mirror of
https://github.com/colbymchenry/codegraph.git
synced 2026-11-15 01:29:02 +08:00
fd57eaaa456e02fba3b5a4e1cd0ac63ba46d4b03
12
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Colby MchenryandClaude Opus 5.5
|
fd57eaaa45 |
fix(mcp): a tools/call whose arguments aren't an object gets invalid params, not a crash (#3071)
A tools/call request passes its arguments as an object. MCPSession took
params.arguments || {} without checking that, so a string or number went
straight to the tool handler, where the session-view check
('_cgExploreSession' in args) threw. The call then came back as a tool
result flagged isError: "This is an internal codegraph error, retry the
call once; if it persists, continue without codegraph". That reports a
client's malformed request as codegraph's own malfunction, with advice to
stop using it. An array went through as if it were the arguments. The
stdio proxy, serving in process while the daemon is unavailable, had the
same unchecked read.
Both now read the arguments through one helper, toolCallArguments(), and
answer anything but an object with a JSON-RPC invalid-params error
(-32602, "Tool arguments must be an object"), as a call with no tool
name already is; no tool runs, and the proxy starts no engine for it.
Missing, null or another empty value still means no arguments.
Validation: new mcp-tool-call-arguments.test.ts covers the session (the
direct stdio server and every daemon client) and the real proxy entry
point in a child process with the daemon unavailable: red on main (2 of
3 failed; the well-formed control passed), green with the fix.
explore-session-state and proxy-shutdown pass. Driving serve --mcp over
stdio: on main, codegraph_explore, codegraph_node and codegraph_search
with a string argument returned isError "internal codegraph error" and
codegraph_status accepted [1], 42 and true; with the fix those six get
-32602, while "", null, {} and absent arguments run as before.
Reimplements PR #2986 by @kjgggggg.
Fixes #2981
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
||
|
Colby MchenryandClaude Opus 5.5
|
e7c9ffd068 |
fix(security): an MCP session no longer opens a sensitive folder as its default project (#3012)
The MCP server's default project comes from the client (initialize's rootUri or first workspaceFolders entry, or its roots/list answer), the launch cwd, or --path. Only an agent's projectPath argument went through the sensitive-folder guard of PR #2929: the default root was opened with no check, and opening it also started a file watcher and a catch-up sync, and from the launcher a shared daemon keyed on that folder. A session whose default was ~/.config, ~/.ssh or a system folder holding an index served the files inside to the agent. (On main a warm query pool happened to refuse such a call with isError; before it warmed, the main thread served it.) resolveServerRoot, which every default-project resolution goes through (the engine's open and its per-call retry, the initialize handshake and the launcher's daemon root), now applies the refusal a projectPath gets: on the path searched from when it exists, and on the root it lands on, by up-walk or by the sub-project down-scan. A refused root resolves to null with the reason, so the session has no default project. Nothing there is opened, watched or synced; no daemon, lock or socket is set up in the folder; initialize sends the no-default-project instructions; and a call without projectPath gets the usual success-shaped "pass projectPath" guidance, saying why. A call that names the folder keeps its PathRefusalError, and sub-projects below a refused folder aren't listed. --path is refused the same way, as `codegraph ui` refuses its root, but the server stays up with no default project instead of exiting, so the agent keeps codegraph for its other projects. A daemon started by hand for such a folder exits. The sensitive-folder half of validateProjectPath is split out as sensitiveDirectoryRefusal; validateProjectPath behaves as before. Validation on Windows 11: - 6 new tests in security.test.ts. On main's sources every entry point is red: the engine opened ~/.config from the folder, a folder inside it, a missing folder under it and a junction to it, serving a fake token and taking writer.pid; rootUri, workspaceFolders, cwd and roots/list sessions served the token; the down-scan adopted or listed sub-projects; a launch from the cwd started a daemon in the folder. The ordinary-project control passes on both. All 6 pass with the fix. - security.test.ts: 70 passed, 4 skipped (POSIX and macOS gates). 51 MCP, daemon, proxy and directory suites: 646 passed, 0 failed. - The real serve --mcp against a private HOME, from a sensitive cwd and with a sensitive --path: no-default instructions, the guidance instead of the token, no daemon.pid or writer.pid. An ordinary project is unchanged. - Cost: resolveServerRoot 141 -> 377 us per call on an ordinary project (median of 7 rounds of 2000 calls). It runs at the handshake, the engine open and the launcher, and per tool call only while a session has no default project. Follow-up to PR #2929. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
||
|
Colby Mchenry
|
a5c2709e6d |
fix(mcp): adopt a single indexed sub-project below the server root + say when no project resolves (#1606, #1607) (#1614)
