Skip to content

feat(chat): render every warm welcome fact in the gateway - #33032

Closed
iamwhatever wants to merge 1 commit into
mainfrom
feat/warm-welcome-gateway-facts
Closed

iamwhatever wants to merge 1 commit into
mainfrom
feat/warm-welcome-gateway-facts

Conversation

@iamwhatever

@iamwhatever iamwhatever commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: The warm welcome and the Board state only facts that gateway code read itself, each with its read time, so an owner can act on a welcome without asking what is true.

A truth audit of the 71 warm welcomes posted 2026-11-02 to 2026-11-07 found the gateway's own pull-request rows right 34 of 34 times, the model's sentences false 11 of 58 times, and sentences copied from worker reports stale 5 of 9 times. The existing value check would have caught 1 of the 11. A UX review of the same welcomes found 2 of 71 an owner could act on within five seconds. The Board showed no pull-request state at all.

Owner-directed shape. The owner directed this as ONE pull request holding both the RFC amendment (docs/request-for-change/rfc-delayed-task-brief.md section 3.11) and all code, on 2026-11-08, relayed by the conductor. Design and First Principles: the RFC change in this PR is the owner's own ruling, not an agent's proposal.

Why it matters

The welcome is the first thing an owner reads on return. When one sentence in five is false, the owner has to re-check everything, and the welcome costs time instead of saving it. Owners asked a follow-up question in 32 of 55 replies.

Not a goal

  • Card buttons that replace the chip bar (the RFC 3.10 Q1 follow-up).
  • The RFC 3.8.1 wake writes and gated close (unchanged, as the owner ruled).
  • A "Check now" button or any network read on Board page load.
  • A running-worker count in the welcome (the Board shows each worker's liveness).

What changed (motivation → approach → change)

Root cause: the model wrote prose about facts and a phrase list tried to catch it. The fix moves every fact to gateway code.

  • Welcome (warm_task_brief_welcome.py, warm_task_brief.py). meta.brief version 4: count line ("Waiting on you: N" / "N 件事等你") plus the first must-do; at most 3 must-do cards from awaits_person (the Board's own test); tags from the ledger and this welcome's live PR read, bad first; a PR pill only for a PR this welcome read; at most 3 "since you left" rows, bad first, "+N more on the Board"; a Board link. The conductor's why, options with outcome and pick come from its goal-board asks record and show under "Suggested HH:MM" / "建议(HH:MM)" and "Recommended" / "推荐". A merged or closed PR drops every ask about it. No model text reaches the welcome: the owner allowed one framing line "or none", and a word list cannot prove a sentence holds no fact (CI review: "The tests succeeded." passed every gate), so framing and body stay empty as this PR's default. Owner ruling 2026-11-09: model pictures and the framing line stay out of this PR; RFC 3.11.1 records it. The per-return one-call model call is removed; only the RFC 3.8.1 wake still runs a model turn. Conductor options draw as plain text rows, and every gateway string is redacted on its whole scan views before any cut. The welcome no longer shows a running count; the Board shows each worker's liveness. Every gateway string passes the secret scan views and is redacted on every path. Facts are read again at post time; the retry-on-change loop is gone. Cards are static once posted and each says "checked HH:MM" (owner ruling 2026-11-09); live cards that hide once their item stops waiting are deferred to a follow-up. A model failure costs only the framing line.
  • Ask record. goal-board manifest v2 widens asks to {what, why, options: [{label, outcome}], pick, pick_why, written_at}; written_at can never be later than the field's write time. The goal-conductor skill says how to write it.
  • Board PR facts. object/observed gains one code-only producer, warm_brief (the welcome's live read, once per read, no extra GitHub call). Which PR belongs to an item has one key, ledger_ref (acceptance.pr, then item.pr); the welcome, pr_facts and goal-board (via a stamped pr_url) all use it. PR state, checks, review and mergeable come only from the warm_brief producer's newest read. Deferred: refreshing the Board on conductor wakes (recording accept_eval verdicts) is cut from this PR, because the evaluator maps an expired gh login to fail and the Board would show it as failed checks. RFC 3.11.1 records it; follow-up #33688. A new objects slot fold keeps the newest read per subject and producer (64 subjects, 2 KiB facts, row cost measured at 9,144 bytes and charged 9,200). /api/crew-board adds pr_facts and ask_records; goal-board gets a prs field. Both draw the warm read's facts with its time.
  • Preparing hint. PreparingReplyBubble (lazy-loaded, so the App chunk does not grow) puts the caption inside a reply bubble in ChatTranscriptView and ChatPane; it folds out in place as the welcome lands (website UX lens 13).
  • RFC and specs. RFC section 3.11 (rulings, shape, ask record, objects fold, preparing hint, supersedes); the stale board:409 reference fixed; crew-log core, emitter and session-types specs updated.

