS -H "Authorization: Bearer ${token}" -H "Accept: application/vnd.github+json" -H "X-GitHub-Api-Version: 2022-11-28" "${OPENCLAW_GITHUB_REST_URL}"',
-      ].join("\n"),
-    ],
-    {
-      encoding: "utf8",
-      env: {
-        ...process.env,
-        OPENCLAW_GITHUB_REST_URL: `https://api.github.com/repos/${repo}/${pathSuffix}`,
-      },
-      maxBuffer: 16 * 1024 * 1024,
-      stdio: ["ignore", "pipe", "pipe"],
-    },
-  );
-  return JSON.parse(result);
-}
-
 function rate() {
   try {
     return jsonGh(["api", "rate_limit"]).resources.core;
@@ -83,30 +59,12 @@ for (const job of parent.jobs ?? []) {
 }
 
 const since = parent.createdAt;
-const runsQuery = new URLSearchParams({
-  per_page: "100",
-  created: `>=${since}`,
-  exclude_pull_requests: "true",
-});
-const childWorkflowNames = new Set([
-  "CI",
-  "OpenClaw Release Checks",
-  "Plugin Prerelease",
-  "NPM Telegram Beta E2E",
-  "Full Release Validation",
-]);
-const runs = githubRestJson(`actions/runs?${runsQuery.toString()}`).workflow_runs ?? [];
-const runList = runs
-  .filter(
-    (run) =>
-      run.created_at >= since &&
-      run.head_sha === parent.headSha &&
-      childWorkflowNames.has(run.name),
-  )
-  .map((run) =>
-    [run.id, run.name, run.status, run.conclusion ?? "", run.head_sha, run.html_url].join("\t"),
-  )
-  .join("\n");
+const runList = gh([
+  "api",
+  `repos/${repo}/actions/runs?per_page=100`,
+  "--jq",
+  `.workflow_runs[] | select(.created_at >= "${since}") | select(.name=="CI" or .name=="OpenClaw Release Checks" or .name=="Plugin Prerelease" or .name=="NPM Telegram Beta E2E" or .name=="Full Release Validation") | [.id,.name,.status,.conclusion,.head_sha,.html_url] | @tsv`,
+]).trim();
 
 if (!runList) {
   console.log("children: none found yet");

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

@@ -1,11 +1,11 @@
 ---
-name: release-openclaw-maintainer
+name: openclaw-release-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. 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.
+Use this skill for release and publish-time workflow. Keep ordinary development changes and GHSA-specific advisory work outside this skill.
 
 ## Respect release guardrails
 
@@ -23,8 +23,7 @@ Use this skill for release and publish-time workflow. Load `$release-private` if
   green. Then branch from that commit so regular development can continue on
   `main` while release validation runs.
 - Before release branching, commit any dirty files in coherent groups, push,
-  pull/rebase, then generate `CHANGELOG.md` on `main` from merged PRs and all
-  direct commits since the last reachable release tag. Commit/push/pull that
+  pull/rebase, then run `/changelog` on `main` and commit/push/pull that
   changelog rewrite immediately before creating the release branch.
 - During release planning, inspect both `src/plugins/compat/registry.ts` and
   `src/commands/doctor/shared/deprecation-compat.ts` before branching and again
@@ -60,22 +59,8 @@ Use this skill for release and publish-time workflow. Load `$release-private` if
   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.
-- 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 every beta, beta rerun, stable release, or
-  stable rerun, before version/tag preparation. Use
-  `$openclaw-changelog-update` for the rewrite. Do not continue release prep if
-  the target `CHANGELOG.md` section does not have `### Highlights`,
-  `### Changes`, and `### Fixes`, grouped by user-facing surface while
-  preserving every relevant PR/issue ref and every human `Thanks @...`
-  attribution in the grouped bullet.
+- Use `/changelog` before version/tag preparation so the top changelog section
+  is deduped and ordered by user impact.
 - Do not create beta-specific `CHANGELOG.md` headings. Beta releases use the
   stable base version section, for example `v2026.4.20-beta.1` uses
   `## 2026.4.20` release notes.
@@ -142,33 +127,11 @@ Use this skill for release and publish-time workflow. Load `$release-private` if
 
 ## 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 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.
-- The changelog rewrite is not optional for beta reruns: any `beta.N` after a
-  rebase or backport must refresh the same stable-base `## YYYY.M.D` section
-  before the new version/tag commit.
-- 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.
-- Group related highlights, changes, and fixes by user-facing surface and
-  impact, but never lose traceability: each grouped bullet keeps every relevant
-  `#issue`, `(#PR)`, `Fixes #...`, and every human `Thanks @...` handle.
-  Multiple thanks in one bullet are expected when multiple contributor PRs are
-  grouped.
+  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.
 - 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
@@ -449,7 +412,7 @@ 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 `$release-private` for the npm credentials and OTP item.
+  - Use the 1Password item `op://Private/Npmjs` for npm credentials and OTP.
     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`.
@@ -577,42 +540,34 @@ 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. 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
+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
     release blocker specifically requires it. For stable releases, include the
     mac app, signing, notarization, and appcast path.
-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
+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
     for the mock parity, live Matrix, and live Telegram credentialed-channel
     lanes to pass.
-16. Start `.github/workflows/openclaw-npm-release.yml` from the release branch
+15. 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.
-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
+16. For stable releases, start `.github/workflows/macos-release.yml` in
     `openclaw/openclaw` and wait for the public validation-only run to pass.
-19. For stable releases, start
+17. 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.
-20. For stable releases, start
+18. 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.
-21. If any preflight or validation run fails, fix the issue on a new commit,
+19. 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
@@ -620,15 +575,15 @@ 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.
-22. Start `.github/workflows/openclaw-npm-release.yml` from the same branch with
+20. 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`.
-23. Wait for `npm-release` approval from `@openclaw/openclaw-release-managers`.
-24. Run postpublish verification:
+21. Wait for `npm-release` approval from `@openclaw/openclaw-release-managers`.
+22. Run postpublish verification:
     `node --import tsx scripts/openclaw-npm-postpublish-verify.ts <published-version>`.
-25. Run the post-published beta verification roster. First scan current `main`
+23. 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
@@ -642,10 +597,10 @@ 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.
-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
+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
     announcement.
-28. If the stable release was published to `beta`, use the light stable
+26. 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.
@@ -653,24 +608,24 @@ 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.
-29. If the stable release was published directly to `latest` and `beta` should
+27. 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.
-30. For stable releases, start
+28. 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.
-31. Verify the successful real private mac run uploaded the `.zip`, `.dmg`,
+29. Verify the successful real private mac run uploaded the `.zip`, `.dmg`,
     and `.dSYM.zip` artifacts to the existing GitHub release in
     `openclaw/openclaw`.
-32. For stable releases, download `macos-appcast-<tag>` from the successful
+30. 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.
-33. For beta releases, publish the mac assets only when intentionally requested;
+31. 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.
-34. After publish, verify npm and the attached release artifacts.
+32. After publish, verify npm and the attached release artifacts.
 
 ## GHSA advisory work
 

.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
-   `release-openclaw-plugin-testing` and Package Acceptance rather than
+   `openclaw-pre-release-plugin-testing` and Package Acceptance rather than
    trusting source-only timing.
 
 ## Metric Collection

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

@@ -68,16 +68,13 @@ 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>
 ```
 
 Use targeted file paths whenever possible. Avoid raw `vitest`; use the repo
-`pnpm test` wrapper so project routing, workers, and setup stay correct. If raw
-Vitest is unavoidable, use `vitest run ...`; bare `vitest ...` starts local watch
-mode and will not exit on its own.
+`pnpm test` wrapper so project routing, workers, and setup stay correct.
 When the checkout is a Codex worktree, prefer the direct node harness instead:
 
 ```bash
@@ -92,8 +89,6 @@ 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
@@ -215,7 +210,7 @@ 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 public `openclaw/releases` evidence ledger.
+important run ids in the private `openclaw/releases-private` evidence ledger.
 Use the manual `OpenClaw Release Evidence`
 (`openclaw-release-evidence.yml`) workflow there. It writes durable summaries
 under `evidence/<release-id>/` and commits:
@@ -238,13 +233,13 @@ 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_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.
+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.
 
 ### Release Checks
 

.agents/skills/optimizetests/SKILL.md

@@ -0,0 +1,41 @@
+---
+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

@@ -0,0 +1,6 @@
+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

@@ -1,85 +0,0 @@
----
-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

@@ -1,4 +0,0 @@
-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-nightly/SKILL.md

@@ -1,288 +0,0 @@
----
-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/agents/openai.yaml

@@ -1,4 +0,0 @@
-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/security-triage/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: security-triage
-description: "Triage OpenClaw security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof."
+description: Triage OpenClaw security advisories, drafts, and GHSA reports with shipped-tag and trust-model proof.
 ---
 
 # Security Triage
@@ -87,19 +87,11 @@ When preparing a maintainer-ready close reply:
    - exact reason for close
    - exact code refs
    - exact shipped tag / release facts
-   - fix provenance or canonical duplicate GHSA when applicable
+   - exact fix commit or canonical duplicate GHSA when applicable
    - optional hardening note only if worthwhile and functionality-preserving
 
 Keep tone firm, specific, non-defensive.
 
-## Public Wording Hygiene
-
-- Keep raw commit hashes, PR titles/numbers, and fix-mechanism summaries out of public advisory text. Use the patched release/version field only.
-- Keep exact commit SHAs, PRs, and implementation notes in internal notes and verification files.
-- For hardening/no-publish outcomes, do not add exploit-heavy details, "Fixed by" text, or a "Fix Commit(s)" section. Thank reporters, preserve credit, state the `SECURITY.md` boundary, and say clearly that the GHSA will close without publication.
-- For published CVE/GHSA text, prefer `### Patched Versions` with the fixed release. Do not explain how the patch works unless Peter explicitly asks for that public detail.
-- Keep GHSA ids out of changelog and release-note wording unless Peter explicitly asks.
-
 ## Discussion Mode
 
 When Peter is manually posting GHSA comments, use this flow:

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

@@ -1,79 +0,0 @@
----
-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

@@ -1,32 +0,0 @@
----
-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

@@ -1,30 +0,0 @@
----
-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

@@ -1,31 +0,0 @@
----
-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

@@ -1,10 +0,0 @@
-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

@@ -1,28 +0,0 @@
----
-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

@@ -1,145 +0,0 @@
-# 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

@@ -1,116 +0,0 @@
-# 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

@@ -1,128 +0,0 @@
-# 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

@@ -1,54 +0,0 @@
-# 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

@@ -1,121 +0,0 @@
-# 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

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

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

@@ -1,87 +0,0 @@
----
-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

@@ -1,21 +1,23 @@
 profile: openclaw-check
-# Default OpenClaw runner spend to the Azure-backed Crabbox account.
-# Use `--provider aws` only for AWS-specific runner proof.
-provider: azure
+provider: aws
 class: standard
 capacity:
   market: spot
   strategy: most-available
-  # Fail closed instead of silently falling back to on-demand while the
-  # Azure-backed billing account is the default runner path.
-  fallback: spot-only
+  fallback: on-demand-after-120s
   hints: true
+  availabilityZones:
+    - eu-west-1a
+    - eu-west-1b
+    - eu-west-1c
+  regions:
+    - eu-west-1
+    - eu-west-2
+    - eu-central-1
+    - us-east-1
+    - 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:
@@ -23,14 +25,7 @@ actions:
     - openclaw
   runnerVersion: latest
   ephemeral: true
-blacksmith:
-  org: openclaw
-  workflow: .github/workflows/ci-check-testbox.yml
-  job: check
-  ref: main
 aws:
-  # AWS-specific overrides still pin direct `--provider aws` runs without
-  # leaking AWS region names into the Azure default capacity fallback list.
   region: eu-west-1
   rootGB: 400
 sync:

.gitattributes

@@ -1,6 +1,3 @@
 * 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

@@ -11,16 +11,8 @@
 /.github/workflows/codeql.yml @openclaw/openclaw-secops
 /.github/workflows/codeql-android-critical-security.yml @openclaw/openclaw-secops
 /.github/workflows/codeql-critical-quality.yml @openclaw/openclaw-secops
-/.github/workflows/dependency-guard.yml @openclaw/openclaw-secops
-/test/scripts/dependency-guard-workflow.test.ts @openclaw/openclaw-secops
-/test/scripts/dependency-guard-script.test.ts @openclaw/openclaw-secops
-/scripts/github/dependency-guard.mjs @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
+/.github/workflows/dependency-change-awareness.yml @openclaw/openclaw-secops
+/test/scripts/dependency-change-awareness-workflow.test.ts @openclaw/openclaw-secops
 /src/security/ @openclaw/openclaw-secops
 /src/secrets/ @openclaw/openclaw-secops
 /src/config/*secret*.ts @openclaw/openclaw-secops
@@ -31,7 +23,7 @@
 /src/gateway/**/*secret*.ts @openclaw/openclaw-secops
 /src/gateway/security-path*.ts @openclaw/openclaw-secops
 /src/gateway/resolve-configured-secret-input-string*.ts @openclaw/openclaw-secops
-/packages/gateway-protocol/src/**/*secret*.ts @openclaw/openclaw-secops
+/src/gateway/protocol/**/*secret*.ts @openclaw/openclaw-secops
 /src/gateway/server-methods/secrets*.ts @openclaw/openclaw-secops
 /src/agents/*auth*.ts @openclaw/openclaw-secops
 /src/agents/**/*auth*.ts @openclaw/openclaw-secops

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -11,8 +11,6 @@ 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/actionlint.yaml

@@ -14,10 +14,6 @@ self-hosted-runner:
     - blacksmith-16vcpu-ubuntu-2404-arm
     - blacksmith-6vcpu-macos-latest
     - blacksmith-12vcpu-macos-latest
-    - blacksmith-6vcpu-macos-15
-    - blacksmith-12vcpu-macos-15
-    - blacksmith-6vcpu-macos-26
-    - blacksmith-12vcpu-macos-26
 
 # Ignore patterns for known issues
 paths:

.github/actions/detect-docs-changes/action.yml

@@ -35,29 +35,17 @@ runs:
           exit 0
         fi
 
-        docs_changed=false
-        non_docs=false
-        while IFS= read -r changed_path; do
-          case "$changed_path" in
-            test/fixtures/*)
-              non_docs=true
-              ;;
-            docs/* | *.md | *.mdx)
-              docs_changed=true
-              ;;
-            *)
-              non_docs=true
-              ;;
-          esac
-        done <<< "$CHANGED"
-
-        if [ "$docs_changed" = "true" ]; then
+        # Check if any changed file is a doc
+        DOCS=$(echo "$CHANGED" | grep -E '^docs/|\.md$|\.mdx$' || true)
+        if [ -n "$DOCS" ]; then
           echo "docs_changed=true" >> "$GITHUB_OUTPUT"
         else
           echo "docs_changed=false" >> "$GITHUB_OUTPUT"
         fi
 
-        if [ "$non_docs" = "false" ]; then
+        # Check if all changed files are docs or markdown
+        NON_DOCS=$(echo "$CHANGED" | grep -vE '^docs/|\.md$|\.mdx$' || true)
+        if [ -z "$NON_DOCS" ]; then
           echo "docs_only=true" >> "$GITHUB_OUTPUT"
           echo "Docs-only change detected — skipping heavy jobs"
         else

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

@@ -123,14 +123,14 @@ runs:
       shell: bash
       run: |
         set -euo pipefail
-        bash scripts/ci-docker-pull-retry.sh "${OPENCLAW_DOCKER_E2E_BARE_IMAGE}"
+        docker pull "${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
-        bash scripts/ci-docker-pull-retry.sh "${OPENCLAW_DOCKER_E2E_FUNCTIONAL_IMAGE}"
+        docker pull "${OPENCLAW_DOCKER_E2E_FUNCTIONAL_IMAGE}"
 
     - name: Validate Docker E2E credentials
       if: inputs.hydrate-artifacts == 'true'
@@ -140,33 +140,13 @@ runs:
       run: |
         set -euo pipefail
         credentials=",$CREDENTIALS,"
-        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
+          [[ -n "${OPENAI_API_KEY:-}" ]] || {
+            echo "OPENAI_API_KEY is required for selected Docker E2E lanes." >&2
+            exit 1
+          }
         fi
-        if [[ "$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
+        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
+          exit 1
         fi

.github/actions/ensure-base-commit/action.yml

@@ -38,15 +38,9 @@ runs:
           exit 0
         fi
 
-        fetch_base_ref() {
-          timeout --signal=TERM --kill-after=10s 30s git \
-            -c protocol.version=2 \
-            fetch "$@"
-        }
-
         for deepen_by in 25 100 300; do
           echo "Base commit missing; deepening $FETCH_REF by $deepen_by."
-          if ! fetch_base_ref --no-tags --deepen="$deepen_by" origin -- "$FETCH_REF"; then
+          if ! git fetch --no-tags --deepen="$deepen_by" origin -- "$FETCH_REF"; then
             echo "::warning title=ensure-base-commit fetch failed::Failed to deepen $FETCH_REF by $deepen_by while looking for $BASE_SHA"
           fi
           if git rev-parse --verify "$BASE_SHA^{commit}" >/dev/null 2>&1; then
@@ -56,7 +50,7 @@ runs:
         done
 
         echo "Base commit still missing; fetching full history for $FETCH_REF."
-        if ! fetch_base_ref --no-tags origin -- "$FETCH_REF"; then
+        if ! git fetch --no-tags origin -- "$FETCH_REF"; then
           echo "::warning title=ensure-base-commit fetch failed::Failed to fetch full history for $FETCH_REF while looking for $BASE_SHA"
         fi
         if git rev-parse --verify "$BASE_SHA^{commit}" >/dev/null 2>&1; then

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

@@ -7,6 +7,14 @@ 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
@@ -19,48 +27,28 @@ inputs:
     description: Whether to use --frozen-lockfile for install.
     required: false
     default: "true"
-  use-actions-cache:
-    description: Whether to restore the pnpm store with actions/cache.
-    required: false
-    default: "true"
-  save-actions-cache:
-    description: Whether to save the pnpm store with actions/cache after install when no exact cache restored.
-    required: false
-    default: "false"
 runs:
   using: composite
   steps:
-    - name: Normalize container toolcache
-      shell: bash
-      run: |
-        set -euo pipefail
-        if [[ -d /__t && ! -e /opt/hostedtoolcache ]]; then
-          mkdir -p /opt
-          ln -s /__t /opt/hostedtoolcache
-        fi
-
     - name: Setup Node.js
-      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"
+      uses: actions/setup-node@v6
+      with:
+        node-version: ${{ inputs.node-version }}
+        check-latest: false
 
