config(review-bots): concise high-signal comments only

Owner directive: no fluff on PRs. Greptile: logic-only comments at max
strictness, no diagrams/confidence sections, summary collapsed.
CodeRabbit: three-sentence findings, no sequence diagrams or ASCII
sketches, collapsed walkthrough, no per-push status comments, finishing
touches off. Both: comment only when a finding changes what merges.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
debpalash
2026-07-20 10:10:51 +05:30
co-authored by Claude Fable 5
parent 0c7428b270
commit 8357e89d5e
2 changed files with 24 additions and 19 deletions
+16 -12
View File
@@ -8,26 +8,30 @@ language: "en-US"
early_access: false
# The review voice: a panel of senior domain experts, not a linter.
# Brevity is a hard requirement (owner directive 2026-07-20): comment ONLY
# when a finding would change what gets merged.
tone_instructions: >-
Review as a panel of principal engineers: ML inference, audio DSP, desktop
systems, product polish. Cite exact lines, name the failure mode, give the
concrete fix. No filler praise; raise nits only when they change a decision.
systems, product polish. Comment only on findings that would change what
gets merged: a concrete bug, a violated house rule, a real risk. Per
finding: at most three sentences — the failure mode, the line, the fix. No
praise, no restating the diff, no style nits (linters gate those in CI), no
boilerplate sections, no emojis. If nothing meets the bar, say nothing.
reviews:
# "chill" keeps the bot from blocking merges — it comments, it does not gate.
# Hard gating lives in CI (security.yml) and the constitution's human bar.
profile: chill
request_changes_workflow: false
# Keep the walkthrough minimal: a short summary, no diagrams, no per-push
# status chatter, collapsed by default (owner: no fluff on PRs).
high_level_summary: true
# Every walkthrough gets a visual: mermaid sequence diagrams for the
# mechanics, plus (via the summary instructions) an ASCII before/after
# sketch when the PR touches UI — so each PR is reviewable at a glance.
sequence_diagrams: true
high_level_summary_instructions: >-
If the PR changes UI (JSX/TSX/CSS/Tauri windows), include a compact ASCII
before/after sketch of the affected layout or component. If it changes
behavior, include a short mermaid flowchart of the new mechanism.
review_status: true
Three sentences maximum: what changed, why, and any risk worth a human
look. No diagrams, no sketches, no file-by-file narration.
sequence_diagrams: false
collapse_walkthrough: true
review_status: false
poem: false
auto_review:
@@ -176,9 +180,9 @@ reviews:
finishing_touches:
docstrings:
enabled: true
enabled: false
unit_tests:
enabled: true
enabled: false
# Feed the bot the project constitution and docs, and let it accumulate
# learnings from review conversations ("@coderabbitai always/never …").
+8 -7
View File
@@ -1,8 +1,8 @@
{
"$comment": "Greptile per-repo config — https://www.greptile.com/docs/code-review-bot/greptile-json. The Greptile GitHub App is installed; this file tunes its reviews. Dashboard settings are the org-wide fallback. Greptile also learns from 👍/👎 reactions on its comments — react to train it.",
"instructions": "Review as a panel of passionate senior domain experts (ML inference, audio DSP, desktop systems, product polish): cite exact lines, name the concrete failure mode, propose the fix — no filler praise. OmniVoice is a fully-local desktop app (no cloud, no API keys, no telemetry): flag any new outbound network call that is not GitHub Issues or a HuggingFace model download. In every review summary, make the change visual: if the PR touches UI (JSX/TSX/CSS or Tauri window config), include a compact ASCII before/after mockup of the affected layout or component; if it changes behavior or data flow, include a sequence/flow diagram of the new mechanism. Keep diagrams small and strictly faithful to the diff.",
"commentTypes": ["logic", "syntax", "info"],
"strictness": 2,
"instructions": "Review as a panel of senior domain experts (ML inference, audio DSP, desktop systems). Comment ONLY on findings that would change what gets merged: a concrete bug, a violated house rule from CLAUDE.md, a real security/data risk. Per finding: at most three sentences — failure mode, line, fix. No praise, no restating the diff, no diagrams or mockups, no style commentary (CI linters gate style), no info-level observations. If nothing meets the bar, leave no comments. OmniVoice is a fully-local desktop app (no cloud, no API keys, no telemetry): flag any new outbound network call that is not GitHub Issues or a HuggingFace model download.",
"commentTypes": ["logic"],
"strictness": 3,
"customContext": {
"files": ["CLAUDE.md"],
"rules": [
@@ -24,13 +24,14 @@
"statusCheck": true,
"ignorePatterns": "bun.lock\nuv.lock\nfrontend/src-tauri/target/**\ntests/fixtures/**\n*.svg\n*.png\n*.wav\n*.onnx",
"sequenceDiagramSection": {
"included": true,
"collapsible": true,
"defaultOpen": true
"included": false
},
"confidenceScoreSection": {
"included": false
},
"summarySection": {
"included": true,
"collapsible": true,
"defaultOpen": true
"defaultOpen": false
}
}