feat(triggers): self-authored watcher scripts that wake the bot by claudiusthebot · Pull Request #96 · dylanneve1/talon

claudiusthebot · 2026-04-29T14:20:52Z

Summary

A new "trigger" subsystem: bot-authored long-running scripts (bash / python / node) that run as supervised subprocesses and signal back via stdout to fire wake-up messages into the originating chat. Closes the gap between a fixed cron schedule and a one-shot timer — for cases where the trigger condition is arbitrary code, not a calendar.

Direct response to ScheduleWakeup being banned outside /loop mode: the model now has a real, robust way to schedule its own follow-ups instead of poking at a Claude Code primitive that hangs the dispatcher.

Examples of what it unlocks:

"Wake me when PR #35337 merges" — a 4-line bash polling gh pr view, exit 0 on merge.
"Tell me if my Polymarket position swings >5%" — python loop emitting TALON_FIRE: on every threshold crossing, never exits.
"Ping me when this URL returns 200" — bash with curl --fail.

The contract (the "standard")

Bot writes the script body. Talon spawns it under the right interpreter, captures stdout/stderr, watches for signals.

Mid-run: any stdout line beginning with TALON_FIRE: <text> fires a wake-up immediately. Script keeps running. Use for watchers that emit multiple events.
Exit 0: final fire with the tail of stdout/stderr as payload.
Exit non-zero: error fire with exit code + log tail.
Hard timeout (default 24h, max 7d): SIGTERM → 5s grace → SIGKILL → "timed_out" fire.

Wake-ups go through the existing dispatcher.execute() with source: "trigger", senderName: "Trigger" — same path cron "query" jobs already use. The bot receives a system-prefixed message containing the trigger name, status, and payload, then decides whether to message the user, take an action, or do nothing.

Tools exposed

trigger_create(name, language, script, timeout_seconds?, description?) — write + spawn
trigger_list — status, fire count, last error per trigger in this chat
trigger_cancel(trigger_id) — SIGTERM (then SIGKILL after 5s)
trigger_logs(trigger_id, lines?) — tail of stdout + stderr
trigger_delete(trigger_id) — cancel if running, then rm script + log

Architecture

Modeled directly on the existing cron subsystem:

src/storage/trigger-store.ts — JSON store at ~/.talon/data/triggers.json, dirty-flag auto-save, restart-cleanup that reaps any `running`/`pending` left over from a crashed process.
src/core/triggers.ts — supervisor with per-trigger child handle, in-memory line buffer (so fire payloads don't race with log file flushing), readline-based TALON_FIRE: detection, hard timeout, SIGTERM/SIGKILL escalation.
src/core/tools/triggers.ts — 5 tool definitions, new triggers tag.
gateway-actions.ts — bridge handlers with name-uniqueness check, per-chat cap (5 active), language/script/timeout validation.
paths.ts — ~/.talon/data/trigger-runs/<chatId>/<id>.{sh,py,js} for scripts, <id>.log for runs. Scripts written 0o700; logs 0o600.
bootstrap.ts — `loadTriggers` + `initTriggers({ execute })` + `resumeAfterRestart`.
index.ts — `shutdownTriggers` (await SIGTERM grace) + `flushTriggers` in graceful + crash paths.
types.ts — `source: "trigger"` added to `ExecuteParams`.

Limits / lifecycle

5 active triggers per chat (soft cap to prevent runaway). `trigger_list` so the bot can see what's already running before adding more.
Default 24h hard timeout, max 7d.
Children are killed on Talon shutdown — triggers do not survive restart. Any record left in `running`/`pending` on next load is marked `terminated` so the bot can decide whether to recreate.
4 KB cap on fire payloads; 80-line in-memory rolling buffer per trigger feeds the payload (independent of log file flushing).
Script body capped at 64 KB. Name must match `/^[a-zA-Z0-9 _.-]{1,64}$/` and is unique per chat.
Path-traversal-safe: `chatId` sanitised to `[a-zA-Z0-9_-]` before being used in file paths.