Fixes #1606 and #1607 together — the MCP server's root resolution never got the sub-project down-scan `planFrontload` gained in #964, and the resulting no-default state was completely silent. ## What changed **Adoption (#1606).** A new `resolveServerRoot()` in `src/directory.ts` is the single resolution every server entry point now uses: up-walk first (`findNearestCodeGraphRoot`, the common case, unchanged), and when that misses, the existing bounded down-scan (`findIndexedSubprojectRoots` — depth 4, max 64, heavy dirs skipped). **Exactly one** indexed sub-project is unambiguous and is adopted as the default project — `open` → `startWatching` → `catchUpSync` → query pool, the full normal path. Zero or several candidates → no default, never a guess. Wired into: - `MCPEngine.doInitialize()` and `retryInitializeSync()` — the retry path also picks up a child indexed *after* the server started (its down-scan is throttled to once per 5s so the persistent no-default state doesn't pay a directory walk per tool call; the up-walk still runs every time). - `resolveDaemonRoot()` — the adopted root gets the shared daemon (one watcher, one writer, socket keyed on the child) instead of a direct-mode server per host, exactly as the issue suggested. - `MCPSession.handleInitialize()` — the instructions variant is picked with the same resolution, so a workspace whose single child becomes the default gets the full single-project playbook. Race-free by construction: handshake and engine compute it independently, no ordering assumed. **Workspace-root gate (the open question in #1606).** Decided deliberately: the down-scan runs only when the base has a workspace manifest (`looksLikeProjectRoot`, unchanged list) **or a `.git` entry** — the exact container shape that motivated the report — and never when the base is `$HOME` or the filesystem root. The gate lives in the new helper only; `planFrontload` and the prompt-hook are untouched, so #1454's surface is not widened. **Diagnostics (#1607).** The no-root branch is no longer silent: ``` [CodeGraph MCP] No .codegraph/ at or above <searchFrom>: no default project, live sync disabled. [CodeGraph MCP] Indexed sub-projects found: service-a, service-b. Pass `projectPath` per call, or launch with --path. ``` (second line only when the scan found candidates), plus one line naming the adopted child when adoption happens. The same fact is protocol-reachable: the "No CodeGraph project is loaded" tool response now lists the discovered sub-projects with `projectPath` guidance. The list is engine-maintained (initial resolve + throttled retry) — tool calls never scan — and the response stays SUCCESS-shaped (`NotIndexedError` → `textResult`, never `isError`). ## Tested - New `__tests__/mcp-subproject-adoption.test.ts` (real spawned server over stdio, same harness as `mcp-roots.test.ts`): single child → tool call answers from it, full instructions, adoption stderr; two children → no default, both listed in the tool response and stderr, per-project instructions; no manifest/no `.git` → gate holds, no scan, plain one-line message. - `mcp-subproject-adoption` + `mcp-roots` + `mcp-initialize` + `daemon-bind-failure`: **13/13 pass**. - End-to-end repro harness against the built `dist/` on an unmodified-main build first (confirmed: empty stderr, no adoption, NO_ROOT instructions even with one adoptable child), then on this branch (all three shapes behave as above; catch-up sync runs on the adopted child). 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_01LxZj6W6Y1SHXwvpT3uwJpK |
||
|
Colby McHenry
|
fc31b1e2bf |
feat(mcp): remember what explore already served this session (CG-17)
Explore answers every call as if it were the first: no record of the files and line ranges it already sent, so a 4th call re-serves the 1st call's spine and the tier call budget can only be asked for, never enforced. Track it per MCP session, per resolved project root — files, coalesced line ranges, bytes, and the call's index in the session. Nothing reads it yet: the response is byte-identical, which the suite pins against an untracked call of the same query. The daemon shares ONE ToolHandler and a pool of worker threads across every connected client, so the state can live neither on the handler nor in a worker. It lives on MCPSession and is handed to execute() per call; the session's view rides DOWN on the args and the call's emission rides BACK on the ToolResult, both as plain properties so they survive the structured clone to and from a worker. execute() records the emission on the main thread and deletes it unconditionally — including for callers that track nothing, like the CLI — so it can never reach the wire. A view a client spells itself is discarded rather than trusted. Ranges are reported by the render loop itself (buildSection now returns the spans it slices alongside the text), and only files that survive the final hard-ceiling truncation are recorded. Where a bound forces a choice the record keeps FEWER ranges than were emitted: under-reporting re-serves something the agent has, over-reporting withholds source it never saw and costs a Read. Every bound caps detail only — callCount keeps counting past eviction, so CG-19's decay can't reset itself every 8 calls. |
