fix: fix: agents-update step uses vague instructions and disinto-specific examples — rewrite with mechanical discovery (#476)
All checks were successful
ci/woodpecker/push/ci Pipeline was successful
ci/woodpecker/pr/ci Pipeline was successful

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Claude 2026-04-09 07:45:26 +00:00
parent ddd3651426
commit 87a0036baa

View file

@ -344,13 +344,12 @@ needs = ["grooming"]
[[steps]]
id = "agents-update"
title = "Check AGENTS.md watermarks, update stale files, enforce size limit"
title = "Check AGENTS.md watermarks, discover structural changes, update stale files"
description = """
Check all AGENTS.md files for staleness, update any that are outdated, and
enforce the ~200-line size limit via progressive disclosure splitting.
This keeps documentation fresh runs 2x/day so drift stays small.
Maintain all AGENTS.md files by detecting structural drift since the last
review. Uses git history as the source of truth not vibes.
## Part A: Watermark staleness check and update
## Part A: Discover what changed
1. Read the HEAD SHA from preflight:
HEAD_SHA=$(cat /tmp/gardener-head-sha)
@ -360,102 +359,72 @@ This keeps documentation fresh — runs 2x/day so drift stays small.
3. For each file, read the watermark from line 1:
<!-- last-reviewed: <sha> -->
If no watermark exists, treat the file as fully stale (review everything).
4. Check for changes since the watermark:
git log --oneline <watermark>..HEAD -- <directory>
If zero changes, the file is current skip it.
5. For stale files:
- Read the AGENTS.md and the source files in that directory
- Update the documentation to reflect code changes since the watermark
- Set the watermark to the HEAD SHA from the preflight step
- Conventions: architecture and WHY not implementation details
5. For each stale file, run a STRUCTURAL DIFF this is the core of the step:
## Part B: Size limit enforcement (progressive disclosure split)
a. FILE INVENTORY: list files at watermark vs HEAD for this directory:
git ls-tree -r --name-only <watermark> -- <directory>
git ls-tree -r --name-only HEAD -- <directory>
Diff the two lists. Categorize:
- NEW files: in HEAD but not in watermark
- DELETED files: in watermark but not in HEAD
- Check AGENTS.md layout section: does it list each current file?
Files present in the directory but absent from the layout = GAPS.
Files listed in the layout but missing from the directory = LIES.
After all updates are done, count lines in the root AGENTS.md:
b. REFERENCE VALIDATION: extract every file path, function name, and
shell variable referenced in the AGENTS.md. For each:
- File paths: verify the file exists (ls or git ls-tree HEAD)
- Function names: grep for the definition in the codebase
- Script names: verify they exist where claimed
Any reference that fails validation is a LIE flag it for correction.
c. SEMANTIC CHANGES: for files that existed at both watermark and HEAD,
check if they changed meaningfully:
git diff <watermark>..HEAD -- <directory>/*.sh <directory>/*.py <directory>/*.toml
Look for: new exported functions, removed functions, renamed files,
changed CLI flags, new environment variables, new configuration.
Ignore: internal refactors, comment changes, formatting.
6. For each stale file, apply corrections:
- Add NEW files to the layout section
- Remove DELETED files from the layout section
- Fix every LIE found in reference validation
- Add notes about significant SEMANTIC CHANGES
- Set the watermark to HEAD_SHA
- Conventions: document architecture and WHY, not implementation details
## Part B: Size limit enforcement
After all updates, count lines in the root AGENTS.md:
wc -l < "$PROJECT_REPO_ROOT/AGENTS.md"
If the root AGENTS.md exceeds 200 lines, perform a progressive disclosure
split. The principle: agent reads the map, drills into detail only when
