release: v0.2.5817 — reader.md auto-prepend + perf + security#490
Merged
Conversation
Benchmark Regression ReportThresholds: 10.00% and 50,000 ns absolute delta
|
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7fd3dd6306
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Comment on lines
+673
to
+675
| const cached = explorer.getContent(path, allocator) catch null; | ||
| const content_owned = if (cached) |c| c else blk: { | ||
| break :blk std.Io.Dir.cwd().readFileAlloc(io, path, allocator, .limited(10 * 1024 * 1024)) catch { |
There was a problem hiding this comment.
The new codedb read branch reads arbitrary user-supplied paths without the safety gates used by codedb_read in MCP (isPathSafe + watcher.isSensitivePath), and the fallback uses std.Io.Dir.cwd() directly. This allows traversal/secret reads such as codedb read ../.env (or absolute paths if provided), which bypasses the repository boundary and sensitive-file protections expected by this codebase.
Useful? React with 👍 / 👎.
Bumps semver to 0.2.5816 and consolidates two follow-up fixes from the v0.2.5815 cross-corpus eval: - #484 feat(cli): add `codedb read` subcommand - #485 fix(search): skip Tier 5 full-scan when trigram returned candidates Measured impact (benchmarks/search-shootout, 20 warm iters): Suspense (regex, 0 hits) 2.82 ms → 0.14 ms (20× faster) useState (regex) p99 16.57 ms → 1.67 ms (10× p99) useState (flask) 0.66 ms → 0.18 ms (3.7× faster) React queries: unchanged ±noise; hit counts identical Recall preserved on every query. Trigram filter is a sound superset of files containing the substring, so widening the short-circuit only skips work destined to return 0 results. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
… security Bumps semver to 0.2.5817. Bundles the v0.2.5816 perf+security release (PRs #484, #485, #483, #486, #487) with the experiment/reader-md feature that auto-prepends a hash-verified codebase map to codedb_context. Highlights vs v0.2.5815: Performance (PR #485, deterministic microbenchmarks): Suspense regex p50: 2.82 ms → 0.18 ms (15.6× faster) useState regex p99: 16.57 ms → 2.04 ms (8.1× p99 reduction) CLI surface (PR #484): + codedb read <path> [-L FROM-TO] [--compact] + path-safety + sensitive-file guards + project-root anchoring (uses configured root, not cwd) codedb_context (NEW in 0.2.5817): + auto-prepends .codedb/reader.md when source_hash matches + inline ~6 lines of body for ≤3 symbol_definitions + new "## Callers" section pre-surfaces execution sites + skip-on-short-task gate (≤80 chars) to avoid overhead on narrow lookups reader.md security (this branch): + path-traversal blocked (no absolute / .. in source_files) + source_files capped at 20 (DoS guard) + loc_actual capped at 240 (body bloat guard) + golden blake2b roundtrip test Eval (Sonnet 4.6, n=3 per task, vs v0.2.5815 main lineage): T1 flask median: 5 → 4 (-1) T2 regex median: 13 → 7 (-6) T3 react median: 13 → 10 (-3) All 9 runs across the matrix returned correct answers. Branch wins on median, mode, and best-case for every task. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
justrach
force-pushed
the
release/v0.2.5817
branch
from
7fd3dd6 to
049786e
Compare
6 tasks
Benchmark Regression ReportThresholds: 10.00% and 50,000 ns absolute delta
|
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.
TL;DR
v0.2.5817 ships reader.md: a hash-stable, agent-authored codebase map auto-prepended to `codedb_context` responses. Plus all of v0.2.5816's fixes (perf + security), plus three new codedb_context enhancements (inline symbol bodies, callers section, task-length gate).
Bundled
From release/v0.2.5816:
codedb readsubcommand #484 `codedb read` CLI subcommand (with P1 path-safety guards)New on this branch:
Performance vs v0.2.5815 (Sonnet 4.6 sub-agents, n=3 each)
Deterministic microbench (PR #485):
Security fixes
codedb readsubcommand #484 P1: `codedb read` CLI now rejects absolute paths, `..` traversal, sensitive files (`.env`, `id_rsa`, etc.). Anchors fallback reads to project root, not cwd.Reader.md lifecycle
```
agent → codedb_context
↓
load .codedb/reader.md
↓
blake2b(source_files) match? → prepend body
↘ "stale, regenerate" hint
↘ silent (missing)
↓
(existing composer output follows)
```
Hash verification fires on every call (re-reads source files, recomputes blake2b — ~0.1 ms overhead).
Release artifacts
All 10 assets built locally, both macOS binaries notarized via Apple notary service (Accepted, gatekeeper source=Notarized Developer ID), linux smoke-tested via docker linux/amd64.
What's deferred (not blockers)
From the Sonnet 4.6 critical-review pass:
All P1 review findings closed. P2 follow-ups remain for v0.2.5818+.
Test plan
🤖 Generated with Claude Code