RFC: rfc-delayed-task-brief.md is partial on main; section 3.11 is added by this PR at the owner's direction.

Backwards compatibility

Compatible: a stored brief of version 3 or older keeps drawing in its old shape through WarmBriefCard; a version 1 goal-board asks entry (options: [string]) still reads as labels; the new producers widen a closed vocabulary and add no required field.

Reader: src/kiro_crew/dashboard/warm_task_brief.py:_render -- chat -- replaces the model-written headline/status/lines fields for new welcomes; old rows keep their meta and draw via WarmBriefCard (test_warm_task_brief.py)
Reader: website/src/components/chat/WarmBriefCard.tsx -- chat -- reads version < 4 as before and hands version 4 to WarmWelcomeCard (WarmWelcomeCard.test.tsx)
Reader: src/kiro_crew/dashboard/handlers/work_ledger_board.py:_conductor_asks -- crew page -- still returns option labels per item from the widened record (test_crew_board_asks.py)
Reader: src/kiro_crew/dashboard_templates/builtin/goal-board/template.html:optionsFor -- crew page -- reads both string and {label, outcome} options (goalBoardPage.test.ts, test_dashboard_template_goal-board.py)
Reader: test/test_warm_task_brief_shape.py, test_warm_task_brief_links.py, test_warm_task_brief_asks.py, test_warm_task_brief_unverified.py -- release -- deleted with the model-written shape they tested; their redaction and marker checks moved to test_warm_task_brief_welcome.py

Tests

  • test/test_warm_task_brief_welcome.py (new): count line and 3-card cap; the conductor record shown with its time and hidden without one; a pick outside the labels dropped; a merged or closed PR dropping its asks; only read PRs named; failed read "not checked since"; changes bad first with "+N"; objects fold bounds, producer check and out-of-order reads; the warm_brief producer once per read; token, PEM and marker redaction; a secret in a gateway string redacted on every path; a remote worker's binding kept in the snapshot.
  • test/test_crew_log_fold_eager_memory.py: the objects row measured at its clamps in 4-byte text.
  • test/test_warm_task_brief.py, _redesign.py, _wake.py, _crew_mode.py, _facts.py: adapted to the version 4 shape; race-redo tests removed with the race loop.
  • Website: WarmWelcomeCard.test.tsx, prFactTags.test.ts, goalBoardPage.test.ts (the warm read only, a read from another day dated), ChatPane.preparing.test.tsx and ChatPage.views.test.tsx (caption inside a reply bubble).

Proof: not provable -- other: feature change, not a fix; the tests pin new behaviour rather than a reverted defect

Manual verification

Captured with website/scripts/capture-warm-welcome-gateway.mjs against the capture harness at 1280 and 320 px: the preparing bubble, then the welcome landing in its place; every frame asserted. Not run against a live gateway.

Screenshots / video

Captured on head e8d5f6f (website/scripts/capture-warm-welcome-gateway.mjs, website/scripts/capture-crew-pr-facts.mjs; every frame asserted).

Welcome: preparing bubble folding into the welcome

preparing, 1280
welcome, 1280: static card with "05:58 核实", dated suggestion "建议(05:40)", plain-text options with (推荐)

Ultra Mode Board "Needs your input" ask (left) and Crew Board page row (right): facts named by the PR they were read for (acme/widgets#7, not the worker's #9), tags with read time, neutral labels. Captured before the checker line was removed: the dim "checker HH:MM" line in these frames is no longer drawn.

Board, 1280, en
Board, 1280, zh-CN

320 / 360 px

preparing, 320
welcome, 320
Board, 360, en

Related Issues

Refs #25306. Follow-up: #33688 (Board refresh on conductor wakes, deferred). Fixes #32844 (the preparing hint now sits in the reply bubble). Supersedes #30767 (its survivors are folded in; that PR is not pushed to).

