A multi-word PascalCase query token — typically a project name a user
includes (`SuperBizAgent backend routes`) — splits into sub-tokens
(superbizagent / super / biz / agent) that ALL match the same path segment,
so path relevance summed +5 four times for one concept. In a mixed-stack
repo that ~doubled every score of the lexically-matching stack's file,
burying the stack the query was about.
Score path relevance per original query WORD instead: a word matches a path
level if any of its sub-tokens do, and counts once — while still splitting
the word (via extractSearchTerms on the original case) so it matches across
naming conventions (`getUserName` → `get_user_name`). Distinct words each
still contribute.
Partial fix: this removes the dominant path over-counting (backend rises
from absent-in-top-6 to parity on the reporter's repro). The residual lexical
edge from the project name in the FTS class-name match + dir match is a deeper
down-weighting change, tracked separately. No re-index needed (query-time).
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A function called only from an anonymous func_literal at package level — a
cobra `RunE: func(){…}` handler, a goroutine literal, a callback closure
stored in a `var` — had its call leak to the FILE node, because the Go
var-initializer walk ran with an empty scope. So `callers`/`impact` showed
the function with a file (or no meaningful) caller, unlike JS/TS where an
arrow-in-const becomes a named node whose calls attribute correctly.
Scope the Go top-level var/const initializer walk to the declared symbol, so
a call nested in any func_literal initializer (struct field, slice/map,
nested closure) attributes to the enclosing var. EXTRACTION_VERSION 3->4
(re-index to pick up the corrected attribution).
Validated on cli/cli (858 Go files): node/edge counts identical, file-level
dependents byte-identical (no regression), and 62 top-level-closure calls
correctly moved from file-attributed to var-attributed.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A .gitignore transparently encrypted in place by corporate DLP / endpoint
software (UTF-16 header + ciphertext), or one containing a pattern the
`ignore` library can't compile to a regex (`\[` -> "Unterminated character
class"), crashed the entire sync/index. The throw is LAZY — it surfaces at
match time (`ig.ignores()`), not `.add()` — so the existing add-time
try/catch never caught it, and the error never named the offending file.
Read .gitignore defensively: skip a file that isn't valid UTF-8 text whole
(NUL byte or fatal UTF-8 decode), drop only the individual uncompilable
patterns from a text one (probe-compile, then per-line fallback), and warn
with the file path. Indexing continues either way. The watcher inherits the
fix via buildDefaultIgnore.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
PHP's importTypes only captured namespace_use_declaration, so
include/require(_once) — the dependency mechanism in procedural and
script-style PHP — never produced edges. callers, impact, and trace
missed the entire file-include graph; only namespace `use` became a
dependency edge.
Capture the four include/require expression types and emit file→file
imports edges, reusing the path-based resolution that C/C++ #include
already goes through. Only static string-literal paths are resolved
(relative to the including file); dynamic forms (include $var,
require __DIR__ . '/x', interpolated strings) are skipped.
Include PATHS are distinguished from namespace `use` symbols by shape: a
path contains '/' or '.', which PHP identifiers and FQNs never do. A
path-shaped include that doesn't resolve to a known project file is left
unresolved and does NOT fall back to the symbol name-matcher, which would
otherwise mis-connect "inc/db.php" to an unrelated db.php elsewhere — a
wrong edge is worse than a missing one.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Colby McHenry <me@colbymchenry.com>
A C++ method call whose receiver is another call's result — `Foo::instance().bar()`,
`WidgetFactory::create().draw()`, `openSession()->run()`, or the same stored in an
`auto` local first — lost the receiver's type during extraction. The callee degraded
to a bare method name, so when two classes shared a method name the call silently
resolved to whichever was indexed first (or not at all), corrupting callers / impact /
trace with a plausible-but-wrong edge.
Three parts:
- Capture C++ return types (new nodes.return_type column, schema v5): the
function_definition's `type` field, normalized — smart-pointer pointee unwrapped,
void/primitives dropped.
- Preserve the inner-call receiver in extraction: a C/C++ field_expression whose
receiver is itself a call is encoded `inner().method` instead of dropping to the
bare name. Other languages keep the existing behavior.
- New resolution strategy (matchCppCallChain): infer the receiver's class from the
inner call's return type, then resolve AND validate the method on it. Handles
singletons/accessors, factories returning a different type, free-function
factories, make_unique/make_shared/new/direct construction, single-level member
chains, and namespace-qualified inner calls. A wrong inference yields no edge,
never a wrong one.