||
|
Colby MchenryandClaude Fable 5
|
47823944a3 |
feat(mcp): notice when a newer CodeGraph release exists, without changing anything (#1243) (#1253)
The recommended MCP config launches the local binary, so a server left running drifts behind releases silently — users discover the version gap only when something breaks. Per the reporter's preferred option 1, the server now checks the latest GitHub release in the background on startup (never blocking; reuses the upgrade command's release-redirect resolution so the two can't drift) and surfaces a one-line notice on three surfaces: one stderr line (the MCP host's server log), the initialize instructions (with do-not-run-it-yourself guidance for the agent), and codegraph_status. Discipline: results cache in ~/.codegraph/update-check.json shared across every proxy/daemon on the machine — 24h TTL on success, 1h backoff after failure, an outage never hides an already-known update, and a stale cache re-kicks a background refresh so long-lived daemons keep noticing. The initialize path is a memoized synchronous cache read (the respond-fast contract holds), and both handshake answerers (session + proxy) share one helper so they can't diverge. Never stdout. Hardening: the latest tag arrives from a network redirect via an on-disk cache and ends up inside agent-visible instructions, so only a canonical vX.Y.Z rebuilt from PARSED semver fields is ever interpolated — a tag carrying trailing text (parseSemver is not end-anchored) renders without it, and a non-version tag renders nothing and counts as a failed attempt. Off is off: CODEGRAPH_NO_UPDATE_CHECK=1 (dedicated) or DO_NOT_TRACK=1 (broad convention — already set by data-plane deployments) suppresses the network call and the notice entirely. Documented in TELEMETRY.md. Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Colby MchenryandClaude Fable 5
|
a3f90089e8 |
fix(indexing): bounded-memory yielding pipeline tail + daemon session fixes (#1212) (#1226)
Large-codebase indexing died at the end of "Resolving refs" two ways: watchdog kills of healthy work (24k-file Java on Windows, #1212 — third iteration of the #1091/#1122 class) and hard OOMs (Linux kernel scale, where v1.3.0 could not complete at any watchdog setting). Root causes: ~31 of 37 dynamic-edge synthesis passes ran start-to-finish with no yield points, several materialized whole-graph snapshots (kotlin expect/actual opened with getAllNodes() — 2M nodes in one array; the C fn-pointer pass retained every C file's contents twice plus every function node), and the post-index WAL checkpoint ran minutes of synchronous IO on the main thread, killing even a successful index at the finish line. The pipeline tail now follows the same discipline as the rest: never hold O(graph) in the heap, yield everywhere. - All synthesis passes stream node-kind scans (cursors, not arrays) and yield on time-budgeted checkpoints; language gates skip passes whose filters a project's file languages provably can't satisfy. - kotlin expect/actual filters SQL-side; c-fnptr caches are LRU-bounded, units stream one file at a time, and the all-functions array + write-only id map are gone; spring reads each .java once, not twice. - runMaintenance moved to a worker thread (own SQLite connection); per-file store commits chunk with yields behind a serialized flush chain (preserving #1015 file-order determinism); resolver warm-up streams the DISTINCT name set; resolution batch-tail and merged-edge inserts run in bounded sub-transactions. - Daemon: fixed a socket-handoff race that could leave a fresh MCP session permanently silent (client-hello tail unshifted into a flowing stream with zero listeners — the long-standing #662 test flake was this real bug); first tool call no longer queues behind the query pool's cold start (pool.ready gate). Validation: Linux kernel (70,129 files, 2.05M nodes, 6.4M edges) fully indexes in 27m8s on a 2-core/6GB container at default heap + default watchdog; llvm-project (180k files) completes under 1GB RSS including kill-and-sync recovery; synthesized-edge and full-graph parity are byte-identical vs baseline on elasticsearch/redis/vim; the ex-flaky daemon test passed 25/25 under load. Env-gated diagnostics kept: CODEGRAPH_SYNTH_TIMINGS pass/phase timings, CODEGRAPH_MCP_DEBUG hop tracing. Design record: docs/design/main-thread-stall-followup.md. Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Colby MchenryandClaude Opus 4.8
|
85a8f32fd9 |
fix(mcp): serve tools without a root index + make the front-load hook monorepo-aware (#964) (#966)
The MCP server gated tool availability on whether the server root had a .codegraph/ index, so in a monorepo where only sub-projects are indexed the agent saw zero tools — and couldn't reach an indexed sub-project even by projectPath. A session started before `codegraph init` also never surfaced the tools afterward. The Claude front-load hook had the mirror gap: it only walked UP for an index, so it stayed silent at a monorepo root. MCP server: - Always expose the tool surface; when the root isn't indexed, send a per-project instructions variant (pass projectPath) instead of the "inactive" note. Safety comes from response SHAPE (success-shaped guidance, never isError), not from hiding tools. - Reword the no-default-project guidance to be per-project, not per-session, and sharpen the projectPath schema description. Front-load hook (UserPromptSubmit): - Scan DOWN (bounded depth, workspace-root-gated) for indexed sub-projects and shape the injection by topology: front-load the one the prompt names, nudge about the rest, or list them when ambiguous. Verified: full suite (1703 passed); a live two-package monorepo run confirms the hook front-loads the correct sub-project with no cross-package leakage. The front-load's net speed effect is the existing multi-file-vs-single-file tradeoff, unchanged by this work. Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Colby MchenryandClaude Opus 4.8
