Replaces the two overlapping old mechanisms (30-min setTimeout kill in
container-runner, 10-min heartbeat STALE_THRESHOLD reset in host-sweep)
with message-scoped stuck detection anchored to the processing_ack claim
age + an absolute 30-min ceiling that extends for long-declared Bash
tools.
Old model problems:
- IDLE_TIMEOUT setTimeout fired on plain wall-clock time; slow-but-alive
agents got killed at 30min regardless of activity
- 10-min STALE_THRESHOLD in the sweep was unreliable — the heartbeat is
only touched on SDK events, so legitimate silent tool work (sleep 30,
long WebFetch, npm install) looked identical to a hung container
- Two overlapping sources of truth for "when to let go of a container"
New model:
- Host sweep is the single source of truth.
- Container exposes a new `container_state` single-row table in outbound.db
(schema added; container writes, host reads). PreToolUse hook writes
current_tool + tool_declared_timeout_ms (read from Bash's tool_input);
PostToolUse / PostToolUseFailure clear it.
- Sweep decides with a pure helper `decideStuckAction`:
* absolute ceiling — kill if heartbeat age > max(30min, bash_timeout)
* per-claim stuck — kill if any processing_ack row has claim_age >
max(60s, bash_timeout) AND heartbeat hasn't been touched since claim
* otherwise ok
Kill paths reset leftover processing rows with exponential backoff,
reusing the existing retry machinery.
Tool blocklist expanded:
- AskUserQuestion (SDK placeholder; we have mcp__nanoclaw__ask_user_question)
- EnterPlanMode, ExitPlanMode, EnterWorktree, ExitWorktree (Claude Code UI
affordances; would hang in headless containers)
PreToolUse hook is also defense-in-depth: if a disallowed tool name slips
through, it returns `{ decision: 'block' }` so the agent sees a clear
error instead of appearing stuck.
Removed:
- container-runner.ts: IDLE_TIMEOUT setTimeout, resetIdle callback on
activeContainers entry, resetContainerIdleTimer export.
- delivery.ts: the resetContainerIdleTimer call on successful delivery.
- poll-loop.ts: IDLE_END_MS + its setInterval. Keeping the query open is
cheaper than close+reopen (no cold prompt cache). Liveness is now a
host-side concern.
- host-sweep.ts: 10-min STALE_THRESHOLD_MS + getStuckProcessingIds in the
stale-detection path (still exported for kill reset).
Tests:
- src/host-sweep.test.ts — 9 tests for decideStuckAction covering: fresh
heartbeat, absolute ceiling, absent heartbeat, Bash-timeout extension
(both ceiling and per-claim), claim age below tolerance, heartbeat
touched after claim, unparseable timestamps.
Ref: docs/v1-vs-v2/ACTION-ITEMS.md items 9, 6a, 10.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The active poll (1s, running sessions) and sweep poll (60s, all active
sessions) both call deliverSessionMessages, and a running session is in
both result sets. Without locking they race on the same outbound row:
both read it as undelivered, both call the channel adapter, both
markDelivered. INSERT OR IGNORE hides the DB collision but the user has
already received the message twice.
Adds a per-session inflight guard; the second concurrent caller skips
and picks up any leftover work on the next poll tick.
Also makes outbox cleanup in deliverMessage best-effort: the message is
already on the user's screen, so a cleanup throw must not propagate to
the retry path (which would resend).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