EXTRACTION_VERSION 2->3 (re-index to populate return types).
Validated on the issue repro + spdlog: node count stable (no explosion),
deterministic, and ~100 pre-existing wrong `.size()`-style edges removed.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Two environments that share one working tree — most concretely Windows
and WSL — can't safely share a single `.codegraph/`: the daemon lockfile
records a platform-specific pid + socket (named pipe vs Unix socket), and
SQLite locking across the WSL2/Windows filesystem boundary is unreliable,
so two daemons over one index risks corruption.
Add a `CODEGRAPH_DIR` env var (default `.codegraph`) that overrides the
per-project data directory name, so each environment keeps its own index
in the same tree (e.g. `CODEGRAPH_DIR=.codegraph-win` on Windows). The
name is resolved live and validated (rejects separators / `..` / absolute,
falling back to the default with a one-time stderr warning). Indexing and
file-watching now skip ANY `.codegraph-*` sibling so neither side trips
over the other's data.
Routes the previously-hardcoded `.codegraph` literals (db path, lockfile,
error log, watcher ignore, file-scan skip, installer) through the
resolver. No extraction-version bump — index content is unchanged.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
TypeScript service/RPC contracts written as a tuple of generic types —
`type List = [Service<'query_apply_record', Req, Resp>, …]` — carry their
names only as string-literal type arguments, so static extraction never
indexed them and `codegraph query query_apply_record` returned nothing.
Add a narrow TS/TSX type-alias pass that emits each tuple entry's
string-literal name as a `method` node under the alias (qualifiedName
`List::query_apply_record`), making it searchable. Scope is limited to a
direct literal arg of a generic that is a direct tuple element, with a
valid-identifier filter — so utility types (Pick/Omit/Record), deeper
nested generics, and route paths produce no noise.
Bumps EXTRACTION_VERSION so existing indexes get a re-index hint.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Makes codegraph_node a drop-in faster Read for indexed source files (file-read mode: <n>\t<line> like Read, offset/limit, + blast-radius header; symbolsOnly for the map). Fixes the old file-view dropping imports/line-numbers. #383/#527 preserved. Validated by A/B: explore/node already return source + line numbers, so Read=0 when used. Includes the A/B eval harness scripts. Full suite green (1270).
Corrects the "run non-nested only" conclusion from #734. The codegraph server
is healthy (handshake ~165ms); the flakiness is that on a multi-step
implementation task the agent dives into Read/grep before codegraph finishes
its ~2-3s startup (worse under nested CPU contention), so it runs with no
codegraph. Fix: pre-warm a persistent daemon (high idle timeout) + skip the
startup re-exec (CODEGRAPH_WASM_RELAUNCHED=1) so claude connects before the
agent's first turn. claude's init snapshot can show status:"pending" even when
it then connects — judge by actual codegraph usage, not the init line.
ab-new-vs-baseline.sh now bakes in the pre-warm + skip-re-exec. Validated: a
clean A/B showed the new build's agent used codegraph 2x / 5 Reads vs the
baseline's 0 / 8 on the same fully-implemented task.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Running scripts/agent-eval against a `claude -p` spawned from within a Claude
Code session (nested, e.g. from a Bash tool call) makes the codegraph MCP
attach unreliable: the server is healthy (full handshake ~165ms) but the
nested client marks it status:"pending"/0-tools under CPU/timing contention,
so the agent silently runs with no codegraph. NO_DAEMON + `< /dev/null` don't
fix it — it's the nested client, not the server. Documented in CLAUDE.md's
validation methodology.
Adds ab-new-vs-baseline.sh: A/Bs a retrieval/steering change as new-build vs
baseline-build (both codegraph-on, isolating the change — vs run-all.sh's
with-vs-without), on a throwaway copy of an indexed repo. Run it in a real
terminal.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(mcp): steer agents to codegraph during implementation, not just Q&A
Two changes targeting agents that reach for Read during edits instead of codegraph:
1. Reframe the agent-facing steering (server-instructions + codegraph_node/explore
descriptions): drop "consult BEFORE ... not during"; position codegraph_node as
the Read upgrade for a named symbol (verbatim current on-disk source, safe to
Edit from, + caller/callee trail), explore PRIMARY / node SECONDARY, with the
"cached intelligence — better context, fewer tokens" framing.