What this deliberately doesn't do

No restart survival. The bot was clear: simpler is better. Process group dies with us, store reaps state, bot recreates if needed. Future v2 could add PID-alive detection and log re-attach.
No nested triggers from a fire-handler. Not blocked at the type level — the per-chat cap is the only guard. Anti-loop protection lives in the cap, not in syntax restrictions.
No `subscribe_to_event` / webhook endpoint. Out of scope for this PR. Triggers are the polling/script-driven half; an HTTP webhook surface would be a separate change.

Test plan

`src/tests/trigger-store.test.ts` — 22 tests (validation, CRUD, path helpers, restart cleanup, log tail reading, fs mocked)
`src/tests/triggers.test.ts` — 8 supervisor tests with real bash subprocesses (clean exit / error exit / mid-run multi-fire / cancel / hard timeout / unsupported language / shutdown / log file content)
Compose-tools tag assertion updated to include `triggers`
`tsc --noEmit` clean
Full suite: 1397 passing, 0 failing
Smoke test on the live VPS once merged: `trigger_create` a 60-second `sleep 5` bash script, observe wake-up; cancel an in-flight one; hit the timeout

🤖 Generated with Claude Code

claudiusthebot · 2026-05-08T22:30:02Z

Rebased onto 9b0db075 (main / v1.10.0 + CI improvements). Clean rebase, no conflict sites. New head: 82af753.

typecheck ✅ · format:check ✅ — CI running.

claudiusthebot · 2026-05-09T00:08:58Z

🤖 Heartbeat #175 — branch coverage fix applied

CI was failing with Coverage for branches (59.22%) does not meet global threshold (60%) — introduced when PR #121 added the 60% branch coverage gate.

Added src/__tests__/triggers-extended.test.ts (commit 9096518) with 14 tests covering the previously-untested branches:

Test group	Branches covered
`triggers — alternate languages`	`commandForLanguage` python + node switch arms
`triggers — idempotency`	`spawnTrigger` early-return guard (already-running)
`triggers — cancelTrigger`	`cancelTrigger` false-return (no child for id)
`triggers — resumeAfterRestart`	no-deps guard, empty store, matching trigger, already-fired, old (>5 min)
`trigger-store — branch coverage`	`updateTrigger` + `deleteTrigger` with unknown id
`triggers — large stdout payload truncation`	`FIRE_PAYLOAD_MAX_BYTES` buffer-trimming path
`triggers — finalizeExit status branch`	cancelled-status exit + non-zero exit code

All 14 tests pass locally; CI will confirm coverage ≥ 60%.

claudiusthebot · 2026-05-09T02:02:25Z

Coverage fix — d3cb661 — two CI failures from the previous commit resolved:

1. Windows N22 test failure (trigger-store.test.ts > path helpers > triggerScriptPath)

Root cause: regex used Unix / separators but resolve() returns \ on Windows. macOS N22 and N24 passed; only Windows N22 failed.
Fix: const norm = (p: string) => p.replace(/\\/g, "/") — normalise before matching.

2. Ubuntu N22 coverage 59.67% < 60% (N24 was fine)

Root cause: V8 v11 (Node 22) instruments more branches than V8 v12 (Node 24) for the same code — triggers-extended.test.ts added enough for N24 but fell 0.33% short on N22.
Fix: 4 additional targeted tests:
- persistNow() — covers dirty = true; save() (lines 159-160 of trigger-store.ts)
- readTriggerLogTail catch via EISDIR (line 329 — readFileSync on a directory throws)
- readTriggerLogTail truncated path (line 327)
- fireWakeUp dispatch-error catch (line 394 of triggers.ts — execute() rejects)

typecheck ✅ · format:check ✅ · 18 extended tests pass locally · CI running on d3cb661

claudiusthebot · 2026-05-09T03:59:34Z

Coverage fix round 3 — CATCH #21 (hb #179)

d3cb661 (hb #177) was confirmed as MERGEABLE from the GitHub API in hb #178, but the actual CI run 25588573095 failed: Ubuntu N22 at 59.67% (< 60% threshold). The API's MERGEABLE reflects conflict state, not CI result — hb #178 made the mistake of conflating the two.

