Replace the inlined parent-wake coalescing logic in manager.ts with delegation to the ParentWakeNotifier extracted in c1ccf8d09. The four timer Maps and the related methods now live in their own module with a narrow public API, while BackgroundManager retains the wiring point and the enqueue-callback bridge.
Closes HIGH-9 (step 2: integration)
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Extracts the parent-wake coalescing logic (pending/dispatched wake maps,
timers, notification reply assembly) from manager.ts into a standalone
ParentWakeNotifier class. Takes dependency-injected client, directory,
and an enqueueNotificationForParent callback, so the manager can delegate
parent-wake state to a narrow API.
This commit only introduces the new module; wiring manager.ts to use it
is a follow-up commit so the refactor stays atomic (HIGH-9 step 1 of 2).
Closes HIGH-9 (step 1: extraction)
Refs HIGH-9 (step 2: manager.ts integration deferred until verification)
Co-authored-by: manager-extract (deep / gpt-5.3-codex high)
The regression test for the pane-creation race (PR #4052 / issue #3505)
previously didn't enforce the readiness-then-spawn ordering: mocks
resolved synchronously and the assertion only checked the final
behavior, not the sequencing. A future code change reintroducing the
race could slip past this test silently.
Rewrites the test to explicitly assert call ordering:
waitForSessionReady must complete before executeActions is invoked.
A failure case is added where waitForSessionReady remains pending
when executeActions would otherwise fire; the test asserts the spawn
is correctly deferred.
Addresses cubic-dev-ai's review on PR #4052 (severity 5/10,
test quality).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Fixes BackgroundManager to launch promptAsync before invoking the blocking tmux callback.
- Adds regression test to ensure promptAsync is called before tmux callback.
`opencode attach` was invoked inside a freshly-split tmux pane before the
child session appeared in the opencode server's status map. The process
exited immediately (session not found), tmux auto-closed the pane, and the
subagent ran invisibly in the background — the race documented in #3505.
Fix: call `waitForSessionReady` *before* `executeActions` in
`session-created-handler.ts`, mirroring the guard already present in
`TmuxSessionManager.ensureSessionReadyBeforeSpawn()`. If the session does
not become attachable within the timeout the handler returns early without
spawning a pane at all, eliminating the transient-pane and silent-close
failure modes. The now-unreachable post-spawn readiness-check / pane-close
cleanup branch is removed.
Adds a regression test suite (session-created-handler.test.ts) covering:
- not-ready session → no pane spawned, no polling started
- duplicate session.created → idempotent
- non session.created event type → no action
- already-tracked session → idempotent
Closes#3505
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Keep prompt reservations briefly after successful dispatch so rapid idle/message/error transitions cannot inject the same follow-up twice.
Route all production session prompt calls through the shared gate, restore skipped background resume state, release holds after abort/recovery paths, and preserve Ralph/ULW loop state when a dispatch is deferred.
Add regression coverage for session routing, static prompt route auditing, team-mode live messaging, model suggestion retries, call-omo-agent reuse, background parent wakes, runtime fallback, compaction recovery, Atlas, and Ralph/ULW loops.
scheduleForcedExit was called without exitAfterCleanup=true for SIGTERM/SIGINT.
After cleanup completed, timeout cleared but process.exit() never called.
Process stayed alive waiting for event loop to drain.
Benchmark (systemctl stop):
- Before: 10s+ timeout (systemd had to SIGKILL)
- After: ~30ms instant shutdown
Test results (3 runs):
- Test 1: 30ms
- Test 2: 28ms
- Test 3: 27ms
When many background tasks complete in rapid succession while the parent
session is idle, each completion fired its own promptAsync call, stacking
N consecutive `<system-reminder>` user messages with no assistant turn
between. Hyperplan + many parallel explore subagents made this very
visible to the user.
Route the idle-path through the existing pendingParentWakes queue with a
100ms debounce window. Notifications arriving during the debounce join
the same batch, the 150ms settle window also coalesces newcomers, and a
single batched prompt fires to the parent. Busy-path semantics are
unchanged (still 1s retry).
Prior attempts (1c05c60dc, ea55c385b, a337635e3) all coalesced only the
busy-defer path, leaving the idle-immediate-send path uncoalesced.
Reframe the skill's Lifecycle section so the lead treats teams as
ephemeral, one-per-phase units. The moment a phase ends or the shape
no longer fits, call team_delete and spawn a fresh team. Restructure
through delete-then-create, never in place.
Also fixes a misframing in old step 5: team_shutdown_request is a
per-session self-shutdown signal, not a 'wind down the team' command.
team_delete is what tears the whole team down.
Sync the PR branch with the newest dev branch and resolve the new import-level conflicts in background-agent manager and runtime-fallback tests. Preserve both the delegated bootstrap coverage from this branch and the newer upstream test utilities and runtime wiring changes, then re-verify the affected delegated fallback suites and typecheck.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
The circuit breaker in manager.ts uses recordToolCall to detect when a subagent gets stuck repeating identical tool_use blocks. It passed partInfo.state?.input as the tool-input signature. When a model (Kimi K2.6 in the reporter's case) emits duplicate tool_use parts faster than the tool actually starts running, state.input is still null, so loop-detector falls back to the bare 'tool::__unknown-input__' signature. As soon as one part has state.input populated (next event), the signature flips to 'tool::{actual-args}' and the consecutive counter resets to 1, repeatedly. The breaker never reaches its 20-call threshold.
Add a top-level input?: Record<string, unknown> field to the local MessagePartInfo interface and prefer state.input when present, falling back to the part's own input when state is still pre-running. The OpenCode part payload carries the tool input as soon as the tool_use block is generated, so this fallback restores signature stability across the model's repeated emissions.
Verification: added 2 regression tests in manager-circuit-breaker.test.ts. Test 1 (reproduce) emits 20 part.updated events with only top-level input and asserts the task is cancelled by the breaker — fails before the fix, passes after. Test 2 confirms that when state.input IS present, it still wins over the top-level input (precedence preserved). All 10 manager-circuit-breaker tests pass, all 20 loop-detector tests pass, typecheck clean.
YeonGyu-Kim