2. File-view mode: codegraph_node now accepts a `file` with no `symbol` and returns
that file's symbol map + graph role (its dependents), plus verbatim bodies with
includeCode — so it can displace a path-keyed Read, not just a symbol lookup.
Resolves a path or basename; dedups nested members; budget-capped.
To be A/B'd on an implementation task before shipping (per the retrieval doctrine:
steering changes must be measured, not assumed).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(changelog): note codegraph_node file-view + implementation steering
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The "Attached to shared daemon" line is benign INFO, but it was written to
stderr — and MCP hosts render all server stderr at error level (and append an
`undefined` data field), so on every session start a healthy attach showed up
as `[error] … undefined`. It is now gated behind CODEGRAPH_MCP_LOG_ATTACH=1:
silent by default, opt-in for debugging daemon attach. Both attach sites
(runProxy + connectWithHello) route through one helper. The daemon integration
tests opt the harness into the log so their attach assertions still observe a
successful attach.
Re-applies the approach from #640 by @mturac.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(security): resolve symlinks in path validation to block out-of-root reads (#527)
validatePathWithinRoot was purely lexical (path.resolve + startsWith), so an
in-repo symlink whose logical path is inside the project root but whose real
target escapes it passed validation — and both content-serving read sinks
(codegraph_node includeCode, codegraph_explore source) then readFileSync'd it,
leaking out-of-root file contents (e.g. ~/.ssh, /etc) to the agent.
Add a realpath layer: after the lexical check, resolve symlinks on both the
candidate path and the root and re-compare, rejecting anything whose real path
escapes the root. An in-root symlink is still allowed (no over-blocking).
Comparison is case-insensitive on Windows (NTFS + realpath casing). Not-yet-
existing paths (ENOENT) fall back to the lexical result so about-to-be-written
files still validate; other resolution errors reject.
Removes the dead, never-called isPathWithinRoot / isPathWithinRootReal helpers
(the latter a footgun — it returned true on realpath failure). Adds RED->GREEN
tests: in->out file/dir symlinks rejected, in->in allowed, ../ rejected, ENOENT
allowed, plus an end-to-end test proving getCode no longer serves an out-of-root
file reached through a dir symlink.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(changelog): note the #527 symlink path-escape fix
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Spring `application.{properties,yml}` keys (and Shopify Liquid `{% schema %}`
blocks) were storing the config VALUE in the node docstring, and
`codegraph_explore`'s source section re-read the raw `key = value` line off
disk — so a secret committed to a config file (DB password, API key, JDBC URL
with embedded credentials) could be pushed into an agent's context via
explore/node output without the agent ever opening the file.
Config-leaf nodes (`kind: 'constant'` in a config language) now surface the KEY
only, via a shared `isConfigLeafNode` predicate applied at both surfacing
paths: the value is dropped from extraction, `getCode`/`includeCode` returns
the key instead of the file line, and explore excludes config leaves from
source rendering. The predicate can't match real code (real constants are
ts/java/go/…), so `@Value`/`@ConfigurationProperties` resolution and impact are
unaffected. Adds a regression test asserting a planted secret never appears in
`codegraph_explore` / `codegraph_node` output while the keys still resolve.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Vendor tree-sitter-c-sharp 0.23.5 (ABI 15) for C#, replacing the bundled ABI-13
build that dropped primary-constructor classes. Adds native primary-ctor
parsing, primary-ctor parameter dependency edges, return-type extraction via the
renamed `returns` field, and a preParse that blanks `#if` directive lines the
new grammar mis-parses inside enum bodies. Validated on MediatR / eShopOnWeb /
Newtonsoft.Json + full suite.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add a resolution-phase pass (goCrossFileMethodContainsEdges) that links a Go
method to its same-named receiver type within the same package (= directory),
so a method declared in a different file from its `type` is no longer orphaned
from the struct. Runs before goImplementsEdges so cross-file methods also count
toward interface satisfaction (#584). Adds a regression test + CHANGELOG entry.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Give resolvePythonModuleMember the same absolute-dotted-path fallback that
resolveModuleImportToFile already uses, so a `module.func()` call after
`from pkg import module` / `import pkg.module as module` records its `calls`
edge. Adds a regression test and a CHANGELOG entry.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
When an MCP host (opencode and others) SIGTERM's the shared daemon as a new
session starts, the existing session's proxy used to exit on the dropped socket
— silently losing CodeGraph for that session, and hanging any request in flight
at the drop. The SIGTERM originates in the host's process-tree teardown, not in
CodeGraph (nothing here signals another process), so the fix is proxy
resilience, not chasing the signal.
