@inetafrica/open-claudia 2.6.56 → 2.6.57

package/CHANGELOG.md

@@ -1,5 +1,8 @@
 # Changelog
 
+## v2.6.57
+- **Move the inactivity watchdog into the live runner.** Deep review found v2.6.56 put the watchdog in the legacy `bot-agent.js` monolith, but the LaunchAgent runs `bot.js`, which delegates heavy turns through `core/runner.js`. That meant the installed live path still only had the 6-hour hard timeout and could still wedge on a silent child. This release ports the watchdog to `core/runner.js`, updates activity on child stdout/stderr, terminates the process tree after `OC_TURN_IDLE_MS` of silence, suppresses the confusing partial/no-output final message, clears stuck busy state with a failsafe, and drains any queued follow-up messages instead of stranding them. Adds a static regression test that fails if the watchdog only exists in `bot-agent.js` again.
+
 ## v2.6.56
 - **Stop a single hung child from wedging the whole bot.** Agent mode is single-flight: a heavy turn spawns one child and sets a global `runningProcess` flag; while it's set, every new message is demoted to a lightweight side-chat instead of a full turn. That flag is *only* ever cleared by the child's `close`/`error` events — so a child that hangs (a wedged tool call that never returns) pins it forever. That's exactly what happened: one turn went silent, its child never exited, and from then on the bot stayed alive (health checks passed) but answered nothing of substance — every later message fell through to a side-chat that also couldn't make progress. The fix is an **inactivity watchdog** in `runClaude` (`bot-agent.js`): track `lastActivity`, bumped on every `stdout`/`stderr` chunk from the child, and inside the existing progress-update loop (which already ticks every 2–5s while a task runs) kill the child if it produces no output for longer than the idle limit — SIGTERM to the process group, SIGKILL 3s later, plus a 10s failsafe that force-clears the flag if `close` somehow never fires. The watchdog short-circuits the close handler so the user gets one clear "task stalled — stopped it, I'm responsive again, send /continue" message instead of a confusing "(no output)". Default idle limit is 10 minutes, tunable via `OC_TURN_IDLE_MS`. Deliberately scoped to the wedge only — the v2.6.55 polling fix is healthy and untouched.
 

package/core/runner.js

@@ -1067,6 +1067,17 @@ async function runClaude(prompt, cwd, replyToMsgId, opts = {}) {
   const startTime = Date.now();
   let longRunningNotified = false;
 
+  // Inactivity watchdog. The live bot runs through this modular runner
+  // (`bot.js` → `core/runner.js`), so the guard must live here, not only in
+  // the legacy monolith. `state.runningProcess` is single-flight and normally
+  // clears only on child close/error; a silent wedged child can otherwise pin it
+  // forever and leave every later message queued. Treat child stdout/stderr as
+  // liveness and stop the process group if it goes quiet past the idle limit.
+  const idleLimitMs = Math.max(60000, parseInt(config.OC_TURN_IDLE_MS || process.env.OC_TURN_IDLE_MS || "", 10) || 10 * 60 * 1000);
+  let lastActivity = Date.now();
+  let watchdogTripped = false;
+  let watchdogNotice = null;
+
   const processTimeout = setTimeout(() => {
     if (state.runningProcess === proc) {
       killProcessTree(proc.pid, "SIGTERM");
@@ -1081,8 +1092,60 @@ async function runClaude(prompt, cwd, replyToMsgId, opts = {}) {
     const interval = elapsed > 120 ? 5000 : 2000;
     state.streamInterval = setTimeout(() => chatContext.run(store, updateProgress), interval);
   };
+
+  const drainQueuedMessages = async () => {
+    if (state.messageQueue.length > 0 && state.currentSession) {
+      const drained = state.messageQueue.splice(0);
+      if (drained.length === 1) {
+        const only = drained[0];
+        await runClaude(only.prompt, state.currentSession.dir, only.replyToMsgId, only.opts);
+      } else {
+        const fmtTime = (ts) => {
+          const d = new Date(ts);
+          const hh = String(d.getHours()).padStart(2, "0");
+          const mm = String(d.getMinutes()).padStart(2, "0");
+          const ss = String(d.getSeconds()).padStart(2, "0");
+          return `${hh}:${mm}:${ss}`;
+        };
+        const numbered = drained.map((m, i) => `[${i + 1}] (${fmtTime(m.queuedAt || Date.now())}) ${m.prompt}`).join("\n\n");
+        const batched =
+          `While you were working the user sent these ${drained.length} follow-up messages (oldest first):\n\n` +
+          `${numbered}\n\n` +
+          `Treat each as a distinct follow-up request. Add them to your plan and handle them; ` +
+          `if any contradicts an earlier one, prefer the newer one and call out the conflict.`;
+        const last = drained[drained.length - 1];
+        await runClaude(batched, state.currentSession.dir, last.replyToMsgId, last.opts);
+      }
+    }
+  };
+
   const updateProgress = async () => {
     const elapsed = Math.floor((Date.now() - startTime) / 1000);
+    if (!watchdogTripped && state.runningProcess === proc && Date.now() - lastActivity > idleLimitMs) {
+      watchdogTripped = true;
+      const idleMin = Math.max(1, Math.floor((Date.now() - lastActivity) / 60000));
+      watchdogNotice = `Task stalled — no activity for ${idleMin}min, so I stopped it and I'm responsive again. Send /continue to resume, or just re-ask.`;
+      console.error(`[watchdog] child pid ${proc.pid} idle ${idleMin}min (limit ${Math.floor(idleLimitMs / 60000)}min) — killing`);
+      try { killProcessTree(proc.pid, "SIGTERM"); }
+      catch (e) { try { proc.kill("SIGTERM"); } catch (e2) {} }
+      setTimeout(() => { try { killProcessTree(proc.pid, "SIGKILL"); } catch (e) {} }, 3000);
+      setTimeout(() => chatContext.run(store, async () => {
+        if (state.runningProcess === proc) {
+          state.runningProcess = null;
+          state.preparingRun = false;
+          stopTyping();
+          clearTimeout(state.streamInterval); state.streamInterval = null;
+          clearTimeout(processTimeout);
+          state.statusMessageId = null;
+          if (settings.budget) settings.budget = null;
+          saveState();
+          await drainQueuedMessages();
+        }
+      }), 10000);
+      try { await send(watchdogNotice, { replyTo: replyToMsgId }); } catch (e) {}
+      state.statusMessageId = null;
+      return;
+    }
     try {
       if (adapter && channelId) adapter.typing(channelId).catch(() => {});
       const display = formatProgress(assistantText, toolUses, currentTool, elapsed, currentToolDetail);
@@ -1106,6 +1169,7 @@ async function runClaude(prompt, cwd, replyToMsgId, opts = {}) {
   scheduleUpdate();
 
   proc.stdout.on("data", (data) => {
+    lastActivity = Date.now();
     state.streamBuffer += data.toString();
     const events = parseStreamEvents(state.streamBuffer);
     const lastNewline = state.streamBuffer.lastIndexOf("\n");
@@ -1257,6 +1321,7 @@ async function runClaude(prompt, cwd, replyToMsgId, opts = {}) {
 
   let stderrBuffer = "";
   proc.stderr.on("data", (d) => {
+    lastActivity = Date.now();
     const chunk = d.toString();
     stderrBuffer += chunk;
     console.error("STDERR:", redactSensitive(chunk));
@@ -1269,6 +1334,15 @@ async function runClaude(prompt, cwd, replyToMsgId, opts = {}) {
     clearTimeout(state.streamInterval); state.streamInterval = null;
     clearTimeout(processTimeout);
 
+    if (watchdogTripped) {
+      const note = watchdogNotice || "Task stalled; watchdog stopped the child process.";
+      appendProjectTranscript("system-note", note, { exitCode: code, kind: "watchdog" }, state, getActiveSessionId);
+      if (settings.budget) settings.budget = null;
+      state.statusMessageId = null;
+      await drainQueuedMessages();
+      return;
+    }
+
     if (settings.backend === "claude" && isClaudeAuthErrorText(stderrBuffer)) {
       const authText = claudeAuthRecoveryMessage(stderrBuffer.trim().slice(-800));
       appendProjectTranscript("system-note", authText, { kind: "auth-error" }, state, getActiveSessionId);
@@ -1465,29 +1539,7 @@ async function runClaude(prompt, cwd, replyToMsgId, opts = {}) {
       }
     }
 
