1de7e8f8b57627249ce7aa3ed4709676cfa0cfd0
7
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
  
|
dfe13b03c8 |
feat(mcp): off-load read-tool dispatch to a worker pool to fix concurrent-call timeouts (#1002)
The shared daemon served every session on one event loop with synchronous node:sqlite. codegraph_explore is CPU-bound work stitched together by microtask awaits, so N concurrent explores keep the microtask queue continuously full and starve the macrotask phases — timers AND socket I/O. The transport freezes: no response can flush until the whole batch drains, so with ~10 subagents on a large repo clients routinely time out (reported via X by @symbolic2020). Move the heavy read-tool dispatch onto a worker-thread pool. Each worker holds its own WAL read connection (verified: a worker reader sees the main writer's committed catch-up/watcher writes); the single watcher/writer, the catch-up gate, codegraph_status, and the staleness/worktree notices stay on the main thread. Concurrent reads now run in true parallel up to core count and the main loop stays free for the MCP transport, so responses flush incrementally instead of all-at-once after the batch drains. Enabled for the shared daemon only; direct (single-stdio-client) mode is unchanged. - crash recovery: respawn + retry-once, with a circuit breaker that falls back to in-process dispatch if workers can't run on this platform - graceful backstop: an overloaded pool returns success-shaped "busy, retry" guidance, never isError (so it can't teach the agent to abandon codegraph) - pending-aware growth + capped concurrent cold-starts avoid a startup thundering herd (N simultaneous module-loads + DB opens could stall the loop) - config: CODEGRAPH_QUERY_POOL_SIZE (default clamp(cores-1, 1, 16); 0 disables → in-process), CODEGRAPH_QUERY_BUSY_TIMEOUT_MS (default 45s) 10 concurrent explores on vscode (10.5k files): 31s → ~9s, staggered flush, 0 timeouts, byte-identical output; scales with cores (≈3.3× on 8, 1.8× on 2). Full suite passes plus 10 new query-pool tests (fake-worker injection so the scheduling logic is covered without spawning threads). Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
|
cea4d086f9 |
fix(watcher): degrade cleanly on watch exhaustion and prolonged lock contention (#891)
The live file watcher could stay "alive" after it had stopped being trustworthy. EMFILE/ENFILE watch-resource exhaustion only logged (and was silently tolerated on the Linux per-directory path), and prolonged LockUnavailableError retried forever at the normal debounce cadence — both left auto-sync dead while the index silently drifted stale. Especially bad for long-running MCP/daemon sessions. Add a one-way degrade(): on watch-resource exhaustion (any watch strategy) or on lock contention past a bounded exponential-backoff budget, log once, fire a new onDegraded callback, and stop. start() now returns false consistently when the per-directory path degrades at startup — it previously returned true on Linux, so the MCP server reported the watcher "active" when it had degraded. Wire onDegraded into the MCP server so callers are actually told, and expose isDegraded()/getDegradedReason(). Builds on the approach in #877 by @thismilktea. Validated on macOS (recursive), Linux (per-directory, Docker) and Windows (recursive) — 30/30 watcher + watch-policy tests on each. Closes #876 Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Colby MchenryandGitHub
|
3a1ddf41cd |
feat(mcp): trace relevance + closure-collection + god-file rendering + cold-start handshake (#580)
Trace endpoint relevance (overloaded names resolve to the real implementation instead of an empty protocol/delegate stub), Swift closure-collection synthesizer, multi-phase god-file explore rendering, and serve --mcp cold-start handshake sped ~811ms→~90ms (proxy answers initialize/tools-list locally). Full suite green (1090 pass). |
||
 csw-chenandGitHub
|
cea78ceb1b |
fix(windows): suppress console popup on child_process calls (#498)
On Windows, v0.9.5's detached shared daemon (#411) has no inherited console, so any console-subsystem child it spawns gets a fresh visible console window unless the spawn passes `windowsHide: true`. The fix adds the flag to all ten `spawnSync` / `execFileSync` / `execSync` call sites across extraction, sync, installer, and the WASM-flags relaunch. macOS/Linux ignore the option, so this is a no-op elsewhere. Fixes #485, #510, #530. Co-authored work: - #498 (csw-chen) — full sweep across extraction, sync, installer, and wasm-runtime. **This is the change being merged.** - #505 (yushengruohui) — independently identified and fixed the 7 git execFileSync sites. Superseded by #498's broader sweep; same diagnosis. - #521 (JirA44) — independently identified and fixed the WASM-runtime spawnSync re-exec. Superseded by #498's broader sweep; same diagnosis. Validated on Windows 11 ARM64 (Parallels): a detached parent's 15 git spawns produce 15 visible black flash-windows without the fix and 0 with it. |
||
|
|
71935e37c2 |
feat(mcp): multi-module Go trace-quality + small-repo retrieval tuning (#494)
* feat(go): generated-file down-rank + gRPC stub-impl bridge + trace-failure inlining
Multi-pronged fix to make codegraph competitive on Go multi-module repos
(cosmos-sdk, etcd) where it previously lost or tied. Driven by an 8-question
agent-eval audit across cobra, gin, prometheus, cosmos-sdk, and etcd: the
baseline had codegraph losing ~60% on cost on cosmos-sdk and mixed on etcd
deep cross-module flows, while winning cleanly on the single-module and
non-protobuf-heavy repos.
