When using `opencode run`, the process exits prematurely if the main
agent dispatches background subtasks. The CLI completion checker relies
on `session.children()` + `session.status()` APIs which cannot see
tasks in "pending" state (no session created yet) or tasks whose
sessions are momentarily idle between operations.
This fix bridges BackgroundManager state to the CLI completion checker
using the existing run-continuation-state marker system:
- Add "background-task" continuation marker source
- BackgroundManager writes/clears markers on task lifecycle events
(launch, cancel, complete, crash)
- CLI completion checker blocks exit when marker is active
- Fix todo-continuation-enforcer to also check "pending" task status
Closes#3452
resolveSubagentSpawnContext and related lookups called client.session.get
without the query.directory parameter, causing project-scoped sessions
to 404 under newer OpenCode SDK versions. Threaded directory through
SpawnerContext/BackgroundManager so all four call-sites pass it.
🤖 Generated with OhMyOpenCode assistance
https://github.com/code-yeongyu/oh-my-opencode
Added await for session ready state before sending prompt in
background-agent/manager.ts. Also improved image resizer error handling.
132 tests pass, tsc clean.
Closes#2932
1. [HIGH] Tool restrictions recomputed for fallback agent via
buildFallbackBody() — no longer inherits original agent's restrictions.
2. [HIGH] Double-retry race prevented — handleSessionErrorEvent now
returns early for agent-not-found errors, since the prompt catch
block already handles them with agent fallback. This prevents
tryFallbackRetry from racing with a model-level retry on the same
error (the "not found" pattern in RETRYABLE_MESSAGE_PATTERNS).
3. [MEDIUM] task.agent updated to FALLBACK_AGENT after successful
fallback — notifications, toast, and logging reflect actual agent.
4. [MEDIUM] FALLBACK_AGENT exported from spawner.ts and imported into
manager.ts — single source of truth.
5. [LOW] resumeTask fallback now uses promptWithModelSuggestionRetry
(consistent with startTask), getting timeout protection.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When a model/mode switch happens while a background task is in-flight,
the oh-my-openagent agent registry can be rebuilt without custom agents
(e.g., Sisyphus-Junior). The SDK then rejects the promptAsync call with
"Agent not found", killing the task.
This adds retry logic: when promptAsync fails with "Agent not found",
retry with the "general" agent (always available in opencode). The
original prompt, model, and skill content are preserved — only the
agent routing changes.
Fixes both the spawner (startTask/resumeTask) and manager (inline
launch) code paths. Also improves the error message detection in
manager.ts to recognize "Agent not found" alongside the existing
"agent.name"/"undefined" checks.
Related: #2052, #2875, #2882
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fire-and-forget session.abort() calls during subagent completion left
dangling promises that raced with parent session teardown. In Bun on
WSL2/Linux, this triggered a StringImplShape assertion (SIGABRT) as
WebKit GC collected string data still referenced by the inflight request.
Fix: await session.abort() in all four completion/error paths:
- startTask promptAsync error handler (launch path)
- resume promptAsync error handler (resume path)
- cancelTask (explicit cancel path)
- tryCompleteTask (normal completion path)
Also marks the two .catch() error callbacks as async so the await is
valid.
Test: update session.deleted cascade test to flush two microtask rounds
since cancelTask now awaits abort before cleanupPendingByParent.
TTL (pruneStaleTasksAndNotifications) now resets on last activity:
- Uses task.progress.lastUpdate as TTL anchor for running tasks
(was always using startedAt, causing 30-min hard deadline)
- Added taskTtlMs config option for user-adjustable TTL
- Error message shows actual TTL duration, not hardcoded '30 minutes'
- 3 new tests for the new behavior
- completedTaskSummaries now includes status and error info
- notifyParentSession: noReply=false for failed tasks so parent reacts
- Batch notification distinguishes successful vs failed/cancelled tasks
- notification-template updated to show task errors
- task-poller: session-gone tests (85 new lines)
- CI: add Bun shim to PATH for legacy plugin migration tests
When a subagent session disappears from the status registry (process
crashed), the main agent was waiting the full stale timeout before
acting. Fix:
- Add sessionGoneTimeoutMs config option (default 60s, vs 30min normal)
- task-poller: use shorter timeout when session is gone from status
- manager: verify session existence when gone, fail crashed tasks
immediately with descriptive error
- Add legacy-plugin-toast hook for #2823 migration warnings
- Update schema with new config option
Add support for object-style entries in fallback_models arrays, enabling
per-model configuration of variant, reasoningEffort, temperature, top_p,
maxTokens, and thinking settings.
