Skip to content

fix(dashboard): count a thread switch as away for the warm task brief - #21750

Merged
chenmingwei23 merged 1 commit into
mainfrom
fix/warm-brief-activation
Oct 19, 2026
Merged

chenmingwei23 merged 1 commit into
mainfrom
fix/warm-brief-activation

Conversation

@iamwhatever

@iamwhatever iamwhatever commented Oct 18, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: The warm task brief appears when the owner returns to a crewmate thread after leaving it for another chat, or after a patrol turn ends.

Since #20422 merged, no transcript holds a single warm_task_brief_claim row, so every return was dropped before the claim. The owner's real return left the conductor thread for another chat at 17:10Z and opened it again at 04:59Z. The thread was idle and the gateway had not restarted, yet no brief appeared. The full skip-path audit is in #21749.

Why it matters

The feature is shipped but never fires for the people it was built for. People who move between chats in one dashboard window never get a brief. Conductor and patrol chats lose most of the remaining returns, because they are often mid-turn or post patrol rows during the 60-second model call.

Not a goal

  • Changing the 30-minute minimum, the fixed opener, the prompt, the durable claim, or the one-model-call bound.
  • Changing the frontend. It already sends a slot_focused frame on every thread switch.
  • Adding socket-gap, reconnect, or visible-idle inference. Those false negatives stay accepted as written in RFC 3.3.
  • Adding a second presence signal for windows that stay visible but unfocused.

What changed (motivation → approach → change)

The symptom is that no brief ever appears. Four activation rules in src/kiro_crew/dashboard/warm_task_brief.py cause it:

  1. Only a hidden page starts an away episode. Switching threads never counted. Now a frame naming another thread starts an episode for the thread being left, under the same last-owner-view rule as a hidden page.

  2. Any owner frame ends every episode. A frame for another thread, window, or device wiped the episode. Now an episode ends only when an owner frame names its own thread again. A cap of 256 episodes evicts the oldest, together with its generation row.

  3. A return while slot.running is skipped and never retried. Now the brief waits for the turn to end, polling every 2 s for at most 30 minutes, and only while the owner stays on the thread and no new leave happens. If the owner typed after returning, the brief is skipped.

  4. Any fingerprint change at publication drops the result. Patrol turns, worker reports, and ledger writes all count as changes. Now a prepared result goes stale only on a new genuine user turn, a new away episode, a reset or replaced slot, or a finished task. A turn running at publication defers the result until it ends. The full fingerprint still drives dedup.

  5. The awaited turn cancels its own deferred brief. Its broadcast assistant row and turn admission both called cancel_warm_task_brief. Now only a live user row the person typed cancels a brief in preparation, through cancel_for_live_user_row, which skips automation text. Reset, stop, close and leave still cancel. The claim re-check also defers through _settled, and every real cancel logs a skip reason.

Two smaller changes:

  • session_summary._INJECTED_PREFIXES gains [work-ledger wake]. Without it, the conductor's wake rows count as typed requests, and the brief can quote one as the original request.
  • Each skip logs one debug line with the thread key and a fixed reason. No content is logged.

Design RFC: rfc-delayed-task-brief.md, status accepted on main. This PR adds a dated trigger amendment and updates the spec in docs/system-specs/modules/session.md in the same commit. Spend is unchanged: at most one tool-free background call per claimed fingerprint, and only on a return.

Backwards compatibility

Compatible: no route, frame shape, field, or stored format changes. The in-memory away map now holds one entry per left thread instead of at most one entry, capped at 256.

Removes nothing: the change only widens when an episode starts and narrows when a prepared result counts as stale; no path, row, key or function is removed.