-    - name: Setup pnpm
-      id: setup-pnpm
+    - name: Setup pnpm + cache store
+      id: pnpm-cache
       uses: ./.github/actions/setup-pnpm-store-cache
       with:
         node-version: ${{ inputs.node-version }}
-        use-actions-cache: ${{ inputs.use-actions-cache }}
+        pnpm-version: ${{ inputs.pnpm-version }}
+        cache-key-suffix: ${{ inputs.cache-key-suffix }}
 
     - name: Setup Bun
       if: inputs.install-bun == 'true'
-      shell: bash
-      run: |
-        set -euo pipefail
-        npm install -g bun@1.3.14
+      uses: oven-sh/setup-bun@v2.2.0
+      with:
+        bun-version: "1.3.13"
 
     - name: Runtime versions
       shell: bash
@@ -113,32 +101,12 @@ 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[@]}"
-        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: Save pnpm store cache
-      if: ${{ inputs.install-deps == 'true' && inputs.use-actions-cache == 'true' && inputs.save-actions-cache == 'true' && runner.os != 'Windows' && steps.setup-pnpm.outputs.store-cache-hit != 'true' }}
+      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.setup-pnpm.outputs.store-path }}
-        key: ${{ steps.setup-pnpm.outputs.store-cache-primary-key }}
+        path: ${{ steps.pnpm-cache.outputs.store-path }}
+        key: ${{ steps.pnpm-cache.outputs.primary-key }}

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

@@ -1,108 +1,168 @@
-name: Setup pnpm
-description: Prepare pnpm from the repository packageManager and restore its store cache.
+name: Setup pnpm + store cache
+description: Prepare pnpm via corepack and restore pnpm store cache.
 inputs:
-  package-manager-file:
-    description: package.json file that owns the packageManager pnpm pin.
+  pnpm-version:
+    description: pnpm version to activate via corepack.
     required: false
-    default: "package.json"
-  lockfile-path:
-    description: pnpm lockfile used to key the store cache.
-    required: false
-    default: "pnpm-lock.yaml"
+    default: "11.0.8"
   node-version:
     description: Expected Node.js version already installed by actions/setup-node.
     required: false
-    default: ""
+    default: "24.x"
+  cache-key-suffix:
+    description: Suffix appended to the cache key.
+    required: false
+    default: "node24-pnpm11"
+  use-restore-keys:
+    description: Whether to use restore-keys fallback for actions/cache.
+    required: false
+    default: "true"
   use-actions-cache:
-    description: Whether actions/cache should restore the pnpm store.
+    description: Whether to restore pnpm store with actions/cache.
     required: false
     default: "true"
 outputs:
-  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 }}
-  store-cache-hit:
-    description: Whether the pnpm store cache restored an exact key.
-    value: ${{ steps.pnpm-store-cache.outputs.cache-hit }}
-  store-cache-primary-key:
-    description: Exact pnpm store cache key used for restore/save.
-    value: ${{ steps.pnpm-store-cache.outputs.cache-primary-key }}
+  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 }}
 runs:
   using: composite
   steps:
-    - 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
+    - name: Setup pnpm (corepack retry)
       shell: bash
       env:
         COREPACK_ENABLE_DOWNLOAD_PROMPT: "0"
-        PACKAGE_MANAGER_FILE: ${{ inputs.package-manager-file }}
+        PNPM_VERSION: ${{ inputs.pnpm-version }}
+        REQUESTED_NODE_VERSION: ${{ inputs.node-version }}
       run: |
         set -euo pipefail
-        package_manager="$(node -e "const fs = require('node:fs'); const path = require('node:path'); const pkg = JSON.parse(fs.readFileSync(path.resolve(process.argv[1]), 'utf8')); process.stdout.write(pkg.packageManager || '')" "$PACKAGE_MANAGER_FILE")"
-        case "$package_manager" in
-          pnpm@*) ;;
-          *)
-            echo "::error::Expected packageManager to pin pnpm, got '${package_manager:-<empty>}'"
-            exit 1
-            ;;
-        esac
+        if [[ ! "$PNPM_VERSION" =~ ^[0-9]+(\.[0-9]+){1,2}([.-][0-9A-Za-z.-]+)?$ ]]; then
+          echo "::error::Invalid pnpm-version input: '$PNPM_VERSION'"
+          exit 2
+        fi
+
+        requested_node="${REQUESTED_NODE_VERSION:-${NODE_VERSION:-}}"
+        requested_node="${requested_node#v}"
+
+        node_version_matches() {
+          local actual="$1"
+          local requested="$2"
+          if [[ -z "$requested" ]]; then
+            return 0
+          fi
+          case "$requested" in
+            *x)
+              [[ "${actual%%.*}" == "${requested%%.*}" ]]
+              ;;
+            *.*.*)
+              [[ "$actual" == "$requested" ]]
+              ;;
+            *.*)
+              [[ "$actual" == "$requested".* ]]
+              ;;
+            *)
+              [[ "${actual%%.*}" == "$requested" ]]
+              ;;
+          esac
+        }
+
+        active_node_version="$(node -p 'process.versions.node' 2>/dev/null || true)"
+        if ! node_version_matches "$active_node_version" "$requested_node"; then
+          node_roots=()
+          for root in \
+            "${RUNNER_TOOL_CACHE:-}" \
+            "${AGENT_TOOLSDIRECTORY:-}" \
+            "${ACTIONS_RUNNER_TOOL_CACHE:-}" \
+            "/opt/hostedtoolcache" \
+            "/home/runner/_work/_tool" \
+            "/Users/runner/hostedtoolcache" \
+            "/c/hostedtoolcache/windows"
+          do
+            if [[ -d "$root/node" ]]; then
+              node_roots+=("$root/node")
+            elif [[ "$(basename "$root")" == "node" && -d "$root" ]]; then
+              node_roots+=("$root")
+            fi
+          done
+
+          node_bin=""
+          for node_root in "${node_roots[@]}"; do
+            while IFS= read -r candidate; do
+              candidate_version="$("$candidate" -p 'process.versions.node' 2>/dev/null || true)"
+              if node_version_matches "$candidate_version" "$requested_node"; then
+                node_bin="$candidate"
+                break 2
+              fi
+            done < <(find "$node_root" \( -name node -o -name node.exe \) -type f 2>/dev/null | sort -r)
+          done
+
+          if [[ -n "$node_bin" ]]; then
+            echo "Using Node $("$node_bin" -p 'process.versions.node') from $node_bin"
+            export PATH="$(dirname "$node_bin"):$PATH"
+            hash -r
+          fi
+        fi
+
+        active_node_version="$(node -p 'process.versions.node' 2>/dev/null || true)"
+        if ! node_version_matches "$active_node_version" "$requested_node"; then
+          echo "::error::Expected Node '${requested_node}', but active node is '${active_node_version:-missing}' at $(command -v node || true)"
+          exit 1
+        fi
+
+        node -v
+        command -v node
+        command -v corepack
         corepack enable
         for attempt in 1 2 3; do
-          if corepack prepare "$package_manager" --activate; then
+          if corepack prepare "pnpm@$PNPM_VERSION" --activate; then
+            pnpm -v
             exit 0
           fi
-          sleep $((attempt * 5))
+          echo "corepack prepare failed (attempt $attempt/3). Retrying..."
+          sleep $((attempt * 10))
         done
-        corepack prepare "$package_manager" --activate
+        exit 1
 
     - 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: ${{ inputs.use-restore-keys }}
       run: |
         set -euo pipefail
-        store_path="$(pnpm store path --silent)"
-        node -e "require('node:fs').mkdirSync(process.argv[1], { recursive: true })" "$store_path"
-        echo "path=$store_path" >> "$GITHUB_OUTPUT"
+        echo "enabled=$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
 
     - name: Restore pnpm store cache
-      id: pnpm-store-cache
-      if: ${{ inputs.use-actions-cache == 'true' && runner.os != 'Windows' }}
+      id: pnpm-cache-restore
+      if: inputs.use-actions-cache == 'true'
       uses: actions/cache/restore@v5
       with:
         path: ${{ steps.pnpm-store.outputs.path }}
-        key: pnpm-store-${{ runner.os }}-${{ runner.arch }}-${{ inputs.node-version }}-${{ hashFiles(inputs.package-manager-file) }}-${{ hashFiles(inputs.lockfile-path) }}
-        restore-keys: |
-          pnpm-store-${{ runner.os }}-${{ runner.arch }}-${{ inputs.node-version }}-${{ hashFiles(inputs.package-manager-file) }}-
-          pnpm-store-${{ runner.os }}-${{ runner.arch }}-${{ inputs.node-version }}-
-
-    - 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"
+        key: ${{ steps.pnpm-cache-config.outputs.primary-key }}
+        restore-keys: ${{ steps.pnpm-cache-config.outputs.restore-keys }}

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

@@ -1,223 +0,0 @@
-#!/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 ${roots[@]+"${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

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

.github/codeql/codeql-channel-runtime-boundary-critical-security.yml

@@ -19,7 +19,7 @@ paths:
   - src/config/types.channel*.ts
   - src/gateway/server-channel*.ts
   - src/gateway/server-methods/channels.ts
-  - packages/gateway-protocol/src/schema/channels.ts
+  - src/gateway/protocol/schema/channels.ts
   - src/infra/channel-*.ts
   - src/infra/exec-approval-channel-runtime.ts
   - src/infra/outbound/channel-*.ts

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

@@ -22,15 +22,13 @@ 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
   - src/gateway/**/*auth*.ts
   - src/gateway/*secret*.ts
   - src/gateway/**/*secret*.ts
-  - packages/gateway-protocol/src/**/*secret*.ts
+  - src/gateway/protocol/**/*secret*.ts
   - src/gateway/resolve-configured-secret-input-string*.ts
   - src/gateway/security-path*.ts
   - src/gateway/server-methods/secrets*.ts

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

@@ -30,7 +30,7 @@ paths:
   - src/gateway/**/*auth*.ts
   - src/gateway/*secret*.ts
   - src/gateway/**/*secret*.ts
-  - packages/gateway-protocol/src/**/*secret*.ts
+  - src/gateway/protocol/**/*secret*.ts
   - src/gateway/resolve-configured-secret-input-string*.ts
   - src/gateway/security-path*.ts
   - src/gateway/server-methods/secrets*.ts

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

@@ -15,7 +15,7 @@ query-filters:
 
 paths:
   - src/gateway/method-scopes.ts
-  - packages/gateway-protocol/src
+  - src/gateway/protocol
   - src/gateway/server-methods
   - src/gateway/server-methods.ts
   - src/gateway/server-methods-list.ts

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

@@ -24,15 +24,14 @@ paths:
   - src/agents/openclaw-plugin-tools.ts
   - src/agents/openclaw-tools.runtime.ts
   - src/agents/openclaw-tools.registration.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/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/tools/gateway-tool.ts
   - src/agents/tools/message-tool.ts
   - src/agents/tools/sessions-send-tool.ts

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

@@ -9,7 +9,6 @@ queries:
 paths:
   - src
   - extensions
-  - packages/net-policy/src
 
 paths-ignore:
   - "**/node_modules"

.github/codeql/codeql-network-ssrf-boundary-critical-security.yml

@@ -15,6 +15,7 @@ query-filters:
 
 paths:
   - src/infra/net
+  - src/shared/net
   - src/agents/tools/web-fetch.ts
   - src/agents/tools/web-guarded-fetch.ts
   - src/agents/tools/web-shared.ts
@@ -22,7 +23,6 @@ paths:
   - src/web-fetch
   - src/web/provider-runtime-shared.ts
   - packages/memory-host-sdk/src/host/ssrf-policy.ts
-  - packages/net-policy/src
 
 paths-ignore:
   - "**/node_modules"

.github/codeql/openclaw-boundary/queries/raw-socket-callsite-classification.ql

@@ -76,8 +76,6 @@ predicate allowedRawSocketClientCall(Expr call) {
   or
   allowedOwnerScope(call, "src/proxy-capture/proxy-server.ts", "startDebugProxyServer")
   or
-  allowedOwnerScope(call, "extensions/codex-supervisor/src/json-rpc-client.ts", "connectCodexSupervisorUnixSocket")
-  or
   allowedOwnerScope(call, "extensions/irc/src/client.ts", "connectIrcClient")
   or
   allowedOwnerScope(call, "extensions/qa-lab/src/lab-server-capture.ts", "probeTcpReachability")

.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 `CHANGELOG.md` entries during normal docs work. Capture user-facing release-note context in the PR body or commit message instead.
+- Do not add a changelog entry unless the docs update describes a user-facing behavior/API change from the triggering commit.
 
 Allowed paths:
 

.github/labeler.yml

@@ -10,11 +10,6 @@
           - "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:
@@ -41,18 +36,6 @@
       - 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: workboard":
-  - changed-files:
-      - any-glob-to-any-file:
-          - "extensions/workboard/**"
-          - "docs/plugins/workboard.md"
-          - "docs/plugins/reference/workboard.md"
 "plugin: migrate-hermes":
   - changed-files:
       - any-glob-to-any-file:
@@ -194,7 +177,7 @@
           - "ui/**"
           - "src/gateway/control-ui.ts"
           - "src/gateway/control-ui-shared.ts"
-          - "packages/gateway-protocol/src/**"
+          - "src/gateway/protocol/**"
           - "src/gateway/server-methods/chat.ts"
           - "src/infra/control-ui-assets.ts"
 
@@ -202,7 +185,6 @@
   - changed-files:
       - any-glob-to-any-file:
           - "src/gateway/**"
-          - "packages/gateway-protocol/src/**"
           - "src/daemon/**"
           - "docs/gateway/**"
 
@@ -355,11 +337,6 @@
       - any-glob-to-any-file:
           - "extensions/deepinfra/**"
           - "docs/providers/deepinfra.md"
-"extensions: gmi":
-  - changed-files:
-      - any-glob-to-any-file:
-          - "extensions/gmi/**"
-          - "docs/providers/gmi.md"
 "extensions: tencent":
   - changed-files:
       - any-glob-to-any-file:
@@ -410,17 +387,6 @@
   - changed-files:
       - any-glob-to-any-file:
           - "extensions/codex/**"
-"extensions: codex-supervisor":
-  - changed-files:
-      - any-glob-to-any-file:
-          - "extensions/codex-supervisor/**"
-          - "docs/plugins/reference/codex-supervisor.md"
-          - "docs/specs/claw-supervisor.md"
-"extensions: copilot":
-  - changed-files:
-      - any-glob-to-any-file:
-          - "extensions/copilot/**"
-          - "docs/plugins/copilot.md"
 "extensions: kimi-coding":
   - changed-files:
       - any-glob-to-any-file:
@@ -441,11 +407,6 @@
   - changed-files:
       - any-glob-to-any-file:
           - "extensions/nvidia/**"
-"extensions: novita":
-  - changed-files:
-      - any-glob-to-any-file:
-          - "extensions/novita/**"
-          - "docs/providers/novita.md"
 "extensions: phone-control":
   - changed-files:
       - any-glob-to-any-file:
@@ -524,7 +485,6 @@
   - 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

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

.github/pull_request_template.md

@@ -1,132 +1,165 @@
 ## Summary
 
-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.
+Describe the problem and fix in 2–5 bullets:
 
 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.
 
-</details>
+- Problem:
+- Solution:
+- What changed:
+- What did NOT change (scope boundary):
 
-## Linked context
+## Motivation
 
-Which issue does this close?
+Explain why this change should exist now. Link it to the user pain, failure mode, maintainer need, or product goal. If this is purely mechanical, write `N/A`.
 
-Closes #
+-
 
-Which issues, PRs, or discussions are related?
+## Change Type (select all)
 
-Related #
+- [ ] Bug fix
+- [ ] Feature
+- [ ] Refactor required for the fix
+- [ ] Docs
+- [ ] Security hardening
+- [ ] Chore/infra
 
-Was this requested by a maintainer or owner?
+## Scope (select all touched areas)
 
-<details>
-<summary>Linked context guidance</summary>
+- [ ] Gateway / orchestration
+- [ ] Skills / tool execution
+- [ ] Auth / tokens
+- [ ] Memory / storage
+- [ ] Integrations
+- [ ] API / contracts
+- [ ] UI / DX
+- [ ] CI/CD / infra
 
-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.
+## Linked Issue/PR
 
-</details>
+- Closes #
+- Related #
+- [ ] This PR fixes a bug or regression
 
 ## 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):
 
-<details>
-<summary>Real behavior proof guidance</summary>
+## Root Cause (if applicable)
 
-External contributors must show after-fix evidence from a real OpenClaw setup. Unit tests, mocks, lint, typechecks, snapshots, and CI are supplemental only.
+For bug fixes or regressions, explain why this happened, not just what changed. Otherwise write `N/A`. If the cause is unclear, write `Unknown`.
 
-Screenshots are encouraged even for CLI, console, text, or log changes. Terminal screenshots, copied live output, redacted runtime logs, recordings, and linked artifacts count.
+- Root cause:
+- Missing detection / guardrail:
+- Contributing context (if known):
 
-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.
+## Regression Test Plan (if applicable)
 
-Be mindful of private information like IP addresses, API keys, phone numbers, non-public endpoints, or other private details when providing evidence.
+For bug fixes or regressions, name the smallest reliable test coverage that should catch this. Otherwise write `N/A`.
 
-</details>
+- 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:
 
-## Tests and validation
+## User-visible / Behavior Changes
 
-Which commands did you run?
+List user-visible changes (including defaults/config).  
+If none, write `None`.
 
+## Diagram (if applicable)
 
-What regression coverage was added or updated?
+For UI changes or non-trivial logic flows, include a small ASCII diagram reviewers can scan quickly. Otherwise write `N/A`.
 
+```text
+Before:
+[user action] -> [old state]
 
-What failed before this fix, if known?
+After:
+[user action] -> [new state] -> [result]
+```
 
+## Security Impact (required)
 
-If no test was added, why not?
+- 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:
 
-<details>
-<summary>Testing guidance</summary>
+## Repro + Verification
 
-List focused commands, not every incidental check. CI is useful support, but external PRs still need real behavior proof above when behavior changes.
+### Environment
 
-</details>
+- OS:
+- Runtime/container:
+- Model/provider:
+- Integration/channel (if any):
+- Relevant config (redacted):
 
-## Risk checklist
+### Steps
 
-Did user-visible behavior change? (`Yes/No`)
+1.
+2.
+3.
 
+### Expected
 
-Did config, environment, or migration behavior change? (`Yes/No`)
+-
 
+### Actual
 
-Did security, auth, secrets, network, or tool execution behavior change? (`Yes/No`)
+-
 
+## Evidence
 
-What is the highest-risk area?
+Attach at least one:
 
+- [ ] Failing test/log before + passing after
+- [ ] Trace/log snippets
+- [ ] Screenshot/recording
+- [ ] Perf numbers (if relevant)
 
-How is that risk mitigated?
+## Human Verification (required)
 
-<details>
-<summary>Risk guidance</summary>
+What you personally verified (not just CI), and how:
 
-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.
+- Verified scenarios:
+- Edge cases checked:
+- What you did **not** verify:
 
-</details>
+## Review Conversations
 
-## Current review state
+- [ ] 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.
 