New head: d5ca2f9 — 7 additional tests:

Empty-stdout: fireWake's trimmed ? ... : '(no output)' false branch
Mid-run TALON_FIRE:: handleStdoutLine true branch + fireWake terminal=false ('signalled' header)
validateLanguage false paths: includes() false + typeof short-circuit
sanitizeChatId with special chars: replace() regex path
languageExtension direct call: all 3 switch arms
getTriggerByName returning undefined

25 tests total, all passing locally. Pushing to CI.

claudiusthebot · 2026-05-09T05:55:24Z

Coverage fix round 4 (6e09ec4) — ALL 15 CI CHECKS GREEN ✅ (including Ubuntu N22, Windows N22, all 3 Functional platforms). All 1744 tests pass.

This PR is now MERGEABLE and CI-clean. Six code PRs are all ready in one pass:

PR	Title	Status
#89	feat(gateway): force_dream + set_config	ALL CI GREEN ✅
#90	robustness + test coverage	ALL CI GREEN ✅
#86	feat(plugins): self-healing lifecycle	ALL 25 CI GREEN ✅
#96	feat(triggers)	ALL CI GREEN ✅
#62	feat(observability)	ALL CI GREEN ✅
#122	fix(claude-sdk): MCP prefix turn-terminator	ALL CI GREEN ✅

Suggested merge order: #89 → #90 → #86 → #96 → #62 → #122

Copilot

Pull request overview

This PR introduces a new trigger subsystem that lets the bot create and supervise long-running watcher scripts (bash/python/node) which can wake the bot by emitting TALON_FIRE: lines or by exiting, bridging the gap between cron schedules and one-shot timers.

Changes:

Added persistent trigger metadata store and on-disk layout for scripts/logs under ~/.talon/data/trigger-runs/.
Implemented a trigger supervisor that spawns/kills children, tails logs, detects TALON_FIRE: signals, and dispatches wake-ups via the existing dispatcher.
Exposed new trigger tools (trigger_create/list/cancel/logs/delete) and wired trigger lifecycle into bootstrap + shutdown, with new unit tests for store/supervisor behavior.

Reviewed changes

Copilot reviewed 18 out of 18 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
src/util/paths.ts	Adds trigger data directories/files.
src/util/log.ts	Adds `triggers` log component.
src/util/config.ts	Documents trigger tools/protocol in the system prompt.
src/storage/trigger-store.ts	New persistent store + validation + path helpers for triggers.
src/core/triggers.ts	New supervisor to spawn/monitor scripts and fire wake-ups.
src/core/gateway-actions.ts	Adds gateway action handlers for trigger tool bridging.
src/core/types.ts	Extends dispatcher ExecuteParams source union with `trigger`.
src/core/tools/types.ts	Adds `triggers` tool tag.
src/core/tools/triggers.ts	New tool definitions for trigger operations.
src/core/tools/index.ts	Registers trigger tools in ALL_TOOLS.
src/bootstrap.ts	Loads triggers + initializes/resumes trigger subsystem on startup.
src/index.ts	Shuts down trigger children and flushes trigger store on exit/crash paths.
src/tests/trigger-store.test.ts	Unit tests for trigger-store persistence/validation/helpers.
src/tests/triggers.test.ts	Supervisor tests with real subprocesses (bash) and lifecycle cases.
src/tests/triggers-extended.test.ts	Extended branch coverage for supervisor/store edge cases.
src/tests/compose-tools.test.ts	Asserts `triggers` tag is present.
src/tests/mcp-launcher.test.ts	Adds missing-file branch coverage for launcher.
src/tests/cleanup-registry.test.ts	Adds non-Error throw branch coverage.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

+  if (line.startsWith(FIRE_PREFIX)) {
+    const payload = line.slice(FIRE_PREFIX.length).trim();
+    fireWake(triggerId, "fired", payload, /* terminal */ false).catch((err) =>
+      logError("triggers", `mid-run fire failed [${triggerId}]`, err),
+    );


+  const logStream = createWriteStream(trigger.logPath, {
+    flags: "a",
+    mode: 0o600,
+  });


+  // Truncate payload — we don't want a runaway script blowing out the prompt
+  const trimmed = (payload ?? "").slice(0, FIRE_PAYLOAD_MAX_BYTES);
+


+  if (!t) return undefined;
+  Object.assign(t, updates);
+  dirty = true;


+  timeoutSeconds: number;
+  /** Exit code on terminal status. */
+  exitCode?: number;
+  /** Number of mid-run TALON_FIRE: lines emitted. */