Tests

test/test_warm_task_brief.py:

  • A thread switch arms the thread that was left; returning to it is a candidate.
  • A switch does not arm while another tab still shows the thread.
  • The reported case: switch, hide, a frame from another window, return to the other chat, then open the first thread. The episode survives all of it.
  • The away map is capped oldest-first and evicts the generation row too.
  • On a real _ChatSlot, a return during a turn survives that turn's own broadcast assistant reply and then posts. A patrol turn admitted during the model call defers publication until its reply lands.
  • A typed user row during the deferral cancels the brief. A [work-ledger wake] row does not.
  • Through turn_harness.run_turn, a real _run_chat: an admitted patrol turn does not cancel a pending brief, and a typed turn does.
  • A deferred brief is dropped when the owner leaves, when the deadline passes, or when the owner typed after returning.
  • Patrol activity during the model call still publishes. A user send drops the result.
  • user_fingerprint ignores assistant rows, wake rows, and ledger changes, and moves on a typed turn.
  • [work-ledger wake] rows are injected, not user turns.

These cases were changed to the new rules: unreasoned null never arms; the opener test expects two flushes; the stale-result test now uses a user send. test/test_slot_running_readers.py lists the two new running readers. local-gate.py backend related tests ran 21878 passed with 1 failure, a source-pin budget breach from a first test draft; the final tests replace that draft with run_turn, and test_source_pin_budget.py passes.

Mutation check: 16 hand mutants, one per new rule, and every one fails test/test_warm_task_brief.py. A probe file showed each skip path on main before the fix.

Manual verification

Local gates were green: flake8, mypy, isort, black, comment-history, brand, docs-lint, file line cap, sync-io, loop-bound locks, harness parity, feature map, and the flake-pattern ratchet. local-gate.py backend related tests ran 6832 passed with 1 failure, test_session_token_identity.py::test_native_settings_sources_repeated_permissive_reads_do_not_hide_a_restriction. That test passes in isolation and is outside this diff. Semgrep could not install on this host, so CI's SAST job is the check for it.

A local GPT review found nothing. A local Opus review raised one advisory (a user turn during a deferral) and one low finding (the generation row was not evicted with the cap). Both are fixed. A verifier confirmed them closed on the first head, and confirmed the reviewer's cancellation must-fix closed on 243cca148f.

No harness screenshot. kirocrew pod needs systemd --user, which this host lacks, and the worker sandbox cannot start a dev gateway or run kiro-cli. The diff has no frontend change, and the backend rules are covered by the focused tests above.

Related Issues

Fixes #21749. Follows #20422 and the RFC from #20157.

Pattern harvest

Rule candidate: review-prompt
Pattern: a presence or trigger rule that only one test fixture ever exercises. When the shipped trigger has zero production hits, such as zero claim rows, read real transcripts for one before designing the next rule.

Checklist

  • At most two commits (one is the norm), with a Conventional Commits title (feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert: ...)
  • Existing tests pass and new tests added for new functionality
  • Self-review completed; code follows project style guidelines
  • Documentation updated (if applicable)
  • No secrets, credentials, or internal references in the diff

Contribution License Agreement

Contributions are accepted under the project's Apache-2.0 license.

@iamwhatever
iamwhatever requested review from a team and KiroCrewCaptain as code owners October 18, 2026 05:49
@github-actions

github-actions Bot commented Oct 18, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ⏭️ skipped

Revision 243cca148fe3574436ab353a0f5df2349e32cb1c touches no user-facing surface (no changes under website/ or committed screenshots), so the UX review was skipped. Advisory — does not block merge.

@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Oct 18, 2026
@github-actions

github-actions Bot commented Oct 18, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — ✅ human override accepted

@iamwhatever overrode this lane for 243cca148fe3574436ab353a0f5df2349e32cb1c via /ai-review override (this commit only).

@github-actions

github-actions Bot commented Oct 18, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — 🟡 CONCERNS

Design-level review of 243cca148fe3574436ab353a0f5df2349e32cb1c — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS/CONCERNS are advisory.

Design-Verdict: CONCERNS

The PR rewrites the trigger of a maintainer-accepted RFC through an amendment the author wrote, and no maintainer has signed off on it.