needed. You wouldn't dump a 500-page wiki on a new hire's first morning.
If it exceeds 200 lines, split verbose sections into per-directory files
using progressive disclosure:
6. Identify per-directory sections to extract. Each agent section under
"## Agents" (e.g. "### Dev (`dev/`)", "### Review (`review/`)") and
each helper section (e.g. "### Shared helpers (`lib/`)") is a candidate.
Also extract verbose subsections like "## Issue lifecycle and label
conventions" and "## Phase-Signaling Protocol" into docs/ or the
relevant directory.
7. Identify sections that can be extracted to per-directory files.
Keep the root AGENTS.md as a table of contents brief overview,
directory layout, summary tables with links to detail files.
7. For each section to extract, create a `{dir}/AGENTS.md` file with:
8. For each extracted section, create a `{dir}/AGENTS.md` with:
- Line 1: watermark <!-- last-reviewed: <HEAD_SHA> -->
- The full section content (role, trigger, key files, env vars, lifecycle)
- Keep the same markdown structure and detail level
- The full section content, preserving structure and detail
Example for dev/:
```
<!-- last-reviewed: abc123 -->
# Dev Agent
9. Replace extracted sections in root with concise summaries + links.
**Role**: Implement issues autonomously ...
**Trigger**: dev-poll.sh runs every 10 min ...
**Key files**: ...
**Environment variables consumed**: ...
**Lifecycle**: ...
```
8. Replace extracted sections in the root AGENTS.md with a concise
directory map table. The root file keeps ONLY:
- Watermark (line 1)
- ## What this repo is (brief overview)
- ## Directory layout (existing tree)
- ## Tech stack
- ## Coding conventions
- ## How to lint and test
- ## Agents — replaced with a summary table pointing to per-dir files:
## Agents
| Agent | Directory | Role | Guide |
|-------|-----------|------|-------|
| Dev | dev/ | Issue implementation | [dev/AGENTS.md](dev/AGENTS.md) |
| Review | review/ | PR review | [review/AGENTS.md](review/AGENTS.md) |
| Gardener | gardener/ | Backlog grooming | [gardener/AGENTS.md](gardener/AGENTS.md) |
| ... | ... | ... | ... |
- ## Shared helpers — replaced with a brief pointer:
"See [lib/AGENTS.md](lib/AGENTS.md) for the full helper reference."
Keep the summary table if it fits, or move it to lib/AGENTS.md.
- ## Issue lifecycle and label conventions — keep a brief summary
(labels table + dependency convention) or move verbose parts to
docs/PHASE-PROTOCOL.md
- ## Architecture Decisions — keep in root (humans write, agents enforce)
- ## Phase-Signaling Protocol — keep a brief summary with pointer:
"See [docs/PHASE-PROTOCOL.md](docs/PHASE-PROTOCOL.md) for the full spec."
9. Verify the root AGENTS.md is now under 200 lines:
LINE_COUNT=$(wc -l < "$PROJECT_REPO_ROOT/AGENTS.md")
if [ "$LINE_COUNT" -gt 200 ]; then
echo "WARNING: root AGENTS.md still $LINE_COUNT lines after split"
fi
If still over 200, trim further move more detail into per-directory
files. The root should read like a table of contents, not an encyclopedia.
10. Each new per-directory AGENTS.md must have a watermark on line 1.
The gardener maintains freshness for ALL AGENTS.md files root and
per-directory using the same watermark mechanism from Part A.
10. Verify root is under 200 lines. If still over, extract more.
## Staging
11. Stage ALL AGENTS.md files you created or changed do NOT commit yet.
All git writes happen in the commit-and-pr step at the end:
11. Stage all AGENTS.md files created or changed:
find . -name "AGENTS.md" -not -path "./.git/*" -exec git add {} +
12. If no AGENTS.md files need updating AND root is under 200 lines,
skip this step entirely.
12. If no files need updating AND root is under 200 lines, skip entirely.
CRITICAL: If this step fails for any reason, log the failure and move on.
Do NOT let an AGENTS.md failure prevent the commit-and-pr step.