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; see the Licensing section of CONTRIBUTING.md.

@iamwhatever
iamwhatever requested review from a team and KiroCrewCaptain as code owners November 8, 2026 08:28
@iamwhatever
iamwhatever requested a review from Zedmor November 8, 2026 08:28
@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Nov 8, 2026
@github-actions

github-actions Bot commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

Design Review (Opus 5.5) — ✅ PASS (a BLOCK with no Trigger and no Outcome does not block)

Design-level review of fc1db03cffa5ca2172fdab4742faa44d4214fac5 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

Design-Verdict: PASS

cannot evaluate: missing screenshot or recording of the version 4 WarmWelcomeCard, the PreparingReplyBubble fold-out, and the Board's new PR-fact tags. The PR adds these surfaces, but the evidence list shows nothing downloaded or committed.

Blockers

This revision has no rendered evidence for the new chat and Board surfaces
Trigger: The diff adds new files website/src/components/chat/WarmWelcomeCard.tsx and PreparingReplyBubble.tsx/PreparingReplyBubbleView.tsx, and changes CrewBoardPage.tsx with prFactTags.ts. The description says "Captured with website/scripts/capture-warm-welcome-gateway.mjs … at 1280 and 320 px", but design-evidence.txt lists 0 images, 0 recordings, 0 committed media and 0 transport failures.
Outcome: With nothing rendered, I can't check the shape claims: the count line, the 3-card cap, "Suggested HH:MM", the "checked HH:MM" stamps, the bubble folding out in place, and the Board pills at 320 px. A layout regression on the first surface an owner reads on return would ship unreviewed.
Fix: attach the capture script's output to the PR description as github.com/user-attachments images, or commit it under temp-screenshots/warm-welcome-v4/, and re-run.
Clears when: the evidence list names at least one image or recording of the v4 welcome card, the preparing bubble and the Board PR tags from head fc1db03c.

Notes

[DESIGN-REVIEWED] fc1db03

Description read

[DESCRIPTION-READ] 27cb51213fbab1fb24314587bd006eda1ffb18ab516b289158a1ebb1137db65e

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 Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

First Principles Review (Opus 5.5) — 🔴 BLOCK

Premise-level review of e89ddc629056226e27a80766a7c222491fc0474a — why this exists and whether the shipped surface is the smallest honest version. Updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

First-Principles-Verdict: BLOCK

The warm welcome's default shape changes for every owner: the model call is removed and the gateway renders the welcome itself. The only record of that decision is RFC section 3.11, and this PR adds that section itself.

What this change ships

Inventory (10 items) — 9 justified

Intent: give an owner a welcome made only of facts the gateway checked, so they can act on it without asking what is true. ADDITION.

  1. The welcome is now gateway-rendered (version 4): a "Waiting on you: N" line, at most 3 must-do cards, at most 3 "since you left" rows and a Board link. It replaces the model's headline and cards. — product shape, no recorded decision
  2. A return no longer makes a background model call. Only the section 3.8.1 wake still runs one. — justified
  3. The conductor's why, options and pick show with their written time under "Suggested HH:MM" / "Recommended". — justified
  4. A merged or closed PR drops every ask about it. — justified
  5. The retry-on-change loop is gone. Facts are read again at post time, and cards say "checked HH:MM". — justified
  6. The goal-board asks record is widened (manifest v2, options carry outcomes). — justified
  7. A warm_brief producer for object/observed, plus a new objects slot fold. — justified
  8. The Board and goal-board show PR state with its read time (pr_facts, prs). — justified
  9. The "preparing" caption moves into a pending reply bubble. — justified
  10. The goal-conductor skill now says how to write the ask record. — justified

Blockers

product-shape change without accepted RFC: the gateway-rendered welcome (item 1)
Trigger: the diff adds ### 3.11 Gateway-facts amendment … the model states no fact, which "Supersedes … section 3.10.4 entirely". The description says "section 3.11 is added by this PR". The base list has rfc-delayed-task-brief.md:status: partial, and its base text (3.10) has the model writing the cards.
Outcome: what every owner's welcome says, and whether a model writes it, changes with no decision recorded on the base. The "owner-directed" sentence in the description is a proposal, not a record.
Clears when: section 3.11 merges non-draft on the base, followed by a push or rebase; or a maintainer posts /ai-review override first-principles e89ddc629056226e27a80766a7c222491fc0474a product-shape: <decision>.

[FIRST-PRINCIPLES-REVIEWED] e89ddc6

Description read

[DESCRIPTION-READ] a5e34acfe3e9727a3738b56bb26a0590fea59c0e2cb21546df83684eb0112356

That sha256 names the PR description this verdict read. Recompute it with .github/scripts/pr-description-capture.sh; if it differs, the description changed after this verdict was formed and any finding drawn from the description is unproven.

@github-actions

github-actions Bot commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

UX Review (Opus 5.5) — ✅ PASS (a BLOCK with no Trigger and no Outcome does not block)

UX-level review of fc1db03cffa5ca2172fdab4742faa44d4214fac5 — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS does not.

UX-Verdict: PASS

cannot evaluate: missing screenshots and a recording. The PR changes the warm welcome card, the Board's PR facts and the preparing bubble, but attaches no image, so the blind read was not performed.

Evidence gaps

  • Version 4 warm welcome card (WarmWelcomeCard.tsx): no screenshot shows it. That covers the count line ("Waiting on you: N"), the must-do cards, the "checked HH:MM" stamp, the PR pill, the "since you left" rows with "+N more on the Board", the Board link, and the "Suggested HH:MM" / "Recommended" ask rows. Closed by screenshots at 1280 and 320 px, plus one of the failed-read "not checked since" state.
  • Board PR facts (CrewBoardPage.tsx, prFactTags.ts, goal-board prs): no screenshot shows them. Closed by a screenshot of the Board with PR tags and their read time, including a read from another day.
  • Goal-board ask options (template.html optionsFor): the new options with outcomes are not shown. Closed by a screenshot of the goal board.
  • Preparing bubble folding into the welcome (PreparingReplyBubbleView.tsx, AnimatePresence): the description says it "folds out in place", but the recording list is empty. Closed by attaching the capture from capture-warm-welcome-gateway.mjs as a recording, plus stills of the bubble before and after.

[UX-REVIEWED] fc1db03

Description read

[DESCRIPTION-READ] 779c0e25f3a761b2a8656ad7afac64b3f363b374fe6db6aabccf8a56f928e768

That sha256 names everything this verdict read: the PR description, plus the 3 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 Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

GPT 6.1 Review — ✅ no blocking findings

GPT 6.1 completed its review of fc1db03cffa5ca2172fdab4742faa44d4214fac5 and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] fc1db03

False positive or not applicable? A repository writer can comment:
/ai-review override gpt fc1db03cffa5ca2172fdab4742faa44d4214fac5 false-positive: <reason, 20 to 500 characters>

@github-actions

github-actions Bot commented Nov 8, 2026 •

Copy link
Copy Markdown
Contributor

Opus 5.5 Review — ✅ no blocking findings

Reviewed fc1db03cffa5ca2172fdab4742faa44d4214fac5 — this comment is updated in place on each push.

Review details

No findings. All four candidates fail under falsification: the asks options shape is checked on write (dashboard_agentic.check_write → shape_problems), repeat PR reads are served by _live_cache and capped by deadline, mergeable comes from GitHub's mergeability field and never holds dirty, and storing the session key in the owner's own history meta shows nothing to any other reader that was opened.

[OPUS-REVIEWED] fc1db03

Verdict parsed from the review's SHA-scoped output markers for commit fc1db03cffa5ca2172fdab4742faa44d4214fac5.

False positive or not applicable? A repository writer can comment:
/ai-review override fable fc1db03cffa5ca2172fdab4742faa44d4214fac5 false-positive: <reason, 20 to 500 characters>

@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 Nov 8, 2026
@iamwhatever
iamwhatever force-pushed the feat/warm-welcome-gateway-facts branch from 24467b8 to 8ddc557 Compare November 8, 2026 09:00
@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention and removed readiness: action required A blocking check or review needs attention readiness: checking Automated validation is still running labels Nov 8, 2026
@iamwhatever
iamwhatever force-pushed the feat/warm-welcome-gateway-facts branch from 8ddc557 to 9f2f4e3 Compare November 8, 2026 09:34
@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention and removed readiness: action required A blocking check or review needs attention readiness: checking Automated validation is still running labels Nov 8, 2026
@iamwhatever
iamwhatever force-pushed the feat/warm-welcome-gateway-facts branch from 9f2f4e3 to 8afc006 Compare November 8, 2026 10:21
@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention and removed readiness: action required A blocking check or review needs attention readiness: checking Automated validation is still running labels Nov 8, 2026
@iamwhatever
iamwhatever force-pushed the feat/warm-welcome-gateway-facts branch from 8afc006 to 3b7c398 Compare November 8, 2026 11:23
@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 readiness: checking Automated validation is still running labels Nov 8, 2026
@iamwhatever
iamwhatever force-pushed the feat/warm-welcome-gateway-facts branch from 589aea0 to e8d5f6f Compare November 9, 2026 02:42
@iamwhatever