Watch

  • The amendment has no maintainer approval. The RFC's status line records that the maintainer accepted "the user must leave … and return" with "explicit-signal false-negative tradeoff". The PR's 2026-10-18 amendment "supersedes the 'Switch chats', 'Hide on X, return on Y', and 'worker/task change' rows". As a result, a thread switch now counts as away, and the accepted design no longer matches what ships. Nothing records that the person who accepted the tradeoff agreed to reverse it.
    Clears when: a maintainer approves the trigger amendment in a PR comment, linked from the amendment line.
  • A brief can be outdated by the time it posts. _still_current now compares only user_fingerprint. A brief built from the pre-patrol snapshot can therefore publish after a patrol turn has moved the work on. The brief only waits for that turn to end; nothing re-reads the newer state. Because of that, "where it stands" can contradict the crewmate message just above it.
    Clears when: publication re-snapshots after a deferral and drops the result (or regenerates it once) when the full fingerprint moved, or the RFC states this staleness is accepted.

[DESIGN-REVIEWED] 243cca1

Description read

[DESCRIPTION-READ] ab75d1224d742170b3c332850fe2ec0099e44b1d598f38ad04a48c6390e77459

That sha256 names everything this verdict read: the PR description, plus the 1 evidence file(s) the workflow collected from it and handed this review. It covers that evidence because the media strip replaces every attachment URL with the same placeholder, so an edit swapping one attachment for another would leave the description's captured text identical while what this review judged changed. Recompute it with .github/scripts/pr-description-capture.sh over the same inputs; if it differs, the description or that evidence changed after this verdict was formed and any finding drawn from either is unproven.

@github-actions

github-actions Bot commented Oct 18, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of 243cca148fe3574436ab353a0f5df2349e32cb1c and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 243cca1

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 243cca148fe3574436ab353a0f5df2349e32cb1c: <one-sentence reason>

@github-actions

github-actions Bot commented Oct 18, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed 243cca148fe3574436ab353a0f5df2349e32cb1c — this comment is updated in place on each push.

Review details

No findings block the merge; one advisory finding on split-view pane focus.

FINDING — src/kiro_crew/dashboard/warm_task_brief.py:209 — in split view, SessionGridView calls emitSlotFocused(focusedPaneSlot) on the same socket whenever pane focus moves, and the server cannot tell that apart from a sidebar switch, so slot_key != previous now arms an away episode for a crewmate DM pane that never left the screen (crewmate DM slots appear in the split-view picker). Focusing that pane again after 30+ minutes posts an unrequested "Welcome back" opener and starts a background model call → Fix: have the client mark pane-focus frames, or send an explicit leave reason that is_leave requires; either needs a frontend change outside this diff.

[OPUS-REVIEWED] 243cca1

Verdict parsed from the review's SHA-scoped output markers for commit 243cca148fe3574436ab353a0f5df2349e32cb1c.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 243cca148fe3574436ab353a0f5df2349e32cb1c: <one-sentence reason>

@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention and removed readiness: checking Automated validation is still running labels Oct 18, 2026

@bolichen97 bolichen97 left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Not ready. The new defer-until-the-turn-ends path does not survive the turn it waits for.

Head reviewed: 60c8c92.

Rules 1 and 2 (a thread switch arms the thread left; only a frame for the same thread ends its episode) read correctly, and the 256-episode cap evicts the generation row too. The [work-ledger wake] prefix addition is correct.

One must-fix: _wait_for_idle_turn and the publish-time _settled wait run while _warm_task_brief_model_active does not hold the slot. The turn they wait for ends by appending a broadcast assistant row, and _ChatSlot.append calls cancel_warm_task_brief, which cancels the task. A newly admitted turn in chat_runner cancels it the same way. So rule 3 (defer a return during a turn) and the "a turn running at publication defers the result" clause of rule 4 drop the brief in the cases they were written for. The new tests use _BusySlot, which has no cancel hook, so they pass without exercising this path. Details inline.

