mirror of
https://github.com/bmad-code-org/BMAD-METHOD.git
synced 2026-09-19 08:11:52 +08:00
Alex Verkhovsky
eeaaa585ee
* chore(review): swap Augment for Greptile and repair CodeRabbit config Augment is no longer in use, so its guidelines file goes away in favour of greptile.json. Rather than paraphrasing the repo's conventions, both bots are now pointed at the same source files: AGENTS.md and tools/skill-validator.md, plus docs/_STYLE_GUIDE.md scoped to docs. Four CodeRabbit path instructions had gone stale and matched no tracked files: src/**/skills/**, src/**/workflows/**, src/**/tasks/** and src/**/*.agent.yaml. The skill-validator catalog was consequently applied to nothing. Retarget them at src/*-skills/** and src/bmm-skills/agents/**, and drop the two describing layouts the repo no longer has. Three further fixes: `walkthrough: false` is not a schema v2 key, so use collapse_walkthrough; the media filters were root-only globs and left docs/images under review; and the validation-report filter named .md where those files are .html. AGENTS.md gains the prompt-length and testing conventions, which were until now written down nowhere in the repo. CLAUDE.md is unignored and imports it. * chore(review): align catalog scoping and narrow the ignore lists Greptile's global instructions named tools/skill-validator.md and docs/_STYLE_GUIDE.md, but customContext.files supplies those only for skill and documentation paths. Reviewing anything else, Greptile was told to apply catalogs it had not been given — an invitation to invent rules from the filenames. The global clause now names only AGENTS.md, which is loaded on every review; the two scoped catalogs keep their scopes and their own descriptions. website/** was excluding 18 hand-written source files along with the assets — the Astro components and pages, both rehype plugins, the locale and site-url helpers, the i18n JSON. Exclude website/public/** and website/diagrams/** instead, so generated and editor-authored artifacts stay out while the source is reviewed. tools/tests/fixtures/** joins test/fixtures/** ahead of the validator port that moves the skill fixtures there. Those fixtures encode defects deliberately, so any review comment on them is wrong by construction.
118 lines
4.4 KiB
YAML
118 lines
4.4 KiB
YAML
# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
|
|
#
|
|
# Kept deliberately in step with greptile.json: both bots read the same three
|
|
# guideline files and are given the same scoped instructions, so their findings
|
|
# can be compared rather than merged.
|
|
|
|
language: "en-US"
|
|
early_access: true
|
|
tone_instructions: |
|
|
Do not comment on the wording, tone, phrasing, or length of prompt text —
|
|
those are authoring decisions, not defects.
|
|
reviews:
|
|
profile: chill
|
|
high_level_summary: false # don't post summary until explicitly invoked
|
|
request_changes_workflow: false
|
|
review_status: false
|
|
commit_status: false
|
|
collapse_walkthrough: true # `walkthrough: false` is not a schema key; this is the real knob
|
|
poem: false
|
|
auto_review:
|
|
enabled: true
|
|
drafts: false # Don't review drafts automatically
|
|
auto_incremental_review: false # always review the whole PR, not just new commits
|
|
base_branches:
|
|
- main
|
|
path_filters:
|
|
# --- Shared baseline: tool configs ---
|
|
- "!.coderabbit.yaml"
|
|
- "!eslint.config.mjs"
|
|
# --- Shared baseline: build output ---
|
|
- "!dist/**"
|
|
- "!build/**"
|
|
- "!coverage/**"
|
|
# --- Shared baseline: vendored/generated ---
|
|
- "!**/node_modules/**"
|
|
- "!**/*.min.js"
|
|
- "!**/*.generated.*"
|
|
- "!**/*.bundle.md"
|
|
# --- Shared baseline: package metadata ---
|
|
- "!package-lock.json"
|
|
# --- Shared baseline: binary/media (globs, so `**/` is required to reach subdirs) ---
|
|
- "!**/*.png"
|
|
- "!**/*.jpg"
|
|
- "!**/*.svg"
|
|
# --- Shared baseline: test fixtures ---
|
|
- "!test/fixtures/**"
|
|
- "!tools/tests/fixtures/**"
|
|
- "!test/template-test-generator/**"
|
|
- "!tools/template-test-generator/test-scenarios/**"
|
|
# --- Shared baseline: non-project dirs ---
|
|
- "!_bmad*/**"
|
|
- "!website/public/**"
|
|
- "!website/diagrams/**"
|
|
- "!z*/**"
|
|
- "!sample-project/**"
|
|
- "!test-project-install/**"
|
|
# --- Shared baseline: AI assistant dirs ---
|
|
- "!.claude/**"
|
|
- "!.codex/**"
|
|
- "!.agent/**"
|
|
- "!.agentvibes/**"
|
|
- "!.kiro/**"
|
|
- "!.roo/**"
|
|
- "!.github/chatmodes/**"
|
|
# --- Shared baseline: build temp ---
|
|
- "!.bundler-temp/**"
|
|
# --- Shared baseline: generated reports ---
|
|
- "!**/validation-report-*.html"
|
|
- "!CHANGELOG.md"
|
|
path_instructions:
|
|
- path: "src/**"
|
|
instructions: |
|
|
Source changed. Check whether docs/ needs a matching update — new
|
|
features, changed behavior, renamed concepts, altered CLI flags, or
|
|
modified configuration options should all be reflected in the relevant
|
|
doc pages. Flag missing or outdated docs.
|
|
- path: "src/*-skills/**"
|
|
instructions: |
|
|
Skill file. This is prompt text read by an agent at runtime, not
|
|
executable code. Confine review to claims checkable against the
|
|
repository: paths and cross-references that do not resolve, invocation
|
|
syntax that does not match the referenced skill, instructions that
|
|
contradict another file, documented behavior the code does not
|
|
implement, and violations of the rule catalog in
|
|
tools/skill-validator.md — that catalog is the single source of truth
|
|
for SKILL.md metadata, workflow constraints, step file structure, path
|
|
references, variable resolution, sequential execution, and skill
|
|
invocation syntax.
|
|
- path: "src/bmm-skills/agents/**"
|
|
instructions: |
|
|
Agent skill. The persona is configured in customize.toml under [agent]:
|
|
check that every {agent.*} placeholder the SKILL.md interpolates has a
|
|
corresponding key there, and that menu entries name skills that exist
|
|
in this repo.
|
|
- path: "docs/**/*.md"
|
|
instructions: |
|
|
Documentation file. Check that internal markdown links point at files
|
|
that exist, and that the page follows docs/_STYLE_GUIDE.md.
|
|
- path: "tools/**"
|
|
instructions: |
|
|
Build script/tooling. Check error handling and that failures exit
|
|
non-zero.
|
|
- path: "src/scripts/**"
|
|
instructions: |
|
|
Build script/tooling. Check error handling and that failures exit
|
|
non-zero.
|
|
knowledge_base:
|
|
code_guidelines:
|
|
enabled: true
|
|
filePatterns:
|
|
- "AGENTS.md"
|
|
- "tools/skill-validator.md"
|
|
chat:
|
|
auto_reply: true # Response to mentions in comments, a la @coderabbit review
|
|
issue_enrichment:
|
|
auto_enrich:
|
|
enabled: false # don't auto-comment on issues
|