Copy link
Copy Markdown
Contributor Author

Sensitive change review

  • Head commit: e8d5f6f
  • What rule changed: src/kiro_crew/security_posture.py adds one entry, dashboard/warm_task_brief_check.py, to NON_EGRESS_REDACTION_MODULES. No sink, scanner, pattern or redaction rule changes.
  • Before -> after (what was allowed/blocked, now): before, test_every_redactor_call_site_is_a_registered_sink_or_allowlisted failed because the new pure helper redact_whole calls the redactor. After, the helper is listed as a non-egress module with its reason; its callers (dashboard/warm_task_brief.py, a registered sink, and the board's ask-text reader) are what post the text.
  • Worst case if wrong (breaks commands / leaks secret / locks user out): if the helper were an egress point, the security-posture panel would undercount one egress path. The helper returns a redacted copy and writes nothing, so no secret leaves through it.
  • Evidence checked (which sandbox result proves it): N/A, no sandbox rule changes; the omission test (test/test_security_posture.py::TestOmissionDetection) passes locally on this head.
  • No regression:
    • Tools still work (which tools/commands were run, result): no tool or command path is touched; test/test_warm_task_brief*.py and test/test_work_ledger_board.py pass.
    • Backward compatible (old config / old data / old callers still work, how checked): the list only gains an entry; nothing that was allowed is now refused.
    • Existing tests (which suites passed on this head): test/test_security_posture.py, test/test_warm_task_brief*.py, test/test_work_ledger_board.py, test/test_crew_board_asks.py (run locally).
  • How to undo: remove the one dashboard/warm_task_brief_check.py entry and its comment from NON_EGRESS_REDACTION_MODULES.

@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention and removed readiness: action required A blocking check or review needs attention readiness: checking Automated validation is still running merge conflict Branch has merge conflicts with its base — author must resolve before merge labels Nov 9, 2026
@github-actions github-actions Bot added the merge conflict Branch has merge conflicts with its base — author must resolve before merge label Nov 9, 2026
@iamwhatever
iamwhatever force-pushed the feat/warm-welcome-gateway-facts branch from e8d5f6f to 8807ecd Compare November 9, 2026 03:48
@iamwhatever

Copy link
Copy Markdown
Contributor Author

Sensitive change review

  • Head commit: 8807ecd
  • What rule changed: src/kiro_crew/security_posture.py adds one entry, dashboard/warm_task_brief_check.py, to NON_EGRESS_REDACTION_MODULES. No sink, scanner, pattern or redaction rule changes.
  • Before -> after (what was allowed/blocked, now): before, test_every_redactor_call_site_is_a_registered_sink_or_allowlisted failed because the new pure helper redact_whole calls the redactor. After, the helper is listed as a non-egress module with its reason; its callers (dashboard/warm_task_brief.py, a registered sink, and the board's ask-text reader) are what post the text.
  • Worst case if wrong (breaks commands / leaks secret / locks user out): if the helper were an egress point, the security-posture panel would undercount one egress path. The helper returns a redacted copy and writes nothing, so no secret leaves through it.
  • Evidence checked (which sandbox result proves it): N/A, no sandbox rule changes; the omission test (test/test_security_posture.py::TestOmissionDetection) passes locally on this head.
  • No regression:
    • Tools still work (which tools/commands were run, result): no tool or command path is touched; test/test_warm_task_brief*.py and test/test_work_ledger_board.py pass.
    • Backward compatible (old config / old data / old callers still work, how checked): the list only gains an entry; nothing that was allowed is now refused.
    • Existing tests (which suites passed on this head): test/test_security_posture.py, test/test_warm_task_brief*.py, test/test_work_ledger_board.py, test/test_crew_board_asks.py (run locally).
  • How to undo: remove the one dashboard/warm_task_brief_check.py entry and its comment from NON_EGRESS_REDACTION_MODULES.