Diagnostics ruled OUT `go.work` parsing as the gap (prometheus crushes
without it). The actual failure modes were generated-file noise warping
disambiguation, missing gRPC interface→impl bridge in structural-typing Go,
and trace's failure path triggering 3-5 follow-up tool calls instead of
inlining the material the agent needed.
Changes:
- New `src/extraction/generated-detection.ts` — path-pattern classifier
for `.pb.go`, `.pulsar.go`, `_grpc.pb.go`, `_mock.go`, `_mocks.go`,
`mock_*.go`, `.generated.[jt]sx?`, `_pb2(_grpc)?.py`, `.pb.{cc,h}`,
`.g.dart`, `.freezed.dart`. Applied as a stable sort tiebreaker in
`findSymbol`, `findAllSymbols`, `codegraph_search` (MCP + CLI),
`codegraph_explore` file ranking, and context formatter Entry Points /
Related Symbols / Code blocks. Cosmos's `msgServer.Send` now ranks #3
instead of #9 on a `Send` search.
- New `goGrpcStubImplEdges` synthesizer in `callback-synthesizer.ts` —
detects `UnimplementedXxxServer` structs in generated files, identifies
their RPC methods (excluding `mustEmbed*` / `testEmbeddedByValue` gRPC
markers), and emits `calls` edges to the matching methods on any
non-generated struct whose method-name set is a superset. Closes Go's
structural-typing gap that the existing `interfaceOverrideEdges` (Java /
Kotlin only) couldn't bridge. 467 bridge edges on cosmos-sdk; bank's
`UnimplementedMsgServer::Send` points to `x/bank/keeper/msg_server.go`
only, not to `msgClient` siblings or mock files.
- Trace-failure rewrite (`handleTrace`) — when no static path connects
endpoints, instead of telling the agent to call `codegraph_node` (a
3-4-call fan-out), inline both endpoints' bodies (120 lines / 3600 chars
per endpoint), their callers (≤6), and callees (≤8) in one response.
- Trace endpoint-pairing improvements — scores every `from`×`to`
candidate combo by shared directory prefix and tries the best-paired
pair first (the full candidate set, not just FTS top-5). A
less-canonical-path penalty (`enterprise/`, `contrib/`, `examples/`,
`vendor/`, `third_party/`, `deprecated/`, `legacy/`) ensures the
canonical-module pair wins even when a side-experiment shares more of
its directory prefix. Find-path probe budget capped at 20 pairs.
- Test-file deprioritization in `codegraph_explore` `isLowValue` — adds
suffix patterns (`_test.go`, `_spec.rb`, `.test.ts`, `.spec.tsx`,
`Test.java`, `Spec.kt`) alongside the existing directory-style patterns.
Otherwise etcd's `watchable_store_test.go` consumes 5K chars of explore
budget that should go to the hand-written flow source.
Tests:
- New `__tests__/generated-detection.test.ts` (4 unit tests) pins the
suffix patterns.
- New "Go gRPC stub→impl synthesis" integration test suite in
`frameworks-integration.test.ts` (2 tests): positive bridge from stub
to hand-written impl, AND the precision case (don't bridge to a
generated sibling like `msgClient` in the same .pb.go).
- Full suite: 1076/1076 pass.
