Root cause of compact still failing after 1192/1205: in gateway mode,
on_room_message proxies any command not in GATEWAY_LOCAL_COMMANDS to the
active project's sled (proxy_bot_command) and returns — and that proxy
runs BEFORE the local compact interception (try_handle_compact_command).
'compact' was missing from the allowlist, so the gateway shipped it to a
sled (which has no compact command → no-op 'Command succeeded with no
response text'), and the real handler was never reached.
'reset' was already in the list, which is why reset worked in gateway
mode and compact did not. Add 'compact' as its sibling.
Why 1192 and 1205 both missed this: their tests drive
try_handle_compact_command directly, bypassing the gateway-proxy seam
that only exists on the full on_room_message path in gateway mode.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019fHdm92yjvguPi2LiXfLB9
Code review of 1185 (merge 0f4b0c95) found the retry subscriber's central
invariant did not hold: the MergeFailure->Merge bounce caused by its own
retry reset both its attempt counter and the block subscriber's counter,
so the shared merge_failure_block_threshold budget was unreachable and a
deterministic gates failure retried forever.
One subscriber now owns one counter driving both policies:
- Counter survives PipelineEvent::MergeRetryStarted bounces (finding 1);
a third consecutive failure blocks even with retries in between.
- Mixed failure kinds share the single budget (finding 5).
- Retries respect recovery: no counting or scheduling while a mergemaster
is active, and perform_auto_retry re-checks before firing (finding 2).
- perform_auto_retry applies the same eligibility gates as
assign_merge_stage (review hold, frozen, blocked, unmet deps) so freeze
now stops a retry loop (finding 4).
- Per-story scheduling generations invalidate stale sleeping timers
(finding 6).
- One-shot startup scan schedules a catch-up retry for stories already
parked in GatesFailed, so restarts no longer strand them (finding 3);
kept out of the periodic reconciler to avoid re-retrying exhausted
stories every tick.
- Chat is notified only after the merge actually starts; a failed trigger
logs instead of claiming a retry ran (finding 7).
- Config reads moved onto spawn_blocking (finding 8, bug 1170 class).
Deletes merge_failure_retry_subscriber.rs; notification plumbing
(WatcherEvent::MergeAutoRetry et al) is unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019fHdm92yjvguPi2LiXfLB9
read_llm_session acquired the CRDT_STATE mutex, then called
extract_llm_session_view while holding the guard — which called
our_node_id(), which locks the same non-reentrant std::sync::Mutex.
The thread deadlocks itself and parks forever HOLDING the lock; every
other CRDT user then queues behind it. With light traffic that's a
partial wedge (MCP `show`/content reads hang while /health stays
green); during a CRDT-write burst (unblock → auto-assign) enough
tasks pile up to pin every tokio worker: liveness heartbeat stops,
/health dies, full sled freeze. Root cause of bug 1170's repeated
sled freezes, confirmed by live gdb capture: thread parked in
lock_contended at presence::our_node_id ← read_llm_session ←
event_matches_persona, with all other threads queued on CRDT reads.
Fix: extract_llm_session_view now takes local_sled_id as a parameter;
read_llm_session computes it from the guard it already holds. The
trigger path (event_matches_persona on persona-subscribed WS events)
explains the raciness — it needs a chat/persona event racing a
pipeline transition.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019fHdm92yjvguPi2LiXfLB9
Huskies Agent
Timmy