-What is the next action?
+If a bot review conversation is addressed by this PR, resolve that conversation yourself. Do not leave bot review conversation cleanup for maintainers.
 
+## Compatibility / Migration
 
-What is still waiting on author, maintainer, CI, or external proof?
+- Backward compatible? (`Yes/No`)
+- Config/env changes? (`Yes/No`)
+- Migration needed? (`Yes/No`)
+- If yes, exact upgrade steps:
 
+## Risks and Mitigations
 
-Which bot or reviewer comments were addressed?
+List only real risks for this PR. Add/remove entries as needed. If none, write `None`.
 
-<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>
+- Risk:
+  - Mitigation:

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

@@ -41,10 +41,6 @@ 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() {
@@ -61,9 +57,9 @@ jobs:
             git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
+            timeout --signal=TERM 30s git -C "$workdir" \
               -c protocol.version=2 \
-              -c "http.extraheader=AUTHORIZATION: basic ${auth_header}" \
+              -c "http.https://github.com/.extraheader=AUTHORIZATION: basic ${auth_header}" \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
 
@@ -188,21 +184,15 @@ jobs:
         run: |
           set -euo pipefail
 
-          timeout --signal=TERM --kill-after=10s 30s git \
-            -c protocol.version=2 \
-            fetch --no-tags --prune --no-recurse-submodules --depth=50 origin \
-            "+refs/heads/main:refs/remotes/origin/main"
+          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 "$node_bin/corepack" /usr/local/bin/corepack
-          sudo tee /usr/local/bin/pnpm >/dev/null <<'PNPM'
-          #!/usr/bin/env bash
-          exec /usr/local/bin/corepack pnpm "$@"
-          PNPM
-          sudo chmod 0755 /usr/local/bin/pnpm
+          sudo ln -sf "$pnpm_bin" /usr/local/bin/pnpm
 
       - name: Hydrate Testbox provider env helper
         shell: bash
@@ -232,6 +222,6 @@ jobs:
 
       - name: Run Testbox
         uses: useblacksmith/run-testbox@5ca05834db1d3813554d1dd109e5f2087a8d7cbc
-        if: success()
+        if: always()
         env:
           FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"

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

@@ -39,10 +39,6 @@ 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() {
@@ -59,9 +55,9 @@ jobs:
             git -C "$workdir" remote add origin "https://github.com/${CHECKOUT_REPO}"
             git -C "$workdir" config gc.auto 0
 
-            timeout --signal=TERM --kill-after=10s 30s git -C "$workdir" \
+            timeout --signal=TERM 30s git -C "$workdir" \
               -c protocol.version=2 \
-              -c "http.extraheader=AUTHORIZATION: basic ${auth_header}" \
+              -c "http.https://github.com/.extraheader=AUTHORIZATION: basic ${auth_header}" \
               fetch --no-tags --prune --no-recurse-submodules --depth=1 origin \
               "+${CHECKOUT_SHA}:refs/remotes/origin/ci-target" || return 1
 
@@ -89,21 +85,15 @@ jobs:
         run: |
           set -euo pipefail
 
-          timeout --signal=TERM --kill-after=10s 30s git \
-            -c protocol.version=2 \
-            fetch --no-tags --prune --no-recurse-submodules --depth=50 origin \
-            "+refs/heads/main:refs/remotes/origin/main"
+          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 "$node_bin/corepack" /usr/local/bin/corepack
-          sudo tee /usr/local/bin/pnpm >/dev/null <<'PNPM'
-          #!/usr/bin/env bash
-          exec /usr/local/bin/corepack pnpm "$@"
-          PNPM
-          sudo chmod 0755 /usr/local/bin/pnpm
+          sudo ln -sf "$pnpm_bin" /usr/local/bin/pnpm
 
       - name: Hydrate Testbox provider env helper
         shell: bash
@@ -113,7 +103,6 @@ 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 }}
@@ -134,6 +123,7 @@ jobs:
 
       - name: Run Testbox
         uses: useblacksmith/run-testbox@5ca05834db1d3813554d1dd109e5f2087a8d7cbc
-        if: success()
+        if: always()
+        continue-on-error: true
         env:
           FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"

.github/workflows/clawsweeper-dispatch.yml

@@ -24,14 +24,7 @@ concurrency:
 jobs:
   dispatch:
     runs-on: ubuntu-latest
-    if: >-
-      ${{
-        github.event_name == 'issue_comment' ||
-        !(
-          endsWith(github.actor, '[bot]') &&
-          (github.event.action == 'labeled' || github.event.action == 'unlabeled')
-        )
-      }}
+    if: ${{ github.event_name == 'issue_comment' || !(endsWith(github.actor, '[bot]') && (github.event.action == 'labeled' || github.event.action == 'unlabeled')) }}
     env:
       HAS_CLAWSWEEPER_APP_PRIVATE_KEY: ${{ secrets.CLAWSWEEPER_APP_PRIVATE_KEY != '' }}
       CLAWSWEEPER_APP_CLIENT_ID: Iv23liOECG0slfuhz093

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

@@ -33,7 +33,6 @@ on:
       - "packages/plugin-package-contract/**"
       - "packages/plugin-sdk/**"
       - "packages/memory-host-sdk/**"
-      - "packages/net-policy/**"
       - "src/*.ts"
       - "src/**/*.ts"
       - "src/config/**"
@@ -72,9 +71,7 @@ on:
       - "src/acp/control-plane/**"
       - "src/agents/cli-runner/**"
       - "src/agents/command/**"
-      - "src/agents/embedded-agent-runner/**"
-      - "src/agents/sessions/**"
-      - "src/agents/sessions/tools/**"
+      - "src/agents/pi-embedded-runner/**"
       - "src/agents/tools/**"
       - "src/agents/*completion*.ts"
       - "src/agents/*transport*.ts"
@@ -107,13 +104,13 @@ on:
       - "src/gateway/**/*auth*.ts"
       - "src/gateway/*secret*.ts"
       - "src/gateway/**/*secret*.ts"
-      - "packages/gateway-protocol/src/**/*secret*.ts"
+      - "src/gateway/protocol/**/*secret*.ts"
       - "src/gateway/resolve-configured-secret-input-string*.ts"
       - "src/gateway/security-path*.ts"
       - "src/gateway/server-methods/secrets*.ts"
       - "src/gateway/server-startup-memory.ts"
       - "src/gateway/method-scopes.ts"
-      - "packages/gateway-protocol/src/**"
+      - "src/gateway/protocol/**"
       - "src/gateway/server-methods/**"
       - "src/gateway/server-methods.ts"
       - "src/gateway/server-methods-list.ts"
@@ -225,15 +222,7 @@ jobs:
                   network_runtime=true
                   session_diagnostics=true
                   ;;
-                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)
+                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)
                   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)
@@ -245,14 +234,14 @@ jobs:
                 src/config/*)
                   config=true
                   ;;
-                packages/gateway-protocol/src/*secret*.ts|packages/gateway-protocol/src/**/*secret*.ts|src/gateway/server-methods/secrets*.ts)
+                src/gateway/protocol/*secret*.ts|src/gateway/server-methods/secrets*.ts)
                   core_auth_secrets=true
                   gateway=true
                   ;;
                 src/agents/*auth*.ts|src/agents/auth-health*.ts|src/agents/auth-profiles|src/agents/auth-profiles/*|src/agents/bash-tools.exec-host-shared.ts|src/agents/sandbox|src/agents/sandbox.ts|src/agents/sandbox-*.ts|src/agents/sandbox/*|src/cron/service/jobs.ts|src/cron/stagger.ts|src/gateway/*auth*.ts|src/gateway/*secret*.ts|src/gateway/resolve-configured-secret-input-string*.ts|src/gateway/security-path*.ts|src/infra/secret-file*.ts|src/secrets/*|src/security/*)
                   core_auth_secrets=true
                   ;;
-                packages/gateway-protocol/src/*|packages/gateway-protocol/src/**/*|src/gateway/method-scopes.ts|src/gateway/server-methods/*|src/gateway/server-methods.ts|src/gateway/server-methods-list.ts)
+                src/gateway/method-scopes.ts|src/gateway/protocol/*|src/gateway/server-methods/*|src/gateway/server-methods.ts|src/gateway/server-methods-list.ts)
                   gateway=true
                   ;;
                 packages/memory-host-sdk/*|src/commands/doctor-cron-dreaming-payload-migration.ts|src/commands/doctor-memory-search.ts|src/gateway/server-startup-memory.ts|src/memory/*|src/memory-host-sdk/*)
@@ -302,7 +291,7 @@ jobs:
               esac
 
               case "${file}" in
-                src/*.ts|src/**/*.ts|extensions/*.ts|extensions/**/*.ts|packages/net-policy/src/*|packages/net-policy/src/**/*)
+                src/*.ts|src/**/*.ts|extensions/*.ts|extensions/**/*.ts)
                   network_runtime=true
                   ;;
               esac

.github/workflows/codeql-macos-critical-security.yml

@@ -20,7 +20,7 @@ permissions:
 jobs:
   macos:
     name: Critical Security (macOS)
-    runs-on: blacksmith-6vcpu-macos-15
+    runs-on: blacksmith-6vcpu-macos-latest
     timeout-minutes: 45
     steps:
       - name: Checkout

.github/workflows/codeql.yml

@@ -19,15 +19,6 @@ on:
       - ".github/workflows/**"
       - "packages/**"
       - "src/**"
-  push:
-    branches:
-      - main
-    paths:
-      - ".github/actions/**"
-      - ".github/codeql/**"
-      - ".github/workflows/**"
-      - "packages/**"
-      - "src/**"
   schedule:
     - cron: "0 6 * * *"
 
@@ -85,21 +76,10 @@ jobs:
             config_file: ./.github/codeql/codeql-actions-critical-security.yml
     steps:
       - name: Checkout
-        if: ${{ matrix.category != 'actions' }}
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
         with:
           submodules: false
 
-      - name: Checkout Actions security sources
-        if: ${{ matrix.category == 'actions' }}
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          submodules: false
-          sparse-checkout: |
-            .github/actions
-            .github/workflows
-            .github/codeql
-
       - name: Initialize CodeQL
         uses: github/codeql-action/init@95e58e9a2cdfd71adc6e0353d5c52f41a045d225 # v4
         with:

.github/workflows/control-ui-locale-refresh.yml

@@ -138,7 +138,7 @@ jobs:
           OPENAI_API_KEY: ${{ secrets.OPENCLAW_DOCS_I18N_OPENAI_API_KEY || secrets.OPENAI_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           OPENCLAW_CONTROL_UI_I18N_PROVIDER: ${{ secrets.ANTHROPIC_API_KEY != '' && 'anthropic' || 'openai' }}
-          OPENCLAW_CONTROL_UI_I18N_MODEL: ${{ secrets.ANTHROPIC_API_KEY != '' && 'claude-opus-4-8' || vars.OPENCLAW_CI_OPENAI_MODEL_BARE }}
+          OPENCLAW_CONTROL_UI_I18N_MODEL: ${{ secrets.ANTHROPIC_API_KEY != '' && 'claude-opus-4-7' || vars.OPENCLAW_CI_OPENAI_MODEL_BARE }}
           OPENCLAW_CONTROL_UI_I18N_THINKING: low
           OPENCLAW_CONTROL_UI_I18N_AUTH_OPTIONAL: "1"
           LOCALE: ${{ matrix.locale }}

.github/workflows/crabbox-hydrate.yml

@@ -31,17 +31,10 @@ 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:
@@ -49,115 +42,25 @@ jobs:
         with:
           ref: ${{ inputs.ref || github.ref }}
 
-      - name: Setup Node.js
-        uses: actions/setup-node@v6
+      - name: Setup Node environment
+        uses: ./.github/actions/setup-node-env
         with:
-          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
-            timeout --signal=TERM --kill-after=10s 30s git \
-              -c protocol.version=2 \
-              fetch --no-tags --prune --no-recurse-submodules --depth=50 origin \
-              "+refs/heads/main:refs/remotes/origin/main"
-          fi
+          install-bun: "false"
 
       - 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 "$node_bin/corepack" /usr/local/bin/corepack
-          sudo tee /usr/local/bin/pnpm >/dev/null <<'PNPM'
-          #!/usr/bin/env bash
-          exec /usr/local/bin/corepack pnpm "$@"
-          PNPM
-          sudo chmod 0755 /usr/local/bin/pnpm
+          sudo ln -sf "$pnpm_bin" /usr/local/bin/pnpm
 
       - name: Ensure Docker is running
         shell: bash
@@ -166,13 +69,7 @@ jobs:
 
           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
+            curl -fsSL https://get.docker.com | sudo sh
           fi
 
           if command -v systemctl >/dev/null 2>&1; then
@@ -188,42 +85,34 @@ 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 buildx version || true
           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
@@ -253,423 +142,7 @@ jobs:
             fi
           }
           {
-            for key in CI GITHUB_ACTIONS GITHUB_WORKSPACE GITHUB_REPOSITORY GITHUB_RUN_ID GITHUB_RUN_NUMBER GITHUB_RUN_ATTEMPT GITHUB_REF GITHUB_REF_NAME GITHUB_SHA GITHUB_EVENT_NAME GITHUB_ACTOR RUNNER_OS RUNNER_ARCH RUNNER_TEMP RUNNER_TOOL_CACHE XDG_CACHE_HOME COREPACK_HOME 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) {
-            $repo = (Get-Location).Path
-            $fetchInfo = New-Object System.Diagnostics.ProcessStartInfo
-            $fetchInfo.FileName = "git"
-            $fetchInfo.WorkingDirectory = $repo
-            $fetchInfo.UseShellExecute = $false
-            $fetchInfo.Arguments = '-c protocol.version=2 fetch --no-tags --no-progress --prune --no-recurse-submodules --depth=50 origin "+refs/heads/main:refs/remotes/origin/main"'
-
-            $fetch = New-Object System.Diagnostics.Process
-            $fetch.StartInfo = $fetchInfo
-            if (-not $fetch.Start()) {
-              throw "git fetch failed to start"
-            }
-            if (-not $fetch.WaitForExit(30000)) {
-              $fetch.Kill()
-              $fetch.WaitForExit()
-              throw "git fetch timed out after 30 seconds"
-            }
-            if ($fetch.ExitCode -ne 0) {
-              throw "git fetch failed with exit code $($fetch.ExitCode)"
-            }
-          }
-
-      - 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: ${{ inputs.ref || github.ref }}
-
-      - name: Setup Node environment
-        uses: ./.github/actions/setup-node-env
-        with:
-          install-bun: "false"
-          use-actions-cache: "false"
-
-      - name: Prepare Crabbox shell
-        shell: bash
-        run: |
-          set -euo pipefail
-
-          if git rev-parse --is-inside-work-tree >/dev/null 2>&1; then
-            timeout --signal=TERM --kill-after=10s 30s git \
-              -c protocol.version=2 \
-              fetch --no-tags --prune --no-recurse-submodules --depth=50 origin \
-              "+refs/heads/main:refs/remotes/origin/main"
-          fi
-
-          node_bin="$(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" "$value"
-            fi
-          }
-          {
-            for key in CI GITHUB_ACTIONS GITHUB_WORKSPACE GITHUB_REPOSITORY GITHUB_RUN_ID GITHUB_RUN_NUMBER GITHUB_RUN_ATTEMPT GITHUB_REF GITHUB_REF_NAME GITHUB_SHA GITHUB_EVENT_NAME GITHUB_ACTOR RUNNER_OS RUNNER_ARCH RUNNER_TEMP RUNNER_TOOL_CACHE NODE_BIN PNPM_HOME PNPM_CONFIG_CHILD_CONCURRENCY PNPM_CONFIG_MODULES_DIR PNPM_CONFIG_NETWORK_CONCURRENCY PNPM_CONFIG_STORE_DIR PNPM_CONFIG_VERIFY_DEPS_BEFORE_RUN PNPM_CONFIG_VIRTUAL_STORE_DIR PATH; do
+            for key in CI GITHUB_ACTIONS GITHUB_WORKSPACE GITHUB_REPOSITORY GITHUB_RUN_ID GITHUB_RUN_NUMBER GITHUB_RUN_ATTEMPT GITHUB_REF GITHUB_REF_NAME GITHUB_SHA GITHUB_EVENT_NAME GITHUB_ACTOR RUNNER_OS RUNNER_ARCH RUNNER_TEMP RUNNER_TOOL_CACHE; do
               write_export "$key"
             done
           } > "${env_file}.tmp"

