Merge pull request 'refactor(install): clone HarborForge.Cli to /tmp instead of fixed path' (#12) from refactor/install-cli-clone-from-repo into main

`installCli()` used to look for the CLI source at a fixed path relative
to the plugin checkout: either `./HarborForge.Cli` or `../HarborForge.Cli`.
That breaks any install layout where the plugin lives on its own — the
script just logs "Skipping CLI installation" and returns. Same anti-
pattern installManagedMonitor had already fixed for the monitor binary.

Mirror the monitor flow:

  1. git clone --depth 1 --branch <cliBranch> CLI_REPO_URL → /tmp/<dir>
  2. go build -ldflags Version=<date>+<branch>-<sha> -o $openclaw/bin/hf
  3. chmod 755 + delete tmp dir on success or failure

Adds `--cli-branch <name>` (default: main) for parity with --monitor-branch.

Also stamps the binary with a real version string (was 'dev' before this
patch) so `hf version` is informative for debugging.

plugin/index.ts

@@ -25,6 +25,25 @@ import {
   CalendarScheduler,
 } from './calendar/index.js';
 
+// ---------------------------------------------------------------------------
+// Module-scope calendar scheduler singleton.
+//
+// `register()` is called multiple times per gateway boot — once per agent
+// (we see 5 `HarborForge plugin registered` lines for 5 agents on dind-t2).
+// `gateway_start` only fires once, so before this lift the
+// `startCalendarScheduler()` setup ran inside ONE closure while four other
+// closures kept their own `calendarScheduler = null`. Whichever of the five
+// tool registrations the gateway picked at call time was effectively a coin
+// flip, and four times out of five `harborforge_calendar_status` returned
+// `Calendar scheduler not running` even though the scheduler was active.
+//
+// Keeping the singleton at module scope removes the per-`register()` shadow:
+// the scheduler is started once, every closure reads the same binding, and
+// `startCalendarScheduler()` is idempotent so duplicate `gateway_start`
+// firings are harmless.
+// ---------------------------------------------------------------------------
+let calendarScheduler: MultiAgentSchedulerHandle | CalendarScheduler | null = null;
+
 interface PluginAPI {
   logger: {
     info: (...args: any[]) => void;
@@ -54,6 +73,30 @@ interface PluginAPI {
   getAgentStatus?: () => Promise<{ status: string } | null>;
 }
 
+/**
+ * Coerce a tool execute() return value into the MCP `{ content: [...] }`
+ * shape that the openclaw Codex tool dispatcher requires.
+ *
+ * Background: openclaw's `convertToolContents()` does `result.content.reduce(...)`
+ * to compute total text length before flattening. Every HF tool here returned a
+ * bare object (`{ running, processing, currentSlot, ... }`) which has no
+ * `.content` field, so `undefined.reduce` threw and every call to
+ * `harborforge_*` from a Codex-harness agent surfaced as the cryptic
+ * `Cannot read properties of undefined (reading 'reduce')`. The fix is to
+ * wrap every tool's execute return; doing it at the `registerTool` boundary
+ * keeps each tool body unchanged.
+ */
+function ensureMcpContentShape(result: unknown): { content: Array<{ type: 'text'; text: string }> } {
+  if (
+    result && typeof result === 'object' &&
+    Array.isArray((result as { content?: unknown }).content)
+  ) {
+    return result as { content: Array<{ type: 'text'; text: string }> };
+  }
+  const text = typeof result === 'string' ? result : JSON.stringify(result, null, 2);
+  return { content: [{ type: 'text', text }] };
+}
+
 function register(api: PluginAPI): void {
     const logger = api.logger || {
       info: (...args: any[]) => console.log('[HarborForge]', ...args),
@@ -62,6 +105,22 @@ function register(api: PluginAPI): void {
       warn: (...args: any[]) => console.warn('[HarborForge]', ...args),
     };
 
