shouldDeferParentWakeForSessionHistory previously had only one escape
path from the defer state: stale pending tool call. If the assistant
had unfinished text but no pending tool call (session crashed
mid-stream, model errored after partial text, network died), the
escape never fired and parent-wake deferred forever. Background-agent
completions never woke the parent.
Add a second escape: when the assistant text blocks but no tool wait
is pending, dispatch the wake after toolCallDeferMaxMs anyway. The
prompt-async-gate still defends if the assistant text turns out to be
live; we just stop deferring indefinitely.
Closes pre-publish blocker V11.
The lead currently leaves teams alive after the task list drains because
none of the prompt surfaces tell it WHEN to close or HOW. omx-style
'self-closing' behavior was missing for four reasons (diagnosed via
prompt-engineering A/B/C: wrong / misframed / missing):
1. builtin team-mode skill 'Lifecycle' (B+C): 'phase ends / shape
outgrown' is qualitative, so the model maps it to 'wait for user'.
Step 6 jumped to team_delete without the request/approve pair the
tool contract requires. Replaced with a 'Closure Contract' (a
computable predicate over team_task_list + team_status) and an
explicit 'Closure Sequence' (request -> approve -> delete, with
force=true reserved for unrecoverable paths only).
2. TEAM_MESSAGE keyword injection (C): spent 100%% of its one-shot
budget on routing ('do not substitute delegate_task'), 0%% on
closure. Added the same closure rule in compressed form. Kept the
'NEVER substitute with delegate_task' literal that
keyword-detector/index.test.ts depends on.
3. team-mode-status-injector body (C): the only per-session injection
for team mode had no closure obligation. Replaced the optional
'load the team-mode skill ... otherwise use the team_* tools'
sentence with a 'Closure invariant' clause that ties the check to
every team_task_update.
4. member-guidance Wrap-up (A+B): step 3 said 'so the lead can decide
whether to request shutdown', but team_shutdown_request is
lead-only - members cannot initiate it. Step ordering also placed
the completion message before team_task_update, so the lead's
closable check would see stale data. Reordered to
task_update -> check task_list for new work -> if nothing left,
send a single 'closure-ready' message and idle. Test assertion
updated to match the new accurate contract.
Also: stripped Korean alternation from TEAM_PATTERN per directive
('절대로 코드 내에 한국어 적지 마라'). Pattern is now
/\\bteam[\\s_-]?mode\\b/i. Removed 4 Korean test cases
(2 positive triggers + 2 false-positive guards) that the pattern no
longer needs to defend, and updated the keyword-detector AGENTS.md
row.
Net: -71 lines across prompt surfaces. The Closure Contract is the
only addition; everything else tightened.
Tests: 428/428 pass across src/features/team-mode/,
src/features/builtin-skills/, src/hooks/keyword-detector/,
src/hooks/team-mode-status-injector/, src/hooks/team-mailbox-injector/,
src/hooks/team-tool-gating/, src/hooks/team-session-events/.
LSP: no errors introduced (one pre-existing error in
keyword-detector/index.test.ts confirmed pre-existing on dev).
In v4.1.0+, users observed duplicate assistant streams rendering the same
content in two languages simultaneously (e.g. Chinese + English), most often
at the end of a turn.
Root cause: ParentWakeNotifier.requeueWake() unconditionally requeued ANY
wake that arrived during the background-agent-parent-wake post-dispatch
hold window. When a duplicate completion edge fired during that hold, the
same wake was replayed after the hold expired, triggering a second prompt
dispatch and a parallel assistant stream.
The fix compares the new wake against dispatchedParentWakes.get(sessionID)
and drops identical wakes during the gate hold, while preserving the existing
requeue behavior for genuinely-new wakes and failed-dispatch retries.
Regression test added in given/when/then style covering the duplicate-during-
hold scenario (TDD red-then-green).
Fixes#4256Fixes#4019
- prometheus-prompt.test.ts: close missing }) on the OpenSpec expanded
commands describe block (introduced by d66b6bcbf, parse error).
- agent-sort-shim/agent-config-integration/continuation-injection/
unstable-agent-babysitter/subagent-resolver/sync-executor/
resolve-caller-team-lead tests: expect 'Sisyphus - ultraworker'
(lowercase) to match production after cd39f8858, which lowercased the
display name to dodge a TUI ZWSP rendering glitch. Legacy uppercase
inputs that exercise the normalization path are preserved.
- sync-executor.ts + resolve-caller-team-lead.ts: route legacy display
name inputs through normalizeAgentForPrompt so prompt agent names and
caller team lead lookups produce the canonical lowercase form.
PR #4146 fixed the async resolvers (resolveSkillContentAsync, resolveMultipleSkillsAsync) to support unambiguous short-name skill lookups by routing through matchSkillByName. But the public getSkillByName API (exported from src/features/opencode-skill-loader/) was left on the old skills.find(s => s.name === name) lookup, so any external caller asking for 'systematic-debugging' on a 'superpowers/systematic-debugging' skill silently gets undefined.
Wire getSkillByName through the same matchSkillByName helper so the public API matches the async resolution semantics:
- Exact full-name lookup (case-insensitive) is preferred.
- Unambiguous short-name lookup falls back to the unique namespaced match.
- Ambiguous short-name (>=2 namespaces share the same short tail) returns undefined, mirroring matchSkillByName.
Regression tests added to src/features/opencode-skill-loader/loader.test.ts under a new 'getSkillByName' describe block:
- exact full-name returns the skill
- namespaced skill resolves by its unique short name
- ambiguous short name returns undefined
Verification: 3/3 new cases pass, 129/129 full src/features/opencode-skill-loader tests pass (was 126/126 pre-fix), bun run typecheck clean.
Treat resolved abort responses with a non-null error payload the same as rejected aborts. This prevents stale-timeout cancellation bookkeeping from reporting success when the child session was not actually aborted.
Plan: .omo/plans/subagent-timeout-active-output.md
Convert OpenCode v2 session.next stream events into the existing message part activity path so child sessions that are still producing text, reasoning, or tool output refresh lastUpdate before stale polling runs.
This keeps the timeout poller from cancelling active subagents and preserves tool-call progress for session.next.tool.called events.
Plan: .omo/plans/subagent-timeout-active-output.md
Cubic caught that clearing recent parent activity on session.idle could reopen the stale-idle race. Keep the fresh activity marker until its normal expiry so background completions still defer while the parent turn is actively reasoning.
Red: parent idle after fresh reasoning delta dispatched an unexpected parent wake. Green: focused parent-wake regression suite passes.
Record fresh parent session message activity before parent-wake flushing so stale idle status cannot dispatch a background completion into a live reasoning turn.
Add regression coverage for the Discord 4.2.3/OpenCode 1.15.5 duplicate-branch repro shape where a parent reasoning delta arrives before the background all-complete wake.
Refs #4212
Refs #4019
Refs #3774
Plan: plans/background-notification-active-turn-queue.md
YeonGyu-Kim