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

@@ -0,0 +1,171 @@
+name: Dependency Change Awareness
+
+on:
+  pull_request_target: # zizmor: ignore[dangerous-triggers] metadata-only workflow; no checkout or untrusted code execution
+    types: [opened, reopened, synchronize, ready_for_review]
+
+permissions:
+  pull-requests: write
+  issues: write
+
+concurrency:
+  group: dependency-change-awareness-${{ github.event.pull_request.number }}
+  cancel-in-progress: true
+
+jobs:
+  dependency-change-awareness:
+    if: ${{ !github.event.pull_request.draft }}
+    runs-on: ubuntu-24.04
+    timeout-minutes: 5
+    steps:
+      - name: Label and comment on dependency changes
+        uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9
+        with:
+          script: |
+            const marker = "<!-- openclaw:dependency-change-awareness -->";
+            const labelName = "dependencies-changed";
+            const maxListedFiles = 25;
+            const pullRequest = context.payload.pull_request;
+
+            if (!pullRequest) {
+              core.info("No pull_request payload found; skipping.");
+              return;
+            }
+
+            const isDependencyFile = (filename) =>
+              filename === "package.json" ||
+              filename === "pnpm-lock.yaml" ||
+              filename === "pnpm-workspace.yaml" ||
+              filename === "ui/package.json" ||
+              filename.startsWith("patches/") ||
+              /^packages\/[^/]+\/package\.json$/u.test(filename) ||
+              /^extensions\/[^/]+\/package\.json$/u.test(filename);
+
+            const sanitizeDisplayValue = (value) =>
+              String(value)
+                .replace(/[\u0000-\u001f\u007f]/gu, "?")
+                .slice(0, 240);
+            const markdownCode = (value) =>
+              `\`${sanitizeDisplayValue(value).replaceAll("`", "\\`")}\``;
+            const ignoreUnavailableWritePermission = (action) => (error) => {
+              if (error?.status === 403) {
+                core.warning(
+                  `Skipping dependency change ${action}; token does not have issue write permission.`,
+                );
+                return;
+              }
+              if (error?.status === 404 || error?.status === 422) {
+                core.warning(`Dependency change ${action} is unavailable.`);
+                return;
+              }
+              throw error;
+            };
+
+            const files = await github.paginate(github.rest.pulls.listFiles, {
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              pull_number: pullRequest.number,
+              per_page: 100,
+            });
+            const dependencyFiles = files
+              .map((file) => file.filename)
+              .filter((filename) => typeof filename === "string" && isDependencyFile(filename))
+              .sort((left, right) => left.localeCompare(right));
+
+            const comments = await github.paginate(github.rest.issues.listComments, {
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: pullRequest.number,
+              per_page: 100,
+            });
+            const existingComment = comments.find(
+              (comment) =>
+                comment.user?.login === "github-actions[bot]" && comment.body?.includes(marker),
+            );
+
+            const labels = await github.paginate(github.rest.issues.listLabelsOnIssue, {
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: pullRequest.number,
+              per_page: 100,
+            });
+            const hasLabel = labels.some((label) => label.name === labelName);
+
+            if (dependencyFiles.length === 0) {
+              if (hasLabel) {
+                await github.rest.issues.removeLabel({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: pullRequest.number,
+                  name: labelName,
+                }).catch(ignoreUnavailableWritePermission("label removal"));
+              }
+              if (existingComment) {
+                await github.rest.issues.deleteComment({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  comment_id: existingComment.id,
+                }).catch(ignoreUnavailableWritePermission("comment deletion"));
+              }
+              await core.summary
+                .addHeading("Dependency Change Awareness")
+                .addRaw("No dependency-related file changes detected.")
+                .write();
+              core.info("No dependency-related file changes detected.");
+              return;
+            }
+
+            if (!hasLabel) {
+              await github.rest.issues.addLabels({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: pullRequest.number,
+                labels: [labelName],
+              }).catch(ignoreUnavailableWritePermission(`label "${labelName}" update`));
+            }
+
+            const listedFiles = dependencyFiles.slice(0, maxListedFiles);
+            const omittedCount = dependencyFiles.length - listedFiles.length;
+            const fileLines = listedFiles.map((filename) => `- ${markdownCode(filename)}`);
+            if (omittedCount > 0) {
+              fileLines.push(`- ${omittedCount} additional dependency-related files not shown`);
+            }
+
+            const body = [
+              marker,
+              "",
+              "### Dependency Changes Detected",
+              "",
+              "This PR changes dependency-related files. Maintainers should confirm these changes are intentional.",
+              "",
+              "Changed files:",
+              ...fileLines,
+              "",
+              "Maintainer follow-up:",
+              "- Review whether the dependency changes are intentional.",
+              "- Inspect resolved package deltas when lockfile or workspace dependency policy changes are present.",
+              "- 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");
+
+            if (existingComment) {
+              await github.rest.issues.updateComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                comment_id: existingComment.id,
+                body,
+              }).catch(ignoreUnavailableWritePermission("comment update"));
+            } else {
+              await github.rest.issues.createComment({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: pullRequest.number,
+                body,
+              }).catch(ignoreUnavailableWritePermission("comment creation"));
+            }
+
+            await core.summary
+              .addHeading("Dependency Change Awareness")
+              .addRaw(`Detected ${dependencyFiles.length} dependency-related file change(s).`)
+              .addList(dependencyFiles.map((filename) => markdownCode(filename)))
+              .write();
+            core.notice(`Detected ${dependencyFiles.length} dependency-related file change(s).`);

.github/workflows/dependency-guard.yml

@@ -1,109 +0,0 @@
-name: Dependency Guard
-
-on:
-  pull_request_target: # zizmor: ignore[dangerous-triggers] checks trusted base script only; never checks out PR head
-    types: [opened, reopened, synchronize, ready_for_review]
-
-permissions:
-  contents: read
-  pull-requests: write
-  issues: write
-
-concurrency:
-  group: dependency-guard-${{ github.event.pull_request.number }}
-  cancel-in-progress: true
-
-jobs:
-  dependency-guard-detect:
-    if: ${{ !github.event.pull_request.draft }}
-    runs-on: ubuntu-24.04
-    timeout-minutes: 5
-    outputs:
-      autoscrub: ${{ steps.guard.outputs.autoscrub }}
-      autoscrub-owner: ${{ steps.guard.outputs.autoscrub-owner }}
-      autoscrub-repository: ${{ steps.guard.outputs.autoscrub-repository }}
-    steps:
-      - name: Check out trusted base workflow scripts
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          ref: ${{ github.event.pull_request.base.sha }}
-          persist-credentials: false
-
-      - name: Detect dependency changes
-        id: guard
-        env:
-          GITHUB_TOKEN: ${{ github.token }}
-          OPENCLAW_DEPENDENCY_GUARD_MODE: detect
-          OPENCLAW_SECURITY_APPROVERS: vincentkoc,steipete,joshavant
-          OPENCLAW_SECURITY_TEAM_SLUG: openclaw-secops
-        run: node scripts/github/dependency-guard.mjs
-
-  dependency-guard-autoscrub:
-    if: ${{ !github.event.pull_request.draft && needs.dependency-guard-detect.outputs.autoscrub == 'true' }}
-    needs: dependency-guard-detect
-    runs-on: ubuntu-24.04
-    timeout-minutes: 5
-    permissions:
-      contents: read
-      issues: write
-      pull-requests: read
-    steps:
-      - name: Check out trusted base workflow scripts
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          ref: ${{ github.event.pull_request.base.sha }}
-          persist-credentials: false
-
-      - name: Create autoscrub app token
-        id: app-token
-        continue-on-error: true
-        uses: actions/create-github-app-token@1b10c78c7865c340bc4f6099eb2f838309f1e8c3 # v3.1.1
-        with:
-          app-id: "2729701"
-          private-key: ${{ secrets.GH_APP_PRIVATE_KEY }}
-          owner: ${{ needs.dependency-guard-detect.outputs.autoscrub-owner }}
-          repositories: ${{ needs.dependency-guard-detect.outputs.autoscrub-repository }}
-          permission-contents: write
-
-      - name: Create fallback autoscrub app token
-        id: app-token-fallback
-        continue-on-error: true
-        if: steps.app-token.outcome == 'failure'
-        uses: actions/create-github-app-token@1b10c78c7865c340bc4f6099eb2f838309f1e8c3 # v3.1.1
-        with:
-          app-id: "2971289"
-          private-key: ${{ secrets.GH_APP_PRIVATE_KEY_FALLBACK }}
-          owner: ${{ needs.dependency-guard-detect.outputs.autoscrub-owner }}
-          repositories: ${{ needs.dependency-guard-detect.outputs.autoscrub-repository }}
-          permission-contents: write
-
-      - name: Remove package lockfile changes
-        env:
-          GITHUB_TOKEN: ${{ github.token }}
-          OPENCLAW_DEPENDENCY_GUARD_AUTOSCRUB_TOKEN: ${{ steps.app-token.outputs.token || steps.app-token-fallback.outputs.token }}
-          OPENCLAW_DEPENDENCY_GUARD_MODE: autoscrub
-          OPENCLAW_SECURITY_APPROVERS: vincentkoc,steipete,joshavant
-          OPENCLAW_SECURITY_TEAM_SLUG: openclaw-secops
-        run: node scripts/github/dependency-guard.mjs
-
-  dependency-guard:
-    if: ${{ !github.event.pull_request.draft && always() }}
-    needs:
-      - dependency-guard-detect
-      - dependency-guard-autoscrub
-    runs-on: ubuntu-24.04
-    timeout-minutes: 5
-    steps:
-      - name: Check out trusted base workflow scripts
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6
-        with:
-          ref: ${{ github.event.pull_request.base.sha }}
-          persist-credentials: false
-
-      - name: Enforce dependency guard
-        env:
-          GITHUB_TOKEN: ${{ github.token }}
-          OPENCLAW_DEPENDENCY_GUARD_MODE: enforce
-          OPENCLAW_SECURITY_APPROVERS: vincentkoc,steipete,joshavant
-          OPENCLAW_SECURITY_TEAM_SLUG: openclaw-secops
-        run: node scripts/github/dependency-guard.mjs

.github/workflows/docker-release.yml

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

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

@@ -58,7 +58,6 @@ on:
           - qa-parity
           - qa-live
           - npm-telegram
-          - performance
       live_suite_filter:
         description: Optional exact live/E2E suite id, or comma-separated QA live lanes such as qa-live-matrix,qa-live-telegram; blank runs all selected live suites
         required: false
@@ -80,7 +79,7 @@ on:
         default: ""
         type: string
       evidence_package_spec:
-        description: Optional published package spec to prove in the release evidence report
+        description: Optional published package spec to prove in the private release evidence report
         required: false
         default: ""
         type: string
@@ -120,6 +119,7 @@ env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   GH_REPO: ${{ github.repository }}
   NODE_VERSION: "24.15.0"
+  PNPM_VERSION: "11.0.8"
 
 jobs:
   resolve_target:
@@ -135,7 +135,7 @@ jobs:
           ref: ${{ github.ref_name }}
           path: workflow
           fetch-depth: 1
-          persist-credentials: true
+          persist-credentials: false
           submodules: false
 
       - name: Resolve target SHA
@@ -182,11 +182,6 @@ jobs:
             else
               echo "- Normal CI: skipped by rerun group"
             fi
-            if [[ "$RERUN_GROUP" == "all" || "$RERUN_GROUP" == "performance" ]]; then
-              echo "- Product performance: \`OpenClaw Performance\` with \`target_ref=${TARGET_SHA}\`"
-            else
-              echo "- Product performance: skipped by rerun group"
-            fi
             if [[ "$RERUN_GROUP" == "all" || "$RERUN_GROUP" == "plugin-prerelease" ]]; then
               echo "- Plugin prerelease: \`Plugin Prerelease\` with \`target_ref=${TARGET_SHA}\`"
             else
@@ -225,7 +220,7 @@ jobs:
           } >> "$GITHUB_STEP_SUMMARY"
 
   docker_runtime_assets_preflight:
-    name: Verify Docker runtime image assets
+    name: Verify Docker runtime-assets prune path
     needs: [resolve_target]
     if: inputs.rerun_group == 'all'
     runs-on: ubuntu-24.04
@@ -238,61 +233,18 @@ jobs:
         with:
           ref: ${{ needs.resolve_target.outputs.sha }}
           fetch-depth: 1
-          persist-credentials: true
+          persist-credentials: false
 
       - name: Verify Docker runtime-assets prune path
         env:
           DOCKER_BUILDKIT: "1"
         run: |
           set -euo pipefail
-          timeout --kill-after=30s 35m docker build \
+          timeout --foreground --kill-after=30s 35m docker build \
             --target runtime-assets \
-            --build-arg OPENCLAW_EXTENSIONS="diagnostics-otel,codex" \
+            --build-arg OPENCLAW_EXTENSIONS="matrix" \
             .
 
-      - name: Build and smoke test final Docker runtime image
-        env:
-          DOCKER_BUILDKIT: "1"
-          TARGET_SHA: ${{ needs.resolve_target.outputs.sha }}
-        run: |
-          set -euo pipefail
-          image_ref="openclaw-release-runtime-smoke:${TARGET_SHA}"
-          timeout --kill-after=30s 35m docker build \
-            --build-arg OPENCLAW_EXTENSIONS="diagnostics-otel,codex" \
-            -t "${image_ref}" \
-            .
-          docker run --rm --entrypoint /bin/sh "${image_ref}" -lc '
-            set -eu
-            test -f /app/src/agents/templates/HEARTBEAT.md
-            temp_root="$(mktemp -d)"
-            trap "rm -rf \"${temp_root}\"" EXIT
-            mkdir -p "${temp_root}/home" "${temp_root}/cwd"
-            cd "${temp_root}/cwd"
-            set +e
-            HOME="${temp_root}/home" \
-            USERPROFILE="${temp_root}/home" \
-            OPENCLAW_HOME="${temp_root}/home" \
-            OPENCLAW_NO_ONBOARD=1 \
-            OPENCLAW_SUPPRESS_NOTES=1 \
-            OPENCLAW_DISABLE_BUNDLED_PLUGINS=1 \
-            OPENCLAW_DISABLE_BUNDLED_ENTRY_SOURCE_FALLBACK=1 \
-            AWS_EC2_METADATA_DISABLED=true \
-            AWS_SHARED_CREDENTIALS_FILE="${temp_root}/home/.aws/credentials" \
-            AWS_CONFIG_FILE="${temp_root}/home/.aws/config" \
-              node /app/openclaw.mjs agent --message "workspace bootstrap smoke" --session-id "workspace-bootstrap-smoke" --local --timeout 1 --json \
-              >"${temp_root}/out.log" 2>&1
-            status="$?"
-            set -e
-            if grep -F "Missing workspace template:" "${temp_root}/out.log"; then
-              cat "${temp_root}/out.log"
-              exit 1
-            fi
-            test -f "${temp_root}/home/.openclaw/workspace/HEARTBEAT.md"
-            if [ "${status}" -ne 0 ]; then
-              cat "${temp_root}/out.log"
-            fi
-          '
-
   normal_ci:
     name: Run normal full CI
     needs: [resolve_target, docker_runtime_assets_preflight]
@@ -319,31 +271,9 @@ jobs:
             shift
 
             local before_json dispatch_output run_id status conclusion url poll_count
-            gh_with_retry() {
-              local output status attempt
-              for attempt in 1 2 3 4 5 6; do
-                set +e
-                output="$(gh "$@" 2>&1)"
-                status=$?
-                set -e
-                if [[ "$status" -eq 0 ]]; then
-                  printf '%s\n' "$output"
-                  return 0
-                fi
-                if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
-                  echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
-                  sleep $((attempt * 10))
-                  continue
-                fi
-                printf '%s\n' "$output" >&2
-                return "$status"
-              done
-              printf '%s\n' "$output" >&2
-              return "$status"
-            }
-            before_json="$(gh_with_retry run list --workflow "$workflow" --event workflow_dispatch --limit 100 --json databaseId --jq '[.[].databaseId]')"
+            before_json="$(gh run list --workflow "$workflow" --event workflow_dispatch --limit 100 --json databaseId --jq '[.[].databaseId]')"
 
-            dispatch_output="$(gh_with_retry workflow run "$workflow" --ref "$CHILD_WORKFLOW_REF" "$@")"
+            dispatch_output="$(gh workflow run "$workflow" --ref "$CHILD_WORKFLOW_REF" "$@" 2>&1)"
             printf '%s\n' "$dispatch_output"
             run_id="$(
               printf '%s\n' "$dispatch_output" |
@@ -354,7 +284,7 @@ jobs:
             if [[ -z "$run_id" ]]; then
               for _ in $(seq 1 60); do
                 run_id="$(
-                  BEFORE_IDS="$before_json" gh_with_retry run list --workflow "$workflow" --event workflow_dispatch --limit 50 --json databaseId,createdAt \
+                  BEFORE_IDS="$before_json" gh run list --workflow "$workflow" --event workflow_dispatch --limit 50 --json databaseId,createdAt \
                     --jq 'map(select(.databaseId as $id | (env.BEFORE_IDS | fromjson | index($id) | not))) | sort_by(.createdAt) | reverse | .[0].databaseId // empty'
                 )"
                 if [[ -n "$run_id" ]]; then
@@ -372,14 +302,6 @@ jobs:
             echo "Dispatched ${workflow}: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
             echo "run_id=${run_id}" >> "$GITHUB_OUTPUT"
 
-            fetch_child_run_json() {
-              gh_with_retry api "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
-            }
-
-            fetch_child_jobs() {
-              gh_with_retry api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/jobs?per_page=100" --jq '.jobs[]'
-            }
-
             cancel_child() {
               if [[ -n "${run_id:-}" ]]; then
                 echo "Cancelling child workflow ${workflow}: ${run_id}" >&2
@@ -390,26 +312,26 @@ jobs:
 
             poll_count=0
             while true; do
-              status="$(fetch_child_run_json | jq -r '.status')"
+              status="$(gh run view "$run_id" --json status --jq '.status')"
               if [[ "$status" == "completed" ]]; then
                 break
               fi
               poll_count=$((poll_count + 1))
               if (( poll_count % 10 == 0 )); then
                 echo "Still waiting on ${workflow}: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
-                fetch_child_jobs | jq 'select(.status != "completed") | {name, status, url: .html_url}' || true
+                gh run view "$run_id" --json jobs --jq '.jobs[] | select(.status != "completed") | {name, status, url}' || true
               fi
               sleep 30
             done
             trap - EXIT INT TERM
 
-            conclusion="$(fetch_child_run_json | jq -r '.conclusion // ""')"
-            url="$(fetch_child_run_json | jq -r '.html_url')"
+            conclusion="$(gh run view "$run_id" --json conclusion --jq '.conclusion')"
+            url="$(gh run view "$run_id" --json url --jq '.url')"
             echo "${workflow} finished with ${conclusion}: ${url}"
             echo "url=${url}" >> "$GITHUB_OUTPUT"
             echo "conclusion=${conclusion}" >> "$GITHUB_OUTPUT"
             if [[ "$conclusion" != "success" ]]; then
-              fetch_child_jobs | jq 'select(.conclusion != "success" and .conclusion != "skipped") | {name, conclusion, url: .html_url}' || true
+              gh run view "$run_id" --json jobs --jq '.jobs[] | select(.conclusion != "success" and .conclusion != "skipped") | {name, conclusion, url}' || true
               exit 1
             fi
           }
@@ -449,31 +371,9 @@ jobs:
             shift
 
             local before_json dispatch_output run_id status conclusion url poll_count
-            gh_with_retry() {
-              local output status attempt
-              for attempt in 1 2 3 4 5 6; do
-                set +e
-                output="$(gh "$@" 2>&1)"
-                status=$?
-                set -e
-                if [[ "$status" -eq 0 ]]; then
-                  printf '%s\n' "$output"
-                  return 0
-                fi
-                if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
-                  echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
-                  sleep $((attempt * 10))
-                  continue
-                fi
-                printf '%s\n' "$output" >&2
-                return "$status"
-              done
-              printf '%s\n' "$output" >&2
-              return "$status"
-            }
-            before_json="$(gh_with_retry run list --workflow "$workflow" --event workflow_dispatch --limit 100 --json databaseId --jq '[.[].databaseId]')"
+            before_json="$(gh run list --workflow "$workflow" --event workflow_dispatch --limit 100 --json databaseId --jq '[.[].databaseId]')"
 