+    // Wrap api.registerTool so every tool's execute() return is coerced into
+    // the MCP `{ content: [...] }` shape openclaw expects. See
+    // `ensureMcpContentShape` above.
+    const _origRegisterTool = api.registerTool.bind(api);
+    api.registerTool = (factory: (ctx: any) => any) => {
+      _origRegisterTool((ctx: any) => {
+        const def = factory(ctx);
+        if (!def || typeof def.execute !== 'function') return def;
+        const origExecute = def.execute;
+        return {
+          ...def,
+          execute: async (...args: any[]) => ensureMcpContentShape(await origExecute(...args)),
+        };
+      });
+    };
+
     function resolveConfig() {
       return getPluginConfig(api);
     }
@@ -69,7 +128,9 @@ function register(api: PluginAPI): void {
     /** Resolve agent ID from env, config, or fallback. */
     function resolveAgentId(): string {
       if (process.env.AGENT_ID) return process.env.AGENT_ID;
-      const cfg = api.runtime?.config?.loadConfig?.();
+      // Read from cached `api.config` first — see pushMetaToMonitor for why
+      // the deprecated `api.runtime?.config?.loadConfig?.()` path is heavy.
+      const cfg = (api as any).config ?? api.runtime?.config?.loadConfig?.();
       return cfg?.agents?.list?.[0]?.id ?? cfg?.agents?.defaults?.id ?? 'unknown';
     }
 
@@ -108,7 +169,7 @@ function register(api: PluginAPI): void {
         },
         openclaw: {
           version: api.runtime?.version || api.version || 'unknown',
-          pluginVersion: '0.3.2', // Bumped for PLG-CAL-004
+          pluginVersion: '0.3.4', // Bumped for PLG-CAL-004
         },
         timestamp: new Date().toISOString(),
       };
@@ -117,18 +178,33 @@ function register(api: PluginAPI): void {
     // Periodic metadata push interval handle
     let metaPushInterval: ReturnType<typeof setInterval> | null = null;
 
-    // Calendar scheduler instance.
-    //
-    // In multi-agent sync mode (the only path today) this is a
-    // {@link MultiAgentSchedulerHandle}. The legacy `CalendarScheduler` type
-    // is retained in the union for compatibility with the typed-only single-
-    // agent path that may be reintroduced later.
-    let calendarScheduler: MultiAgentSchedulerHandle | CalendarScheduler | null = null;
+    // (calendarScheduler is module-scope — see top of file for the why.
+    //  Tools and lifecycle hooks all reference the same binding so the
+    //  multi-register/single-start mismatch can't shadow them again.)
 
     /**
      * Push OpenClaw metadata to the Monitor bridge.
      * This enriches Monitor heartbeats with OpenClaw version/plugin/agent info.
      * Failures are non-fatal — Monitor continues to work without this data.
+     *
+     * IMPORTANT — read config from the cached `api.config` surface, NOT from
+     * the deprecated `api.runtime?.config?.loadConfig?.()` path. The
+     * deprecated path triggers a full plugin-metadata-snapshot rebuild on
+     * every call: realpathSync walks every plugin's package.json + manifest
+     * + source paths (lstats up the directory tree), `hashWatchedFiles`
+     * fingerprints all watched plugin files, and `discoverInDirectory`
+     * re-scans every `dist/extensions/<plugin>` dir. On t2 with ~100 plugins
+     * each rebuild costs ~6-7s of CPU; with this push firing every 30s
+     * (default reportIntervalSec) the chronic baseline was ~22-25% gateway
+     * CPU even with zero agent activity (V8 profile 2026-05-27 08:14:00 60s:
+     * lstat 44.2%, statSync 6.9%, hashWatchedFiles via memo key 1.7%, all
+     * routed through readPersistedInstalledPluginIndexInstallRecordsSync ->
+     * discoverInDirectory). Switching to `api.config` reads from the
+     * already-loaded snapshot cache; the elsewhere-in-this-file pattern was
+     * already `api.config ?? api.runtime?.config?.loadConfig?.()`.
+     *
+     * Same fix is applied to `resolveAgentId` below — that's read once at
+     * gateway start so the impact is smaller, but it's the same anti-pattern.
      */
     async function pushMetaToMonitor() {
       const bridgeClient = getBridgeClient();
@@ -136,7 +212,7 @@ function register(api: PluginAPI): void {
 
       let agentNames: string[] = [];
       try {
-        const cfg = api.runtime?.config?.loadConfig?.();
+        const cfg = (api as any).config ?? api.runtime?.config?.loadConfig?.();
         const agentsList = cfg?.agents?.list;
         if (Array.isArray(agentsList)) {
           agentNames = agentsList
@@ -147,7 +223,7 @@ function register(api: PluginAPI): void {
 
       const meta: OpenClawMeta = {
         version: api.runtime?.version || api.version || 'unknown',
-        plugin_version: '0.3.2',
+        plugin_version: '0.3.4',
         agents: agentNames.map(name => ({ name })),
       };
 