The local-handshake proxy now treats a daemon disconnect as recoverable rather
than terminal: it falls back to its in-process engine for the rest of the
session (the same path used when no daemon is reachable at startup, and what
CODEGRAPH_NO_DAEMON does) and re-serves any requests that were in flight to the
dead daemon, so the host never hangs. The proxy still exits when the HOST goes
away (stdin close / PPID watchdog) — only daemon loss is now non-fatal.
Also replaces the over-the-wire liveness-sweep test added in #712 — which was
flaky under heavy parallel load (a raced raw-socket connect) — with a
deterministic Daemon.reapDeadClients unit test. The client-hello round-trip is
still exercised by every daemon test (the real proxy now sends it).
Validated with a reproduction (proxy stays alive, in-flight request answered,
post-drop request recovers) and a regression test in mcp-daemon.test.ts.
Confirmed on macOS (full suite green) and a Windows 11 VM.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Layer-2 defense-in-depth follow-up to the Windows PPID watchdog fix (#711).
That fix makes an orphaned proxy exit so its socket closes and the daemon
reaps via the refcount + idle timer. This adds two daemon-side safety nets for
the residual case where a socket close is never delivered (a Windows named-pipe
hazard) and a phantom client would otherwise pin the daemon forever:
- Liveness sweep: a proxy now sends an optional client-hello carrying its pid
(+ host pid) right after verifying the daemon hello; the daemon periodically
drops any client whose peer process is dead, re-arming the idle timer.
Fail-safe and version-pinned — a connection that never sends the hello just
falls back to the socket-close lifecycle, and the daemon reads it before the
transport so a non-hello first line is handed through untouched.
- Inactivity backstop: the daemon exits after a generous no-traffic window
(CODEGRAPH_DAEMON_MAX_IDLE_MS, default 30 min) even with clients attached, so
a phantom client that sends nothing can't keep it alive.
Pure helpers (parseClientHelloLine, peerIsDead) are unit-tested; the full
handshake + sweep and the backstop are covered end-to-end in mcp-daemon.test.ts.
Validated on a real Windows 11 VM: the sweep reaps a dead-pid client over a
named pipe and the backstop fires with a client still connected.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
On Windows the PPID watchdog could never fire: orphans aren't reparented, so
`process.ppid` stays constant after the parent dies (defeating the ppid-change
check), and the standalone bundle pre-bakes `--liftoff-only`, skipping the
relaunch that sets `CODEGRAPH_HOST_PPID` (defeating the host-liveness check).
With neither signal available, an orphaned proxy / direct server ran forever,
the shared daemon never saw the client disconnect, and its idle timer never
armed — node processes accumulated until CPU saturated.
Add a win32-only signal: poll the original parent's liveness directly, since
ppid is stable there. Gated to Windows so POSIX double-fork cases keep relying
on the ppid-change signal (a dead original parent is not proof of orphaning on
POSIX). The decision is extracted into a pure, unit-tested helper shared by all
three watchdog sites (proxy socket, proxy local-handshake, direct mode).
Validated on a real Windows 11 VM: in the exact bundle scenario (direct mode,
no HOST_PPID) an orphaned server now exits within one watchdog poll via the new
path; the POSIX reparent path is unchanged and its integration test still passes.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
`codegraph upgrade [version]` detects how the CLI was installed — the standalone
install.sh/install.ps1 bundle, npm-global, npx, or a source checkout — and
updates in place: re-running the canonical install.sh on macOS/Linux, an
in-place rename-and-extract swap on Windows (a running node.exe can't be
deleted, only renamed, so the detached-helper approach is avoided), and
npm/npx/source-specific guidance otherwise. Flags: `--check` (report only),
`--force`, and a positional version to pin.
Each full index is now stamped with the engine's EXTRACTION_VERSION in
project_metadata; `codegraph status` (and `--json`) flags an index built by an
older engine and recommends re-indexing, and `upgrade` prints the same reminder.
Gated on EXTRACTION_VERSION so it never nags on extraction-neutral releases.
Validated end-to-end on macOS (real bundle upgrade), Linux (Docker, real
curl|sh) and Windows (Parallels VM, real in-place swap). 32 new unit tests.