|
848fde9f59 |
feat(telemetry): anonymous usage telemetry — documented schema, opt-out, public ingest worker (#834)
Adds anonymous usage statistics (commands/tools used, languages indexed, connecting agents) with a strict, auditable allowlist. Never code, paths, file/symbol names, queries, or IPs. - src/telemetry/: zero-dep client — consent resolution (DO_NOT_TRACK > CODEGRAPH_TELEMETRY > stored choice > default-on), random machine UUID, in-memory counters → capped JSONL buffer → completed-day rollups; sync exit-append (survives process.exit) + opportunistic bounded sends; the first-run notice gates the first SEND, never local buffering, so the installer's consent toggle always precedes it. Off is off: no recording, no socket, buffered data deleted. - codegraph telemetry status|on|off; per-command counting via preAction hook. - MCP: tool counting after the reply is on the wire (session + proxy in-process fallback), agent attribution from initialize clientInfo, unref'd daemon flush interval. Zero hot-path cost, zero stdout. - Installer: visible default-on consent toggle (asked once, never re-asked), install/index/uninstall lifecycle events. - telemetry-worker/: public Cloudflare Worker behind telemetry.getcodegraph.com — allowlist validation, IP stripping, per-machine rate limit, forwards to PostHog as anonymous events. Ships nowhere with the npm package. - TELEMETRY.md (field-by-field contract) + README section + design doc. - 20 unit tests; suite-wide CODEGRAPH_TELEMETRY=0 guard so tests never pollute real telemetry. Full suite: 1448 passing. Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Colby MchenryandClaude Opus 4.8
|
f9fcc2cd6a |
feat(mcp): unindexed sessions go quiet — empty tools/list + inactive instructions, no-error policy (#769) (#817)
An MCP session in a workspace with no .codegraph/ previously got the full "lean on codegraph for everything" playbook plus all 8 tools, then every call returned isError — and one or two early errors teach an agent to abandon codegraph for the whole session (maintainer-observed). Now the initialize response picks an instructions variant by index state (cheap sync walk-up, #172 respond-fast contract holds) and tools/list serves an EMPTY list when unindexed: absence is the one signal an agent can't misread. Indexing is deliberately the user's call — the inactive note tells the agent not to run init itself. No-error policy in the tool handler: expected/recoverable conditions (NotIndexedError — cross-project query to an unindexed path, default- project detection miss) return SUCCESS-shaped guidance instead of isError; security refusals (PathRefusalError) stay hard errors without retry encouragement; genuine internal failures keep isError but add a retry-once note so a transient blip doesn't convert to permanent abandonment. Principle recorded in CLAUDE.md. Also: codegraph_search kind:"type" (advertised by its own schema enum) silently matched nothing — now maps to type_alias; codegraph_explore's query param no longer tells agents to run codegraph_search first (contradicted explore's call-FIRST design); server-instructions §Limitations rewords the unindexed case to stay-out-for-the-session. Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
Colby MchenryandClaude Opus 4.8
|
ddb1a8f72d |
fix: issue-triage quick wins (extraction, MCP probes, gitignore, CJK, impact) (#654)
Batch of small, localized fixes from an open-issue triage: - .codegraph/.gitignore now ignores everything but itself, so the database, daemon.pid, sockets, and logs stop showing up in git status (#492, #484) - MCP server answers resources/list and prompts/list with empty lists instead of -32601, clearing scary log lines in opencode/Codex (#621) - index SAP HANA .xsjs/.xsjslib as JavaScript (#556) and TS .mts/.cts (#366) - visit anonymous AMD/CommonJS/IIFE wrapper bodies so their inner functions and calls are indexed instead of coming up empty (#528) - batch the changed-file lookup so a huge first sync no longer hits "too many SQL variables" (#540) - list files with `git ls-files -z` so non-ASCII/CJK paths survive core.quotepath and are no longer silently skipped (#541) - attach Go methods on generic receivers (*T[P]) to their type (#583, RC1) - impact no longer climbs the structural `contains` edge, so a leaf symbol stops dragging in its sibling methods (#536) - README: explicit `codegraph install` step, run in a new shell (#631) Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Colby Mchenry
|
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). |
||
|
|
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> |