@@ -252,10 +328,22 @@ function register(api: PluginAPI): void {
           )}\n\`\`\``;
         }
 
+        // The wakeup dispatcher's `deliver` callback below only logs the
+        // reply text — it does NOT inspect any ack token. The earlier
+        // `WAKEUP_OK` first-line-ack convention was prompt-only theatre;
+        // nothing in this plugin or in openclaw acted on it. The only
+        // thing that ends a wake cycle is the slot transitioning out of
+        // `not_started`, which happens when the agent calls
+        // `harborforge_calendar_complete` or `harborforge_calendar_abort`.
+        // Tell the agent that plainly instead of asking for a fake ack.
         const wakeupMessage =
-          `You have due slots. Follow the \`hf-wakeup\` workflow of skill ` +
-          `\`hf-hangman-lab\` to proceed. Only reply \`WAKEUP_OK\` in this ` +
-          `session.${slotBlock}`;
+          `You have due slots. Drive the \`hf-wakeup\` workflow of skill ` +
+          `\`hf-hangman-lab\` to completion in this session — read slot ` +
+          `context, call the harborforge_calendar_* tools, route to the ` +
+          `right sub-workflow, and finish with harborforge_calendar_complete ` +
+          `or harborforge_calendar_abort. The scheduler keeps re-waking you ` +
+          `every 30s until the slot transitions out of \`not_started\`, so ` +
+          `partial work or silence just produces another wake.${slotBlock}`;
 
         const result = await dispatchInboundMessageWithDispatcher({
           ctx: {
@@ -291,8 +379,16 @@ function register(api: PluginAPI): void {
 
     /**
      * Initialize and start the calendar scheduler.
+     *
+     * Idempotent — `gateway_start` may fire once per `register()` invocation
+     * (the host calls `register` per agent), and we only want one set of
+     * sync/check intervals across the whole process.
      */
     function startCalendarScheduler(): void {
+      if (calendarScheduler) {
+        logger.info('Calendar scheduler already started, skipping duplicate gateway_start');
+        return;
+      }
       const live = resolveConfig();
 
       // Create bridge client (claw-instance level, not per-agent)
@@ -322,6 +418,94 @@ function register(api: PluginAPI): void {
         }
       }
 