Empirical (post-fix, n=2 average per question):
| Repo / Q | WITH | WITHOUT | Reads (W/WO) | Time (W/WO)
|-------------------------|------------|-------------|--------------|------------
| cobra (parse cmds) | $0.27 | $0.27 | 0 / 4 | 39s / 60s
| prometheus (scrape→TSDB)| $0.63 | $0.70 | 0 / 6 | 106s/143s
| cosmos-sdk Q1 (MsgSend) | $0.41 | $0.26 | 1 / 2 | 67s / 64s
| cosmos-sdk Q2 (Delegate)| $0.47 | $0.46 | 0 / 5 | 50s / 73s
| cosmos-sdk Q3 (gov tally)| $0.34 | $0.31 | 1.5 / 3 | 54s / 76s
| etcd Q1 (Put→raft) | $0.65 | $0.78 | 0 / 4 | 98s / 129s
| etcd Q2 (watch) | $0.36 | $0.50 | 0 / 4+ | 58s / 89s
Codegraph wins on reads + time on every question. Cost is mixed: 3 clean
wins, 3 tied (within 10%), 1 stubborn cost loss on the grep-favored Q1.
Compared to baseline, the cosmos-sdk cost-gap collapsed from -60% to -15%
on average, and Q3 went from a 75% loss to a tie. Raw run artifacts in
`/tmp/cg-finalv2-*/` and `/tmp/cg-final-*/`.
Memory written at `project_go_multi_module_audit.md` for the methodology
+ before/after numbers.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(mcp): auto-inline trace in codegraph_context for flow queries
When a codegraph_context task contains a flow keyword ("trace", "from",
"reach", "flow", "propagat", "how does", "how do") AND at least two
distinct PascalCase / camelCase identifiers, internally invoke trace
between the first two extracted symbols and splice the trace body into
the context response. Conservative trigger by design: false positives
waste one graph query; false negatives just fall back to the agent
calling trace itself (existing path-proximity wiring handles either
case).
Goal: collapse the agent's typical context → trace → explore sequence
into a single context call for clear flow queries, closing the
remaining cost-overhead gap on multi-call patterns. The path-proximity
+ less-canonical-path scoring + the trace-failure-inlined-bodies
behavior already let the inline trace land on the right endpoint pair
and return enough material that no follow-up codegraph_node/Read is
needed.
Doesn't fire on:
- cobra's "How does cobra parse commands and flags?" (no PascalCase
symbols) — verified in regression run, no behavior change ($0.260
WITH vs $0.257 WITHOUT, basically tied)
- queries where the agent doesn't call codegraph_context at all
(cosmos Q1 in the audit went search → trace → node → trace → node)
Tests: 1076/1076 still pass.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(mcp): trace failure inlines TO file siblings to displace node fan-out
The cosmos-Q1 audit revealed a static-resolution gap: msgServer.Send's
*real* next hop is `k.Keeper.SendCoins` — an interface-method call on an
embedded field that tree-sitter can't resolve. The static getCallees list
for msgServer.Send is all utility/error functions (StringToBytes, Wrapf,
…). The actual flow (SendCoins → subUnlockedCoins → addCoins →
setBalance) lives entirely inside `x/bank/keeper/send.go`, which is also
where the TO endpoint (setBalance) lives.
When trace fails (no static path), inline the **top 5 functions/methods
in the destination file**, ordered by line-distance from the TO node.
This catches the flow that interface-method calls obscure — the
canonical "k.<Iface>.<Method>" pattern in Go, also relevant to Java
dependency-injection / Rails service-object dispatch / etc. where
interface dispatch hides the real call.
Conservative: only fires on trace FAILURE (no static path); the success
path is unchanged. Per-body cap (40 lines / 1200 chars), top 5 siblings.
Bookkeeps with `inlinedBodies` Set so endpoints already shown above
aren't duplicated.
Result: cosmos-Q1 — historically the most stubborn cost loss (-2.2× to
-39% across the audit) — flipped to a clean WIN: $0.257 WITH vs $0.449
WITHOUT (-43%), 34s vs 79s, 0 Reads vs 2 Reads + 5 Greps, 5 codegraph
calls vs 12. Regression-checked: prometheus, cobra, cosmos-Q2, etcd-Q1
all still WIN; Q3 is high-variance ($0.30-$0.45 range historically) and
fell within that on this run.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat: extend coverage to all supported languages, not just Go
PR review feedback: the audit was Go-driven, so the patterns I added
were Go-flavored. Extend each axis to every language CodeGraph
supports per the README, so the same improvements help Java / C# /
Python / TS / Swift / Dart projects too.
