Repository navigation
feat(warm-brief): check facts first and draw one card per pr or task - #30767
iamwhatever wants to merge 1 commit into
Conversation
Design Review (Opus 5.5) — ✅ PASSDesign-level review of Design-Verdict: PASS Nothing blocks: the PR fixes the root causes it names (claims checked against fact values, times checked against check times, word maps lower-cased per field), and the one thing it takes away is listed with a test. Notes
[DESIGN-REVIEWED] d01bffa Description read[DESCRIPTION-READ] 5c22e8947bc7df7183acf28a7e6bdf62fa4c91db34ef6837d28bbb5308dbd48a 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 |
First Principles Review (Opus 5.5) — ✅ PASSPremise-level review of First-Principles-Verdict: PASS Nothing blocks. The base RFC Notes
What this change shipsInventory (10 items) — 10 justifiedIntent: when the owner returns to a busy thread, the welcome states freshly checked facts (conflicts, failed checks) and shows each ask once, on its own card. A FIX plus a redesign; RFC §3.10 covers both.
[FIRST-PRINCIPLES-REVIEWED] d01bffa Description read[DESCRIPTION-READ] f14461e274035318df7feb18f3ffb1ad74aa95fbad302c772dda45fc66165997 That sha256 names the PR description this verdict read. Recompute it with |
UX Review (Opus 5.5) — ✅ PASSUX-level review of UX-Verdict: PASS No blocker: the screenshots cover every new card state, the blind reader read the PR pill correctly, and the answer lists are plain text by design. Notes
[UX-REVIEWED] d01bffa Description read[DESCRIPTION-READ] bafdc668040464a925490c5262571979dcfb3f6598f33303faca5bf98ed78437 That sha256 names everything this verdict read: the PR description, plus the 14 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 |
Opus 5.5 Review — 🔴 changes requested (blocking)Reviewed When the ledger changes while the brief is being written, the fallback welcome still draws its task, waiting-on-you and ask cards from the snapshot taken before the change, so the owner sees work-item states that are already out of date. BLOCKING — src/kiro_crew/dashboard/warm_task_brief.py:1891 [BLOCK-MERGE] d01bffa Verdict parsed from the review's SHA-scoped output markers for commit False positive or not applicable? A repository writer can comment: |
GPT 6.1 Review — 🔴 changes requested (blocking)GPT 6.1 found at least one blocking issue that must be resolved before merging This comment is updated in place on each push. BLOCKING -- src/kiro_crew/dashboard/warm_task_brief.py:1891 -- Changed-state fallback retains obsolete task and ask facts
[BLOCK-MERGE] d01bffa Adjudication (Opus 5.5) — is blocking on each finding proportionate?F1: MEDIUM. This is wrong output on the very path that exists to keep the post truthful. Confirmed in code:
The real fix is cheap: in False positive or not applicable? A repository writer can comment: |
1794ff3 to
09657d1
Compare
09657d1 to
0ef7818
Compare
0ef7818 to
04da77b
Compare
04da77b to
133b811
Compare
133b811 to
68eb1c5
Compare
68eb1c5 to
0c0ae8a
Compare
0c0ae8a to
cb1ab56
Compare
The 16:47Z welcome read GitHub at 16:47 and saw both PRs conflicting with 3 failed checks, yet said "blocked waiting for your approval at 11:17": lines were checked for fact ids, not for what they said, times passed when they appeared anywhere in the snapshot, lower-case provider values missed both word maps, and worker summaries stood beside the facts as yellow cards with the same asks drawn four times. A fact registry now runs one checker per kind before the model call (PR, task, waits on you, worker chat, approvals, goal-board asks, artifact stats, time); worker reports become hints that a newer PR read supersedes. The gateway builds one card per PR or task with its own tags in the brief's language, keeps a model sentence only when it contradicts no fact on its card, makes the headline cite a bad fact or uses its own, takes each ask's options from that subject's ask fact only, and accepts an HH:MM only when a fact carries it. The board stamps the same facts from the in-memory cache, with no network read.
cb1ab56 to
d01bffa
Compare
|
Superseded by #33032, which carries the surviving parts of this change (fact registry, Board PR tags, casing and time fixes) in the owner-directed one-PR redesign. Closing per owner decision 2026-11-09. |
Problem / Motivation
Goal: When the owner returns to a busy thread, the welcome states what the gateway just checked, so a conflicting PR or a failed check is always shown, and each ask appears once, with its own answers, on the card it belongs to.
The 16:47Z welcome on 2026-11-05 ("Crew Mate Harness Provider Support") read GitHub at 16:47 and saw both PRs conflicting with 3 failed checks each. Yet it said "#29509 is blocked waiting for your approval on two tool calls the chat made at 11:17", and the conflict showed only in a footnote. The top of the card held raw worker reports cut with "…", including "Could not read GitHub" from before the 16:47 read. The same four options were drawn four times under one ask, though they belonged to three different things. In zh the footnote showed the raw English words "review required · conflicting".
Why it matters
The welcome is the first thing the owner reads on return. When it contradicts a fresh read, the owner acts on stale words. That means approving or restarting work that first needs a rebase, and missing failed checks. Raw worker reports and repeated asks make the card slow to scan and easy to misread.