Design call for the maintainer: First Principles is BLOCK on this head because the trigger amendment reverses accepted rows of rfc-delayed-task-brief.md (the "Switch chats" and "Hide on X, return on Y" rows, and the "worker/task change" staleness rule). As the maintainer who accepted that RFC, please record the decision on the amendment, through the override or a separate merged amendment. Design Review also asks for the expected brief rate on a conductor thread with periodic patrols. I did not post an override.

Not repeated: the split-view pane-focus false arm (Opus advisory) stands as written there.

return current


async def _wait_for_idle_turn(

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🔴 The deferral waits for a turn whose own reply cancels the deferral

_wait_for_idle_turn polls slot.running while the brief task is not marked model-active. The running turn ends with slot.append("assistant", ...) (broadcast), and _ChatSlot.append calls cancel_warm_task_brief(owner, slot.key). That function cancels any task not in _warm_task_brief_model_active. The asyncio.sleep here then raises CancelledError and the brief is gone. The publish-time wait in _settled has the same gap: model_active is discarded before it runs, so a patrol turn that starts at publication (admitted turns call cancel_warm_task_brief in chat_runner) or that ends with an assistant row also cancels it.

    while slot.running:
        if (
            ...
        ):
            return False
        await asyncio.sleep(_IDLE_POLL_SECS)
    return True

Why it matters: Rule 3 and the publication deferral in rule 4 are the fixes for conductor and patrol threads. In production they drop the brief in exactly those cases, with no skip log line. The new tests use _BusySlot, which has no append cancel hook, so test_return_during_a_turn_defers_until_the_turn_ends and test_patrol_activity_during_the_model_call_still_publishes pass without the real cancellation path.

Suggestion: Keep the task protected from non-user cancellation for both waits (for example, hold the slot in a "deferring" set that cancel_warm_task_brief respects for assistant rows and non-user admitted turns, with finally cleanup), and keep the existing user_fingerprint and generation checks as the staleness gate. Add a test that drives a real assistant append through the cancel hook during the deferral. If the running turn's reply in fact reaches the slot with broadcast=False, I will withdraw this.
Rule: SAGE correctness; testing-conventions (test the claimed path)

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed in 243cca1.

You were right. The awaited turn's own broadcast assistant row, and turn admission in chat_runner, both cancelled the deferring brief.

  • slot_transcript.append now cancels only on a broadcast role-user row, through cancel_for_live_user_row. That helper skips automation text such as [work-ledger wake] and [auto-nudge cycle.
  • Assistant rows and turn admission no longer cancel a brief. A typed turn still cancels through its own user row: chat_send.py:1051, the steer at chat_delivery.py:895, and the queued drain at responsive_chat.py:784.
  • Reset, stop, close and leave still cancel.
  • The claim re-check now goes through _settled as well, so a patrol turn admitted before the opener defers it instead of dropping it.
  • Every real cancel logs warm task brief skipped for <key>: cancelled.

The tests now run on the real paths:

  • test_return_during_a_turn_survives_that_turns_own_reply and test_patrol_turn_at_publication_defers_and_still_publishes use a real _ChatSlot. The awaited turn ends with a real broadcast append("assistant", ...).
  • test_an_admitted_patrol_turn_does_not_cancel_a_brief and test_a_typed_turn_cancels_a_brief drive a real _run_chat through turn_harness.run_turn.

Against the old head, four of these fail. Mutation check: 16 of 16 hand mutants fail the suite, including re-adding the assistant-row cancel and the admission cancel.

@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • needs-a-decision: maintainer approval of the 2026-10-18 trigger amendment span=ac9fe1e66240

Agreed: the author wrote the amendment, and it reverses two accepted §3.2 rows.
The evidence for reversing them: zero claim rows in any transcript since #20422, and the owner's real return was a chat switch (#21749).
This waits on the owner's ruling, which the conductor has asked for. Approval clears this item and the First Principles block; no code change is planned for it.

