Skip to content

chore(prepare-pr): hold the skill under its 68000-byte ceiling - #14404

Merged
iamwhatever merged 1 commit into
mainfrom
chore/slim-prepare-pr-skill
Sep 27, 2026
Merged

iamwhatever merged 1 commit into
mainfrom
chore/slim-prepare-pr-skill

Conversation

@iamwhatever

Copy link
Copy Markdown
Contributor

Problem / Motivation

Goal: Keep the prepare-pr skill under its 68000-byte ceiling so every open PR's Backend Tests stay green.

The prepare-pr SKILL.md grew to 68015 bytes on main. The test test_slim_skills_do_not_regrow_duplicate_guidance_or_wire_model_ids[prepare-pr-68000] asserts the file stays at or under 68000 bytes, so it now fails on main and every open PR inherits that red through its merge-ref.

Why it matters

A red on main's byte-ceiling test blocks the Backend Tests shard on every open PR, regardless of what the PR changes. Contributors cannot go green until main is back under the ceiling.

Not a goal

  • Not raising the byte ceiling — the fix is to trim content, not loosen the gate.
  • Not restructuring the skill or changing any operational instruction the loop executes.

What changed (motivation → approach → change)

Symptom: the file is 15 bytes over its 68000 ceiling. Root cause: it sat right at the edge for several revisions and #14181 pushed it over. The skill's own top note says it should carry only what the loop executes — rationale and justification belong in references/rationale.md.

Change: removed the why that strength column from the "Two checks, two strengths" table. That column held only justification prose (an unnamed change is how a stray edit rides along, with the ledger complete, a cap cuts only restated facts; the diff is the evidence) — it explained why the two checks pull in opposite directions, which is reader-facing rationale, not an instruction the loop follows. The operational columns (check, what it measures, on breach — including exit 20 and exit 21) are unchanged.

Result: 68015 → 67854 bytes, 146 under the ceiling with margin for a future one-line edit.

Backwards compatibility

Compatible: only reader-facing prose was removed; every instruction, exit code, and threshold the loop reads is unchanged.

Tests

No test added — the existing test_slim_skills_do_not_regrow_duplicate_guidance_or_wire_model_ids[prepare-pr-68000] case is what this restores to green. Verified locally: 3 passed, 17 deselected.

Manual verification

N/A — the byte-ceiling assertion is the verification, and it passes.

Pattern harvest

Not generalizable: a single skill file drifting past a per-file byte ceiling is a one-off content-size overage, cleared by trimming justification prose the file itself says belongs in a rationale doc.

@github-actions github-actions Bot added the readiness: checking Automated validation is still running label Sep 27, 2026
@github-actions

Copy link
Copy Markdown
Contributor

GPT 5.6 Review — ✅ no blocking findings

GPT 5.6 completed its review of 03919d7fe64f4b7cdeff83ef418933ff91a1488c and found no blocking issues.

This comment is updated in place on each push.

Review details

No findings.
[GPT-REVIEWED] 03919d7

False positive or not applicable? A repository writer can comment:
/ai-review override gpt 03919d7fe64f4b7cdeff83ef418933ff91a1488c: <one-sentence reason>

@github-actions

Copy link
Copy Markdown
Contributor

First Principles Review (Fable 5) — ✅ PASS

Premise-level review of 03919d7fe64f4b7cdeff83ef418933ff91a1488c — 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/CONCERNS are advisory.

First-Principles-Verdict: PASS

Nothing to check.

What this change ships

Inventory (1 item) — 1 justified

Intent: get the prepare-pr skill file back under the 68000-byte ceiling pinned by test_review_repair_routing_skill.py, unwedging the red Backend Tests shard on main and every open PR — a FIX.

  1. The "why that strength" rationale column disappears from the skill's two-checks table; its content stays in references/rationale.md, which the table intro still points at — justified

[FIRST-PRINCIPLES-REVIEWED] 03919d7

@github-actions

Copy link
Copy Markdown
Contributor

Design Review (Fable 5) — 🟡 CONCERNS

Design-level review of 03919d7fe64f4b7cdeff83ef418933ff91a1488c — updated in place on each push. A BLOCK verdict blocks PR readiness; PASS/CONCERNS are advisory.

Design-Verdict: CONCERNS

Stated harm no longer exists at this base: #14398 (the base commit) already trimmed SKILL.md to 67854 bytes, so the ceiling test is green without this PR.

Watch

  • The description's motivation and accounting are stale: it claims main is red at 68015 and "Result: 68015 → 67854", but the base commit f2c732e already carries a different 161-byte trim that restored green, and this diff actually takes 67854 → 67693. Merging as-is records byte math that describes fix(ci): unbreak the two base-side gates red on every open PR #14398's change, not this one; a human should decide whether this now ships as a headroom top-up (the trim itself is sound — the column held only rationale, which references/rationale.md still covers via the existing pointer) or closes as superseded.
    Clears when: the "What changed"/Result accounting is corrected to 67854 → 67693 and the motivation reframed as headroom, or the PR is closed as superseded by #14398.

[DESIGN-REVIEWED] 03919d7

@github-actions

Copy link
Copy Markdown
Contributor

Opus 5 Review — ✅ no blocking findings

Reviewed 03919d7fe64f4b7cdeff83ef418933ff91a1488c — this comment is updated in place on each push.

Review details

No findings.

[OPUS-REVIEWED] 03919d7

Verdict parsed from the review's SHA-scoped output markers for commit 03919d7fe64f4b7cdeff83ef418933ff91a1488c.

False positive or not applicable? A repository writer can comment:
/ai-review override fable 03919d7fe64f4b7cdeff83ef418933ff91a1488c: <one-sentence reason>

@github-actions github-actions Bot added readiness: passed Eligible automated validation passed for the current revision and removed readiness: checking Automated validation is still running labels Sep 27, 2026
@iamwhatever

Copy link
Copy Markdown
Contributor Author

Simple change to unlock pr-readiness characters count cap. Will follow another PR to get more changes done.

@iamwhatever
iamwhatever merged commit e257f91 into main Sep 27, 2026
96 checks passed
@iamwhatever
iamwhatever deleted the chore/slim-prepare-pr-skill branch September 27, 2026 07:56
@github-actions github-actions Bot removed the readiness: passed Eligible automated validation passed for the current revision label Sep 27, 2026
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.

1 participant