**generated-detection.ts** — Added patterns for:
- TS/JS: `.gen.[jt]sx?`, `.pb.[jt]s`, `_pb.[jt]s`, `_grpc_pb.[jt]s`
(ts-proto, gRPC-web, Apollo / GraphQL codegen, Hasura).
- Python: `_pb2.pyi` (mypy stubs from protobuf).
- C#: `.g.cs` (T4 / Razor codegen), `Grpc.cs` (protoc-gen-csharp).
- Java: `OuterClass.java` (protoc-gen-java), `Grpc.java`
(protoc-gen-grpc-java; this is where the `*ImplBase` abstract
class lives — same shape as the Go `Unimplemented*Server` stub).
- Swift: `.pb.swift` (protoc-gen-swift).
- Dart: `.pb.dart`, `.pbgrpc.dart`, `.chopper.dart`.
- Rust: `.generated.rs`.
**test-file deprioritization** (`isLowValue` in `codegraph_explore`)
— Added per-language conventions that the previous regex missed:
- Python: `test_*.py` (pytest discovery) and `*_test.py`.
- Ruby: `*_test.rb` (minitest) — `*_spec.rb` already covered.
- C#: `*Tests.cs`, `*Test.cs`, `*Spec.cs`.
- Swift: `*Tests.swift` (XCTest).
- Dart: `*_test.dart`.
**IFACE_OVERRIDE_LANGS** in `callback-synthesizer.ts`'s
`interfaceOverrideEdges` — extended from `java, kotlin` to
`java, kotlin, csharp, typescript, javascript, swift, scala`. Same
shape across these (nominal `implements`/`extends` on a class to an
interface/abstract base). Also iterates `struct` (Swift value types
conforming to a protocol) in addition to `class`. The existing
matchesSymbol-style logic and `getOutgoingEdges(..., ['implements',
'extends'])` work unchanged.
**CLAUDE.md** — Added a House rule: when the user references issues
or comments, anchor them to a date and version (last release vs.
last main commit vs. current branch tip) BEFORE concluding a fix is
incomplete. Issue #388 comments from May 25-27 were responding to
the released v0.9.5 / merged-PR-469 state — not to this branch's
in-flight work. The new rule walks through the disambiguation:
`grep -m1 '^## \[' CHANGELOG.md` for release version, `git log
--first-parent main -1` for main tip.
Tests: 1076/1076 still pass.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(mcp): tiny-repo tool gating + shorter tool descriptions
Two cumulative changes targeting the small-repo cost gap surfaced by
the cross-language audit:
1. **Tool descriptions trimmed** (~2.1KB total saved across 10 tools).
The verbose marketing prose on codegraph_context / codegraph_node /
codegraph_explore / codegraph_trace / etc. wasn't moving the agent
toward better tool choices on top of the actual usage, but it was
adding ~525 tokens of cache-creation overhead to every question.
The trimmed descriptions keep the operational hints (e.g. "Query is
a bag of symbol/file names, not a question" for explore) but drop
the redundant prose.
2. **Dynamic tiny-repo tool gating** in `ToolHandler.getTools()`. On a
project with < 150 indexed files, the MCP server only exposes the
5 core tools (search, context, node, explore, trace) instead of all
10 — the omitted callers/callees/impact/status/files tools' use
cases on a sub-150-file repo reduce to one grep anyway. The MCP
tool-defs overhead is the #1 source of cost loss on tiny repos
(~$0.10-0.15 fixed cache-creation per question); cutting 5 tools
drops that by ~50%.
Effect on ky (~25 files, the worst pre-fix offender):
- Before: $0.59 WITH vs $0.42 WITHOUT (+42% loss, n=1)
- After: $0.32 WITH vs $0.44 WITHOUT (-26%, **flipped to WIN**)
Effect on cobra/sinatra/slim (50-80 files): still cost-loss, but
the gating doesn't regress them — same call-count, same reads.
The structural lower bound on those repos is what the agent's
grep+read path costs in absolute terms (~$0.20-0.30).
Non-breaking for medium+/large repos: all 10 tools remain exposed
when fileCount >= 150.