+        text:
+          `Created trigger "${name}" (id: ${id})\n` +
+          `Language: ${lang}\n` +
+          `Timeout: ${timeoutSeconds}s\n` +
+          `Status: running`,


… on terminal, etc. Address 5 of the 6 Copilot review threads on PR #96. The 6th (mid-run TriggerStatus rename) is a larger semantic refactor and deferred to a later commit; this commit pairs the smallest reasonable fix at each site with regression tests where they're cleanly testable. 1. src/core/triggers.ts:128 — log WriteStream missing error handler. createWriteStream() with no .on("error") emits an unhandled EventEmitter `error` event if the log file becomes unwritable (disk full, permission flip), which crashes the Node process. Added a logError-routing handler so disk-tier failures degrade gracefully without killing the supervisor. 2. src/storage/trigger-store.ts:60 — fireCount doc/semantics mismatch. The doc-comment claimed "Number of mid-run TALON_FIRE: lines" but the supervisor increments fireCount for every wake (mid-run and terminal). Fixed the comment to match the actual semantics; same counter, accurate meaning. Avoids breaking any caller that already relies on fireCount as a total. 3. src/core/triggers.ts:fireWake — mid-run prompt says "Status: fired" even when terminal=false, which can mislead downstream handling into treating an in-flight watcher as a completed run. Decoupled the prompt-display status from the on-disk TriggerStatus enum: non-terminal fires now show "Status: signalled" in both the header and the "Status:" line. Terminal fires unchanged. 4. src/core/triggers.ts:bufferAsPayload + fireWake — FIRE_PAYLOAD_MAX_BYTES truncation used String.prototype.slice (UTF-16 code units), so a payload of N multi-byte characters could exceed the documented byte cap and split a character mid-codepoint. Introduced truncateUtf8Tail/ truncateUtf8Head helpers that encode to UTF-8 bytes, slice on a byte boundary, then walk over UTF-8 continuation bytes (10xxxxxx) so we never cut a multi-byte sequence in half. The byte cap is now actually enforced as bytes. 5. src/storage/trigger-store.ts:282 + supervisor — updateTrigger only marks the store dirty (10s autosave window). For terminal status transitions (errored/cancelled/timed_out/fired) a crash inside that window would leave on-disk status as "running", which loadTriggers() then misclassifies as "terminated by previous restart". Added persistNow() calls at the four supervisor transition sites: failTrigger, cancelTrigger, the hard-timeout handler, and the finalizeExit path. The on-disk store now always agrees with the in-memory state across terminal transitions. 6. src/core/gateway-actions.ts:trigger_create — always returned "Status: running" even when spawnTrigger() failed without throwing (unsupported language slipping past validation, child.pid undefined, failTrigger() routing). With #5 above, the store now reflects the real state synchronously, so we re-read getTrigger(id) after spawn and return ok:false + lastError when it landed in "errored", or surface the actual status string otherwise. Callers no longer get false success responses. Regression tests (triggers-extended.test.ts): - mid-run prompt asserts "Status: signalled" appears and "Status: fired" does NOT, on a still-running trigger. Covers fix #3. - multi-byte UTF-8 payload (2000× 💧 = 8000 bytes vs 4000 string length) asserts the prompt's byte length stays bounded AND contains no Unicode replacement character (U+FFFD), which would indicate a mid-codepoint split. Covers fix #4. The remaining Copilot thread (introducing a dedicated non-terminal status enum value, replacing the TriggerStatus|"signalled" display- status hack) is a wider type change with API/store implications; better tackled in a follow-up than bundled into a defensive sweep. Verification: - npx vitest run → 1747/1748 pass (the 1 failure is the pre-existing package.functional "Stopped" expectation that fails whenever a live Talon daemon is running on the host — same env-dependent failure noted in PR #144 and PR #90's verification blocks). - npx vitest run src/__tests__/triggers* src/__tests__/trigger-store* → 74/74 pass (35 in triggers-extended including 2 new, 22 in trigger-store, 17 in triggers). - npx tsc --noEmit → clean. - npx prettier --check on all 4 changed files → clean. - npm run lint → 0 errors in changed files (10 pre-existing warnings elsewhere unchanged). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

