Testing showed semantic search produces significantly better results for
natural language queries that Claude writes. FTS alone often ranks
properties above their parent classes and misses conceptual matches.
Embeddings are now always on — the vector manager is created eagerly,
with model download and embedding generation still happening lazily.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Eliminates anonymous error reporting functionality that was collecting stack traces and error context via Sentry. Removes all telemetry-related code, configuration options, and documentation references.
Name matching was creating false `calls` edges between unrelated modules
in monorepos because `findBestMatch()` had no concept of directory
proximity — functions with common names (e.g. `navigate`) in different
apps scored identically and resolved to whichever came first.
Adds path proximity scoring (shared directory segments) so same-module
candidates strongly win over cross-boundary ones, and lowers confidence
for distant matches so import-based resolution takes precedence.
Closes#67
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sentry error reporting can now be disabled by:
1. Declining during the interactive installer (sets CODEGRAPH_TELEMETRY=off
in the MCP server config env)
2. Setting CODEGRAPH_TELEMETRY=off in your shell environment
README updated with a Telemetry section documenting what is collected
and how to opt out.
Closes#68
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The installer previously ran `npm install -g` silently without user
consent. Now it asks for confirmation first, explains why the global
install is needed (hooks & MCP server), and gracefully skips if declined.
README updated to document this step.
Closes#69
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
extractSearchTerms now splits camelCase, PascalCase, snake_case, and
dot.notation into individual tokens (e.g. "getUserName" → ["user", "name"]).
Stop words expanded with code-specific noise words (code, file, function,
method, class, type, etc.) to improve search precision.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
AI picking the entry point was unreliable. Now:
- Type a symbol name → dropdown shows matches
- Click a result (or Enter to pick first) → traces its call graph depth 3
- The user picks the starting point, the graph does the rest deterministically
No more AI guesswork. Search + graph traversal = reliable flows.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Completely reworked the explore approach:
- Claude (or keyword search) finds ONE entry point, not a list of symbols
- getCallGraph(entry, depth=3) traces the actual call chain deterministically
- No more AI-guessed symbol lists, bridge passes, or relevance filtering
- Search result clicks also trace the full call graph from that point
The graph data was always accurate — the problem was AI trying to guess
the whole flow. Now AI just finds the starting point, graph does the rest.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Stricter prompt rules: only symbols directly in the execution path,
every symbol must call or be called by the next, no tangential features.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Update Claude prompt to identify the entry point and return symbols in
execution order. The graph now centers on the entry point and auto-opens
its detail panel, giving users a clear starting point to trace the flow.
- Claude returns {entry, flow} instead of flat array
- Entry point is auto-selected and centered on load
- Detail panel opens immediately for the entry point
- Prompt asks for max 8-10 symbols in execution order
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Instead of expanding all callers/callees of seeds (which pulls in noise
from hub nodes like getSession), now:
1. Find direct edges between Claude's seeds
2. Only add non-seed nodes if they bridge 2+ isolated seeds
3. Cross-connection pass discovers hidden edges between result nodes
4. No more unrelated callers of hub nodes polluting the graph
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds `codegraph visualize` command that launches a localhost web UI for
visually exploring code relationships. Users can ask natural language
questions like "how does authentication work?" and see the relevant code
flow rendered as an interactive graph.
Key components:
- Visualizer HTTP server (src/visualizer/server.ts) with REST API
- Single-page frontend with Cytoscape.js graph + highlight.js code preview
- Claude CLI integration for intelligent query interpretation
- Dark theme, right-click context menus, keyboard shortcuts
- Detail panel with source code, callers, callees, hierarchy
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Traverses dependency graph to identify which test files depend on changed source files. Supports stdin input for git integration, custom test file patterns, and configurable traversal depth. Useful for targeted test execution in CI/CD pipelines.
Fixes#47 — "database is locked" after crash and MCP "not initialized"
when project IS initialized.
- FileLock: treat locks older than 10 minutes as stale regardless of PID
status, covering cases where PID was reused or kill signal check fails
- MCP server: log errors from tryInitializeDefault() to stderr instead of
silently swallowing, so transient open failures are diagnosable
- MCP server: retryInitIfNeeded() properly cleans up failed instances
before retrying, preventing resource leaks
- CLI: add 'codegraph unlock' command for manual lock file removal
Fixes#42 — tree-sitter can produce nodes with empty names (e.g. from
complex C/C++ declarators in header files). These nodes were silently
skipped at DB insert time, but their containment edges were still
inserted, causing a FOREIGN KEY constraint violation that crashed
indexing.
Two-layer fix:
- createNode() now returns null for empty names, preventing the node
and its edges from ever being created (Option A)
- storeExtractionResult() filters edges and unresolved refs to only
reference nodes that passed validation, as a safety net (Option B)
Fixes#54 — `codegraph init -i` crashes with "Fatal process out of memory: Zone"
on large codebases because all 16 tree-sitter WASM grammar modules were compiled
upfront by V8, exhausting the WASM Zone allocator.