Closes#679
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Completes the cross-file dependency graph behind impact / affected / explore across all 22 supported languages and 14 web frameworks, validated on real-world repos (measured fair-coverage table added to the README). Per-language resolution + framework resolvers/synthesizers (Lua/Luau require, Shopify OS 2.0 Liquid sections, Delphi forms, Rust cross-module + Rocket macros, Swift Fluent, SvelteKit/Nuxt loader/component conventions, RN/Expo bridges). 0 cross-family false edges, full suite green (1187 passed). See #708.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Regenerate assets/waitlist.svg as "Join the waitlist" (no exclamation),
same cream/8px/padding styling.
- Add ?v=2 cache-buster to the README image URL so the new button shows
immediately instead of waiting on GitHub's image cache.
- CLAUDE.md house rule: version-tag every README image and bump ?v=N in
the same commit whenever the asset changes.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replaces the plain oxblood-filled rectangle + system-font text SVG with a
polished button that matches the getcodegraph.com design language:
- Cream (#f7f6f2) rounded-rect background with a soft hairline border, 8px
radius, 52px height
- Logo mark (graph triangle, mirrors favicon.svg) in ink/oxblood at left
- Hairline divider separating mark from label
- "Join the waitlist!" label rendered as vector outlines (Archivo Bold 760,
17.5px) so the brand typeface renders correctly on GitHub, which blocks
@font-face in statically-served SVGs
- Oxblood arrow at right
Adds assets/generate-waitlist.py (requires fonttools + brotli) so the SVG
can be regenerated from the landing-page's Archivo variable font. Updates
the README img height from 44→52 to match the new geometry.
Advertise the upcoming hosted CodeGraph platform at the top of the README with a "Join the waitlist" CTA (early beta access) linking to getcodegraph.com, plus the button SVG asset.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Vue's extractor parsed only the <script> block, so a component used solely
in another component's <template> (`<MyButton />`) produced no reference —
and thus showed a false 0 callers, even after the barrel-resolution fix in
PR #657. This is the Vue analogue of Svelte's extractTemplateComponents.
extractTemplateComponents() now scans the template (everything outside the
<script>/<style> blocks, which also handles nested <template> tags for
v-if/slots) for component tags:
- PascalCase tags (`<MyButton/>`) — captured as-is.
- kebab-case tags (`<my-button/>`) — converted to PascalCase so they match
the imported component's name. Safe: an unmatched name creates no edge
during resolution, so native custom elements just don't resolve.
- Native HTML elements (lowercase, no hyphen) and Vue built-ins
(Transition, KeepAlive, …) are skipped.
Adds no nodes — only `references` — so node counts stay stable. With this
plus #657, a Vue component re-exported through a barrel and used only in a
template now resolves end-to-end (callers/impact/callees).
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Component barrels (`export { default as X } from './X.svelte'`) and
monorepo workspace imports (`@scope/ui/widgets`) left the consumer↔component
edge uncreated, so live components showed a false `0 callers` — the canonical
dead-code signal — risking deletion of live code.
The Svelte default-barrel case broke at FOUR layers, each of which alone left
it unresolved:
- findExportedSymbol matched only function/class for a default export, never
`component` (Svelte/Vue SFCs are kind 'component').
- extractImportMappings had no svelte/vue branch, so SFC consumers produced
zero import mappings and resolveViaImport never ran.
- EXTENSION_RESOLUTION had no svelte/vue entry, so relative imports from an
SFC (`./lib` -> `/index.ts`) resolved to nothing.
- getReExports parsed the barrel in the CONSUMER's threaded language, so a
.svelte consumer made extractReExports bail on a .ts index barrel.
Workspace package-subpath barrels get a new workspace-packages module
(mirrors go-module/path-aliases): reads package.json `workspaces`
(npm/yarn/bun) + pnpm-workspace.yaml, maps member name->dir, resolves
`@scope/ui/widgets` -> `packages/ui/widgets`. Gated behind the workspaces
field so single-package repos are unaffected.
Bare `./`/`.` directory imports already resolved; covered with a regression
test. Verified both directions (callers/impact AND callees) for Svelte; Vue
script-level imports also resolve. 4 new tests; full suite green (1126).
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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>
The callback/observer synthesizers loaded every function and method node into
memory at once (getNodesByKind('function'/'method')) before scanning them down
to a tiny matched subset. On a symbol-dense project that array is gigabytes, so
indexing spiked the JS heap and aborted with "JavaScript heap out of memory".