-            dispatch_output="$(gh_with_retry workflow run "$workflow" --ref "$CHILD_WORKFLOW_REF" "$@")"
+            dispatch_output="$(gh workflow run "$workflow" --ref "$CHILD_WORKFLOW_REF" "$@" 2>&1)"
             printf '%s\n' "$dispatch_output"
             run_id="$(
               printf '%s\n' "$dispatch_output" |
@@ -484,7 +384,7 @@ jobs:
             if [[ -z "$run_id" ]]; then
               for _ in $(seq 1 60); do
                 run_id="$(
-                  BEFORE_IDS="$before_json" gh_with_retry run list --workflow "$workflow" --event workflow_dispatch --limit 50 --json databaseId,createdAt \
+                  BEFORE_IDS="$before_json" gh run list --workflow "$workflow" --event workflow_dispatch --limit 50 --json databaseId,createdAt \
                     --jq 'map(select(.databaseId as $id | (env.BEFORE_IDS | fromjson | index($id) | not))) | sort_by(.createdAt) | reverse | .[0].databaseId // empty'
                 )"
                 if [[ -n "$run_id" ]]; then
@@ -502,14 +402,6 @@ jobs:
             echo "Dispatched ${workflow}: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
             echo "run_id=${run_id}" >> "$GITHUB_OUTPUT"
 
-            fetch_child_run_json() {
-              gh_with_retry api "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
-            }
-
-            fetch_child_jobs() {
-              gh_with_retry api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/jobs?per_page=100" --jq '.jobs[]'
-            }
-
             cancel_child() {
               if [[ -n "${run_id:-}" ]]; then
                 echo "Cancelling child workflow ${workflow}: ${run_id}" >&2
@@ -520,26 +412,26 @@ jobs:
 
             poll_count=0
             while true; do
-              status="$(fetch_child_run_json | jq -r '.status')"
+              status="$(gh run view "$run_id" --json status --jq '.status')"
               if [[ "$status" == "completed" ]]; then
                 break
               fi
               poll_count=$((poll_count + 1))
               if (( poll_count % 10 == 0 )); then
                 echo "Still waiting on ${workflow}: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
-                fetch_child_jobs | jq 'select(.status != "completed") | {name, status, url: .html_url}' || true
+                gh run view "$run_id" --json jobs --jq '.jobs[] | select(.status != "completed") | {name, status, url}' || true
               fi
               sleep 30
             done
             trap - EXIT INT TERM
 
-            conclusion="$(fetch_child_run_json | jq -r '.conclusion // ""')"
-            url="$(fetch_child_run_json | jq -r '.html_url')"
+            conclusion="$(gh run view "$run_id" --json conclusion --jq '.conclusion')"
+            url="$(gh run view "$run_id" --json url --jq '.url')"
             echo "${workflow} finished with ${conclusion}: ${url}"
             echo "url=${url}" >> "$GITHUB_OUTPUT"
             echo "conclusion=${conclusion}" >> "$GITHUB_OUTPUT"
             if [[ "$conclusion" != "success" ]]; then
-              fetch_child_jobs | jq 'select(.conclusion != "success" and .conclusion != "skipped") | {name, conclusion, url: .html_url}' || true
+              gh run view "$run_id" --json jobs --jq '.jobs[] | select(.conclusion != "success" and .conclusion != "skipped") | {name, conclusion, url}' || true
               exit 1
             fi
           }
@@ -588,32 +480,10 @@ jobs:
             local workflow="$1"
             shift
 
-            local before_json dispatch_output run_id status conclusion url poll_count run_json
-            gh_with_retry() {
-              local output status attempt
-              for attempt in 1 2 3 4 5 6; do
-                set +e
-                output="$(gh "$@" 2>&1)"
-                status=$?
-                set -e
-                if [[ "$status" -eq 0 ]]; then
-                  printf '%s\n' "$output"
-                  return 0
-                fi
-                if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
-                  echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
-                  sleep $((attempt * 10))
-                  continue
-                fi
-                printf '%s\n' "$output" >&2
-                return "$status"
-              done
-              printf '%s\n' "$output" >&2
-              return "$status"
-            }
-            before_json="$(gh_with_retry run list --workflow "$workflow" --event workflow_dispatch --limit 100 --json databaseId --jq '[.[].databaseId]')"
+            local before_json dispatch_output run_id status conclusion url poll_count
+            before_json="$(gh run list --workflow "$workflow" --event workflow_dispatch --limit 100 --json databaseId --jq '[.[].databaseId]')"
 
-            dispatch_output="$(gh_with_retry workflow run "$workflow" --ref "$CHILD_WORKFLOW_REF" "$@")"
+            dispatch_output="$(gh workflow run "$workflow" --ref "$CHILD_WORKFLOW_REF" "$@" 2>&1)"
             printf '%s\n' "$dispatch_output"
             run_id="$(
               printf '%s\n' "$dispatch_output" |
@@ -624,7 +494,7 @@ jobs:
             if [[ -z "$run_id" ]]; then
               for _ in $(seq 1 60); do
                 run_id="$(
-                  BEFORE_IDS="$before_json" gh_with_retry run list --workflow "$workflow" --event workflow_dispatch --limit 50 --json databaseId,createdAt \
+                  BEFORE_IDS="$before_json" gh run list --workflow "$workflow" --event workflow_dispatch --limit 50 --json databaseId,createdAt \
                     --jq 'map(select(.databaseId as $id | (env.BEFORE_IDS | fromjson | index($id) | not))) | sort_by(.createdAt) | reverse | .[0].databaseId // empty'
                 )"
                 if [[ -n "$run_id" ]]; then
@@ -642,54 +512,6 @@ jobs:
             echo "Dispatched ${workflow}: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
             echo "run_id=${run_id}" >> "$GITHUB_OUTPUT"
 
-            fetch_child_run_json() {
-              gh_with_retry api "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
-            }
-
-            fetch_child_jobs() {
-              gh_with_retry api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/jobs?per_page=100" --jq '.jobs[]'
-            }
-
-            release_check_blocking_job() {
-              case "$1" in
-                "resolve_target" | \
-                "Prepare release package artifact" | \
-                "install_smoke_release_checks / "* | \
-                "Run package acceptance" | \
-                "Run package acceptance / "*)
-                  return 0
-                  ;;
-              esac
-              return 1
-            }
-
-            release_checks_advisory_only() {
-              local run_json="$1"
-              local verifier_conclusion name saw_advisory failed
-
-              verifier_conclusion="$(
-                jq -r '.jobs[] | select(.name == "Verify release checks") | .conclusion' <<< "$run_json" |
-                  tail -n 1
-              )"
-              if [[ "$verifier_conclusion" != "success" ]]; then
-                return 1
-              fi
-
-              saw_advisory=0
-              failed=0
-              while IFS= read -r name; do
-                [[ -z "${name// }" ]] && continue
-                if release_check_blocking_job "$name"; then
-                  echo "::error::${name} is a package-safety Tideclaw alpha release-check lane."
-                  failed=1
-                else
-                  saw_advisory=1
-                fi
-              done < <(jq -r '.jobs[] | select(.conclusion != "success" and .conclusion != "skipped") | .name' <<< "$run_json")
-
-              [[ "$saw_advisory" == "1" && "$failed" == "0" ]]
-            }
-
             cancel_child() {
               if [[ -n "${run_id:-}" ]]; then
                 echo "Cancelling child workflow ${workflow}: ${run_id}" >&2
@@ -700,38 +522,26 @@ jobs:
 
             poll_count=0
             while true; do
-              status="$(fetch_child_run_json | jq -r '.status')"
+              status="$(gh run view "$run_id" --json status --jq '.status')"
               if [[ "$status" == "completed" ]]; then
                 break
               fi
               poll_count=$((poll_count + 1))
               if (( poll_count % 10 == 0 )); then
                 echo "Still waiting on ${workflow}: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
-                fetch_child_jobs | jq 'select(.status != "completed") | {name, status, url: .html_url}' || true
+                gh run view "$run_id" --json jobs --jq '.jobs[] | select(.status != "completed") | {name, status, url}' || true
               fi
               sleep 30
             done
             trap - EXIT INT TERM
 
-            jobs_json="$(fetch_child_jobs | jq -s '{jobs: [.[] | {name, conclusion, url: .html_url}]}')"
-            run_json="$(
-              jq -s '.[0] + .[1]' \
-                <(fetch_child_run_json | jq '{conclusion: (.conclusion // ""), url: .html_url}') \
-                <(printf '%s\n' "$jobs_json")
-            )"
-            conclusion="$(jq -r '.conclusion' <<< "$run_json")"
-            url="$(jq -r '.url' <<< "$run_json")"
+            conclusion="$(gh run view "$run_id" --json conclusion --jq '.conclusion')"
+            url="$(gh run view "$run_id" --json url --jq '.url')"
             echo "${workflow} finished with ${conclusion}: ${url}"
             echo "url=${url}" >> "$GITHUB_OUTPUT"
             echo "conclusion=${conclusion}" >> "$GITHUB_OUTPUT"
             if [[ "$conclusion" != "success" ]]; then
-              jq '.jobs[] | select(.conclusion != "success" and .conclusion != "skipped") | {name, conclusion, url}' <<< "$run_json" || true
-              if [[ "$workflow" == "openclaw-release-checks.yml" && "$CHILD_WORKFLOW_REF" =~ ^tideclaw/alpha/[0-9]{4}-[0-9]{2}-[0-9]{2}-[0-9]{4}Z$ ]]; then
-                if release_checks_advisory_only "$run_json"; then
-                  echo "::warning::${workflow} ended with ${conclusion}, but Verify release checks accepted Tideclaw alpha advisory lanes."
-                  return 0
-                fi
-              fi
+              gh run view "$run_id" --json jobs --jq '.jobs[] | select(.conclusion != "success" and .conclusion != "skipped") | {name, conclusion, url}' || true
               exit 1
             fi
           }
@@ -813,7 +623,7 @@ jobs:
       - name: Checkout trusted workflow ref
         uses: actions/checkout@v6
         with:
-          persist-credentials: true
+          persist-credentials: false
           ref: ${{ github.ref_name }}
           fetch-depth: 0
 
@@ -825,6 +635,7 @@ jobs:
         uses: ./.github/actions/setup-node-env
         with:
           node-version: ${{ env.NODE_VERSION }}
+          pnpm-version: ${{ env.PNPM_VERSION }}
           install-bun: "true"
           install-deps: "false"
 
@@ -891,30 +702,7 @@ jobs:
         run: |
           set -euo pipefail
 
-          gh_with_retry() {
-            local output status attempt
-            for attempt in 1 2 3 4 5 6; do
-              set +e
-              output="$(gh "$@" 2>&1)"
-              status=$?
-              set -e
-              if [[ "$status" -eq 0 ]]; then
-                printf '%s\n' "$output"
-                return 0
-              fi
-              if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
-                echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
-                sleep $((attempt * 10))
-                continue
-              fi
-              printf '%s\n' "$output" >&2
-              return "$status"
-            done
-            printf '%s\n' "$output" >&2
-            return "$status"
-          }
-
-          before_json="$(gh_with_retry run list --workflow npm-telegram-beta-e2e.yml --event workflow_dispatch --limit 100 --json databaseId --jq '[.[].databaseId]')"
+          before_json="$(gh run list --workflow npm-telegram-beta-e2e.yml --event workflow_dispatch --limit 100 --json databaseId --jq '[.[].databaseId]')"
 
           args=(-f package_spec="${PACKAGE_SPEC:-openclaw@beta}" -f harness_ref="$TARGET_SHA" -f provider_mode="$PROVIDER_MODE")
           if [[ -z "${PACKAGE_SPEC// }" ]]; then
@@ -932,12 +720,12 @@ jobs:
             args+=(-f scenario="$SCENARIO")
           fi
 
-          gh_with_retry workflow run npm-telegram-beta-e2e.yml --ref "$CHILD_WORKFLOW_REF" "${args[@]}"
+          gh workflow run npm-telegram-beta-e2e.yml --ref "$CHILD_WORKFLOW_REF" "${args[@]}"
 
           run_id=""
           for _ in $(seq 1 60); do
             run_id="$(
-              BEFORE_IDS="$before_json" gh_with_retry run list --workflow npm-telegram-beta-e2e.yml --event workflow_dispatch --limit 50 --json databaseId,createdAt \
+              BEFORE_IDS="$before_json" gh run list --workflow npm-telegram-beta-e2e.yml --event workflow_dispatch --limit 50 --json databaseId,createdAt \
                 --jq 'map(select(.databaseId as $id | (env.BEFORE_IDS | fromjson | index($id) | not))) | sort_by(.createdAt) | reverse | .[0].databaseId // empty'
             )"
             if [[ -n "$run_id" ]]; then
@@ -964,150 +752,32 @@ jobs:
 
           poll_count=0
           while true; do
-            status="$(gh_with_retry run view "$run_id" --json status --jq '.status')"
+            status="$(gh run view "$run_id" --json status --jq '.status')"
             if [[ "$status" == "completed" ]]; then
               break
             fi
             poll_count=$((poll_count + 1))
             if (( poll_count % 10 == 0 )); then
               echo "Still waiting on npm-telegram-beta-e2e.yml: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
-              gh_with_retry run view "$run_id" --json jobs --jq '.jobs[] | select(.status != "completed") | {name, status, url}' || true
+              gh run view "$run_id" --json jobs --jq '.jobs[] | select(.status != "completed") | {name, status, url}' || true
             fi
             sleep 30
           done
           trap - EXIT INT TERM
 
-          conclusion="$(gh_with_retry run view "$run_id" --json conclusion --jq '.conclusion')"
-          url="$(gh_with_retry run view "$run_id" --json url --jq '.url')"
+          conclusion="$(gh run view "$run_id" --json conclusion --jq '.conclusion')"
+          url="$(gh run view "$run_id" --json url --jq '.url')"
           echo "npm-telegram-beta-e2e.yml finished with ${conclusion}: ${url}"
           echo "url=${url}" >> "$GITHUB_OUTPUT"
           echo "conclusion=${conclusion}" >> "$GITHUB_OUTPUT"
           if [[ "$conclusion" != "success" ]]; then
-            gh_with_retry run view "$run_id" --json jobs --jq '.jobs[] | select(.conclusion != "success" and .conclusion != "skipped") | {name, conclusion, url}' || true
+            gh run view "$run_id" --json jobs --jq '.jobs[] | select(.conclusion != "success" and .conclusion != "skipped") | {name, conclusion, url}' || true
             exit 1
           fi
 
-  performance:
-    name: Run product performance evidence
-    needs: [resolve_target, docker_runtime_assets_preflight]
-    if: ${{ always() && needs.resolve_target.result == 'success' && contains(fromJSON('["all","performance"]'), inputs.rerun_group) && (inputs.rerun_group != 'all' || needs.docker_runtime_assets_preflight.result == 'success') }}
-    runs-on: ubuntu-24.04
-    timeout-minutes: 120
-    outputs:
-      run_id: ${{ steps.dispatch.outputs.run_id }}
-      url: ${{ steps.dispatch.outputs.url }}
-      conclusion: ${{ steps.dispatch.outputs.conclusion }}
-    steps:
-      - name: Dispatch and monitor OpenClaw Performance
-        id: dispatch
-        env:
-          GH_TOKEN: ${{ github.token }}
-          TARGET_SHA: ${{ needs.resolve_target.outputs.sha }}
-          CHILD_WORKFLOW_REF: ${{ github.ref_name }}
-        run: |
-          set -euo pipefail
-
-          gh_with_retry() {
-            local output status attempt
-            for attempt in 1 2 3 4 5 6; do
-              set +e
-              output="$(gh "$@" 2>&1)"
-              status=$?
-              set -e
-              if [[ "$status" -eq 0 ]]; then
-                printf '%s\n' "$output"
-                return 0
-              fi
-              if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
-                echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
-                sleep $((attempt * 10))
-                continue
-              fi
-              printf '%s\n' "$output" >&2
-              return "$status"
-            done
-            printf '%s\n' "$output" >&2
-            return "$status"
-          }
-
-          {
-            echo "### Product performance"
-            echo
-            echo "- Target SHA: \`${TARGET_SHA}\`"
-            echo "- Profile: \`release\`"
-            echo "- Repeat: \`3\`"
-            echo "- Deep profile: \`false\`"
-            echo "- Live OpenAI candidate: \`false\`"
-            echo "- Release impact: advisory"
-          } >> "$GITHUB_STEP_SUMMARY"
-
-          before_json="$(gh_with_retry run list --workflow openclaw-performance.yml --event workflow_dispatch --limit 100 --json databaseId --jq '[.[].databaseId]')"
-
-          gh_with_retry workflow run openclaw-performance.yml \
-            --ref "$CHILD_WORKFLOW_REF" \
-            -f target_ref="$TARGET_SHA" \
-            -f profile=release \
-            -f repeat=3 \
-            -f deep_profile=false \
-            -f live_openai_candidate=false \
-            -f fail_on_regression=false
-
-          run_id=""
-          for _ in $(seq 1 60); do
-            run_id="$(
-              BEFORE_IDS="$before_json" gh_with_retry run list --workflow openclaw-performance.yml --event workflow_dispatch --limit 50 --json databaseId,createdAt \
-                --jq 'map(select(.databaseId as $id | (env.BEFORE_IDS | fromjson | index($id) | not))) | sort_by(.createdAt) | reverse | .[0].databaseId // empty'
-            )"
-            if [[ -n "$run_id" ]]; then
-              break
-            fi
-            sleep 5
-          done
-
-          if [[ -z "$run_id" ]]; then
-            echo "::warning::Could not find dispatched run for openclaw-performance.yml."
-            exit 0
-          fi
-
-          echo "Dispatched openclaw-performance.yml: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
-          echo "run_id=${run_id}" >> "$GITHUB_OUTPUT"
-
-          cancel_child() {
-            if [[ -n "${run_id:-}" ]]; then
-              echo "Cancelling child workflow openclaw-performance.yml: ${run_id}" >&2
-              gh run cancel "$run_id" >/dev/null 2>&1 || true
-            fi
-          }
-          trap cancel_child EXIT INT TERM
-
-          poll_count=0
-          while true; do
-            status="$(gh_with_retry run view "$run_id" --json status --jq '.status')"
-            if [[ "$status" == "completed" ]]; then
-              break
-            fi
-            poll_count=$((poll_count + 1))
-            if (( poll_count % 10 == 0 )); then
-              echo "Still waiting on openclaw-performance.yml: https://github.com/${GITHUB_REPOSITORY}/actions/runs/${run_id}"
-              gh_with_retry run view "$run_id" --json jobs --jq '.jobs[] | select(.status != "completed") | {name, status, url}' || true
-            fi
-            sleep 30
-          done
-          trap - EXIT INT TERM
-
-          conclusion="$(gh_with_retry run view "$run_id" --json conclusion --jq '.conclusion')"
-          url="$(gh_with_retry run view "$run_id" --json url --jq '.url')"
-          echo "openclaw-performance.yml finished with ${conclusion}: ${url}"
-          echo "url=${url}" >> "$GITHUB_OUTPUT"
-          echo "conclusion=${conclusion}" >> "$GITHUB_OUTPUT"
-          if [[ "$conclusion" != "success" ]]; then
-            echo "::warning::OpenClaw Performance is advisory and ended with ${conclusion}: ${url}"
-            gh_with_retry run view "$run_id" --json jobs --jq '.jobs[] | select(.conclusion != "success" and .conclusion != "skipped") | {name, conclusion, url}' || true
-          fi
-
   summary:
     name: Verify full validation
-    needs: [resolve_target, docker_runtime_assets_preflight, normal_ci, plugin_prerelease, release_checks, npm_telegram, performance]
+    needs: [resolve_target, docker_runtime_assets_preflight, normal_ci, plugin_prerelease, release_checks, npm_telegram]
     if: always()
     runs-on: ubuntu-24.04
     timeout-minutes: 5
@@ -1119,12 +789,10 @@ jobs:
           PLUGIN_PRERELEASE_RUN_ID: ${{ needs.plugin_prerelease.outputs.run_id }}
           RELEASE_CHECKS_RUN_ID: ${{ needs.release_checks.outputs.run_id }}
           NPM_TELEGRAM_RUN_ID: ${{ needs.npm_telegram.outputs.run_id }}
-          PERFORMANCE_RUN_ID: ${{ needs.performance.outputs.run_id }}
           NORMAL_CI_RESULT: ${{ needs.normal_ci.result }}
           PLUGIN_PRERELEASE_RESULT: ${{ needs.plugin_prerelease.result }}
           RELEASE_CHECKS_RESULT: ${{ needs.release_checks.result }}
           NPM_TELEGRAM_RESULT: ${{ needs.npm_telegram.result }}
-          PERFORMANCE_RESULT: ${{ needs.performance.result }}
           DOCKER_RUNTIME_ASSETS_PREFLIGHT_RESULT: ${{ needs.docker_runtime_assets_preflight.result }}
           RERUN_GROUP: ${{ inputs.rerun_group }}
           TARGET_SHA: ${{ needs.resolve_target.outputs.sha }}
@@ -1132,74 +800,10 @@ jobs:
         run: |
           set -euo pipefail
 