@iamwhatever

iamwhatever commented Oct 18, 2026 •

Copy link
Copy Markdown
Contributor Author
  • needs-a-decision: expected brief rate on a patrolled conductor thread span=17d504ee1387

Expected rate: one background call and two messages per return to a thread after at least 30 minutes on another thread or with the page hidden.
Patrol rows change the dedup fingerprint, so on a patrolled conductor almost every such return qualifies. Returns under 30 minutes, repeat focus, and returns with no open task cost nothing.
Hopping between threads every few minutes never qualifies. The ceiling is one call per 30-minute absence per thread.
This rate has not been accepted yet. The question for the owner: accept it, or narrow dedup so it ignores non-user turns.

@iamwhatever

Copy link
Copy Markdown
Contributor Author

/ai-review override first-principles 60c8c92: owner-directed fix; the shipped trigger never fired (0 claim rows since #20422); switch-as-away, defer-on-running and user-only staleness were decided by the owner, and the RFC amendment ships with the code

@github-actions

Copy link
Copy Markdown
Contributor

Human judgment recorded

@iamwhatever marked the first-principles AI finding as false positive, not applicable, or explicitly accepted for 60c8c92d010b65b74ddb78da39305594d4a06f2b.

owner-directed fix; the shipped trigger never fired (0 claim rows since #20422); switch-as-away, defer-on-running and user-only staleness were decided by the owner, and the RFC amendment ships with the code

This decision applies only to this commit. A new push requires a new judgment.

@iamwhatever
iamwhatever force-pushed the fix/warm-brief-activation branch from 60c8c92 to 243cca1 Compare October 18, 2026 07:37
@iamwhatever

Copy link
Copy Markdown
Contributor Author

On the Opus advisory, split-view pane focus can arm a pane that is still on screen. Rebutted: it cannot reach a brief, so no code change.

  • The brief runs only for member threads. handle_focus_frame skips any other slot as not_member_thread.
  • Member threads never render as split-view panes. isChatPageSurface excludes the member surface (pinned in website/src/utils/channelOrigin.test.ts, "never admits member DM threads into chat-page surfaces"), and member rows open on /members instead (opensElsewhereOf in pages/chat-sidebar/rows.ts).
  • A pane switch therefore arms only ordinary chat slots, and returning to one is rejected before any read or spend. The leftover entry stays under the 256-episode cap.

@github-actions github-actions Bot added readiness: checking Automated validation is still running and removed readiness: action required A blocking check or review needs attention labels Oct 18, 2026
@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • needs-a-decision: maintainer approval of the 2026-10-18 trigger amendment span=ac9fe1e66240

Unchanged from the previous head. The author wrote the amendment, and it reverses two accepted §3.2 rows. The evidence: zero claim rows since #20422, and the owner's real return was a chat switch (#21749).
This waits on the owner's ruling, which the conductor has asked for. The First Principles override is the same decision.

@iamwhatever

Copy link
Copy Markdown
Contributor Author
  • needs-a-decision: expected brief rate on a conductor thread patrolling every 5-15 minutes span=17d504ee1387

Rate: one background call and two messages per qualifying return. A return qualifies after at least 30 minutes on another thread or with the page hidden.
A 5-15 minute patrol adds no briefs. It only changes the fingerprint, so nearly every qualifying return is eligible. Hard ceiling: 48 briefs per thread per day, one per 30-minute absence.
Measured: on 2026-10-17 the owner's conductor thread had about 4 human returns after at least 30 minutes away (00:27->05:43, 05:45->06:16, 06:16->17:06, 17:10->04:59). That is about 4 briefs, or 4 background calls, a day.
Not yet accepted. The owner decides: accept about 4 a day (ceiling 48), or narrow dedup to user turns only, which would cut it to returns after a new typed request.

@github-actions github-actions Bot added readiness: action required A blocking check or review needs attention and removed readiness: checking Automated validation is still running labels Oct 18, 2026

@bolichen97 bolichen97 left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The must-fix from my previous review is fixed on this head. The PR now waits only on a maintainer decision about the RFC amendment.

Head reviewed: 243cca1.