+      // Cross-plugin exposure: agent status lookup for other plugins
+      // (currently Fabric.OpenclawPlugin uses this to skip delivering
+      // `announce` channel messages to busy agents — see DIALECTIC-V2
+      // design doc, Phase 1). Backed by calendarBridge.getAgentStatus
+      // with a small TTL cache to avoid hammering the HF backend.
+      type HfStatus = 'idle' | 'on_call' | 'busy' | 'exhausted' | 'offline';
+      const HF_STATUS_CACHE_TTL_MS = 30_000;
+      const hfStatusCache = new Map<string, { status: HfStatus; at: number }>();
+      const _G = globalThis as Record<string, unknown>;
+      _G['__hfAgentStatus'] = {
+        async get(agentId: string): Promise<HfStatus | undefined> {
+          if (!agentId) return undefined;
+          const cached = hfStatusCache.get(agentId);
+          if (cached && Date.now() - cached.at < HF_STATUS_CACHE_TTL_MS) {
+            return cached.status;
+          }
+          try {
+            const status = await calendarBridge.getAgentStatus(agentId);
+            if (status) {
+              const typed = status as HfStatus;
+              hfStatusCache.set(agentId, { status: typed, at: Date.now() });
+              return typed;
+            }
+          } catch {
+            /* fall through to cached-or-undefined */
+          }
+          return cached?.status;
+        },
+
+        /**
+         * Approximate "does agent have an on_call slot covering [from, to]?"
+         * for cross-plugin pre-check use (currently:
+         * Dialectic.OpenclawPlugin's signup HF coverage).
+         *
+         * v1 honest scope: we only have today's slots in scheduleCache
+         * (synced from /calendar/sync which is today-only). Returns:
+         *   - true  iff window is same-day AND some cached on_call slot
+         *           starts <= from AND ends >= to
+         *   - false iff window is same-day AND no such slot
+         *   - undefined for cross-day windows OR cache empty for this
+         *     agent (caller treats undefined as "I don't know" — see
+         *     Dialectic plugin's hf-precheck.ts which degrades to
+         *     "skipped" gracefully)
+         *
+         * Phase TBD: when HF backend ships a `/calendar/slots?agent&from&to`
+         * endpoint, swap this to call it for arbitrary windows. Until then,
+         * same-day-only coverage gates ~all debates created by analyze-intel
+         * (which schedules <2h windows) without needing a backend change.
+         */
+        async hasOnCallCovering(
+          agentId: string,
+          fromIso: string,
+          toIso: string,
+        ): Promise<boolean | undefined> {
+          if (!agentId || !fromIso || !toIso) return undefined;
+          const from = new Date(fromIso);
+          const to = new Date(toIso);
+          if (isNaN(from.getTime()) || isNaN(to.getTime())) return undefined;
+          if (!(from < to)) return undefined;
+          // Cross-day → cache only has today; can't decide.
+          const fromDate = from.toISOString().slice(0, 10);
+          const toDate = to.toISOString().slice(0, 10);
+          if (fromDate !== toDate) return undefined;
+          // Cache's cachedDate must match our window's date.
+          const cacheStatus = scheduleCache.getStatus();
+          if (cacheStatus.cachedDate !== fromDate) return undefined;
+          const slots = scheduleCache.getAgentSlots(agentId);
+          if (slots.length === 0) return undefined; // cache empty for this agent — can't decide
+          for (const s of slots) {
+            if (s.slot_type !== 'on_call') continue;
+            // status: ignore aborted/cancelled, accept not_started / ongoing / finished
+            if (s.status === 'aborted' || s.status === 'cancelled') continue;
+            const startStr = s.scheduled_at;
+            if (typeof startStr !== 'string') continue;
+            // scheduled_at can be HH:MM:SS (cache-relative date) or full ISO
+            const start =
+              /^\d{2}:\d{2}(:\d{2})?$/.test(startStr)
+                ? new Date(`${fromDate}T${startStr}Z`)
+                : new Date(startStr);
+            if (isNaN(start.getTime())) continue;
+            const dur = typeof s.estimated_duration === 'number' ? s.estimated_duration : 0;
+            const end = new Date(start.getTime() + dur * 60_000);
+            if (start <= from && end >= to) return true;
+          }
+          return false;
+        },
+      };
+
       // Track wakes already dispatched for a slot in the current sync
       // window — the simplified inline scheduler does not PATCH slot
       // status server-side, so without dedupe the check loop re-wakes

plugin/package.json

@@ -1,6 +1,6 @@
 {
   "name": "harbor-forge-plugin",
-  "version": "0.3.2",
+  "version": "0.3.4",
   "description": "OpenClaw plugin for HarborForge monitor bridge and CLI integration",
   "type": "module",
   "main": "dist/index.js",

scripts/install.mjs

@@ -31,6 +31,7 @@ const OLD_PLUGIN_NAME = 'harborforge-monitor';
 const PLUGIN_SRC_DIR = join(__dirname, 'plugin');
 const SKILLS_SRC_DIR = join(__dirname, 'skills');
 const MONITOR_REPO_URL = 'https://git.hangman-lab.top/zhi/HarborForge.Monitor.git';
+const CLI_REPO_URL = 'https://git.hangman-lab.top/zhi/HarborForge.Cli.git';
 
 const args = process.argv.slice(2);
 const options = {
@@ -43,6 +44,7 @@ const options = {
   installCli: args.includes('--install-cli'),
   installMonitor: 'no',
   monitorBranch: 'main',
+  cliBranch: 'main',
 };
 
 const profileIdx = args.indexOf('--openclaw-profile-path');
@@ -60,6 +62,11 @@ if (monitorBranchIdx !== -1 && args[monitorBranchIdx + 1]) {
   options.monitorBranch = String(args[monitorBranchIdx + 1]);
 }
 
