Merged
Conversation
- New adapter: src/brainlayer/ingest/codex.py — parse, classify, chunk, embed, store - CLI command: brainlayer ingest-codex <file|dir> - Smart mapping: function_call_output → file_read/stack_trace/git_diff - Batch ingest with dedup (skips already-indexed sessions) - Fixed source field propagation in index_new.py - 39 tests, validated on real data: 4,129 chunks from 20 sessions Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Organization UI Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (6)
✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
EtanHey
added a commit
that referenced
this pull request
Mar 17, 2026
Remove unused `import sys` and fix import sort order. Pre-existing on main, not from BrainBar changes. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
EtanHey
added a commit
that referenced
this pull request
Mar 17, 2026
* feat: BrainBar Swift daemon — MCP server over Unix socket New Swift menu bar daemon that owns the BrainLayer SQLite database and serves MCP tools over /tmp/brainbar.sock. Eliminates 10 Python processes (931MB RAM) with a single native daemon (~40MB est.). Components (28 tests, all passing): - MCPFraming: Content-Length parser/encoder (7 tests) - MCPRouter: JSON-RPC dispatch for 8 BrainLayer tools (7 tests) - BrainDatabase: SQLite3 C API with FTS5, WAL, PRAGMAs (10 tests) - BrainBarServer: POSIX Unix socket + E2E integration (4 tests) Architecture: direct SQLite3 C bindings (zero external deps), single-writer (eliminates all SQLITE_BUSY errors), 209KB binary. Includes: build-app.sh, Info.plist, LaunchAgent plist, .mcp.json.example updated with socat config. Part of Three-Daemon Sprint (Phase 3). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: address security and robustness issues from self-review Pre-CodeRabbit fixes for 5 MAJOR + 4 MEDIUM issues: MAJOR fixes: - SQL injection in pragma(): whitelist allowed pragma names - JSON injection in tool handlers: use JSONSerialization, not string interpolation - Socket path buffer overflow: add length check before memcpy - Content-Length DoS: cap at 10MB max payload - FULLMUTEX retained: needed for WAL concurrent reads + close() race safety MEDIUM fixes: - FTS5 sanitization: strip * and handle empty queries - Listen backlog: 5 → 16 for connection burst handling - sendResponse: handle EAGAIN on non-blocking sockets - Database exposes isOpen for server startup validation 28/28 tests still GREEN. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: lint errors in codex.py from PR #83 Remove unused `import sys` and fix import sort order. Pre-existing on main, not from BrainBar changes. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: ruff format codex.py and test_ingest_codex.py Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: address CodeRabbit review Round 1 — 14 actionable comments MAJOR fixes: - FTS5 backfill: rebuild index when opening existing DB (critical for 312K chunk DB) - Stub handlers: return notImplemented error instead of fake success - brain_search: clamp num_results to max 100 MEDIUM fixes: - MCPFraming: add 16MB total buffer limit (DoS protection) - build-app.sh: allow BRAINBAR_APP_DIR env override (no sudo needed) - Test: replace force unwrap with XCTUnwrap - LaunchAgent: add ThrottleInterval for restart storms Design decisions (commented on PR): - /tmp/brainbar.sock intentional (not brainlayer.sock) — avoids conflict during migration - brain_tags replaces brain_get_person — per Phase B spec 28/28 tests GREEN. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: align BrainDatabase schema with production DB (312K chunks) Root cause of "SQLite prepare failed: 1": - BrainBar used `chunk_id` — production uses `id` - BrainBar used `session_id` — production uses `conversation_id` - BrainBar created its own FTS5 schema — production uses (content, summary, tags, resolved_query, chunk_id UNINDEXED) - Production requires source_file NOT NULL, metadata NOT NULL Fix: - All SQL now uses production column names (id, conversation_id, etc.) - ensureSchema() skips creation on existing DB (production already has schema) - New/test DBs get production-compatible schema - FTS5 triggers match production (include resolved_query, chunk_id) Tested: brain_search via socat returns real results from 312K chunk DB. 28/28 Swift tests GREEN. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
brainlayer ingest-codexwith dedupTest plan
🤖 Generated with Claude Code