Add QueryBuilder.iterateNodesByKind (a lazy node:sqlite cursor) and stream the
synthesizer scans instead of materializing them. Parsing and reference
resolution were already bounded; only the synthesis enumeration wasn't.
Measured on 80 files x 14k functions (~1.1M nodes): peak RSS 3717 MB -> 1318 MB,
no OOM. Full suite green; synthesized edges unchanged.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
chokidar v4 holds one OS file descriptor per watched file on macOS (libuv's
kqueue backend registers an fd per vnode; fsevents is installed but v4 no
longer uses it). On a large project the `serve --mcp` daemon accumulated tens
of thousands of open REG descriptors and exhausted kern.maxfiles — crashing
unrelated processes system-wide with ENFILE. #276 only trimmed the count by
ignoring directories; the source tree still cost one fd per file.
Replace chokidar with a pure-JS native fs.watch hybrid, keeping codegraph's
zero-native-addon "any OS builds any bundle" invariant:
- macOS / Windows: a single recursive fs.watch (one FSEvents stream /
ReadDirectoryChangesW handle) -> O(1) descriptors regardless of repo size.
- Linux: one inotify watch per directory (O(dirs), dynamic add for new
dirs, capped via CODEGRAPH_MAX_DIR_WATCHES) instead of per-file watches.
Validated empirically: macOS 0 extra fds at 6k and 12k files; Linux 31 inotify
watches at 6k files (per-file would be 6k); Windows recursive catches nested
and new-directory edits. Full test suite green.
Tests drive the watcher through an inertForTests seam (no OS watcher) for
determinism under parallel vitest, with one real-fs end-to-end test exercising
the genuine native path.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Captures three development session checkpoints: per-symbol adaptive sizing (PR #569), trace relevance + cold-start fix (PR #580), and the explore-overhaul arc (explore as sole primary + Zustand store coverage + budget/render tuning). Documents root causes found, gotchas (stale-daemon foot-gun, Mac sleep corrupting benchmarks), validation methodology, and open threads for each session.
## Summary
Completes the explore-overhaul arc: `codegraph_explore` becomes the single primary tool an agent reaches for, and its coverage + output shape are tuned so flow/architecture questions resolve with near-zero Read/Grep.
### What changed
- **explore is the sole primary tool** — removed `codegraph_context` (the fuzzy-input Read-trigger) and `codegraph_trace` (under-picked by agents); explore already surfaces the call flow among the symbols you name. A plain natural-language question now works as the query.
- **Store/handler coverage** — functions defined inside object literals (Zustand `create((set, get) => ({ … }))`, Redux/Pinia/MobX, exported handler/route maps) are indexed as real symbols, including calls through `useStore.getState().fn()` and destructured `const { fn } = useStore.getState()`. A general AST rule, not a per-lib hack.
- **Overload disambiguation** — explore leads with the *right* definition when a method name is overloaded across types (a PascalCase type token in the query biases to that type's own def); `codegraph_node` returns *every* overload's body in one call, with an optional `file`/`line` selector to pin one.
- **Method-atomic render** — explore never returns half a method; at the size budget it drops whole methods/files (and lists what it dropped) instead of truncating a body mid-method.
- **Native-read-shaped output** — per-call output is capped to ~24K with a 25K hard ceiling and concentrated into ~150–250-line flow windows, mirroring how the agent natively reads; repo size scales the *call* budget, not the per-call size (a larger response just gets externalized to a file the host Reads back).
- **Blast radius** folded into explore (dependents + covering tests, locations only).
### Benchmark (refreshed on this build)
Re-validated the 7-repo A/B on 2026-06-02 (Opus 4.8, effort=high, median of 4). WITH arm re-measured on this build, WITHOUT reused:
**~16% cheaper · 47% fewer tokens · 22% faster · 58% fewer tool calls** — 0 file reads on 6 of 7 repos (Gin ~1).
The arc trades larger, cache-heavy explore responses for guaranteed near-zero reads, so cost/token margins soften vs the prior build (Excalidraw and Tokio land at cost break-even) while time and tool-calls stay clear wins everywhere — consistent with the project's stated optimization target (latency + tool-calls, not token cost).
### Validation
- Full suite green: **1112 passed, 2 skipped**.
- 28/28 plain WITH runs across the 7 README repos completed clean; reads median 0 on 6/7.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Cuts the 0.9.8 release, which carries the restored embedded/programmatic
SDK API (#354) along with the rest of the [Unreleased] changelog. The
Release workflow promotes [Unreleased] -> [0.9.8] and appends the link
reference; only the version fields are bumped here.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The 0.9.x thin-installer turned @colbymchenry/codegraph into a bin-only
shim: require("@colbymchenry/codegraph") threw MODULE_NOT_FOUND and no
types shipped, breaking embedded library consumers (e.g. Electron apps)
upgrading from 0.8.0.
Restore programmatic use without re-bloating the thin shim or duplicating
the ~49 MB of grammars the per-platform bundle already carries:
- main -> npm-sdk.js re-exports the installed per-platform bundle's compiled
library (lib/dist/index.js) at runtime, reusing that bundle's own deps; it
falls back to a self-healed cache bundle, else throws an actionable error.
- types -> ship the .d.ts tree only (~590 KB) in the main package, built from
the same release so it can never skew from the runtime it re-exports.
- exports map resolves the `types` condition (nodenext) and the default entry.
- DatabaseConnection + QueryBuilder are now top-level exports, so embedded
callers get the building blocks from the package entry instead of deep
dist/ imports (which the shim no longer ships).
The CLI/MCP `bin` keeps execing the bundled Node; only library consumers run
on their own runtime, which must be Node 22.5+ for the built-in node:sqlite.
Validated end-to-end: built a real darwin-arm64 bundle, packed the npm
packages, installed them into a throwaway consumer, and confirmed require()
plus a full init/indexAll/searchNodes round-trip and the low-level
DatabaseConnection/QueryBuilder path all work on the host Node; types resolve
under both nodenext and classic node resolution; and the CLI shim still
launches. New hermetic tests cover npm-sdk resolution, cache fallback, and the
missing-bundle error.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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).
Sizes codegraph_explore to the answer, not the file count: shows the mechanism +
the exact methods you named in full (even buried in a large file) while collapsing
redundant interchangeable implementations to signatures. Adds uniqueness-aware
spare, per-symbol focused rendering of family files, all-tier test-file exclusion,
and named-method cluster survival in non-sibling god-files.
Validated A/B (Opus 4.8, 7-repo sweep): avg 25%% cheaper / 57%% fewer tokens / 23%%
faster / 62%% fewer tool calls. Django 9->23%% cheaper (0 reads), OkHttp 4->11%%
cheaper; gains across small/medium/large, inert repos unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
codegraph_explore now skeletonizes off-spine, redundant members of a polymorphic
family (OkHttp's interceptor chain, Django's SQLCompiler family) to signatures
instead of shipping every full body, while keeping the dispatch mechanism, the
orchestrator/base, and any method the agent named in full. Sizes the response to
the answer rather than the budget cap, so interface-heavy flows stop costing more
than plain grep/read. Default on; CODEGRAPH_ADAPTIVE_EXPLORE=0 disables.
Gate: off-spine + >=3-impl sibling + not-spared, where spared = the agent named a
callable in the file UNLESS the file defines the family's supertype (a huge
base+subclasses file is Read-anyway, so skeletonizing frees explore budget).
Validated headless A/B (Opus 4.8): both former README cost outliers flipped —
OkHttp and Django went from costlier-than-native to cheaper; full 7-repo average
22%% cheaper / 47%% fewer tokens / 20%% faster / 50%% fewer tool calls, every repo
cost-positive, inert repos unchanged. 7-case regression test.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(agent-eval): detect idle by content-stability, not spinner absence
Opus 4.8's extended-thinking TUI shows no spinner / interrupt hint / timer while it streams its final answer — those appear only during the thinking and tool-use phases. The old detector treated ~5s of not-busy + prompt-present as done, so it killed interactive runs mid-answer, silently truncating both arms of the tmux A/B (low tool counts; the final assistant message left as a mid-investigation preamble). Now a run is done only when the captured pane stops changing for ~8s; while streaming, the pane changes every poll so stability never accrues. BUSY_RE stays as the immediate busy-reset for the thinking/tool/live-timer phase. Content-stability is model-agnostic — it survives future spinner re-wordings.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(readme): refresh VS Code benchmark on v0.9.7 + Opus 4.8