-          gh_with_retry() {
-            local output status attempt
-            for attempt in 1 2 3 4 5 6; do
-              set +e
-              output="$(gh "$@" 2>&1)"
-              status=$?
-              set -e
-              if [[ "$status" -eq 0 ]]; then
-                printf '%s\n' "$output"
-                return 0
-              fi
-              if [[ "$output" == *"Bad credentials"* || "$output" == *"HTTP 401"* || "$output" == *"secondary rate limit"* || "$output" == *"API rate limit"* || "$output" == *"Sorry. Your account was suspended"* ]]; then
-                echo "::warning::gh $* failed on attempt ${attempt}: ${output}" >&2
-                sleep $((attempt * 10))
-                continue
-              fi
-              printf '%s\n' "$output" >&2
-              return "$status"
-            done
-            printf '%s\n' "$output" >&2
-            return "$status"
-          }
-
-          release_check_blocking_job() {
-            case "$1" in
-              "resolve_target" | \
-              "Prepare release package artifact" | \
-              "install_smoke_release_checks / "* | \
-              "Run package acceptance" | \
-              "Run package acceptance / "*)
-                return 0
-                ;;
-            esac
-            return 1
-          }
-
-          release_checks_advisory_only() {
-            local run_json="$1"
-            local verifier_conclusion name saw_advisory failed
-
-            verifier_conclusion="$(
-              jq -r '.jobs[] | select(.name == "Verify release checks") | .conclusion' <<< "$run_json" |
-                tail -n 1
-            )"
-            if [[ "$verifier_conclusion" != "success" ]]; then
-              return 1
-            fi
-
-            saw_advisory=0
-            failed=0
-            while IFS= read -r name; do
-              [[ -z "${name// }" ]] && continue
-              if release_check_blocking_job "$name"; then
-                echo "::error::${name} is a package-safety Tideclaw alpha release-check lane."
-                failed=1
-              else
-                saw_advisory=1
-              fi
-            done < <(jq -r '.jobs[] | select(.conclusion != "success" and .conclusion != "skipped") | .name' <<< "$run_json")
-
-            [[ "$saw_advisory" == "1" && "$failed" == "0" ]]
-          }
-
           check_child() {
             local label="$1"
             local run_id="$2"
             local required="$3"
-            local advisory_ok="${4:-0}"
 
             if [[ -z "${run_id// }" ]]; then
               if [[ "$required" == "0" ]]; then
@@ -1211,7 +815,7 @@ jobs:
             fi
 
             local run_json status conclusion url attempt head_sha
-            run_json="$(gh_with_retry run view "$run_id" --json status,conclusion,url,attempt,headSha,jobs)"
+            run_json="$(gh run view "$run_id" --json status,conclusion,url,attempt,headSha,jobs)"
             status="$(jq -r '.status' <<< "$run_json")"
             conclusion="$(jq -r '.conclusion' <<< "$run_json")"
             url="$(jq -r '.url' <<< "$run_json")"
@@ -1225,12 +829,6 @@ jobs:
             fi
 
             if [[ "$status" != "completed" || "$conclusion" != "success" ]]; then
-              if [[ "$advisory_ok" == "1" && "$label" == "release_checks" ]]; then
-                if release_checks_advisory_only "$run_json"; then
-                  echo "::warning::${label} child run ended with ${status}/${conclusion}, but Verify release checks accepted Tideclaw alpha advisory lanes: ${url}"
-                  return 0
-                fi
-              fi
               echo "::error::${label} child run ended with ${status}/${conclusion}: ${url}"
               jq '.jobs[] | select(.conclusion != "success" and .conclusion != "skipped") | {name, status, conclusion, url}' <<< "$run_json" || true
               return 1
@@ -1258,7 +856,7 @@ jobs:
               fi
 
               local run_json row
-              run_json="$(gh_with_retry run view "$run_id" --json status,conclusion,url,createdAt,updatedAt,headSha)"
+              run_json="$(gh run view "$run_id" --json status,conclusion,url,createdAt,updatedAt,headSha)"
               row="$(
                 jq -r --arg label "$label" '
                   def ts: fromdateiso8601;
@@ -1280,7 +878,6 @@ jobs:
             append_child_row "plugin_prerelease" "$PLUGIN_PRERELEASE_RUN_ID" "$PLUGIN_PRERELEASE_RESULT"
             append_child_row "release_checks" "$RELEASE_CHECKS_RUN_ID" "$RELEASE_CHECKS_RESULT"
             append_child_row "npm_telegram" "$NPM_TELEGRAM_RUN_ID" "$NPM_TELEGRAM_RESULT"
-            append_child_row "product_performance" "$PERFORMANCE_RUN_ID" "$PERFORMANCE_RESULT"
           }
 
           summarize_child_timing() {
@@ -1294,7 +891,7 @@ jobs:
               echo
               echo "### Slowest jobs: ${label}"
               echo
-              gh_with_retry run view "$run_id" --json jobs --jq '
+              gh run view "$run_id" --json jobs --jq '
                 def ts: fromdateiso8601;
                 "| Job | Result | Minutes |",
                 "| --- | --- | ---: |",
@@ -1311,7 +908,7 @@ jobs:
               echo
               echo "### Longest queues: ${label}"
               echo
-              gh_with_retry api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/jobs?per_page=100" --jq ".jobs[] | @json" | jq -sr '
+              gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/jobs?per_page=100" --jq ".jobs[] | @json" | jq -sr '
                 def ts: fromdateiso8601;
                 "| Job | Result | Queue minutes | Run minutes |",
                 "| --- | --- | ---: | ---: |",
@@ -1340,7 +937,7 @@ jobs:
             fi
 
             local run_json status conclusion artifacts_json
-            run_json="$(gh_with_retry run view "$run_id" --json status,conclusion,url,jobs)"
+            run_json="$(gh run view "$run_id" --json status,conclusion,url,jobs)"
             status="$(jq -r '.status' <<< "$run_json")"
             conclusion="$(jq -r '.conclusion' <<< "$run_json")"
             if [[ "$status" == "completed" && "$conclusion" == "success" ]]; then
@@ -1363,7 +960,7 @@ jobs:
               echo
               echo "Artifacts:"
               artifacts_json="$(
-                gh_with_retry api "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/artifacts?per_page=100" 2>/dev/null || true
+                gh api "repos/${GITHUB_REPOSITORY}/actions/runs/${run_id}/artifacts?per_page=100" 2>/dev/null || true
               )"
               if [[ -n "${artifacts_json// }" ]]; then
                 jq -r '
@@ -1421,8 +1018,6 @@ jobs:
 
           if [[ "$RELEASE_CHECKS_RESULT" == "skipped" && -z "${RELEASE_CHECKS_RUN_ID// }" ]]; then
             check_child "release_checks" "" "$release_checks_required" || failed=1
-          elif [[ "$CHILD_WORKFLOW_REF" =~ ^tideclaw/alpha/[0-9]{4}-[0-9]{2}-[0-9]{2}-[0-9]{4}Z$ ]]; then
-            check_child "release_checks" "$RELEASE_CHECKS_RUN_ID" 1 1 || failed=1
           else
             check_child "release_checks" "$RELEASE_CHECKS_RUN_ID" 1 || failed=1
           fi
@@ -1439,7 +1034,6 @@ jobs:
           summarize_child_timing "plugin_prerelease" "$PLUGIN_PRERELEASE_RUN_ID"
           summarize_child_timing "release_checks" "$RELEASE_CHECKS_RUN_ID"
           summarize_child_timing "npm_telegram" "$NPM_TELEGRAM_RUN_ID"
-          summarize_child_timing "product_performance" "$PERFORMANCE_RUN_ID"
 
           if [[ "$failed" != "0" ]]; then
             summarize_failed_child "normal_ci" "$NORMAL_CI_RUN_ID"
@@ -1450,9 +1044,9 @@ jobs:
 
           exit "$failed"
 
-      - name: Request release evidence update
+      - name: Request private evidence update
         env:
-          RELEASES_DISPATCH_TOKEN: ${{ secrets.OPENCLAW_RELEASES_DISPATCH_TOKEN }}
+          RELEASE_PRIVATE_DISPATCH_TOKEN: ${{ secrets.OPENCLAW_RELEASES_PRIVATE_DISPATCH_TOKEN }}
           TARGET_REF: ${{ inputs.ref }}
           PACKAGE_SPEC: ${{ inputs.evidence_package_spec || inputs.npm_telegram_package_spec }}
           GITHUB_RUN_ID_VALUE: ${{ github.run_id }}
@@ -1460,11 +1054,11 @@ jobs:
         run: |
           set -euo pipefail
           if [[ "$RELEASE_CHECKS_RESULT" == "skipped" ]]; then
-            echo "Release checks were skipped by rerun group; skipping automatic release evidence update."
+            echo "Release checks were skipped by rerun group; skipping automatic private evidence update."
             exit 0
           fi
-          if [[ -z "${RELEASES_DISPATCH_TOKEN// }" ]]; then
-            echo "OPENCLAW_RELEASES_DISPATCH_TOKEN is not configured; skipping automatic release evidence update."
+          if [[ -z "${RELEASE_PRIVATE_DISPATCH_TOKEN// }" ]]; then
+            echo "OPENCLAW_RELEASES_PRIVATE_DISPATCH_TOKEN is not configured; skipping automatic private evidence update."
             exit 0
           fi
 
@@ -1483,7 +1077,7 @@ jobs:
           fi
           release_id="$(printf '%s' "$release_id" | tr '/:@ ' '----' | tr -cd 'A-Za-z0-9._-')"
           if [[ -z "$release_id" ]]; then
-            echo "::warning::Could not derive release evidence id from target ref '${TARGET_REF}'; skipping automatic release evidence update."
+            echo "::warning::Could not derive release evidence id from target ref '${TARGET_REF}'; skipping automatic private evidence update."
             exit 0
           fi
 
@@ -1509,18 +1103,18 @@ jobs:
           if ! curl --fail-with-body \
             -X POST \
             -H "Accept: application/vnd.github+json" \
-            -H "Authorization: Bearer ${RELEASES_DISPATCH_TOKEN}" \
+            -H "Authorization: Bearer ${RELEASE_PRIVATE_DISPATCH_TOKEN}" \
             -H "X-GitHub-Api-Version: 2022-11-28" \
-            https://api.github.com/repos/openclaw/releases/dispatches \
+            https://api.github.com/repos/openclaw/releases-private/dispatches \
             -d "$payload"; then
-            echo "::warning::Automatic release evidence dispatch failed; child workflow validation remains authoritative."
+            echo "::warning::Automatic private release evidence dispatch failed; child workflow validation remains authoritative."
             {
-              echo "### Release evidence dispatch failed"
+              echo "### Private release evidence dispatch failed"
               echo
-              echo "Child workflow validation remains authoritative. Backfill durable evidence from \`openclaw/releases\`:"
+              echo "Child workflow validation remains authoritative. Backfill durable evidence from \`openclaw/releases-private\`:"
               echo
               echo "\`\`\`bash"
-              echo "gh workflow run openclaw-release-evidence-from-full-validation.yml --repo openclaw/releases --ref main -f full_validation_run_id=${GITHUB_RUN_ID_VALUE} -f release_id=${release_id} -f release_ref=${TARGET_REF} -f package_spec=${evidence_package_spec}"
+              echo "gh workflow run openclaw-release-evidence-from-full-validation.yml --repo openclaw/releases-private --ref main -f full_validation_run_id=${GITHUB_RUN_ID_VALUE} -f release_id=${release_id} -f release_ref=${TARGET_REF} -f package_spec=${evidence_package_spec}"
               echo "\`\`\`"
             } >> "$GITHUB_STEP_SUMMARY"
           fi
@@ -1537,7 +1131,6 @@ jobs:
           PLUGIN_PRERELEASE_RUN_ID: ${{ needs.plugin_prerelease.outputs.run_id }}
           RELEASE_CHECKS_RUN_ID: ${{ needs.release_checks.outputs.run_id }}
           NPM_TELEGRAM_RUN_ID: ${{ needs.npm_telegram.outputs.run_id }}
-          PERFORMANCE_RUN_ID: ${{ needs.performance.outputs.run_id }}
         run: |
           set -euo pipefail
           manifest_dir="${RUNNER_TEMP}/full-release-validation"
@@ -1556,7 +1149,6 @@ jobs:
             --arg pluginPrereleaseRunId "$PLUGIN_PRERELEASE_RUN_ID" \
             --arg releaseChecksRunId "$RELEASE_CHECKS_RUN_ID" \
             --arg npmTelegramRunId "$NPM_TELEGRAM_RUN_ID" \
-            --arg performanceRunId "$PERFORMANCE_RUN_ID" \
             '{
               version: 1,
               workflowName: $workflowName,
@@ -1572,8 +1164,7 @@ jobs:
                 normalCi: $normalCiRunId,
                 pluginPrerelease: $pluginPrereleaseRunId,
                 releaseChecks: $releaseChecksRunId,
-                npmTelegram: $npmTelegramRunId,
-                productPerformance: $performanceRunId
+                npmTelegram: $npmTelegramRunId
               }
             }' > "${manifest_dir}/full-release-validation-manifest.json"
 

.github/workflows/install-smoke.yml

@@ -109,7 +109,6 @@ 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
@@ -121,7 +120,7 @@ jobs:
       # builder stalls; an explicit buildx invocation fails closed instead.
       - name: Build root Dockerfile smoke image
         run: |
-          timeout --kill-after=30s 45m docker buildx build \
+          timeout 45m docker buildx build \
             --progress=plain \
             --load \
             --build-arg OPENCLAW_EXTENSIONS=matrix \
@@ -132,7 +131,7 @@ jobs:
 
       - name: Run root Dockerfile CLI smoke
         run: |
-          timeout --kill-after=30s 20m docker run --rm --entrypoint sh openclaw-dockerfile-smoke:local -lc '
+          docker run --rm --entrypoint sh openclaw-dockerfile-smoke:local -lc '
             which openclaw &&
             openclaw --version &&
             node -e "
@@ -143,7 +142,7 @@ jobs:
               for (const [dep, rel] of Object.entries(workspace.patchedDependencies ?? {})) {
                 const absolute = path.join(\"/app\", rel);
                 if (!fs.existsSync(absolute)) {
-                  throw new Error(\"missing patch for \" + dep + \": \" + rel);
+                  throw new Error(`missing patch for ${dep}: ${rel}`);
                 }
               }
             "
@@ -163,7 +162,7 @@ jobs:
 
       - name: Smoke test Dockerfile with matrix extension build arg
         run: |
-          timeout --kill-after=30s 20m docker run --rm --entrypoint sh openclaw-ext-smoke:local -lc '
+          docker run --rm --entrypoint sh openclaw-ext-smoke:local -lc '
             which openclaw &&
             openclaw --version &&
             node -e "
@@ -220,7 +219,6 @@ 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
@@ -235,7 +233,7 @@ jobs:
           IMAGE_REF: ${{ needs.preflight.outputs.dockerfile_image }}
         run: |
           set -euo pipefail
-          if timeout --kill-after=30s 180s docker pull "$IMAGE_REF"; then
+          if timeout 180s docker pull "$IMAGE_REF"; then
             echo "exists=true" >> "$GITHUB_OUTPUT"
             echo "Using existing root Dockerfile smoke image: \`$IMAGE_REF\`" >> "$GITHUB_STEP_SUMMARY"
           else
@@ -256,7 +254,7 @@ jobs:
         env:
           IMAGE_REF: ${{ needs.preflight.outputs.dockerfile_image }}
         run: |
-          timeout --kill-after=30s 45m docker buildx build \
+          timeout 45m docker buildx build \
             --progress=plain \
             --push \
             --build-arg OPENCLAW_EXTENSIONS=matrix \
@@ -292,7 +290,6 @@ jobs:
         uses: actions/checkout@v6
         with:
           ref: ${{ inputs.ref || github.ref }}
-          persist-credentials: false
 
       - name: Run QR package install smoke
         env:
@@ -308,7 +305,6 @@ 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
@@ -320,13 +316,13 @@ jobs:
       - name: Pull root Dockerfile smoke image
         env:
           IMAGE_REF: ${{ needs.root_dockerfile_image.outputs.image_ref }}
-        run: timeout --kill-after=30s 600s docker pull "$IMAGE_REF"
+        run: timeout 600s docker pull "$IMAGE_REF"
 