What changed my mind on the cancellation finding:

  • _ChatSlot.append now cancels only for a broadcast user row, through cancel_for_live_user_row, and only when the text is not automation ([work-ledger wake], [auto-nudge cycle, and the other injected prefixes). The running turn's own assistant reply no longer cancels the deferred brief.
  • _run_chat no longer calls cancel_warm_task_brief on admission. A typed turn still cancels through its user row. Reset, stop, close and leave still cancel.
  • The claim re-check now defers through _settled, so a turn admitted after the snapshot also defers the opener.
  • The new tests use a real _ChatSlot whose append routes back through the cancel hook, and a real _run_chat through turn_harness.run_turn. If the role check went back to {"user", "assistant"}, test_return_during_a_turn_survives_that_turns_own_reply would raise CancelledError. If admission cancelled again, test_an_admitted_patrol_turn_does_not_cancel_a_brief would fail. I read these tests; I did not run them locally.

One behaviour to note, inside the amendment as written: a regenerate or continue during the brief no longer supersedes it, because it adds no typed user row and leaves user_fingerprint unchanged. The brief then posts after that reply. This matches rule (5), "only a live row the person typed cancels", so I do not ask for a change.

Remaining decision: First Principles is BLOCK on 243cca1. The override recorded earlier applies only to 60c8c92, and the author's own disposition on this head says the amendment still waits on the owner's ruling. A maintainer needs to record that decision on this head, through the override or a separate merged amendment on main. The same decision answers the Design Review item on the expected brief rate, which the amendment now states (about four a day on a busy conductor thread, ceiling 48). I did not post an override.

The one red backend shard, Backend Tests (Windows) (2), fails in test/test_history_consolidation_idle_seed.py with a Windows PermissionError on a temp rename. That file is outside this diff.

@bolichen97
bolichen97 dismissed their stale review October 18, 2026 08:10

Withdrawn: the push at 243cca1 fixes the cancellation gap (a waiting brief is now cancelled only by a row the person typed) and the new tests use a real slot and run loop. What remains is the maintainer decision on the First Principles check.

@iamwhatever

Copy link
Copy Markdown
Contributor Author

/ai-review override first-principles 243cca1: Maintainer decision. I accept the trigger amendment: switch-as-away, defer-on-running and user-only staleness, with the RFC amendment shipping alongside the code. The shipped trigger never fired (0 claim rows since #20422). I also accept the brief rate in the Design reply: about 4 a day measured on a conductor thread, ceiling 48. bolichen97's must-fix is resolved on this head.

@github-actions

Copy link
Copy Markdown
Contributor

Human judgment recorded

@iamwhatever marked the first-principles AI finding as false positive, not applicable, or explicitly accepted for 243cca148fe3574436ab353a0f5df2349e32cb1c.

Maintainer decision. I accept the trigger amendment: switch-as-away, defer-on-running and user-only staleness, with the RFC amendment shipping alongside the code. The shipped trigger never fired (0 claim rows since #20422). I also accept the brief rate in the Design reply: about 4 a day measured on a conductor thread, ceiling 48. bolichen97's must-fix is resolved on this head.

This decision applies only to this commit. A new push requires a new judgment.

@github-actions github-actions Bot added readiness: passed Eligible automated validation passed for the current revision and removed readiness: action required A blocking check or review needs attention labels Oct 19, 2026
@chenmingwei23
chenmingwei23 merged commit 5494e55 into main Oct 19, 2026
158 of 167 checks passed
@chenmingwei23
chenmingwei23 deleted the fix/warm-brief-activation branch October 19, 2026 02:21
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Oct 19, 2026
iamwhatever pushed a commit that referenced this pull request Oct 26, 2026
Bring the delayed-task-brief RFC and its directory index into agreement
with the document's amendments and with what shipped on main.

The warm task brief shipped in #20422 and its 2026-10-18, 2026-10-22 and
2026-10-24 amendments shipped in #21750, #22828, #22839 and #23847, but
the RFC still read `accepted` ("nothing built yet") with
implementation-prs [] and a 2026-10-14 audit stamp.