Tests: 1076/1076 still pass.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(mcp): combined tiny-tier — smaller explore + tool gating (cobra/ky flip to WIN)
Combines the tool gating from the previous commit with a matching
explore-budget cut for projects under 150 files. The two together close
the cost gap that neither closes alone:
- Tool gating alone helped ky (WIN) but didn't move cobra/slim/sinatra
- Explore-budget cut alone helped slim slightly but regressed cobra
- COMBINED: cobra flips to WIN, ky stays a WIN, ky/cobra both clean
`getExploreOutputBudget(fileCount < 150)` returns:
maxOutputChars: 13000 (was 18000)
defaultMaxFiles: 4 (was 5)
gapThreshold: 7 (was 8)
maxSymbolsInFileHeader: 5 (was 6)
maxEdgesPerRelationshipKind: 4 (was 6)
includeRelationships: true (kept ON — cheap structural signal)
maxCharsPerFile: 3800 (unchanged — monotonic invariant w/ next tier)
This survives the cobra-regression-with-trim that the earlier
budget-only attempt suffered: with only 5 tools to choose from, the
agent doesn't fall back to extra codegraph_node calls when explore
returns less — there's no node call available.
Results on the four worst small-repo losses (combined intervention):
| Repo | Files | WITH (combo)| WITHOUT | Verdict (pre → post) |
|--------|-------|-------------|-------------|--------------------------|
| cobra | ~50 | $0.25 | $0.31 | loss → **WIN** (-19%) |
| ky | ~25 | $0.39 | $0.39 | -42% → tied |
| slim | ~80 | $0.31 | $0.24 | LOSS 31% → still LOSS |
| sinatra| ~60 | $0.30 | $0.23 | LOSS 18% → still LOSS |
sinatra/slim remain a cost-loss because their WITHOUT path is
structurally cheap (~$0.20 — fewer than 4 cheap grep+read calls).
Codegraph can't beat that absolute floor with any meaningful response.
Both still WIN on time + reads + tool-call count.
Tests: tier boundary cases updated to cover the new <150 / 150-499 /
500-4999 / 5000-14999 / >=15000 progression. Off-by-one guard updated
to include the new 149↔150 boundary. All 1076 tests pass.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(context): trim maxNodes default to 8 on tiny repos
On a <150-file project the entire repo is grep-able in one turn, so the
20-node default `codegraph_context` was paying for a graph subset that
exceeds the agent's actual question. Cutting the tiny-repo default to 8
(typical 1-3 entry points + their immediate 1-hop neighbors) reduces
the context-tool response body without hitting sufficiency on the flow
shapes small repos actually contain.
Non-breaking: the agent can still pass an explicit `maxNodes` to
override; medium+ repos (>=150 files) keep the 20-node default.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs(mcp): pin the empirical 5-tool gating floor for tiny repos
n=2 audit on cobra/ky/sinatra ruled out cutting below 5 tools (search +
context + node + explore + trace) on the tiny-repo tier. The smaller
3-tool gate (search + context + trace) saved ~$0.025 of prompt overhead
but the agent fell back to extra Reads to cover what codegraph_node and
codegraph_explore would have answered — net cost regression on all three
test repos (cobra 17% → 48% loss, sinatra 18% → 96% loss). Documented
inline so future tuners don't re-try this dead-end.
No behavior change beyond the comment: the 5-tool gate remains the
production setting.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs(mcp): pin empirical lower bound on tool gating after n=2 micro test
Tested the hypothesis that exposing FEWER tools on micro repos (<50
files) would close the cost gap. Results:
- 1-tool gate (codegraph_search only):
- ky: +44% (worse than 5-tool +30%)
- express: +107% (catastrophic — was -43% WIN with all 10)
- cobra: +126% (way worse than 5-tool +17%)
The single-tool gate forces the agent to read everything because it
can't navigate the call graph. The 5 omitted tools (context, node,
explore, trace) were doing real work that grep+Read can't replicate.
Conclusion: 5 tools (search + context + node + explore + trace) is the
empirical lower bound on the tiny-repo tier. Cutting below regresses
EVERY tested repo. The remaining ~$0.04-0.08 of structural cost overhead
on tiny repos is unavoidable without sacrificing the value codegraph
provides at that scale (which would also make WITH = WITHOUT, defeating
the install).
