Repository navigation
cat-mode: allowlist intervention-must-automate as a flag token. - #1313
Merged
Conversation
Agents kept narrating by-model health and patching charts before splitting volume, fill, resolve, and filter — lock that check into standing defaults. Co-authored-by: Cursor <cursoragent@cursor.com> Change-Id: I8efc336daf9878751865cf3c4bac4d55cd50733f
Phrase-judge rejected leads that named only the trigger phrase; state the split and the stop-first catch as the lesson, with the triggers as examples. Co-authored-by: Cursor <cursoragent@cursor.com> Change-Id: I7dad9e54f9d280bb4d8f41ac06662293e39c9e05
…mple phrasing. Co-authored-by: Cursor <cursoragent@cursor.com> Change-Id: Idebc0f0ba74e47864bf479446a8e27b0574cdcde
…lesson. Co-authored-by: Cursor <cursoragent@cursor.com> Change-Id: Iaa84683fcf5a66e8f70a0dbf99ebcf19acc1d7a7
The dashboard-health defaults name that audit flag in backticks; the skill-existence check must treat it as a process token, not a skill path. Co-authored-by: Cursor <cursoragent@cursor.com> Change-Id: I1afa1d44a91d2886300ab5f17843b8e583dbda0c
This was referenced Oct 8, 2026
Bugbot couldn't run - usage limit reachedBugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit. A user or team admin can review and increase usage limits in the Cursor dashboard. (requestId: 4a9f874f-5268-4964-8113-3cc192acf277) |
4 tasks done
EdbertChan
changed the base branch from
stack/EdbertChan/automate/dashboard-health-receipt/cat-mode-lead-multi-emitter-backfill-done-gate--aa84683f
to
main
October 13, 2026 09:12
Contributor
|
This pull request does not currently match the merge queue conditions, so it cannot be queued from here. The box comes back if it matches again. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
The personal working guide now gives clearer stop rules for analytics investigations before dashboard changes continue.
Before, chart filters or partial backfills could stand in for proof that model data was really resolved. One automation flag was also read like a missing skill reference.
The update requires a health receipt, separates volume, fill, resolve, and filter ownership, and treats that automation flag as a process token.
Review Claim
The guidance blocks analytics dashboard conclusions until health and resolver evidence are named.
Review Lane
behavior
Review Unit
corpus-lesson
Safety Invariant
This changes only skill prose, skill fixtures, and the root regression test that checks them. Runtime hooks and production data paths are unchanged.
Non-goals
Slice Rationale
The prose, fixtures, and regression assertions describe one lesson: analytics dashboard claims need health and resolver proof before more chart work. The flag allowlist rides with that lesson because the new prose names the process token.
Measured
none: this is a corpus lesson change, with behavior covered by the regression tests below.
Test Plan
Test Plan
python3 engine/skills/make-pr/scripts/preflight.py --base origin/main --commit-only --dry-run—ok preflight passedpython3 -m unittest tests.test_cat_mode.TestPublishingAnalyticsDefaults tests.test_cat_mode.TestAnalyticsThrashCheckpoints tests.test_cat_mode.TestCatModeReferences—Ran 17 tests in 0.056s/OKnode engine/skills/draft-pr/scripts/validate-pr-body.mjs --body-file /tmp/pr1313-fixed-body.md --changed-files-file /tmp/pr1313-changed-files.txt—PR body validation passed.Revert Plan
Revert Plan
git revert 0d0f5afd5ad4b5e981e29e56ad19d11309714dc4