+const cliBranchIdx = args.indexOf('--cli-branch');
+if (cliBranchIdx !== -1 && args[cliBranchIdx + 1]) {
+  options.cliBranch = String(args[cliBranchIdx + 1]);
+}
+
 function resolveOpenclawPath() {
   if (options.openclawProfilePath) return options.openclawProfilePath;
   if (process.env.OPENCLAW_PATH) return resolve(process.env.OPENCLAW_PATH);
@@ -316,39 +323,40 @@ async function installCli() {
   if (!options.installCli) return;
   const totalSteps = 6;
   logStep(5, totalSteps, 'Building and installing hf CLI...');
-  
+
   const openclawPath = resolveOpenclawPath();
   const binDir = join(openclawPath, 'bin');
   mkdirSync(binDir, { recursive: true });
-  
-  // Find CLI source — look for HarborForge.Cli relative to project root
-  const projectRoot = resolve(__dirname, '..');
-  const cliDir = join(projectRoot, 'HarborForge.Cli');
-  
-  if (!existsSync(cliDir)) {
-    // Try parent directory (monorepo layout)
-    const monoCliDir = resolve(projectRoot, '..', 'HarborForge.Cli');
-    if (!existsSync(monoCliDir)) {
-      logErr(`Cannot find HarborForge.Cli at ${cliDir} or ${monoCliDir}`);
-      logWarn('Skipping CLI installation');
-      return;
-    }
-  }
-  
-  const effectiveCliDir = existsSync(cliDir) 
-    ? cliDir 
-    : resolve(projectRoot, '..', 'HarborForge.Cli');
-  
-  log(` Building hf from ${effectiveCliDir}...`, 'blue');
-  
+
+  // Clone CLI repo to /tmp, build there, copy artifact out. Mirrors
+  // installManagedMonitor so the install never depends on a checked-out
+  // sibling repo at a fixed path.
+  const tmpDir = join('/tmp', `harborforge-cli-${Date.now()}`);
+  const hfBinary = join(binDir, 'hf');
+
   try {
-    const hfBinary = join(binDir, 'hf');
-    exec(`go build -o ${hfBinary} ./cmd/hf`, { cwd: effectiveCliDir, silent: !options.verbose });
+    log(` Cloning ${CLI_REPO_URL} (branch ${options.cliBranch}) → ${tmpDir}...`, 'blue');
+    exec(`git clone --branch ${shellEscape(options.cliBranch)} --depth 1 ${shellEscape(CLI_REPO_URL)} ${shellEscape(tmpDir)}`, { silent: !options.verbose });
+
+    // Stamp the binary with the version string the prod CLI surfaces in
+    // `hf version`. Fall back to a date-only label if rev-parse fails for
+    // any reason (shallow clone shouldn't, but be defensive).
+    let versionLabel = `${new Date().toISOString().slice(0, 10)}+install`;
+    try {
+      const sha = exec(`git rev-parse --short HEAD`, { cwd: tmpDir, silent: true }).trim();
+      if (sha) versionLabel = `${new Date().toISOString().slice(0, 10)}+${options.cliBranch}-${sha}`;
+    } catch { /* keep fallback */ }
+
+    log(` Building hf (version=${versionLabel})...`, 'blue');
+    const ldflags = `-X git.hangman-lab.top/zhi/HarborForge.Cli/internal/commands.Version=${versionLabel}`;
+    exec(`go build -ldflags ${shellEscape(ldflags)} -o ${shellEscape(hfBinary)} ./cmd/hf`, { cwd: tmpDir, silent: !options.verbose });
     chmodSync(hfBinary, 0o755);
-    logOk(`hf binary → ${hfBinary}`);
+    logOk(`hf binary → ${hfBinary} (branch hint: ${options.cliBranch})`);
   } catch (err) {
     logErr(`Failed to build hf CLI: ${err.message}`);
     logWarn('CLI installation failed, plugin still installed');
+  } finally {
+    rmSync(tmpDir, { recursive: true, force: true });
   }
 }