       - name: Run root Dockerfile CLI smoke
         env:
           IMAGE_REF: ${{ needs.root_dockerfile_image.outputs.image_ref }}
         run: |
-          timeout --kill-after=30s 20m docker run --rm --entrypoint sh "$IMAGE_REF" -lc '
+          docker run --rm --entrypoint sh "$IMAGE_REF" -lc '
             which openclaw &&
             openclaw --version &&
             node -e "
@@ -337,7 +333,7 @@ jobs:
               for (const [dep, rel] of Object.entries(workspace.patchedDependencies ?? {})) {
                 const absolute = path.join(\"/app\", rel);
                 if (!fs.existsSync(absolute)) {
-                  throw new Error(\"missing patch for \" + dep + \": \" + rel);
+                  throw new Error(`missing patch for ${dep}: ${rel}`);
                 }
               }
             "
@@ -359,7 +355,7 @@ jobs:
         env:
           IMAGE_REF: ${{ needs.root_dockerfile_image.outputs.image_ref }}
         run: |
-          timeout --kill-after=30s 20m docker run --rm --entrypoint sh "$IMAGE_REF" -lc '
+          docker run --rm --entrypoint sh "$IMAGE_REF" -lc '
             which openclaw &&
             openclaw --version &&
             node -e "
@@ -414,7 +410,6 @@ 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
@@ -426,7 +421,7 @@ jobs:
       - name: Pull root Dockerfile smoke image
         env:
           IMAGE_REF: ${{ needs.root_dockerfile_image.outputs.image_ref }}
-        run: timeout --kill-after=30s 600s docker pull "$IMAGE_REF"
+        run: timeout 600s docker pull "$IMAGE_REF"
 
       - name: Set up Blacksmith Docker Builder
         uses: useblacksmith/setup-docker-builder@722e97d12b1d06a961800dd6c05d79d951ad3c80 # v1
@@ -435,7 +430,7 @@ jobs:
 
       - name: Build installer smoke image
         run: |
-          timeout --kill-after=30s 20m docker buildx build \
+          timeout 20m docker buildx build \
             --progress=plain \
             --load \
             -t openclaw-install-smoke:local \
@@ -444,7 +439,7 @@ jobs:
 
       - name: Build installer non-root image
         run: |
-          timeout --kill-after=30s 20m docker buildx build \
+          timeout 20m docker buildx build \
             --progress=plain \
             --load \
             -t openclaw-install-nonroot:local \
@@ -459,10 +454,10 @@ jobs:
 
       - name: Run installer docker tests
         env:
-          OPENCLAW_INSTALL_URL: file:///tmp/openclaw-install.sh
-          OPENCLAW_INSTALL_CLI_URL: file:///tmp/openclaw-install-cli.sh
+          OPENCLAW_INSTALL_URL: https://openclaw.ai/install.sh
+          OPENCLAW_INSTALL_CLI_URL: https://openclaw.ai/install-cli.sh
           OPENCLAW_NO_ONBOARD: "1"
-          OPENCLAW_INSTALL_SMOKE_SKIP_CLI: "0"
+          OPENCLAW_INSTALL_SMOKE_SKIP_CLI: "1"
           OPENCLAW_INSTALL_SMOKE_SKIP_IMAGE_BUILD: "1"
           OPENCLAW_INSTALL_NONROOT_SKIP_IMAGE_BUILD: "1"
           OPENCLAW_INSTALL_SMOKE_SKIP_NONROOT: "0"
@@ -473,24 +468,6 @@ 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'
@@ -500,7 +477,6 @@ 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
@@ -512,7 +488,7 @@ jobs:
       - name: Pull root Dockerfile smoke image
         env:
           IMAGE_REF: ${{ needs.root_dockerfile_image.outputs.image_ref }}
-        run: timeout --kill-after=30s 600s docker pull "$IMAGE_REF"
+        run: timeout 600s docker pull "$IMAGE_REF"
 
       - name: Setup Node environment for Bun smoke
         uses: ./.github/actions/setup-node-env
@@ -539,7 +515,6 @@ 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", "npm-shrinkwrap.json", "yarn.lock", "bun.lockb"]);
+            const excludedLockfiles = new Set(["pnpm-lock.yaml", "package-lock.json", "yarn.lock", "bun.lockb"]);
             const totalChangedLines = files.reduce((total, file) => {
               const path = file.filename ?? "";
-              if (path.startsWith("docs/") || excludedLockfiles.has(path) || path.endsWith("/package-lock.json") || path.endsWith("/npm-shrinkwrap.json")) {
+              if (path.startsWith("docs/") || excludedLockfiles.has(path)) {
                 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", "npm-shrinkwrap.json", "yarn.lock", "bun.lockb"]);
+              const excludedLockfiles = new Set(["pnpm-lock.yaml", "package-lock.json", "yarn.lock", "bun.lockb"]);
               const totalChangedLines = files.reduce((total, file) => {
                 const path = file.filename ?? "";
-                if (path.startsWith("docs/") || excludedLockfiles.has(path) || path.endsWith("/package-lock.json") || path.endsWith("/npm-shrinkwrap.json")) {
+                if (path.startsWith("docs/") || excludedLockfiles.has(path)) {
                   return total;
                 }
                 return total + (file.additions ?? 0) + (file.deletions ?? 0);

.github/workflows/macos-release.yml

@@ -25,6 +25,7 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
+  PNPM_VERSION: "11.0.8"
 
 jobs:
   validate_macos_release_request:
@@ -52,6 +53,7 @@ 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
@@ -93,8 +95,8 @@ jobs:
             echo "It does not sign, notarize, or upload macOS assets."
             echo
             echo "Next step:"
-            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."
+            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."
           } >> "$GITHUB_STEP_SUMMARY"

.github/workflows/mantis-discord-smoke.yml

@@ -25,6 +25,7 @@ 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"
 
@@ -141,6 +142,7 @@ 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

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

@@ -32,6 +32,7 @@ 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"
 
@@ -254,6 +255,7 @@ 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

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

@@ -32,6 +32,7 @@ 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"
 
@@ -244,6 +245,7 @@ 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

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

@@ -17,11 +17,6 @@ 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
@@ -35,14 +30,6 @@ 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
@@ -68,6 +55,7 @@ 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
@@ -174,6 +162,7 @@ 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
@@ -240,11 +229,9 @@ 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: ${{ inputs.approval_checkpoints }}
         shell: bash
         run: |
           set -euo pipefail
@@ -265,15 +252,6 @@ jobs:
           require_var OPENCLAW_QA_CONVEX_SITE_URL
           require_var OPENCLAW_QA_CONVEX_SECRET_CI
           require_var CRABBOX_COORDINATOR_TOKEN
-          if [[ -z "${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="$(pwd)/.artifacts/qa-e2e/mantis/slack-desktop-smoke-worktrees/candidate"
           output_rel=".artifacts/qa-e2e/mantis/slack-desktop-smoke"
@@ -289,22 +267,6 @@ jobs:
           else
             keep_args=(--no-keep-lease)
           fi
-          market_args=()
-          if [[ -n "${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 \
@@ -314,7 +276,7 @@ jobs:
             --class standard \
             --idle-timeout 45m \
             --ttl 120m \
-            "${gateway_args[@]}" \
+            --gateway-setup \
             --credential-source convex \
             --credential-role ci \
             --provider-mode live-frontier \
@@ -322,9 +284,7 @@ jobs:
             --model openai/gpt-5.5 \
             --alt-model openai/gpt-5.5 \
             --fast \
-            "${scenario_args[@]}" \
-            "${approval_args[@]}" \
-            "${market_args[@]}" \
+            --scenario "$SCENARIO_ID" \
             "${keep_args[@]}" \
             "${lease_args[@]}"
           mantis_exit=$?
@@ -354,81 +314,27 @@ 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_label" \
-            --arg summary "$evidence_summary" \
-            --arg expected "$expected_result" \
-            --argjson checkpoint_artifacts "$checkpoint_artifacts" \
+            --arg scenario "$SCENARIO_ID" \
             --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: $summary,
+              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.",
               scenario: $scenario,
               comparison: {
-                candidate: { sha: $candidate_sha, expected: $expected, status: $status, fixed: ($status == "pass") },
+                candidate: { sha: $candidate_sha, expected: "Slack QA and VM gateway setup pass", 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: $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 },
+              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 },
                 { 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" },
@@ -436,7 +342,7 @@ 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"

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

@@ -45,11 +45,10 @@ 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:
@@ -225,7 +224,6 @@ jobs:
       - name: Checkout harness ref
         uses: actions/checkout@v6
         with:
-          ref: main
           persist-credentials: false
           fetch-depth: 0
 
@@ -241,6 +239,9 @@ jobs:
           set -euo pipefail
 
           git fetch --no-tags origin +refs/heads/main:refs/remotes/origin/main
+          if [[ -n "${PR_NUMBER:-}" ]]; then
+            git fetch --no-tags origin "+refs/pull/${PR_NUMBER}/head:refs/remotes/origin/pr/${PR_NUMBER}" || true
+          fi
 
           resolve_commit() {
             local input_ref="$2"
@@ -254,6 +255,7 @@ 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 ${baseline_revision}, which is not on main." >&2
             exit 1
@@ -267,11 +269,6 @@ jobs:
           pr_state="$(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
@@ -359,6 +356,7 @@ 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
@@ -426,7 +424,7 @@ jobs:
           {
             printf '%s\n' 'Defaults env_keep += "CODEX_HOME CODEX_INTERNAL_ORIGINATOR_OVERRIDE"'
             printf '%s\n' 'Defaults env_keep += "BASELINE_REF BASELINE_SHA CANDIDATE_REF CANDIDATE_SHA"'
-            printf '%s\n' 'Defaults env_keep += "CRABBOX_ACCESS_CLIENT_ID CRABBOX_ACCESS_CLIENT_SECRET CRABBOX_COORDINATOR CRABBOX_COORDINATOR_TOKEN CRABBOX_AWS_REGION CRABBOX_CAPACITY_REGIONS 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_LEASE_ID CRABBOX_PROVIDER"'
             printf '%s\n' 'Defaults env_keep += "GH_TOKEN MANTIS_CANDIDATE_TRUST MANTIS_INSTRUCTIONS MANTIS_OUTPUT_DIR MANTIS_PR_NUMBER"'
             printf '%s\n' 'Defaults env_keep += "OPENCLAW_BUILD_PRIVATE_QA OPENCLAW_ENABLE_PRIVATE_QA_CLI OPENCLAW_QA_CONVEX_SECRET_CI OPENCLAW_QA_CONVEX_SITE_URL OPENCLAW_QA_CREDENTIAL_OWNER_ID OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR_TOKEN"'
             printf '%s\n' 'Defaults env_keep += "OPENCLAW_TELEGRAM_USER_CRABBOX_BIN OPENCLAW_TELEGRAM_USER_CRABBOX_PROVIDER OPENCLAW_TELEGRAM_USER_DRIVER_SCRIPT OPENCLAW_TELEGRAM_USER_PROOF_CMD"'
@@ -455,8 +453,6 @@ 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: ${{ github.token }}
@@ -498,11 +494,8 @@ jobs:
             exit 0
           fi
           status=0
-          mapfile -d '' session_files < <(sudo find .artifacts/qa-e2e -name session.json -type f -print0)
+          mapfile -d '' session_files < <(sudo find .artifacts/qa-e2e -path '*/telegram-user-crabbox/*/session.json' -type f -print0)
           for session_file in "${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 "$lease_file" ]]; then
               continue
@@ -517,11 +510,8 @@ jobs:
               status=1
             fi
           done
-          mapfile -d '' lease_files < <(sudo find .artifacts/qa-e2e -path '*/.session/lease.json' -type f -print0)
+          mapfile -d '' lease_files < <(sudo find .artifacts/qa-e2e -path '*/telegram-user-crabbox/*/.session/lease.json' -type f -print0)
           for lease_file in "${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" \
@@ -628,6 +618,7 @@ 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

@@ -41,11 +41,10 @@ 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:
@@ -321,6 +320,7 @@ 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
@@ -377,7 +377,6 @@ jobs:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           OPENCLAW_QA_CONVEX_SITE_URL: ${{ secrets.OPENCLAW_QA_CONVEX_SITE_URL }}
           OPENCLAW_QA_CONVEX_SECRET_CI: ${{ secrets.OPENCLAW_QA_CONVEX_SECRET_CI }}
-          OPENCLAW_QA_CREDENTIAL_ACQUIRE_TIMEOUT_MS: "1800000"
           OPENCLAW_QA_REDACT_PUBLIC_METADATA: "1"
           OPENCLAW_QA_TELEGRAM_CAPTURE_CONTENT: "1"
           CRABBOX_COORDINATOR: ${{ secrets.CRABBOX_COORDINATOR }}
@@ -386,8 +385,6 @@ jobs:
           OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR_TOKEN: ${{ secrets.OPENCLAW_QA_MANTIS_CRABBOX_COORDINATOR_TOKEN }}
           CRABBOX_ACCESS_CLIENT_ID: ${{ secrets.CRABBOX_ACCESS_CLIENT_ID }}
           CRABBOX_ACCESS_CLIENT_SECRET: ${{ secrets.CRABBOX_ACCESS_CLIENT_SECRET }}
-          CRABBOX_AWS_REGION: ${{ env.CRABBOX_AWS_REGION }}
-          CRABBOX_CAPACITY_REGIONS: ${{ env.CRABBOX_CAPACITY_REGIONS }}
           CRABBOX_LEASE_ID: ${{ needs.resolve_request.outputs.lease_id }}
           CRABBOX_PROVIDER: ${{ needs.resolve_request.outputs.crabbox_provider }}
           SCENARIO_INPUT: ${{ needs.resolve_request.outputs.scenario }}

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

@@ -104,6 +104,7 @@ concurrency:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
+  PNPM_VERSION: "11.0.8"
 
 jobs:
   run_package_telegram_e2e:
@@ -146,6 +147,7 @@ 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
@@ -218,7 +220,6 @@ jobs:
           OPENCLAW_NPM_TELEGRAM_CREDENTIAL_ROLE: ci
           OPENCLAW_QA_CONVEX_SITE_URL: ${{ secrets.OPENCLAW_QA_CONVEX_SITE_URL }}
           OPENCLAW_QA_CONVEX_SECRET_CI: ${{ secrets.OPENCLAW_QA_CONVEX_SECRET_CI }}
-          OPENCLAW_QA_CREDENTIAL_ACQUIRE_TIMEOUT_MS: "1800000"
           OPENCLAW_QA_REDACT_PUBLIC_METADATA: "1"
           OPENCLAW_QA_TELEGRAM_CAPTURE_CONTENT: "1"
           INPUT_SCENARIO: ${{ inputs.scenario }}

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

@@ -193,6 +193,7 @@ 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' }}
@@ -338,7 +339,7 @@ jobs:
           ref: ${{ steps.workflow_ref.outputs.value }}
           path: workflow
           fetch-depth: 1
-          persist-credentials: true
+          persist-credentials: false
 
       - name: Checkout public source ref
         if: inputs.candidate_artifact_name == ''
@@ -348,21 +349,21 @@ jobs:
           ref: ${{ inputs.ref }}
           path: source
           fetch-depth: 0
-          persist-credentials: true
+          persist-credentials: false
           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 }}
-
-      - 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' }}
+          cache: pnpm
+          cache-dependency-path: ${{ inputs.candidate_artifact_name == '' && 'source/pnpm-lock.yaml' || 'workflow/pnpm-lock.yaml' }}
 
       - name: Ensure pnpm store cache directory exists
         run: mkdir -p "$(pnpm store path --silent)"
@@ -451,7 +452,7 @@ jobs:
           OUTPUT_DIR: ${{ runner.temp }}/openclaw-cross-os-release-checks/prepare/baseline
         run: |
           mkdir -p "${OUTPUT_DIR}"
-          timeout --preserve-status 300s npm pack --ignore-scripts --json "${BASELINE_SPEC}" --pack-destination "${OUTPUT_DIR}" > "${OUTPUT_DIR}/pack.json"
+          npm pack --ignore-scripts --json "${BASELINE_SPEC}" --pack-destination "${OUTPUT_DIR}" > "${OUTPUT_DIR}/pack.json"
 
       - name: Capture candidate metadata
         id: candidate_metadata
@@ -537,31 +538,20 @@ jobs:
           ref: ${{ needs.prepare.outputs.workflow_ref }}
           path: workflow
           fetch-depth: 1
-          persist-credentials: true
+          persist-credentials: false
+
+      - 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 }}
 
-      - 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 }}
@@ -569,38 +559,11 @@ 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: ${BASELINE_TGZ}"
-            exit 1
-          fi
-
       - name: Run cross-OS release checks
         shell: bash
         env:
@@ -651,8 +614,7 @@ jobs:
           if [[ -f "${SUMMARY_PATH}" ]]; then
             cat "${SUMMARY_PATH}" >> "$GITHUB_STEP_SUMMARY"
           else
-            mkdir -p "$(dirname "${SUMMARY_PATH}")"
-            echo "No summary generated." | tee "${SUMMARY_PATH}" >> "$GITHUB_STEP_SUMMARY"
+            echo "No summary generated." >> "$GITHUB_STEP_SUMMARY"
           fi
 
       - name: Upload release-check artifacts

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

@@ -102,11 +102,6 @@ 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
@@ -213,11 +208,6 @@ 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
@@ -229,8 +219,6 @@ on:
         required: false
       ANTHROPIC_API_TOKEN:
         required: false
-      FACTORY_API_KEY:
-        required: false
       BYTEPLUS_API_KEY:
         required: false
       CEREBRAS_API_KEY:
@@ -320,6 +308,7 @@ permissions:
 env:
   FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
   NODE_VERSION: "24.15.0"
+  PNPM_VERSION: "11.0.8"
 
 jobs:
   validate_selected_ref:
@@ -480,40 +469,11 @@ jobs:
           fi
           exit 1
 
-  plan_release_workflow_matrices:
-    needs: validate_selected_ref
-    runs-on: ubuntu-24.04
-    outputs:
-      docker_e2e_count: ${{ steps.plan.outputs.docker_e2e_count }}
-      docker_e2e_matrix: ${{ steps.plan.outputs.docker_e2e_matrix }}
-      docker_e2e_omitted_json: ${{ steps.plan.outputs.docker_e2e_omitted_json }}
-      live_models_count: ${{ steps.plan.outputs.live_models_count }}
-      live_models_matrix: ${{ steps.plan.outputs.live_models_matrix }}
-      live_models_omitted_json: ${{ steps.plan.outputs.live_models_omitted_json }}
-    steps:
-      - name: Checkout trusted release harness
-        uses: actions/checkout@v6
-        with:
-          persist-credentials: false
-          ref: ${{ github.sha }}
-          fetch-depth: 1
-
-      - name: Plan release workflow matrices
-        id: plan
-        env:
-          DOCKER_LANES: ${{ inputs.docker_lanes }}
-          INCLUDE_LIVE_SUITES: ${{ inputs.include_live_suites }}
-          INCLUDE_RELEASE_PATH_SUITES: ${{ inputs.include_release_path_suites }}
-          LIVE_MODEL_PROVIDERS: ${{ inputs.live_model_providers }}
-          LIVE_SUITE_FILTER: ${{ inputs.live_suite_filter }}
-          RELEASE_TEST_PROFILE: ${{ inputs.release_test_profile }}
-        run: node scripts/plan-release-workflow-matrix.mjs >> "$GITHUB_OUTPUT"
-
   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')
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     timeout-minutes: 20
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -531,6 +491,7 @@ 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
@@ -563,7 +524,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_repo_e2e && inputs.live_suite_filter == ''
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ inputs.release_test_profile == 'full' && 90 || 60 }}
     env:
       OPENCLAW_VITEST_MAX_WORKERS: "2"
@@ -578,6 +539,7 @@ 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
@@ -585,9 +547,6 @@ 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
 