The front matter now records status implemented, those five PRs, and
last-audited 2026-10-26 at 1cf77b5; the section 1 status and
"Audited on" lines match it; and the snapshot's third field is renamed
"Suggested actions" to match the section 3.5 output it feeds.

The README index row no longer describes the superseded preparing-status
design or says implementation waits for the RFC. It reads implemented,
names the shipped PRs, and summarises the shipped trigger and card.
The audit paragraph gains a dated re-audit sentence for the row.

Closes #20887
iamwhatever pushed a commit that referenced this pull request Oct 28, 2026
Bring the delayed-task-brief RFC and its directory index into agreement
with the document's amendments and with what shipped on main.

The warm task brief shipped in #20422 and its amendments shipped in
#21750, #22828, #22839, #23847, #24512 and #24307, but the RFC still
read `accepted` ("nothing built yet") with implementation-prs [] and a
2026-10-14 audit stamp.

The front matter now records status implemented, those seven PRs, and
last-audited 2026-10-28 at 7cbf872; the section 1 status and
"Audited on" lines match it; and the snapshot's third field is renamed
"Suggested actions" to match the section 3.5 output it feeds.

The README index row no longer describes the superseded preparing-status
design or says implementation waits for the RFC. It reads implemented,
names the shipped PRs, and summarises the shipped trigger, the
free-form brief card and the leave-after-opener rule. The audit
paragraph gains a dated re-audit sentence for the row.

Closes #20887
iamwhatever pushed a commit that referenced this pull request Oct 29, 2026
Bring the delayed-task-brief RFC and its directory index into agreement
with the document's amendments and with what shipped on main.

The warm task brief shipped in #20422 and its amendments shipped in
#21750, #22828, #22839, #23847, #24512 and #24307, but the RFC still
read `accepted` ("nothing built yet") with implementation-prs [] and a
2026-10-14 audit stamp.

The 2026-10-28 writer amendment (section 3.8, #25433) is design only:
main has no wake turn and no `dashboard.warm_brief_wake` setting. So
the front matter now records status partial, those seven PRs, and
last-audited 2026-10-29 at 4d36177; the section 1 status line
names what shipped and that section 3.8 is not built; the "Audited on"
line matches; and the snapshot's third field is renamed "Suggested
actions" to match the section 3.5 output it feeds.

The README index row no longer describes the superseded preparing-status
design or says implementation waits for the RFC. It reads partial,
names the shipped PRs, summarises the shipped trigger, the free-form
brief card and the leave-after-opener rule, and names the unbuilt
writer amendment. The audit paragraph gains a dated re-audit sentence
for the row.

Closes #20887
iamwhatever pushed a commit that referenced this pull request Nov 2, 2026
…21712)

Bring the delayed-task-brief RFC and its directory index into agreement
with the document's amendments and with what shipped on main.

The warm task brief shipped in #20422 and its amendments shipped in
#21750, #22828, #22839, #23847, #24512, #24307, #25881 (Crew Mode
scope), #26500 (fixed progress orb) and #26652 (first part of the
2026-10-31 redesign), yet the front matter and README row still
read `accepted` ("nothing built yet") with implementation-prs [] and a
2026-10-14 audit stamp.

Not built on main: the 2026-10-28 writer amendment (section 3.8; main
has no wake turn and no `dashboard.warm_brief_wake` setting), the
2026-11-01 trigger amendment (#26938 is open), and the live checks,
links and copied option buttons of section 3.9.3. So the front matter
now records status partial, those ten PRs, and last-audited 2026-11-01
at fed53fc; the section 1 status line names what shipped and what
is not built; the "Audited on" line matches; and the snapshot's third
field is renamed "Suggested actions" to match the section 3.5 output it
feeds.

The README index row no longer describes the superseded preparing-status
design or says implementation waits for the RFC. It reads partial,
names the shipped PRs, summarises the shipped trigger, the one-message
brief with its fixed card and quiet return, and names the unbuilt
parts. The audit paragraph gains a dated re-audit sentence for the row.

Closes #20887
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

fix: warm task brief never shows after a chat switch or during a running turn

3 participants