Four test failures in the PR #156 CI run all reflected old assertions that match the bugs the PR explicitly fixes: - cron-store: "does not write when not dirty" was asserting the very bug being fixed (flush should always persist defensively, matching flushSessions/flushHistory). Updated to assert writeFileSync IS called. - errors: "uses extracted status instead of 429 default" was relying on '200' being matched by the old [2-5]\d{2} regex — the whole point of the PR is to stop matching 2xx/3xx. Switched the example to 418 and added a regression test that 200ms in an error message no longer pollutes status. - dream (timeout fake-timers): the mocked query awaited a never-resolving Promise, so the new `await agentPromise.catch(() => {})` (matching the heartbeat.ts pattern that waits for the subprocess before releasing the lock) hung the test. Switched to a controllable promise and resolve it after the timeout fires to simulate the agent finishing post-timeout. - dream (executeDream catch): cascading failure from the same hang — vi.useRealTimers() at the end of the timeout test was unreachable, so fake timers leaked into the next test's `setTimeout(r, 0)`. Fixed by unhanging the timeout test. Plus prettier --write on formatting.ts and history.ts (the PR's edits nudged both files past the line-length limit). Verified locally: 1900/1901 pass (the one remaining failure is the pre-existing package.functional env-dependent flake, same as PR #144/#90/#96). typecheck clean, prettier --check clean on all touched files. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

… component, flush consistency, status regex) (#156) * fix: six correctness and safety bugs found by code review - dream.ts: capture and clear the 10-minute timeout handle in a finally block, and call .unref() on it. Without this the timer kept the Node.js event loop alive after a successful dream run and, when it eventually fired, rejected a Promise with no handler → UnhandledPromiseRejection warning. The fix mirrors the already-correct pattern in heartbeat.ts and additionally waits for the agent to finish before releasing the dreaming lock on timeout, preventing overlapping dream runs. - formatting.ts: HTML-escape the URL before embedding it in the <a href> attribute. A crafted markdown link such as [x](https://a.com" onX="y) could inject arbitrary HTML attributes into the generated anchor tag. - history.ts: fix two log() / logError() calls that passed "sessions" as the component instead of "history", causing history-load events to appear under the wrong tag in structured logs. - cron-store.ts / chat-settings.ts: add `dirty = true` before the final save() in flushCronJobs() and flushChatSettings() to guarantee the store is written on shutdown regardless of auto-save timer timing. Matches the defensive pattern already used by flushSessions() and flushHistory(). - errors.ts: narrow the HTTP status-code regex from /\b([2-5]\d{2})\b/ to /\b([45]\d{2})\b/. Only 4xx/5xx codes are acted on by the classifier; matching 2xx/3xx codes was harmless for control flow but could stamp a spurious status (e.g. 200 from "took 200ms") onto a TalonError, making diagnostic logs misleading. https://claude.ai/code/session_01Xq1CTjS2UG5ErEbqVaELRn * test+style: align tests with #156 corrected behaviour + prettier Four test failures in the PR #156 CI run all reflected old assertions that match the bugs the PR explicitly fixes: - cron-store: "does not write when not dirty" was asserting the very bug being fixed (flush should always persist defensively, matching flushSessions/flushHistory). Updated to assert writeFileSync IS called. - errors: "uses extracted status instead of 429 default" was relying on '200' being matched by the old [2-5]\d{2} regex — the whole point of the PR is to stop matching 2xx/3xx. Switched the example to 418 and added a regression test that 200ms in an error message no longer pollutes status. - dream (timeout fake-timers): the mocked query awaited a never-resolving Promise, so the new `await agentPromise.catch(() => {})` (matching the heartbeat.ts pattern that waits for the subprocess before releasing the lock) hung the test. Switched to a controllable promise and resolve it after the timeout fires to simulate the agent finishing post-timeout. - dream (executeDream catch): cascading failure from the same hang — vi.useRealTimers() at the end of the timeout test was unreachable, so fake timers leaked into the next test's `setTimeout(r, 0)`. Fixed by unhanging the timeout test. Plus prettier --write on formatting.ts and history.ts (the PR's edits nudged both files past the line-length limit). Verified locally: 1900/1901 pass (the one remaining failure is the pre-existing package.functional env-dependent flake, same as PR #144/#90/#96). typecheck clean, prettier --check clean on all touched files. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Claudius <claudiusthebot@gmail.com>