@github-actions github-actions Bot added readiness: checking Automated validation is still running readiness: action required A blocking check or review needs attention and removed readiness: action required A blocking check or review needs attention merge conflict Branch has merge conflicts with its base — author must resolve before merge readiness: checking Automated validation is still running labels Nov 9, 2026
@iamwhatever
iamwhatever force-pushed the feat/warm-welcome-gateway-facts branch from 8807ecd to e89ddc6 Compare November 9, 2026 04:50
@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 Nov 9, 2026
@iamwhatever

Copy link
Copy Markdown
Contributor Author

Sensitive change review

  • Head commit: e89ddc6
  • What rule changed: src/kiro_crew/security_posture.py adds one entry, dashboard/warm_task_brief_check.py, to NON_EGRESS_REDACTION_MODULES. No sink, scanner, pattern or redaction rule changes.
  • Before -> after (what was allowed/blocked, now): before, test_every_redactor_call_site_is_a_registered_sink_or_allowlisted failed because the new pure helper redact_whole calls the redactor. After, the helper is listed as a non-egress module with its reason; its callers (dashboard/warm_task_brief.py, a registered sink, and the board's ask-text reader) are what post the text.
  • Worst case if wrong (breaks commands / leaks secret / locks user out): if the helper were an egress point, the security-posture panel would undercount one egress path. The helper returns a redacted copy and writes nothing, so no secret leaves through it.
  • Evidence checked (which sandbox result proves it): N/A, no sandbox rule changes; the omission test (test/test_security_posture.py::TestOmissionDetection) passes locally on this head.
  • No regression:
    • Tools still work (which tools/commands were run, result): no tool or command path is touched; test/test_warm_task_brief*.py and test/test_work_ledger_board.py pass.
    • Backward compatible (old config / old data / old callers still work, how checked): the list only gains an entry; nothing that was allowed is now refused.
    • Existing tests (which suites passed on this head): test/test_security_posture.py, test/test_warm_task_brief*.py, test/test_work_ledger_board.py, test/test_crew_board_asks.py (run locally).
  • How to undo: remove the one dashboard/warm_task_brief_check.py entry and its comment from NON_EGRESS_REDACTION_MODULES.

@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 Nov 9, 2026
@iamwhatever

Copy link
Copy Markdown
Contributor Author

Sensitive change review

  • Head commit: 2a82f0c
  • What rule changed: src/kiro_crew/security_posture.py adds one entry, dashboard/warm_task_brief_check.py, to NON_EGRESS_REDACTION_MODULES. No sink, scanner, pattern or redaction rule changes.
  • Before -> after (what was allowed/blocked, now): before, test_every_redactor_call_site_is_a_registered_sink_or_allowlisted failed because the new pure helper redact_whole calls the redactor. After, the helper is listed as a non-egress module with its reason; its callers (dashboard/warm_task_brief.py, a registered sink, and the board's ask-text reader) are what post the text.
  • Worst case if wrong (breaks commands / leaks secret / locks user out): if the helper were an egress point, the security-posture panel would undercount one egress path. The helper returns a redacted copy and writes nothing, so no secret leaves through it.
  • Evidence checked (which sandbox result proves it): N/A, no sandbox rule changes; the omission test (test/test_security_posture.py::TestOmissionDetection) passes locally on this head.
  • No regression:
    • Tools still work (which tools/commands were run, result): no tool or command path is touched; test/test_warm_task_brief*.py and test/test_work_ledger_board.py pass.
    • Backward compatible (old config / old data / old callers still work, how checked): the list only gains an entry; nothing that was allowed is now refused.
    • Existing tests (which suites passed on this head): test/test_security_posture.py, test/test_warm_task_brief*.py, test/test_work_ledger_board.py, test/test_crew_board_asks.py (run locally).
  • How to undo: remove the one dashboard/warm_task_brief_check.py entry and its comment from NON_EGRESS_REDACTION_MODULES.

The warm welcome's model wrote prose about facts and a phrase check
tried to catch it; a truth audit of 71 welcomes found 11 of 58 model
sentences false. Gateway code now renders every state, count, tag,
time and "since you left" row from its own reads, with read times.
The conductor's why, options with outcomes and pick come from its
widened goal-board asks record, shown as its words with their time.
The model writes at most one fact-free framing line and picture.