- Zod schema for FallbackModelObject with full validation
- normalizeFallbackModels() and flattenToFallbackModelStrings() utilities
- Provider-agnostic model resolution pipeline with fallback chain
- Session prompt params state management
- Fallback chain construction with prefix-match lookup
- Integration across delegate-task, background-agent, and plugin layers
Previously, when an explicit model was configured, the agent name was
omitted to prevent opencode's built-in agent fallback chain from
overriding the user-specified model. This removes that conditional logic
and always passes the agent name alongside the model. Tests are updated
to reflect this behavior change.
🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Keep BackgroundManager launch and resume from sending both agent and model so OpenCode does not override configured subagent models. Add launch and resume regressions for the live production path.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
rootDescendantCounts was incremented on every spawn but never decremented
when tasks reached terminal states (completed, cancelled, error, interrupt,
stale-pruned). This made maxDescendants=50 a session-lifetime quota instead
of its intended semantics as a concurrent-active agent cap.
Fix: add unregisterRootDescendant() in five terminal-state handlers:
- tryCompleteTask(): task completes successfully
- cancelTask(): running task cancelled (wasRunning guard prevents
double-decrement for pending tasks already handled by
rollbackPreStartDescendantReservation)
- session.error handler: task errors
- promptAsync catch (startTask): task interrupted on launch
- promptAsync catch (resume): task interrupted on resume
- onTaskPruned callback: stale task pruned (wasPending guard)
Fixes: code-yeongyu/oh-my-openagent#2700
Switch background task loop detection from percentage-based sliding window
(80% of 20-call window) to consecutive same-tool counting. Triggers when
same tool signature is called 20+ times in a row; a different tool resets
the counter.
- Replace countedToolPartIDs string[] with Set<string> for O(1) has/add vs O(n) includes/spread (C2)
- Cache resolveCircuitBreakerSettings at manager level to avoid repeated object creation (C3)
- Optimize recordToolCall to avoid full array copy with slice (L1)
Previously, pollRunningTasks() and checkAndInterruptStaleTasks() treated
any non-"idle" session status as "still running", which caused tasks with
terminal statuses like "interrupted" to be skipped indefinitely — both
for completion detection AND stale timeout. This made the parent session
hang forever waiting for an ALL COMPLETE notification that never came.
Extract isActiveSessionStatus() and isTerminalSessionStatus() that
classify session statuses explicitly. Only known active statuses
("busy", "retry", "running") protect tasks from completion/stale checks.
Known terminal statuses ("interrupted") trigger immediate completion.
Unknown statuses fall through to the standard idle/gone path with output
validation as a conservative default.
Introduced by: a0c93816 (2026-02-14), dc370f7f (2026-03-08)
Adds a configurable maxToolCalls limit (default: 200) that automatically
cancels background tasks when they exceed the threshold. This prevents
runaway subagent loops from burning unlimited tokens, as reported in #2571
where a Gemini subagent ran 809 consecutive tool calls over 3.5 hours
costing ~$350.
The circuit breaker triggers in the existing tool call tracking path
(message.part.updated/delta events) and cancels the task with a clear
error message explaining what happened. The limit is configurable via
background_task.maxToolCalls in oh-my-opencode.jsonc.
Fixes#2571
- MCP teardown race: add shutdownGeneration counter to prevent
in-flight connections from resurrecting after disconnectAll
- MCP multi-key disconnect race: replace disconnectedSessions Set
with generation-based Map to track per-session disconnect events
- MCP clients: check shutdownGeneration in stdio/http client
creators before inserting into state.clients
- BackgroundManager: call clearTaskHistoryWhenParentTasksGone after
timer-based task removal in scheduleTaskRemoval and notifyParentSession
- BackgroundManager: clean completedTaskSummaries when parent has
no remaining tasks
- Plugin dispose: remove duplicate tmuxSessionManager.cleanup call
since BackgroundManager.shutdown already handles it via onShutdown
H3: cancelTask(skipNotification=true) now schedules task removal.
Previously the early return path skipped cleanup, leaking task objects
in this.tasks Map permanently. Extracted scheduleTaskRemoval() helper
called from both skipNotification and normal paths.
H2: Per-task completion cleanup timer decoupled from allComplete check.
Previously cleanup timer only ran when ALL sibling tasks completed. Now
each finished task gets its own removal timer regardless of siblings.
H1+C2: TaskHistory.clearAll() added and wired into shutdown(). Added
clearSession() calls on session error/deletion and prune cycles.
taskHistory was the only data structure missed by shutdown().
Tests: 10 pass (3 cancel + 3 completion + 4 history)
柯杨