Triggers are bot-authored long-running scripts (bash / python / node) that run as supervised subprocesses and signal back via stdout to fire wake-up messages into the originating chat. Built for the case where a fixed cron schedule doesn't fit — "wake me when this PR merges", "tell me if BTC moves >5%", "watch this URL until it returns 200". Contract: - Mid-run: a stdout line `TALON_FIRE: <text>` fires immediately and the script keeps running (multi-event watchers). - Exit 0: final fire with the tail of stdout/stderr as payload. - Exit non-zero: error fire with exit code + log tail. - Hard timeout (default 24h, max 7d): SIGTERM → SIGKILL → timed_out fire. Tools exposed: trigger_create, trigger_list, trigger_cancel, trigger_logs, trigger_delete. Per-chat cap of 5 active. Children are killed on Talon shutdown — they do not survive a restart, and any trigger left in running/pending on load is reaped to "terminated". New modules: - src/storage/trigger-store.ts: persistence + validation - src/core/triggers.ts: supervisor (spawn, line buffers, fire dispatch) - src/core/tools/triggers.ts: 5 tool definitions - gateway-actions.ts: trigger_* bridge handlers - paths.ts: ~/.talon/data/trigger-runs/<chatId>/ for scripts and logs - bootstrap.ts: loadTriggers + initTriggers + resumeAfterRestart - index.ts: shutdownTriggers + flushTriggers in shutdown paths Tests: 30 new (22 store + 8 supervisor including real-bash spawn integration). 1397/1397 passing.

…erRestart/store Adds targeted tests that bring branch coverage above the 60% global threshold imposed by PR #121. Exercises: commandForLanguage python & node paths, spawnTrigger idempotency guard, cancelTrigger false-return, resumeAfterRestart (no-deps / empty / matching / already-fired / old), trigger-store unknown-id paths, FIRE_PAYLOAD_MAX_BYTES truncation, and finalizeExit status-branch (cancelled exit + non-zero exit code). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Two CI failures in the coverage-fix commit (9096518): 1. Windows N22 — trigger-store.test.ts: triggerScriptPath regex used Unix forward-slashes but resolve() returns backslashes on Windows. Fixed by normalising path separators before matching. 2. Ubuntu N22 — branch coverage 59.67% < 60% (threshold differs from N24 due to V8 v11 vs v12 branch instrumentation). Added 4 more targeted tests in triggers-extended.test.ts: - trigger-store persistNow() path (lines 159-160) - readTriggerLogTail catch path via EISDIR (line 329) - readTriggerLogTail truncated:true path (line 327) - fireWakeUp dispatch-error catch path (line 394 of triggers.ts) All 18 extended tests pass. typecheck ✅ · format:check ✅. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

… and store helpers Ubuntu Node 22 (V8 v11) instruments more branches than Node 24 (V8 v12), causing coverage to land at 59.67% on N22 while passing on N24. Added 7 new tests to triggers-extended.test.ts: - Empty stdout: covers fireWake's `trimmed ? ... : (no output)` false branch - Mid-run TALON_FIRE: covers handleStdoutLine true branch + fireWake terminal=false ("signalled" header path) - validateLanguage false paths: includes() false + typeof short-circuit - sanitizeChatId with special chars: confirms replace() regex path - languageExtension direct call: covers all 3 switch arms explicitly - getTriggerByName returning undefined: covers find() undefined path Also imports getTriggerByName, validateLanguage, sanitizeChatId, and languageExtension from trigger-store for direct testing. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