The Board reads pull-request facts that code recorded: the welcome's
live read and the accept_eval tool emit object/observed (producers
warm_brief, accept_eval) into a new objects slot fold, which the
Ultra Mode Board and goal-board draw with read times.

The preparing caption moves into a reply bubble in both chat
surfaces. RFC rfc-delayed-task-brief.md section 3.11 records the
owner's rulings.
@iamwhatever

Copy link
Copy Markdown
Contributor Author

Sensitive change review

  • Head commit: 71a12d88a70b0ffce2b7e5d4f60c7f53c3d1f76f
  • What rule changed: src/kiro_crew/security_posture.py adds one entry, dashboard/warm_task_brief_check.py, to NON_EGRESS_REDACTION_MODULES. No sink, scanner, pattern or redaction rule changes.
  • Before -> after (what was allowed/blocked, now): before, test_every_redactor_call_site_is_a_registered_sink_or_allowlisted failed because the new pure helper redact_whole calls the redactor. After, the helper is listed as a non-egress module with its reason; its callers (dashboard/warm_task_brief.py, a registered sink, and the board's ask-text reader) are what post the text.
  • Worst case if wrong (breaks commands / leaks secret / locks user out): if the helper were an egress point, the security-posture panel would undercount one egress path. The helper returns a redacted copy and writes nothing, so no secret leaves through it.
  • Evidence checked (which sandbox result proves it): N/A, no sandbox rule changes; the omission test (test/test_security_posture.py::TestOmissionDetection) passes locally on this head.
  • No regression:
    • Tools still work (which tools/commands were run, result): no tool or command path is touched; test/test_warm_task_brief*.py and test/test_work_ledger_board.py pass.
    • Backward compatible (old config / old data / old callers still work, how checked): the list only gains an entry; nothing that was allowed is now refused.
    • Existing tests (which suites passed on this head): test/test_security_posture.py, test/test_warm_task_brief*.py, test/test_work_ledger_board.py, test/test_crew_board_asks.py (run locally).
  • How to undo: remove the one dashboard/warm_task_brief_check.py entry and its comment from NON_EGRESS_REDACTION_MODULES.

@iamwhatever

Copy link
Copy Markdown
Contributor Author

Sensitive change review

  • Head commit: fc1db03
  • What rule changed: src/kiro_crew/security_posture.py adds one entry, dashboard/warm_task_brief_check.py, to NON_EGRESS_REDACTION_MODULES. No sink, scanner, pattern or redaction rule changes.
  • Before -> after (what was allowed/blocked, now): before, test_every_redactor_call_site_is_a_registered_sink_or_allowlisted failed because the new pure helper redact_whole calls the redactor. After, the helper is listed as a non-egress module with its reason; its callers (dashboard/warm_task_brief.py, a registered sink, and the board's ask-text reader) are what post the text.
  • Worst case if wrong (breaks commands / leaks secret / locks user out): if the helper were an egress point, the security-posture panel would undercount one egress path. The helper returns a redacted copy and writes nothing, so no secret leaves through it.
  • Evidence checked (which sandbox result proves it): N/A, no sandbox rule changes; the omission test (test/test_security_posture.py::TestOmissionDetection) passes locally on this head.
  • No regression:
    • Tools still work (which tools/commands were run, result): no tool or command path is touched; test/test_warm_task_brief*.py and test/test_work_ledger_board.py pass.
    • Backward compatible (old config / old data / old callers still work, how checked): the list only gains an entry; nothing that was allowed is now refused.
    • Existing tests (which suites passed on this head): test/test_security_posture.py, test/test_warm_task_brief*.py, test/test_work_ledger_board.py, test/test_crew_board_asks.py (run locally).
  • How to undo: remove the one dashboard/warm_task_brief_check.py entry and its comment from NON_EGRESS_REDACTION_MODULES.

@iamwhatever

Copy link
Copy Markdown
Contributor Author

Closing per owner decision 2026-11-09: the warm welcome restarts from main with a simpler four-part shape (goal, what needs you, what is being done now, what comes after). A new PR will replace this one.

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.

Warm welcome: no indicator while the brief is prepared, so the owner types and cancels it

1 participant