@@ -595,7 +554,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_repo_e2e && (inputs.live_suite_filter == '' || inputs.live_suite_filter == 'openshell-e2e')
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
@@ -622,6 +581,7 @@ 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
@@ -665,22 +625,78 @@ jobs:
         run: ${{ matrix.command }}
 
   validate_docker_e2e:
-    needs: [validate_selected_ref, prepare_docker_e2e_image, plan_release_workflow_matrices]
-    if: inputs.include_release_path_suites && inputs.docker_lanes == '' && needs.plan_release_workflow_matrices.outputs.docker_e2e_count != '0'
+    needs: [validate_selected_ref, prepare_docker_e2e_image]
+    if: inputs.include_release_path_suites && inputs.docker_lanes == ''
     name: Docker E2E (${{ matrix.label }})
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
-      matrix: ${{ fromJson(needs.plan_release_workflow_matrices.outputs.docker_e2e_matrix) }}
+      matrix:
+        include:
+          - chunk_id: core
+            label: core
+            timeout_minutes: 60
+            profiles: stable full
+          - chunk_id: package-update-openai
+            label: package/update OpenAI install
+            timeout_minutes: 45
+            profiles: beta minimum stable full
+          - chunk_id: package-update-anthropic
+            label: package/update Anthropic install
+            timeout_minutes: 60
+            profiles: beta minimum stable full
+          - chunk_id: package-update-core
+            label: package/update core
+            timeout_minutes: 60
+            profiles: beta minimum stable full
+          - chunk_id: plugins-runtime-plugins
+            label: plugins/runtime plugins
+            timeout_minutes: 60
+            profiles: stable full
+          - chunk_id: plugins-runtime-services
+            label: plugins/runtime services
+            timeout_minutes: 60
+            profiles: stable full
+          - chunk_id: plugins-runtime-install-a
+            label: plugins/runtime install A
+            timeout_minutes: 60
+            profiles: stable full
+          - chunk_id: plugins-runtime-install-b
+            label: plugins/runtime install B
+            timeout_minutes: 60
+            profiles: stable full
+          - chunk_id: plugins-runtime-install-c
+            label: plugins/runtime install C
+            timeout_minutes: 60
+            profiles: stable full
+          - chunk_id: plugins-runtime-install-d
+            label: plugins/runtime install D
+            timeout_minutes: 60
+            profiles: stable full
+          - chunk_id: plugins-runtime-install-e
+            label: plugins/runtime install E
+            timeout_minutes: 60
+            profiles: stable full
+          - chunk_id: plugins-runtime-install-f
+            label: plugins/runtime install F
+            timeout_minutes: 60
+            profiles: stable full
+          - chunk_id: plugins-runtime-install-g
+            label: plugins/runtime install G
+            timeout_minutes: 60
+            profiles: stable full
+          - chunk_id: plugins-runtime-install-h
+            label: plugins/runtime install H
+            timeout_minutes: 60
+            profiles: stable full
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       OPENAI_BASE_URL: ${{ secrets.OPENAI_BASE_URL }}
       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 }}
@@ -741,7 +757,6 @@ 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
 
@@ -749,23 +764,24 @@ 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)
-        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
-        env:
-          GHCR_USERNAME: ${{ github.actor }}
-          GITHUB_TOKEN: ${{ github.token }}
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ 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
@@ -827,35 +843,15 @@ jobs:
         run: |
           set -euo pipefail
           credentials=",$CREDENTIALS,"
-          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
+            [[ -n "${OPENAI_API_KEY:-}" ]] || {
+              echo "OPENAI_API_KEY is required for selected Docker E2E lanes." >&2
+              exit 1
+            }
           fi
-          if [[ "$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
+          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
+            exit 1
           fi
 
       - name: Run Docker E2E chunk
@@ -903,7 +899,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.docker_lanes != ''
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-4vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-4vcpu-ubuntu-2404' }}
     timeout-minutes: 5
     outputs:
       groups_json: ${{ steps.groups.outputs.groups_json }}
@@ -911,7 +907,6 @@ jobs:
       - name: Checkout trusted release harness
         uses: actions/checkout@v6
         with:
-          persist-credentials: false
           ref: ${{ github.sha }}
           fetch-depth: 1
 
@@ -932,7 +927,7 @@ jobs:
     if: inputs.docker_lanes != ''
     name: Docker E2E targeted lanes (${{ matrix.group.label }})
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 60
     strategy:
       fail-fast: false
@@ -944,7 +939,6 @@ 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 }}
@@ -1003,28 +997,28 @@ 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
-        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
-        env:
-          GHCR_USERNAME: ${{ github.actor }}
-          GITHUB_TOKEN: ${{ github.token }}
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ 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
@@ -1087,35 +1081,15 @@ jobs:
         run: |
           set -euo pipefail
           credentials=",$CREDENTIALS,"
-          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
+            [[ -n "${OPENAI_API_KEY:-}" ]] || {
+              echo "OPENAI_API_KEY is required for selected Docker E2E lanes." >&2
+              exit 1
+            }
           fi
-          if [[ "$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
+          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
+            exit 1
           fi
 
       - name: Run targeted Docker E2E lanes
@@ -1164,7 +1138,7 @@ jobs:
     if: inputs.include_openwebui && !inputs.include_release_path_suites && inputs.docker_lanes == ''
     name: Docker E2E (openwebui)
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 60
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -1191,15 +1165,17 @@ jobs:
           path: .release-harness
 
       - name: Log in to GHCR for shared Docker E2E image
-        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
-        env:
-          GHCR_USERNAME: ${{ github.actor }}
-          GITHUB_TOKEN: ${{ github.token }}
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ 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
@@ -1290,7 +1266,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_release_path_suites || inputs.include_openwebui || inputs.docker_lanes != ''
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ inputs.release_test_profile == 'full' && 90 || 60 }}
     permissions:
       actions: read
@@ -1359,6 +1335,7 @@ 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
@@ -1449,10 +1426,11 @@ jobs:
 
       - name: Log in to GHCR
         if: steps.plan.outputs.needs_e2e_image == '1'
-        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
-        env:
-          GHCR_USERNAME: ${{ github.actor }}
-          GITHUB_TOKEN: ${{ github.token }}
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ github.token }}
 
       - name: Check existing shared Docker E2E images
         id: image_exists
@@ -1533,7 +1511,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_live_suites && (inputs.live_suite_filter == '' || startsWith(inputs.live_suite_filter, 'live-') || startsWith(inputs.live_suite_filter, 'docker-live-models'))
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 60
     permissions:
       contents: read
@@ -1563,10 +1541,11 @@ jobs:
           echo "Shared live-test image: \`${live_image}\`" >> "$GITHUB_STEP_SUMMARY"
 
       - name: Log in to GHCR
-        run: bash scripts/ci-docker-login-ghcr.sh
-        env:
-          GHCR_USERNAME: ${{ github.actor }}
-          GITHUB_TOKEN: ${{ github.token }}
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ github.token }}
 
       - name: Check existing shared live-test image
         id: image_exists
@@ -1603,14 +1582,42 @@ jobs:
 
   validate_live_models_docker:
     name: Docker live models (${{ matrix.provider_label }})
-    needs: [validate_selected_ref, prepare_live_test_image, plan_release_workflow_matrices]
-    if: inputs.include_live_suites && inputs.live_model_providers == '' && (inputs.live_suite_filter == '' || inputs.live_suite_filter == 'docker-live-models') && needs.plan_release_workflow_matrices.outputs.live_models_count != '0'
+    needs: [validate_selected_ref, prepare_live_test_image]
+    if: inputs.include_live_suites && inputs.live_model_providers == '' && (inputs.live_suite_filter == '' || inputs.live_suite_filter == 'docker-live-models')
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 45
     strategy:
       fail-fast: false
-      matrix: ${{ fromJson(needs.plan_release_workflow_matrices.outputs.live_models_matrix) }}
+      matrix:
+        include:
+          - provider_label: Anthropic
+            providers: anthropic
+            profiles: stable full
+          - provider_label: Google
+            providers: google
+            profiles: stable full
+          - provider_label: MiniMax
+            providers: minimax
+            profiles: stable full
+          - provider_label: OpenAI
+            providers: openai
+            profiles: beta minimum stable full
+          - provider_label: OpenCode
+            providers: opencode-go
+            profiles: full
+          - provider_label: OpenRouter
+            providers: openrouter
+            profiles: full
+          - provider_label: xAI
+            providers: xai
+            profiles: full
+          - provider_label: Z.ai
+            providers: zai
+            profiles: full
+          - provider_label: Fireworks
+            providers: fireworks
+            profiles: full
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       OPENAI_BASE_URL: ${{ secrets.OPENAI_BASE_URL }}
@@ -1672,6 +1679,7 @@ 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
@@ -1680,16 +1688,15 @@ jobs:
 
       - name: Log in to GHCR
         if: contains(matrix.profiles, inputs.release_test_profile)
-        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
-        env:
-          GHCR_USERNAME: ${{ github.actor }}
-          GITHUB_TOKEN: ${{ github.token }}
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ github.token }}
 
       - name: Validate provider credential
         if: contains(matrix.profiles, inputs.release_test_profile)
         shell: bash
-        env:
-          LIVE_MODEL_PROVIDERS: ${{ matrix.providers }}
         run: |
           set -euo pipefail
 
@@ -1706,7 +1713,7 @@ jobs:
             exit 1
           }
 
-          case "${LIVE_MODEL_PROVIDERS}" in
+          case "${{ matrix.providers }}" in
             anthropic) require_any Anthropic ANTHROPIC_API_KEY ANTHROPIC_API_KEY_OLD ANTHROPIC_API_TOKEN ;;
             google) require_any Google GEMINI_API_KEY GOOGLE_API_KEY ;;
             minimax) require_any MiniMax MINIMAX_API_KEY ;;
@@ -1717,7 +1724,7 @@ jobs:
             zai) require_any Z.ai ZAI_API_KEY Z_AI_API_KEY ;;
             fireworks) require_any Fireworks FIREWORKS_API_KEY ;;
             *)
-              echo "Unhandled live model provider shard: ${LIVE_MODEL_PROVIDERS}" >&2
+              echo "Unhandled live model provider shard: ${{ matrix.providers }}" >&2
               exit 1
               ;;
           esac
@@ -1731,7 +1738,7 @@ jobs:
     needs: [validate_selected_ref, prepare_live_test_image]
     if: inputs.include_live_suites && inputs.live_model_providers != '' && (inputs.live_suite_filter == '' || inputs.live_suite_filter == 'docker-live-models')
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: 45
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -1791,6 +1798,7 @@ 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
@@ -1803,6 +1811,7 @@ 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" ;;
@@ -1855,10 +1864,11 @@ jobs:
         run: bash scripts/ci-hydrate-live-auth.sh
 
       - name: Log in to GHCR
-        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
-        env:
-          GHCR_USERNAME: ${{ github.actor }}
-          GITHUB_TOKEN: ${{ github.token }}
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ github.token }}
 
       - name: Validate provider credentials
         shell: bash
@@ -1904,7 +1914,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_live_suites && !inputs.live_models_only && (inputs.live_suite_filter == '' || (startsWith(inputs.live_suite_filter, 'native-live-') && !startsWith(inputs.live_suite_filter, 'native-live-extensions-media') && inputs.live_suite_filter != 'native-live-extensions-a-k'))
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
@@ -1932,7 +1942,7 @@ 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_THINKING=low OPENCLAW_LIVE_GATEWAY_PROVIDERS=anthropic OPENCLAW_LIVE_GATEWAY_MODELS=anthropic/claude-opus-4-8 node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
+            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
             timeout_minutes: 30
             profile_env_only: false
             advisory: true
@@ -1940,26 +1950,26 @@ 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_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
+            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
             timeout_minutes: 30
             profile_env_only: false
             advisory: true
             profiles: full
           - suite_id: native-live-src-gateway-profiles-google
             label: Native live gateway profiles Google
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=google OPENCLAW_LIVE_GATEWAY_MODELS=google/gemini-3.1-pro-preview node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
+            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=google OPENCLAW_LIVE_GATEWAY_MODELS=google/gemini-3.1-pro-preview,google/gemini-3-flash-preview node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
             timeout_minutes: 60
             profile_env_only: false
             profiles: stable full
           - suite_id: native-live-src-gateway-profiles-minimax
             label: Native live gateway profiles MiniMax
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=minimax,minimax-portal OPENCLAW_LIVE_GATEWAY_MODELS=minimax/MiniMax-M2.7,minimax-portal/MiniMax-M2.7 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
+            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=minimax,minimax-portal OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
             timeout_minutes: 60
             profile_env_only: false
             profiles: stable full
           - suite_id: native-live-src-gateway-profiles-openai
             label: Native live gateway profiles OpenAI
-            command: OPENCLAW_LIVE_GATEWAY_THINKING=off OPENCLAW_LIVE_GATEWAY_PROVIDERS=openai OPENCLAW_LIVE_GATEWAY_MODELS=openai/gpt-5.5 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=180000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=600000 node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
+            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=openai OPENCLAW_LIVE_GATEWAY_MODELS=openai/gpt-5.5 node .release-harness/scripts/test-live-shard.mjs native-live-src-gateway-profiles
             timeout_minutes: 60
             profile_env_only: false
             profiles: beta minimum stable full
@@ -2158,6 +2168,7 @@ 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
@@ -2206,7 +2217,6 @@ 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
@@ -2226,7 +2236,7 @@ jobs:
     needs: [validate_selected_ref, prepare_live_test_image]
     if: inputs.include_live_suites && !inputs.live_models_only && (inputs.live_suite_filter == '' || startsWith(inputs.live_suite_filter, 'live-'))
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-32vcpu-ubuntu-2404' }}
     timeout-minutes: ${{ matrix.timeout_minutes }}
     strategy:
       fail-fast: false
@@ -2234,49 +2244,49 @@ jobs:
         include:
           - suite_id: live-gateway-docker
             label: Docker live gateway OpenAI
-            command: OPENCLAW_LIVE_GATEWAY_THINKING=off OPENCLAW_LIVE_GATEWAY_PROVIDERS=openai OPENCLAW_LIVE_GATEWAY_MODELS=openai/gpt-5.5 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=1 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=600000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 40
+            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="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 30
             profile_env_only: false
             profiles: beta minimum stable full
           - suite_id: live-gateway-anthropic-docker
             label: Docker live gateway Anthropic
-            command: OPENCLAW_LIVE_GATEWAY_THINKING=low OPENCLAW_LIVE_GATEWAY_PROVIDERS=anthropic OPENCLAW_LIVE_GATEWAY_MODELS=anthropic/claude-sonnet-4-6,anthropic/claude-haiku-4-5 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=600000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 40
+            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="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 30
             profile_env_only: false
             profiles: stable full
           - suite_id: live-gateway-google-docker
             label: Docker live gateway Google
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=google OPENCLAW_LIVE_GATEWAY_MODELS=google/gemini-3.1-pro-preview OPENCLAW_LIVE_GATEWAY_MAX_MODELS=1 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=180000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 40
+            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="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 30
             profile_env_only: false
             profiles: stable full
           - suite_id: live-gateway-minimax-docker
             label: Docker live gateway MiniMax
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=minimax,minimax-portal OPENCLAW_LIVE_GATEWAY_MODELS=minimax/MiniMax-M2.7,minimax-portal/MiniMax-M2.7 OPENCLAW_LIVE_GATEWAY_MAX_MODELS=1 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=180000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 40
+            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="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 30
             profile_env_only: false
             profiles: stable full
           - suite_id: live-gateway-advisory-docker-deepseek-fireworks
             suite_group: live-gateway-advisory-docker
             label: Docker live gateway advisory DeepSeek/Fireworks
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=deepseek,fireworks OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=180000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 40
+            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="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 30
             profile_env_only: false
             advisory: true
             profiles: full
           - suite_id: live-gateway-advisory-docker-opencode-openrouter
             suite_group: live-gateway-advisory-docker
             label: Docker live gateway advisory OpenCode/OpenRouter
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=opencode-go,openrouter OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=180000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 40
+            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="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 25m bash .release-harness/scripts/test-live-gateway-models-docker.sh
+            timeout_minutes: 30
             profile_env_only: false
             advisory: true
             profiles: full
           - suite_id: live-gateway-advisory-docker-xai-zai
             suite_group: live-gateway-advisory-docker
             label: Docker live gateway advisory xAI/Z.ai
-            command: OPENCLAW_LIVE_GATEWAY_PROVIDERS=xai,zai OPENCLAW_LIVE_GATEWAY_MAX_MODELS=2 OPENCLAW_LIVE_GATEWAY_STEP_TIMEOUT_MS=90000 OPENCLAW_LIVE_GATEWAY_MODEL_TIMEOUT_MS=180000 OPENCLAW_LIVE_DOCKER_REPO_ROOT="$GITHUB_WORKSPACE" timeout --foreground --kill-after=30s 35m bash .release-harness/scripts/test-live-gateway-models-docker.sh
-            timeout_minutes: 40
+            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
             profile_env_only: false
             advisory: true
             profiles: full
@@ -2376,6 +2386,7 @@ 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
@@ -2384,10 +2395,11 @@ 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-')))
-        run: bash .release-harness/scripts/ci-docker-login-ghcr.sh
-        env:
-          GHCR_USERNAME: ${{ github.actor }}
-          GITHUB_TOKEN: ${{ github.token }}
+        uses: docker/login-action@4907a6ddec9925e35a0a9e82d7399ccc52663121 # v4
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ 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-')))
@@ -2425,7 +2437,6 @@ 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
@@ -2445,7 +2456,7 @@ jobs:
     needs: validate_selected_ref
     if: inputs.include_live_suites && !inputs.live_models_only && (inputs.live_suite_filter == '' || startsWith(inputs.live_suite_filter, 'native-live-extensions-media') || inputs.live_suite_filter == 'native-live-extensions-a-k')
     continue-on-error: ${{ inputs.advisory }}
-    runs-on: ${{ inputs.use_github_hosted_runners && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
+    runs-on: ${{ github.event_name == 'workflow_call' && 'ubuntu-24.04' || 'blacksmith-8vcpu-ubuntu-2404' }}
     container:
       image: ghcr.io/openclaw/openclaw-live-media-runner:ubuntu-24.04
       credentials:
@@ -2594,6 +2605,7 @@ 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
@@ -2613,7 +2625,6 @@ 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 }}