Not a goal
welcomeframe profile.What changed (motivation → approach → change)
Root causes, read at
origin/mainbefore this PR:typed_lineskept a line when its fact ids existed, never comparing the sentence with the fact's values._unbacked_factsaccepted any HH:MM in the grounding text, not only a check time.conflicting,review_required), but both word maps keyed on upper case. Both maps were also keyed by value alone, so a PR'sblockedmergeability got the task word.[OPTIONS:]line was copied under one ask.Approach (design:
warm-welcome-v3/report.mdsections 1–3; the owner accepted all eight recommendations):Fact registry (
dashboard/warm_task_brief_registry.py). One checker per kind runs before the model call:pr: the live read, as before.taskwaits_on_you: the board's ownawaits_person, so the welcome and the board agree.chat: running / interrupted / idle / closed.interruptedis the sidebar's own test.approval: per worker slot.ask: the goal-boardasksentry per item, then waiting question and change cards. The free[OPTIONS:]line is not a source.file:os.statonly, at most 10 artifact paths, inside the workspace root, never a sensitive path.timeEach fact is marked
badwhen it is a conflict, a failed check, requested changes, a closed worker chat on an open task, or a waiting approval. Closed tasks and remote workers ask nothing. A worker report older than a read of the item's own PR is superseded by that read. A wake check's file facts are preferred over stat-only ones (prefer_wake_files).Claim check (
dashboard/warm_task_brief_claims.py). Each bad value forbids a short, fixed phrase list stating its opposite, in all seven fixed-line languages: an exact lookup, not an open text scan (owner Q2). A sentence that contradicts a fact on its card is dropped.Cards (
dashboard/warm_task_brief_cards.py,components/chat/WarmBriefCards.tsx). There is one card per work item that needs attention, per PR no item holds, and per waiting question or change card.asksentry counts only while the item still waits on the person. There is one ask per subject, and a closed task keeps none.Buttons split out. Card answer buttons moved to a follow-up PR, which will fill an answer together with the item it answers. Local review blocked the button hand-off on different grounds four times, so this PR ships text only.
Chip bar kept as the click path. Whenever the last conductor turn had an
[OPTIONS:]line, the welcome copies today's chip bar unchanged. With the card buttons gone, it is the one-click answer.Time rule. An HH:MM must be the "as of" time or a time a fact carries (RFC 3.9.6 as written).
Casing. Both word maps are per field and lower case. The legacy card still reads older upper-case rows.
Dashboard.
with_worker_factsstamps each open goal-board item with its cached PR facts and that read's own time, only while the item still holds the PR that was read. The goal-board draws the same conflict, failed-check and review tags. Chat and approval state are never shown from the cache, and nothing is read from the network on page load.warm_task_brief.pystays under the 2,000-line cap: the prompt moved todashboard/warm_task_brief_prompt.py.This is a product-shape change to the welcome. Its RFC amendment (section 3.10 of
docs/request-for-change/rfc-delayed-task-brief.md) is in a companion docs PR, so First Principles may block until that merges.Backwards compatibility
Compatible: rows stored before this PR keep their old shape and still draw with the legacy card. Only new welcomes write
meta.brief.version: 3. The PR-number, SHA and secret scans are unchanged.The diff also takes one thing away: the tighter time rule. The welcome rejects an HH:MM that appears only in the transcript or the change list.
Reader: src/kiro_crew/dashboard/warm_task_brief.py:_unbacked_facts -- chat -- the prompt now names the allowed times;
test_a_time_only_the_snapshot_holds_fails_the_checkReader: src/kiro_crew/dashboard/member_waiting.py:pending_options -- chat -- still read and copied on every welcome;
test_a_note_in_the_live_window_wins_over_the_settled_disk_read,test_a_card_that_asks_keeps_the_chip_barReader: website/src/components/chat/WarmBriefCard.tsx:warmBriefOf -- chat -- older rows keep the legacy render; the existing
warmTaskBrief.test.tsxcasesTests
test/test_warm_task_brief_v3.py(new) covers:blockedkept apart from a task's.website/src/test/warmTaskBrief.test.tsxcovers per-field casing; the v3 card (tags, check line, no old sections, PR pill URL check); answers as text with no button; andErrorNoticefor a failed read.Proof: not provable -- other: a feature PR, not a fix; prove.py reverts fix hunks only
Manual verification
Screenshots / video
Before (today's card on the real 16:47Z row):
After (same 16:47Z facts; answers as text, the chip bar below the row is unchanged):
A PR that could not be read (dashed pill, "not checked" tag, error notice):
The goal-board with the same PR tags and their read time:
The other widths and themes
The "after" model sentences are written in the owner's language from the row's own words; the option labels are the conductor's own. The row stored no chat liveness, so there are no chat tags.
Related Issues
Refs #30527 (wake turn: its proven file, deploy and ticket checks join this fact table as one more source).
Checklist
feat|fix|docs|style|refactor|perf|test|chore|ci|build|revert: ...)Contribution License Agreement
Contributed under the project's Apache-2.0 license.