Comment documents the dead-ends so future tuners don't relitigate.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(mcp): iter3/iter4 — raise tool-gate to 500, sufficiency steering in context, hard-exclude low-value files
Three layered changes targeting the sinatra/slim/small-repo cost gap
that iter2's body-shrink failed to close (smaller bodies just pushed
the agent to Read instead):
1. **Tool-gate threshold 150 → 500** (`TINY_REPO_FILE_THRESHOLD`).
Sinatra (~159 files) and slim (~200 files) have the same structural
problem as cobra (
* feat(context): iter7 — core-directory boost to surface dominant-file siblings in search ranking
On projects with a single file holding the dense majority of internal
call edges (e.g. sinatra's `lib/sinatra/base.rb` at ~85% of in-file
edges), text search was favoring small focused extension files over the
core file. A small focused file like `multi_route.rb` wins on verbatim
name match + file-size normalization, burying the 1500-line core file's
longer method names (e.g. `route!` vs `route`).
Fix: detect the "dominant file" — the file whose in-file edge count is
≥3× the next candidate's — then add +25 to all results sharing its
directory prefix. This pulls the core file's siblings above
sibling-package extensions without hardcoding any repo structure.
`getDominantFile()` excludes test/spec files and generated files
(e.g. etcd's `rpc.pb.go` has 4× the in-file edges of `server.go` and
would otherwise hijack the boost toward generated protobuf stubs).
SQL pulls the top 20 candidates; path-pattern filtering handles what
SQLite LIKE can't express.
* feat(mcp): iter10+iter12 — routing manifest inline + probe-sweep harness
On small projects (<500 files) with a routing-shaped query, build a
URL→handler manifest directly from the graph (each `route` node joins to
its handler via `references`/`calls` edges) and inline the top handler
file's source. The agent gets the canonical routing answer in ONE
codegraph_context call — no need to parse framework DSL, Glob for
controllers, or chase down handler files.
The lever is "make the backend smarter so the agent doesn't have to":
- Parsing routes.rb / routes/api.php / urls.py DSL is the agent's job
in the WITHOUT arm. Codegraph already has it parsed as `route` nodes
with edges to handlers — we just project that to a manifest table.
- The handler implementations are right there in the index too; inline
the highest-handler-count file so the agent sees real code, not just
symbol names.
Results on the realworld template repos that were losing badly:
rails-rw +89% LOSS → -15% WIN (agent often answers with 0-1 tool calls)
laravel-rw +29% LOSS → +12% (tight gap)
gin-rw +30% LOSS → +23% (still loss but smaller)
flask-mb +64% LOSS → +25% (smaller gap)
The residual losses are mostly the agent's defensive read behavior on
super-cheap-WITHOUT repos (express-rw still does 4 Reads even with a
19-row manifest + service file inlined). That's an agent-side ceiling
the backend can't reach further without removing tools.
Also lands `scripts/agent-eval/probe-sweep.mjs` — a direct-MCP test
harness that runs context probes across 21 repos in ~600ms (vs ~30min
for a real claude audit). Enables rapid iteration on backend changes:
edit tools.ts / context-builder, npm run build, re-run probe-sweep,
compare signals (manifest fired? handler file inlined? response size?)
before paying for a claude run.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(mcp): first tool call awaits catch-up sync (no stale rows for deleted files)
`MCPEngine.catchUpSync()` reconciles the index against the working tree
after open (catching `git pull`/`checkout`/`rebase` and any edits or
deletes made while no server was running). It was fire-and-forget — so a
tool call landing in the first ~50-300ms could race past it and serve
rows for files that no longer exist on disk. The per-file staleness
banner can't help here, because that signal is populated by the file
watcher (not by catch-up).
The fix: `catchUpSync()` now pushes its promise into `ToolHandler` via
`setCatchUpGate(p)`; the first `execute()` call awaits the gate and then
clears it. Subsequent calls pay nothing. Catch-up rejections are logged
by the engine and swallowed by the handler so a transient sync failure
never breaks tools.
Most visible on the "deleted everything between sessions" case, where
MCP previously returned stale rows pointing at non-existent files.