…2 CI pass Add 15 new tests across 4 test files to cover previously-unreachable branches, specifically the ones V8 v11 (Node 22) counts but were uncovered since hb #179: trigger-store.test.ts (+9 tests): - loadTriggers: file-not-present, non-object JSON, corrupt primary (3 variants) - Backup parses as null (line 94 ternary false arm) - save() catch: Error throw and non-Error string throw (both instanceof arms) - readTriggerLogTail: non-Error throw (false arm of err instanceof Error) triggers-extended.test.ts (+5 new describe blocks): - fireWake with undefined payload (payload ?? '' false arm) - fireCount undefined treated as 0 (fireCount ?? 0 false arm) - finalizeExit with null exit code — signal kill (code ?? undefined false arm) - handleStdoutLine with no lineBuffer entry (pushBufferLine if(!buf) true arm) - shutdownTriggers when no children running (if(children.size===0) true arm) - Child process error event handler (line 152 handler covered) - Timeout timer fires after child already exited (if(!c) return true arm) cleanup-registry.test.ts (+1 test): - Handler throws a non-Error string (err instanceof Error false arm) mcp-launcher.test.ts (+1 test): - ensureLauncher throws when file does not exist (if(!existsSync) true arm) Uses vi.doMock to intercept node:fs before fresh module import. Node 24 local result: 60.26% (2146/3561). Previous Node 22 CI: 59.73%. 1744 tests, all passing. tsc clean, prettier clean. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

… on terminal, etc. Address 5 of the 6 Copilot review threads on PR #96. The 6th (mid-run TriggerStatus rename) is a larger semantic refactor and deferred to a later commit; this commit pairs the smallest reasonable fix at each site with regression tests where they're cleanly testable. 1. src/core/triggers.ts:128 — log WriteStream missing error handler. createWriteStream() with no .on("error") emits an unhandled EventEmitter `error` event if the log file becomes unwritable (disk full, permission flip), which crashes the Node process. Added a logError-routing handler so disk-tier failures degrade gracefully without killing the supervisor. 2. src/storage/trigger-store.ts:60 — fireCount doc/semantics mismatch. The doc-comment claimed "Number of mid-run TALON_FIRE: lines" but the supervisor increments fireCount for every wake (mid-run and terminal). Fixed the comment to match the actual semantics; same counter, accurate meaning. Avoids breaking any caller that already relies on fireCount as a total. 3. src/core/triggers.ts:fireWake — mid-run prompt says "Status: fired" even when terminal=false, which can mislead downstream handling into treating an in-flight watcher as a completed run. Decoupled the prompt-display status from the on-disk TriggerStatus enum: non-terminal fires now show "Status: signalled" in both the header and the "Status:" line. Terminal fires unchanged. 4. src/core/triggers.ts:bufferAsPayload + fireWake — FIRE_PAYLOAD_MAX_BYTES truncation used String.prototype.slice (UTF-16 code units), so a payload of N multi-byte characters could exceed the documented byte cap and split a character mid-codepoint. Introduced truncateUtf8Tail/ truncateUtf8Head helpers that encode to UTF-8 bytes, slice on a byte boundary, then walk over UTF-8 continuation bytes (10xxxxxx) so we never cut a multi-byte sequence in half. The byte cap is now actually enforced as bytes. 5. src/storage/trigger-store.ts:282 + supervisor — updateTrigger only marks the store dirty (10s autosave window). For terminal status transitions (errored/cancelled/timed_out/fired) a crash inside that window would leave on-disk status as "running", which loadTriggers() then misclassifies as "terminated by previous restart". Added persistNow() calls at the four supervisor transition sites: failTrigger, cancelTrigger, the hard-timeout handler, and the finalizeExit path. The on-disk store now always agrees with the in-memory state across terminal transitions. 6. src/core/gateway-actions.ts:trigger_create — always returned "Status: running" even when spawnTrigger() failed without throwing (unsupported language slipping past validation, child.pid undefined, failTrigger() routing). With #5 above, the store now reflects the real state synchronously, so we re-read getTrigger(id) after spawn and return ok:false + lastError when it landed in "errored", or surface the actual status string otherwise. Callers no longer get false success responses. Regression tests (triggers-extended.test.ts): - mid-run prompt asserts "Status: signalled" appears and "Status: fired" does NOT, on a still-running trigger. Covers fix #3. - multi-byte UTF-8 payload (2000× 💧 = 8000 bytes vs 4000 string length) asserts the prompt's byte length stays bounded AND contains no Unicode replacement character (U+FFFD), which would indicate a mid-codepoint split. Covers fix #4. The remaining Copilot thread (introducing a dedicated non-terminal status enum value, replacing the TriggerStatus|"signalled" display- status hack) is a wider type change with API/store implications; better tackled in a follow-up than bundled into a defensive sweep. Verification: - npx vitest run → 1747/1748 pass (the 1 failure is the pre-existing package.functional "Stopped" expectation that fails whenever a live Talon daemon is running on the host — same env-dependent failure noted in PR #144 and PR #90's verification blocks). - npx vitest run src/__tests__/triggers* src/__tests__/trigger-store* → 74/74 pass (35 in triggers-extended including 2 new, 22 in trigger-store, 17 in triggers). - npx tsc --noEmit → clean. - npx prettier --check on all 4 changed files → clean. - npm run lint → 0 errors in changed files (10 pre-existing warnings elsewhere unchanged). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

The README hadn't kept pace with what landed across PRs #96, #160, #161, #165, #169, #170, and #172: - Kilo and OpenCode backends were missing or misrepresented (the badge still said "Claude Agent SDK", the backend config row listed only claude/opencode, the architecture tree didn't mention kilo, remote-server, or shared). - Discord frontend (PR #160) was absent from every list. - Triggers (PR #96) were absent from the features table. - Test count was stale at "1300+" — the suite is now 2200+ across the unit / SDK-stub / MCP-functional / integration tiers. - Prerequisites assumed a single backend (Claude CLI on PATH). Changes: - New "Backends" section explaining the three options + their transport shape + shared remote-server infrastructure. - Backends badge replaces the Claude Agent SDK badge. - Features table: dedicated "Pluggable backend" row, new "Triggers" row, MCP tools row mentions triggers. - Architecture tree refreshed: backend/registry.ts, backend/shared/, backend/remote-server/, kilo/, plus discord/ under frontend. - Backend-specific prerequisites called out under Quick Start. - Dependency rule paragraph mentions the QueryBackend interface. - Config table: backend accepts claude/kilo/opencode, frontend accepts discord, model description is backend-agnostic. - Development: test count updated to 2200+ across the tier matrix, added `npm run format`.

claudiusthebot requested a review from dylanneve1 as a code owner April 29, 2026 14:20

This was referenced May 2, 2026

Improve Talon robustness and test coverage #90

Closed

feat(plugins): self-healing lifecycle for built-in plugins #86

Closed

dylanneve1 force-pushed the feat/triggers branch from e411832 to 82af753 Compare May 8, 2026 22:29

dylanneve1 requested a review from Copilot May 12, 2026 12:31

Copilot AI reviewed May 12, 2026

View reviewed changes

claudiusthebot mentioned this pull request May 13, 2026

fix: six correctness and safety bugs (timer leak, HTML injection, log component, flush consistency, status regex) #156

Merged

7 tasks

claudiusthebot and others added 7 commits May 13, 2026 14:09

style: auto-format with prettier

0cfcdf4

dylanneve1 force-pushed the feat/triggers branch from 4dc789e to f34a06d Compare May 13, 2026 13:09

dylanneve1 enabled auto-merge (squash) May 13, 2026 13:09

dylanneve1 merged commit cafc8d4 into main May 13, 2026
22 checks passed

dylanneve1 mentioned this pull request May 18, 2026

chore(main): release 1.12.0 #209

Merged

Navigation Menu

feat(triggers): self-authored watcher scripts that wake the bot - #96

feat(triggers): self-authored watcher scripts that wake the bot#96
dylanneve1 merged 7 commits into
mainfrom
feat/triggers

claudiusthebot commented Apr 29, 2026

Uh oh!

claudiusthebot commented May 8, 2026

Uh oh!

claudiusthebot commented May 9, 2026

Uh oh!

claudiusthebot commented May 9, 2026

Uh oh!

claudiusthebot commented May 9, 2026

Uh oh!

claudiusthebot commented May 9, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

		// Truncate payload — we don't want a runaway script blowing out the prompt
		const trimmed = (payload ?? "").slice(0, FIRE_PAYLOAD_MAX_BYTES);

Conversation

claudiusthebot commented Apr 29, 2026

Summary

The contract (the "standard")

Tools exposed

Architecture

Limits / lifecycle

What this deliberately doesn't do

Test plan

Uh oh!

claudiusthebot commented May 8, 2026

Uh oh!

claudiusthebot commented May 9, 2026

Uh oh!

claudiusthebot commented May 9, 2026

Uh oh!

claudiusthebot commented May 9, 2026

Uh oh!

claudiusthebot commented May 9, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants