alvin-bot 4.14.1 → 4.14.2

package/CHANGELOG.md

@@ -2,6 +2,49 @@
 
 All notable changes to Alvin Bot are documented here.
 
+## [4.14.2] — 2026-04-16
+
+### 🐛 Patch: watcher zombie-entry fix (missing outputFile > 10 min = failed)
+
+**Edge case Ali caught today:** a pending async-agent entry stuck in `/subagents list` for 3+ hours showing "running" — but the underlying `alvin_dispatch_agent` subprocess had already died (its output file was gone). The entry would have continued haunting the list until the 12-hour `giveUpAt` ceiling fired.
+
+**Root cause:** `async-agent-watcher`'s `pollOnce` handled four states from `parseOutputFileStatus` — `completed` / `failed` / `running` / `missing`. For `missing` (file doesn't exist or is empty), the watcher just kept polling forever, on the assumption that a slow subprocess might eventually write. If the subprocess crashed before writing ANY output, the file never appeared, and we polled for 12 hours before timing out.
+
+**Fix:** when `status.state === "missing"` AND `now - entry.startedAt > MISSING_FILE_FAILURE_MS` (default 10 min, configurable via `ALVIN_MISSING_FILE_FAILURE_MS` env var), deliver as failed with an explicit message:
+
+> *Dispatched subprocess never wrote its output file (N m after start). Likely crashed before initializing, or the file was removed externally.*
+
+10 minutes is well above any legitimate `claude -p` startup variance (normal first-write latency is seconds) and well below the 12-hour hard ceiling.
+
+### What's preserved (regression-guard tested)
+
+- Running agents (file has content but no `end_turn`/`result` yet) are untouched by this path — they still keep polling as before.
+- Completed agents (clean `end_turn` or `stream-json result` event) still deliver normally.
+- Explicit `failed` state from the parser (if ever used) still delivers error normally.
+- v4.12.4's "file is stale but has text → deliver partial" path takes precedence over the new zombie check (the file has content, so not "missing").
+- 12-hour `giveUpAt` hard ceiling still applies as the ultimate safety net.
+- Session's `pendingBackgroundCount` decrement fires on zombie failure, same as every other delivery path.
+
+### Testing
+
+- **Baseline**: 498 tests (v4.14.1)
+- **New**: `test/watcher-zombie-fix.test.ts` — 6 tests:
+  - Young missing file (<threshold) stays pending
+  - Old missing file (>threshold) delivers failed + removes from pending
+  - Default threshold is 10 min when env var unset
+  - Running file (has content) is unaffected by zombie check
+  - Completed file delivers as completed (regression guard)
+  - Session's `pendingBackgroundCount` decrements on zombie delivery
+- **Total**: 504 tests, all green, TSC clean
+
+### Files changed
+
+- **Modified**: `src/services/async-agent-watcher.ts` (new `getMissingFileFailureMs()` + zombie branch in `pollOnce`)
+- **NEW tests**: `test/watcher-zombie-fix.test.ts`
+- **Version**: `package.json` 4.14.1 → 4.14.2
+
+---
+
 ## [4.14.1] — 2026-04-16
 
 ### 🐛 Patch: `/subagents list` now shows v4.13+ dispatch agents too

package/dist/services/async-agent-watcher.js

@@ -33,6 +33,31 @@ const POLL_INTERVAL_MS = 15_000;
  *  a timeout banner. SEO audits historically take ~13 min, so 12h
  *  is absurdly generous and protects against state-file growth. */
 const MAX_AGENT_AGE_MS = 12 * 60 * 60 * 1000;
+/**
+ * v4.14.2 — When a dispatched subprocess never creates its outputFile
+ * (spawn failure, crash before first write, file deleted externally),
+ * `parseOutputFileStatus` returns "missing" on every poll. Pre-v4.14.2
+ * that meant waiting the full 12h MAX_AGENT_AGE_MS before delivering a
+ * timeout — a 12-hour zombie in `/subagents list`.
+ *
+ * This threshold caps how long we tolerate a missing file before
+ * declaring the agent failed. `claude -p` normally writes its first
+ * JSONL line within seconds of spawn; 10 minutes is way above any
+ * legitimate startup variance and well below the 12h ceiling.
+ *
+ * Configurable via the ALVIN_MISSING_FILE_FAILURE_MS env var. Tests
+ * use shorter values via the same hook. Only the getter is exposed
+ * so callers always see the current env value, not a stale constant.
+ */
+function getMissingFileFailureMs() {
+    const raw = process.env.ALVIN_MISSING_FILE_FAILURE_MS;
+    if (raw) {
+        const n = Number(raw);
+        if (Number.isFinite(n) && n > 0)
+            return n;
+    }
+    return 10 * 60 * 1000; // default 10 min
+}
 // ── Module state ──────────────────────────────────────────────────
 const pending = new Map();
 let pollTimer = null;
@@ -139,6 +164,7 @@ export function stopWatcher() {
 export async function pollOnce() {
     const now = Date.now();
     const toRemove = [];
+    const missingFileFailureMs = getMissingFileFailureMs();
     for (const entry of pending.values()) {
         entry.lastCheckedAt = now;
         // Timeout check first — if the agent is past its giveUpAt, give up
@@ -157,7 +183,15 @@ export async function pollOnce() {
             await deliverAsFailure(entry, "error", status.error);
             toRemove.push(entry.agentId);
         }
-        // running / missing → keep polling next cycle
+        else if (status.state === "missing" &&
+            now - entry.startedAt > missingFileFailureMs) {
+            // v4.14.2 — Zombie guard: the subprocess never created its
+            // output file within `missingFileFailureMs` (default 10 min).
+            // Declare failed instead of polling until the 12h giveUpAt.
+            await deliverAsFailure(entry, "error", `Dispatched subprocess never wrote its output file (${Math.round((now - entry.startedAt) / 60_000)}m after start). Likely crashed before initializing, or the file was removed externally.`);
+            toRemove.push(entry.agentId);
+        }
+        // running / missing-but-young → keep polling next cycle
     }
     if (toRemove.length > 0) {
         for (const id of toRemove)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "alvin-bot",
-  "version": "4.14.1",
+  "version": "4.14.2",
   "description": "Alvin Bot \u2014 Your personal AI agent on Telegram, WhatsApp, Discord, Signal, and Web.",
   "type": "module",
   "main": "dist/index.js",

package/test/watcher-zombie-fix.test.ts

@@ -0,0 +1,252 @@
+/**
+ * v4.14.2 — zombie-entry fix for async-agent-watcher.
+ *
+ * Problem: when the dispatched `claude -p` subprocess never produces
+ * its outputFile (crashed before the first write, spawn failed, file
+ * got deleted externally), `parseOutputFileStatus` returns "missing"
+ * on every poll. The watcher keeps polling forever until `giveUpAt`
+ * (12 hours) fires, then delivers a timeout banner. Meanwhile the
+ * entry hangs in `/subagents list` as a permanent "running" zombie.
+ *
+ * Fix: when status is "missing" for longer than
+ * `MISSING_FILE_FAILURE_MS` (default 10 min, env-configurable), the
+ * watcher declares the agent failed with a clear "output file never
+ * appeared" reason, delivers the failure banner, and removes the
+ * entry. 10 minutes is well above normal startup variance (seconds)
+ * and well below the 12h hard ceiling.
+ *
+ * Invariants preserved:
+ *   - An agent whose output file DOES appear, even slowly, continues
+ *     normally (missing on first poll, running on second, completed
+ *     on third — same as v4.14.1).
+ *   - The `completed` path (end_turn or stream-json result) is
+ *     unchanged.
+ *   - The `failed` path (existing "error" state from parser) is
+ *     unchanged.
+ *   - The 12h giveUpAt ceiling still applies — it's now just less
+ *     likely to be hit because missing-file zombies resolve earlier.
+ */
+import { describe, it, expect, beforeEach, afterEach, vi } from "vitest";
+import fs from "fs";
+import os from "os";
+import { resolve } from "path";
+
+const TEST_DATA_DIR = resolve(
+  os.tmpdir(),
+  `alvin-zombie-${process.pid}-${Date.now()}`,
+);
+
+interface Delivered {
+  info: { name: string; status: string };
+  result: { status: string; output: string; error?: string };
+}
+let delivered: Delivered[] = [];
+
+beforeEach(async () => {
+  if (fs.existsSync(TEST_DATA_DIR)) {
+    fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
+  }
+  fs.mkdirSync(TEST_DATA_DIR, { recursive: true });
+  process.env.ALVIN_DATA_DIR = TEST_DATA_DIR;
+  // Reset the env override between tests
+  delete process.env.ALVIN_MISSING_FILE_FAILURE_MS;
+  delivered = [];
+  vi.resetModules();
+  vi.doMock("../src/services/subagent-delivery.js", () => ({
+    deliverSubAgentResult: async (info: unknown, result: unknown) => {
+      delivered.push({
+        info: info as Delivered["info"],
+        result: result as Delivered["result"],
+      });
+    },
+    attachBotApi: () => {},
+    __setBotApiForTest: () => {},
+  }));
+});
+
+afterEach(async () => {
+  try {
+    const mod = await import("../src/services/async-agent-watcher.js");
+    mod.stopWatcher();
+    mod.__resetForTest();
+  } catch {}
+  delete process.env.ALVIN_MISSING_FILE_FAILURE_MS;
+});
+
+describe("watcher zombie fix (v4.14.2)", () => {
+  it("missing file younger than threshold stays pending (no premature fail)", async () => {
+    // Threshold = 10 min. Backdate only 2 min. Expect: still pending.
+    const mod = await import("../src/services/async-agent-watcher.js");
+    mod.registerPendingAgent({
+      agentId: "young-zombie",
+      outputFile: `${TEST_DATA_DIR}/nonexistent.jsonl`,
+      description: "young",
+      prompt: "p",
+      chatId: 1,
+      userId: 1,
+      toolUseId: null,
+    });
+    // Forcibly set startedAt to 2 min ago
+    const pending = mod.listPendingAgents();
+    expect(pending).toHaveLength(1);
+    (pending[0] as { startedAt: number }).startedAt = Date.now() - 2 * 60_000;
+
+    await mod.pollOnce();
+
+    expect(delivered).toHaveLength(0);
+    expect(mod.listPendingAgents()).toHaveLength(1);
+  });
+
+  it("missing file older than threshold delivers failed + removes from pending", async () => {
+    process.env.ALVIN_MISSING_FILE_FAILURE_MS = "120000"; // 2 min for test
+    const mod = await import("../src/services/async-agent-watcher.js");
+    mod.registerPendingAgent({
+      agentId: "old-zombie",
+      outputFile: `${TEST_DATA_DIR}/never-appears.jsonl`,
+      description: "stuck crash zombie",
+      prompt: "p",
+      chatId: 1,
+      userId: 1,
+      toolUseId: null,
+    });
+    // Backdate 5 min (> 2 min threshold)
+    const pending = mod.listPendingAgents();
+    (pending[0] as { startedAt: number }).startedAt = Date.now() - 5 * 60_000;
+
+    await mod.pollOnce();
+
+    expect(delivered).toHaveLength(1);
+    expect(delivered[0].result.status).toBe("error");
+    // Error message should be explicit so user understands
+    expect(delivered[0].result.error).toMatch(/output file|never appeared|never wrote/i);
+    expect(mod.listPendingAgents()).toHaveLength(0);
+  });
+
+  it("default threshold is 10 min when env var is not set", async () => {
+    const mod = await import("../src/services/async-agent-watcher.js");
+    mod.registerPendingAgent({
+      agentId: "at-default",
+      outputFile: `${TEST_DATA_DIR}/z.jsonl`,
+      description: "default threshold",
+      prompt: "p",
+      chatId: 1,
+      userId: 1,
+      toolUseId: null,
+    });
+    // Backdate 9 min — still under the 10-min default, should stay pending
+    let p = mod.listPendingAgents();
+    (p[0] as { startedAt: number }).startedAt = Date.now() - 9 * 60_000;
+    await mod.pollOnce();
+    expect(delivered).toHaveLength(0);
+    expect(mod.listPendingAgents()).toHaveLength(1);
+
+    // Backdate to 11 min — over threshold, should fire
+    p = mod.listPendingAgents();
+    (p[0] as { startedAt: number }).startedAt = Date.now() - 11 * 60_000;
+    await mod.pollOnce();
+    expect(delivered).toHaveLength(1);
+  });
+
+  it("running file (has content, no end_turn) is unaffected by zombie check", async () => {
+    // A file WITH content should never trigger the missing-file path
+    // regardless of age.
+    const outPath = `${TEST_DATA_DIR}/running.jsonl`;
+    fs.writeFileSync(
+      outPath,
+      JSON.stringify({
+        type: "assistant",
+        isSidechain: true,
+        agentId: "x",
+        message: {
+          role: "assistant",
+          content: [{ type: "tool_use", name: "Bash", input: {} }],
+          stop_reason: "tool_use",
+        },
+      }) + "\n",
+      "utf-8",
+    );
+    const mod = await import("../src/services/async-agent-watcher.js");
+    mod.registerPendingAgent({
+      agentId: "active-work",
+      outputFile: outPath,
+      description: "legitimately running",
+      prompt: "p",
+      chatId: 1,
+      userId: 1,
+      toolUseId: null,
+    });
+    const p = mod.listPendingAgents();
+    (p[0] as { startedAt: number }).startedAt = Date.now() - 30 * 60_000; // 30 min old
+
+    await mod.pollOnce();
+
+    // v4.12.4 staleness detection COULD fire here because the file has
+    // text content and is stale. That's a different (benign) path — the
+    // agent gets delivered as "completed with partial output". Either
+    // way, the zombie-fix error path must NOT fire.
+    const anyZombieError = delivered.some(
+      (d) => d.result.error && /output file never/i.test(d.result.error),
+    );
+    expect(anyZombieError).toBe(false);
+  });
+
+  it("completed file delivers as completed (unchanged)", async () => {
+    const outPath = `${TEST_DATA_DIR}/done.jsonl`;
+    fs.writeFileSync(
+      outPath,
+      JSON.stringify({
+        type: "assistant",
+        agentId: "x",
+        message: {
+          content: [{ type: "text", text: "all good" }],
+          stop_reason: "end_turn",
+        },
+      }) + "\n",
+      "utf-8",
+    );
+    const mod = await import("../src/services/async-agent-watcher.js");
+    mod.registerPendingAgent({
+      agentId: "done-agent",
+      outputFile: outPath,
+      description: "clean completion",
+      prompt: "p",
+      chatId: 1,
+      userId: 1,
+      toolUseId: null,
+    });
+    // Backdate 1h — would trigger zombie if misapplied
+    const p = mod.listPendingAgents();
+    (p[0] as { startedAt: number }).startedAt = Date.now() - 60 * 60_000;
+
+    await mod.pollOnce();
+
+    expect(delivered).toHaveLength(1);
+    expect(delivered[0].result.status).toBe("completed");
+  });
+
+  it("decrements session counter on zombie failure delivery", async () => {
+    process.env.ALVIN_MISSING_FILE_FAILURE_MS = "1000"; // 1 sec for fast test
+    const sessionMod = await import("../src/services/session.js");
+    const session = sessionMod.getSession("zombie-session");
+    session.pendingBackgroundCount = 1;
+
+    const mod = await import("../src/services/async-agent-watcher.js");
+    mod.registerPendingAgent({
+      agentId: "session-zombie",
+      outputFile: `${TEST_DATA_DIR}/gone.jsonl`,
+      description: "zombie for counter",
+      prompt: "p",
+      chatId: 1,
+      userId: 1,
+      toolUseId: null,
+      sessionKey: "zombie-session",
+    });
+    const p = mod.listPendingAgents();
+    (p[0] as { startedAt: number }).startedAt = Date.now() - 5000; // 5 sec ago, > 1sec threshold
+
+    await mod.pollOnce();
+
+    expect(delivered).toHaveLength(1);
+    expect(session.pendingBackgroundCount).toBe(0);
+  });
+});