Validated end-to-end on a 10,640-file VS Code index: with the gate, a
codegraph_search for "ExtensionHost" against an empty (but stale-DB)
directory returns "No results found" after the catch-up drains the DB;
without the gate, the same call returns 10 stale hits.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* docs(changelog): cover small-repo retrieval tuning + auto-trace + iface-override expansion
Add entries for work that landed on this branch but wasn't yet in
[Unreleased]: tiny-repo tool gating + sufficiency steering + budget
tier, auto-inline trace in codegraph_context, routing manifest inline,
core-directory ranking boost, JVM-only interfaceOverrideEdges extended
to C#/TS/JS/Swift/Scala, and the shorter tool descriptions.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
|
b48170e69f |
feat(mcp): per-file staleness banner + tunable watcher debounce (#403) (#428)
Two coupled changes addressing the issue's underlying ask — "how does the
agent know when the index lags" — without resorting to a static wait.
Per-file staleness banner
-------------------------
FileWatcher now tracks per-path `pendingFiles` (path, firstSeenMs,
lastSeenMs, indexing) — events since the last successful sync, cleared
only after a sync whose `syncStartedMs >= lastSeenMs` commits. Chokidar
initial-scan events are gated behind a `ready` flag (with `waitUntilReady()`
exposed so tests can deterministically wait through it) so a fresh startup
doesn't falsely flag every existing file as pending.
ToolHandler now wraps every code-returning response (search, context,
callers, callees, impact, trace, explore, node, files) with
`withStalenessNotice`: intersects "files referenced in the response" with
`getPendingFiles()` and emits a hybrid signal —
* banner at the top for files referenced AND pending (with edit age +
indexing/pending-sync state, telling the agent to Read those specific
files directly; the rest of the response stays fresh and codegraph
stays authoritative for it),
* compact footer for pending files elsewhere in the project not
referenced above (capped at 5).
Cost is one boolean check + N substring matches when pending; zero
allocation when idle. `codegraph_status` surfaces the same data as a
first-class `### Pending sync:` section so the agent can ask "is the index
caught up?" in one call.
Cross-project quirk: when an agent passes `projectPath` matching the
default session's project, the staleness wrapper switches from the cached
cross-project CodeGraph (no watcher) to the default one (with watcher) so
the signal still fires. Same fix applied to `handleStatus`.
CODEGRAPH_WATCH_DEBOUNCE_MS
---------------------------
MCP `serve --mcp` now reads `CODEGRAPH_WATCH_DEBOUNCE_MS` and forwards it
to `cg.watch({ debounceMs })`. Clamped to [100ms, 60s]; out-of-range or
non-numeric values fall back to the FileWatcher default (2000ms). Active
value is logged to stderr on watcher startup so it's discoverable. The
docs in `server-instructions.ts`, `installer/instructions-template.ts`,
and `.cursor/rules/codegraph.mdc` no longer claim "~500ms"; they now
describe the banner mechanism instead — since per-file staleness replaces
the "wait N ms" guidance entirely, the docs become accurate at any
debounce value.
Validation
----------
* 847 unit/integration tests pass (added 15 new ones — pending-file
tracking, banner/footer routing, status section, env-var parsing).
* Direct MCP probe through a real `codegraph serve --mcp` process: edit a
file, query within the debounce window, banner fires naming the
edited file with edit-age.
* Real Claude TUI session via `scripts/agent-eval/itrun.sh` with
`CODEGRAPH_WATCH_DEBOUNCE_MS=10000`: agent edits `math.ts`, calls
`codegraph_explore`, reads the banner, **and discloses it unprompted in
its final reply**: "note: symbol index is mid-sync for the new `divide`,
but the source it returned is verbatim from disk."
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
995da54430 |
feat(mcp): share one serve --mcp per project across MCP clients (#411)
One shared, detached daemon per project root: every `codegraph serve --mcp` is a thin stdio<->socket proxy (Unix socket / Windows named pipe) to it, so N agents in one repo share a single file watcher, SQLite connection, and tree-sitter warm-up instead of N copies. The daemon outlives any single session and reaps via client-refcount + idle timeout; `CODEGRAPH_NO_DAEMON=1` opts out. Hardened during review: detached-process lifecycle (preserves the #277 watchdog via the proxy; the daemon no longer orphans on host SIGKILL), atomic lockfile + pid-verified stale-clear (no double-daemon on concurrent startup), realpath root canonicalization. Validated on macOS, Linux (Docker - 3x fewer inotify watches for 3 agents), and Windows (named pipes); A/B confirms byte-identical tool output vs direct mode. Closes #411. Co-Authored-By: Colby McHenry <me@colbymchenry.com> Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |