Repository navigation
docs(decisions): a Conductor's board tab replaces its in-chat task board - #18900
Conversation
UX Review (Opus 5.5) — ⏭️ skippedRevision |
First Principles Review (Opus 5.5) — ⏭️ skippedRevision |
Design Review (Opus 5.5) — ✅ PASSDesign-level review of Design-Verdict: PASS Before merging, confirm that @iamwhatever has restated the decision on this PR and given the [DESIGN-REVIEWED] 3097b22 Description read[DESCRIPTION-READ] 8754c4fa44299a67d40675061ff18dafc36b73dfcd8db0a7792996bd1fd548af 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 |
Opus 5.5 Review — ✅ human override acceptedReviewed Human judgment by @iamwhatever overrides the Opus 5.5 finding for [OPUS-OVERRIDE] 3097b22 Verdict recorded from an authorized human decision for commit False positive or not applicable? A repository writer can comment: |
GPT 6.1 Review — ✅ human override acceptedHuman judgment by @iamwhatever overrides the GPT 6.1 finding for [GPT-OVERRIDE] 3097b22 This comment is updated in place on each push. The model was not re-run because an authorized human decision supersedes it. False positive or not applicable? A repository writer can comment: |
|
Dispositions for head
What is still needed, and only a maintainer can do it:
No new push: the entry is unchanged, so a push would only restart every lane. cc @bolichen97 (author of the 2026-10-02 entry). |
|
/ai-review override gpt 3097b22: the recorded-decisions rule blocks every Supersedes: entry by design and asks for maintainer judgment; this entry is the author's own product decision (the Conductor's board moves from in-chat to the Dashboard tab), the superseded 2026-10-02 entry stays immutable per rule 2, and the README index row is present. |
|
/ai-review override fable 3097b22: same judgment as the gpt override above: a deliberate, author-owned supersession recorded per the decisions rule, with the old entry left intact. |
Human judgment recorded@iamwhatever marked the gpt AI finding as false positive, not applicable, or explicitly accepted for
This decision applies only to this commit. A new push requires a new judgment. |
Human judgment recorded@iamwhatever marked the fable AI finding as false positive, not applicable, or explicitly accepted for
This decision applies only to this commit. A new push requires a new judgment. |
bolichen97
left a comment
There was a problem hiding this comment.
Reviewed the diff: change matches its stated goal, tests cover the new behaviour, readiness passed at this head.
Problem / Motivation
Goal: Record the maintainer's decision that a Conductor whose Dashboard tab shows the task board does not write a second board in the chat, superseding the 2026-10-02 Conductor entry.
The implementation #18608 is blocked by
recorded-decisions-are-not-regressions:docs/decisions/2026-10-02-conductor-introduces-itself-in-every-chat.mdsays every Conductor chat reports with a live task board, and a change of mind needs a superseding entry in its own PR (docs/decisions/README.mdrule 3).Why it matters
The RFC #18620 is merged, so the direction is decided; without this entry the decision ledger still says the opposite, and #18608 cannot land.
Not a goal
What changed (motivation → approach → change)
docs/decisions/2026-10-10-conductor-board-tab-replaces-the-in-chat-board.md: new entry,Supersedes: 2026-10-02-conductor-introduces-itself-in-every-chat.md. It keeps the introduction and "Needs you" first everywhere; on agoal-board/work-kanbantab the tab is the board and no in-chat widget ortask-dashboardartifact is written.docs/decisions/README.md: one index row.Decided by Joe Guo (@iamwhatever, maintainer in
MAINTAINERS.md): merged RFC #18620 and commented on record. Per rule 4, @iamwhatever please restate the decision in a comment on this PR, and per rule 3 this PR needs a maintainer/ai-review overrideof the reviewer rule to land. cc @bolichen97, author of the 2026-10-02 entry.Backwards compatibility
Compatible: documentation only.
Removes nothing: adds one entry and one index row; the 2026-10-02 entry stays byte-identical (
check_decisions_history.pyOK).Tests
N/A — docs only;
scripts/docs-lint.shandDECISIONS_BASE_REF=origin/main scripts/check_decisions_history.pypass locally.Manual verification
N/A — docs only.
Related Issues
RFC #18620; implementation #18608.
Checklist
Contribution License Agreement
Contributions are accepted under the project's Apache-2.0 license.