-    if (state.messageQueue.length > 0 && state.currentSession) {
-      const drained = state.messageQueue.splice(0);
-      if (drained.length === 1) {
-        const only = drained[0];
-        await runClaude(only.prompt, state.currentSession.dir, only.replyToMsgId, only.opts);
-      } else {
-        const fmtTime = (ts) => {
-          const d = new Date(ts);
-          const hh = String(d.getHours()).padStart(2, "0");
-          const mm = String(d.getMinutes()).padStart(2, "0");
-          const ss = String(d.getSeconds()).padStart(2, "0");
-          return `${hh}:${mm}:${ss}`;
-        };
-        const numbered = drained.map((m, i) => `[${i + 1}] (${fmtTime(m.queuedAt || Date.now())}) ${m.prompt}`).join("\n\n");
-        const batched =
-          `While you were working the user sent these ${drained.length} follow-up messages (oldest first):\n\n` +
-          `${numbered}\n\n` +
-          `Treat each as a distinct follow-up request. Add them to your plan and handle them; ` +
-          `if any contradicts an earlier one, prefer the newer one and call out the conflict.`;
-        const last = drained[drained.length - 1];
-        await runClaude(batched, state.currentSession.dir, last.replyToMsgId, last.opts);
-      }
-    }
+    await drainQueuedMessages();
   }));
 
   proc.on("error", (err) => chatContext.run(store, async () => {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@inetafrica/open-claudia",
-  "version": "2.6.56",
+  "version": "2.6.57",
   "description": "Your always-on AI coding assistant — Claude Code, Cursor Agent, and OpenAI Codex via Telegram or Kazee Chat",
   "main": "bot.js",
   "bin": {
@@ -9,7 +9,7 @@
   "scripts": {
     "setup": "node setup.js",
     "start": "node bot.js",
-    "test": "OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node -e \"require('./vault'); console.log('OK')\" && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-usage-accounting.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-recall-engine.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-recall-graph.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-recall-discoverer.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-project-transcripts-smoke.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-abilities.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-ability-extraction.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-ability-couse.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-ability-transfer.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-ability-tiers.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-ability-merge-guard.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-learning-e2e.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-pack-nesting.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-read-signal.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-tools.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-tool-graph.js"
+    "test": "OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node -e \"require('./vault'); console.log('OK')\" && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-runner-watchdog-static.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-usage-accounting.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-recall-engine.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-recall-graph.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-recall-discoverer.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-project-transcripts-smoke.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-abilities.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-ability-extraction.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-ability-couse.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-ability-transfer.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-ability-tiers.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-ability-merge-guard.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-learning-e2e.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-pack-nesting.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-read-signal.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-tools.js && OPEN_CLAUDIA_TEST=1 WORKSPACE=/tmp/open-claudia-test CLAUDE_PATH=node node test-tool-graph.js"
   },
   "files": [
     "bot.js",
@@ -30,6 +30,7 @@
     ".env.example",
     "README.md",
     "CHANGELOG.md",
+    "test-runner-watchdog-static.js",
     "test-usage-accounting.js",
     "test-recall-engine.js",
     "test-recall-graph.js",

package/test-runner-watchdog-static.js

@@ -0,0 +1,21 @@
+#!/usr/bin/env node
+const assert = require('assert');
+const fs = require('fs');
+const path = require('path');
+
+const root = __dirname;
+const runner = fs.readFileSync(path.join(root, 'core', 'runner.js'), 'utf8');
+const monolith = fs.readFileSync(path.join(root, 'bot-agent.js'), 'utf8');
+
+assert.match(runner, /OC_TURN_IDLE_MS/, 'live core/runner.js must read OC_TURN_IDLE_MS');
+assert.match(runner, /watchdogTripped/, 'live core/runner.js must guard close handling after watchdog trip');
+assert.match(runner, /lastActivity\s*=\s*Date\.now\(\)/, 'live core/runner.js must track last child activity');
+assert.match(runner, /proc\.stdout\.on\("data",[\s\S]{0,120}\blastActivity\s*=\s*Date\.now\(\)/, 'stdout must refresh lastActivity');
+assert.match(runner, /proc\.stderr\.on\("data",[\s\S]{0,120}\blastActivity\s*=\s*Date\.now\(\)/, 'stderr must refresh lastActivity');
+assert.match(runner, /killProcessTree\(proc\.pid,\s*"SIGTERM"\)/, 'watchdog must terminate the child process tree first');
+assert.match(runner, /killProcessTree\(proc\.pid,\s*"SIGKILL"\)/, 'watchdog must force-kill the child process tree after grace');
+assert.match(runner, /await drainQueuedMessages\(\)/, 'watchdog path must not strand queued follow-up messages');
+
+assert.match(monolith, /OC_TURN_IDLE_MS/, 'legacy bot-agent.js watchdog should remain for monolith users');
+
+console.log('runner watchdog static OK');