Re-ran the VS Code A/B (headless median-of-4) on the current build and model. Cost savings held at 26% ($0.66->$0.89), but token/time/tool-call savings narrowed (78->63%, 52->20%, 85->69%) because Opus 4.8's without-CodeGraph arm explores far more efficiently than 4.7's did (16 tool calls vs 55, no Explore-subagent fan-out); the WITH arm is unchanged at 5 calls / 0 reads. Recomputed the average row and noted that the VS Code row is now a different model/version epoch than the other six.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(resolution): synthesize gin middleware-chain edges (Next -> registered handlers)
Gin runs its entire handler chain through one dynamic line in (*Context).Next -- c.handlers[c.index](c), a slice-index dispatch tree-sitter can't resolve. So callees(Next) dead-ended at the len() helper and the flow ServeHTTP -> handleHTTPRequest -> Next stopped at the exact symbol a 'how does the middleware chain work' question is about, sending the agent to re-query and Read/grep (a measured gin WITH-arm rabbit-hole: 2/4 headless runs spiraled to ~5min, one mis-firing the opt-in Workflow orchestration tool). Find the chain dispatcher (a Go method invoking a handlers slice by index) and link it -> every HandlerFunc registered via .Use/.GET/.../.Handle, so callees(Next) and trace(ServeHTTP, handler) connect end-to-end. Gated on the dispatcher existing (inert on non-gin Go repos), named handlers only (inline closures skipped), capped; provenance heuristic / synthesizedBy gin-middleware-chain, registeredAt = the registration site. Validated: gin callees(Next) now surfaces Logger/Recovery/ErrorLogger + handlers (node count stable at 2,544; 5 precise edges); agent A/B (headless median-of-4, Opus 4.8) flipped gin from -58% cost / -129% time to +7% cost / +35% tokens / +8% time / 38% tool calls, all 4 WITH runs clean (0 Read/Grep/Bash). 167/167 unit tests pass incl. the new gin-middleware-chain test.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(readme): publish uniform Opus 4.8 benchmark + per-repo breakdown accordion
Refresh all 7 benchmark rows to the v0.9.7 / Opus 4.8 headless median-of-4 (was a mix of the 4.8 VS Code row + six 4.7 rows). New average 18% cheaper / 51% fewer tokens / 16% faster / 57% fewer tool calls; headline + methodology note updated 4.7->4.8. The gap is smaller than the prior 4.7 numbers because Opus 4.8's native grep/read is more efficient (the without-arm no longer fans out into large Explore-subagent sweeps) -- not a codegraph regression; CodeGraph still cuts tool calls and tokens on all 7 repos, with cost marginal/negative only on django + okhttp. Adds a top-level 'Per-repo breakdown' accordion (per-metric Time/Reads/Grep-Bash/Tool calls/Tokens/Cost, WITH vs WITHOUT, per repo) directly below the condensed summary; methodology/queries/why-wins move to a second accordion.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(changelog): note Gin middleware-chain synthesizer under [Unreleased]
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
`codegraph init` now runs the initial index automatically. The -i/--index
flag is kept but is now a no-op, accepted for backward compatibility so
existing muscle memory and scripts don't break. Addresses #483, where a user
asked why -i wasn't implicit.
README and site/ docs are intentionally NOT updated in this commit — they
describe the currently-released 0.9.7 behavior (where -i is still required).
Update them at the 0.9.8 release so users on 0.9.7 aren't misled.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A user asked what the `-i` flag does and why it isn't the default. Add a short
note under the Initialize Projects quickstart: plain `init` only scaffolds the
`.codegraph/` dir, `-i`/`--index` also runs the first index, and without it you
run `codegraph index` afterwards.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Completes #357. The no-symbol file-level class is yaml/twig/properties, but the
count fix only covered yaml/twig — so a .properties-only project still printed
"No files found to index" even though the files were stored. Introduce a single
isFileLevelOnlyLanguage predicate (the canonical set behind the tree-sitter
no-symbol branch, xml excluded since its MyBatis extractor emits a file node)
and use it at both count sites and the extraction dispatch so the list can't
drift. Adds .properties regression coverage for indexAll() and indexFiles().
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Update the 'Writing changelog entries' guidance to match the rewritten CHANGELOG:
friendly New Features / Fixes sections (Breaking Changes / Security only when
present), one plain sentence per bullet, strip internal paths/symbols/benchmarks,
keep #PR refs + contributor thanks. Notes why multi-word headings are safe on the
normal release path.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Distill every release's engineer-facing entry into plain-language, user-readable
notes (New Features / Fixes, with Breaking Changes / Security surfaced where they
apply). Also reconcile the mislabeled [0.7.8] block to [0.7.9] to match the
published GitHub release tag and fix its dead link reference.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
github-actions[bot]
luo jiyinandGitHub