Skip to content

mind: record feature-ranker-ignores-header-keys shipped - #176

Merged
Jammy2211 merged 1 commit into
mainfrom
claude/automind-task-planning-8wk4ag
Aug 10, 2026
Merged

mind: record feature-ranker-ignores-header-keys shipped#176
Jammy2211 merged 1 commit into
mainfrom
claude/automind-task-planning-8wk4ag

Conversation

@Jammy2211

Copy link
Copy Markdown
Collaborator

The ranker fix shipped as PyAutoBrain#217 (e099383; pytest 3.12 + 3.13, 291 passed / 0 failed). Records it to complete/2026/08/feature-ranker-ignores-header-keys.md and removes the draft. lifecycle.py check and index --check both OK.

What the ranker now does

_feature.py mentioned Difficulty exactly once — where it printed its own re-derived score — and read no header key at all, despite REFERENCE.md promising that the value Intake persists is "the one the Feature Agent later acts on". It now honours Difficulty: (declared overrides derived, disagreement reported), Priority: (orders the shortlist), and Status: blocked / Blocked-by: (never the recommended pick).

Measured on this repo's live backlog: the offending prompt drops rank 1 → last of 27, two further blocked prompts surfaced that nobody had spotted by hand, and draft_staleness_detection_signals moves too-large #26medium #5.

Three things the record keeps

  • The fenced-block skip is load-bearing, not tidiness. The bug prompt quotes the offending header in a ```-block, so a naive line scan makes the bug report declare itself blocked. This repo's lifecycle.py:draft_gate_refs had already hit this and solved it the same way.
  • Length is a bad size proxy. The derived score weights prompt size, and a prompt grows as it accumulates findings — so a long, well-documented prompt derives too-large for work that is not. That is what a declared Difficulty: is for.
  • test_skill_install.py fails 2 tests in a cloud session and passes in CI (the installer reports Environment: web-github / ci-only). Recorded so nobody chases them locally.

A second instance of the same defect class — recorded, not fixed

Running pyauto-brain bug on this very prompt returned "Fix strategy: defer/re-home (looks like a feature/ task, not a bug)" — because the prompt says "Feature Agent" repeatedly and the Bug Agent classifies on prose keywords while ignoring the declared Type: bug header. Same family as the bug just fixed, different conductor. Left unfixed and unfiled deliberately: it is its own task, and folding it in here would have made a small fix a speculative one.

🤖 Generated with Claude Code

https://claude.ai/code/session_01WSCA1h6cSKMNwFmWEsxuCL


Generated by Claude Code

The ranker fix shipped as PyAutoBrain#217 (e099383, 291 passed / 0 failed on
3.12 + 3.13). Records it to complete/2026/08/ and removes the draft.

The record keeps the three things worth not rediscovering:

- the fenced-block skip is load-bearing, not tidiness. The bug prompt QUOTES
  the offending header in a ```-block, so a naive line scan makes the bug
  report declare itself blocked. lifecycle.py:draft_gate_refs had already hit
  this and solved it the same way.
- length is a bad size proxy: the derived score weights prompt size, and a
  prompt grows as it accumulates findings, so a long well-documented prompt
  derives too-large for work that is not. That is what a declared Difficulty:
  is for.
- test_skill_install.py fails 2 tests in a cloud session and passes in CI
  (the installer reports "web-github / ci-only"). Do not chase them locally.

Also records a SECOND instance of the same defect class, found while doing
this and deliberately not fixed here: `pyauto-brain bug` on this very prompt
answered "looks like a feature/ task, not a bug" — because the prompt says
"Feature Agent" repeatedly and the Bug Agent classifies on prose keywords
while ignoring the declared `Type: bug` header. Same family, different
conductor, currently unfiled.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WSCA1h6cSKMNwFmWEsxuCL
@Jammy2211
Jammy2211 merged commit c11fcf7 into main Aug 10, 2026
1 check passed
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.

2 participants