Changes:
- initGrammars() now only initializes the tree-sitter WASM runtime (Parser.init()),
no longer eagerly loads all grammar files
- New loadGrammarsForLanguages() loads only grammars for languages actually present
in the project (e.g. a Dart project loads ~2-3 grammars instead of 16)
- Orchestrator detects needed languages after file scan, before parsing begins
- Embedding pipeline now uses quantized model (~67MB vs ~270MB) to further reduce
WASM memory pressure when embeddings are enabled
The serve command without --mcp prints a help banner. Writing this to
stdout breaks MCP stdio clients (like Cursor) that expect only JSON-RPC
on stdout. Move all banner output to stderr so stdout stays clean.
Fixes#43
Bumps version to 0.6.2 in both package.json and lockfile to align release metadata and prevent silent install failures on fresh installs.
Relates to silent install fix
command -v codegraph is unreliable inside npx because npx puts a
temporary binary in PATH. The check always passes, so the global
install is always skipped — which is the root cause of #37 and #38.
Fix: remove the check entirely, always run npm install -g.
- Revert configs (MCP, hooks) to use bare `codegraph` command
- Remove all npx references from configs and messaging
- Add preuninstall script that runs on `npm uninstall -g` to clean up
MCP server, permissions, hooks, and CLAUDE.md section
- Show uninstall instructions in post-install next steps
Global install is still attempted for bare `codegraph` convenience,
but now verifies the command is actually in PATH after install. If it
fails, users get clear actionable messages instead of silent swallowing.
Configs (MCP server, hooks) always use npx regardless — those never
break even if global install fails.
Remove the npm install -g attempt from the installer that silently
fails on many systems (permissions, PATH, node version managers).
All configs (MCP server, hooks, next-steps) now always use
npx @colbymchenry/codegraph. Global install offered as an optional tip.
Fixes#37, #38
Replace native tree-sitter with web-tree-sitter + tree-sitter-wasms for
universal cross-platform support. Add node-sqlite3-wasm as a fallback
when better-sqlite3 native bindings aren't available. Move better-sqlite3
and sqlite-vss to optionalDependencies so installs never fail.
Fix installer to use npx fallback when global npm install fails, so MCP
config, hooks, and quick-start instructions all work without the bare
codegraph command in PATH.
Fix tests: update schema version expectation, fix db test paths and
method names, extract MAX_OUTPUT_LENGTH as module constant, normalize
Windows path separators in import resolver.
The resolving refs phase stalled on large projects (3400+ files, 38k+ nodes)
because matchFuzzy loaded ALL functions/methods/classes per ref, import
mappings were re-extracted per ref, and fileExists hit disk every call.
Add kindCache, lowerNameCache, importMappingCache, and knownFiles set to
warmCaches(). Rewrite matchFuzzy to use O(1) lowercase index lookup instead
of 3x getNodesByKind scans. Cache import mappings per file. Pre-build file
existence set from the index for O(1) fileExists checks.
Fixes#28 - Python site-packages directories (e.g.
audio_tools/python/Lib/site-packages/) were not excluded by default,
causing massive index bloat and FOREIGN KEY failures when indexing
large libraries like tensorflow. The FK crash itself was already fixed
via INSERT OR IGNORE, but excluding these directories prevents the
bloat in the first place.
- Remove getNodesByIds, getNodesByKinds (zero callers)
- Remove getFileHashMap, getFileSyncMap (zero callers)
- Remove getDynamicStmt cache (only used by removed batch methods)
- Revert getStaleFiles to simple implementation (zero callers, no need to optimize)
- Remove intent field from SearchOptions (never read in search logic)
- extraction/index.ts: use picomatch with static import (replacing
dynamic require) and keep normalizePath for other call sites
- utils.ts: keep normalizePath from main, take PR's PID-based FileLock
Both functions have zero callers — dead code on arrival. Remove them
and their tests (9 tests) to keep the module focused on what's
actually used: search term extraction, path relevance scoring, and
kind bonuses.
- Remove extractFunctionVariable() and its dispatch (already handled by extractVariable)
- Remove dead getGrammar() export (zero callers)
- Deduplicate indexFile by delegating to indexFileWithContent
- Remove redundant arrow function variable extraction tests (covered by existing suite)
Normalize paths to forward slashes in matchesGlob() and scanDirectory()
so glob exclude patterns work on Windows. Add getGitIgnoredDirectories()
using git ls-files to skip .gitignore'd directories during indexing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
All grammar packages now have compatible peer deps with tree-sitter 0.21.x,
resulting in zero warnings during npm install. Downgraded grammars:
c 0.24.1→0.23.2, php 0.24.2→0.23.11, python 0.23.6→0.23.4,
rust 0.24.0→0.23.1, swift 0.7.1→0.6.0.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Reduces peer dependency warnings during install by upgrading grammars that
have newer versions accepting ^0.22.x: c 0.23.4→0.24.1, php 0.23.11→0.24.2,
rust 0.23.2→0.24.0. Python 0.23.6 and swift 0.7.1 already compatible.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
tree-sitter-kotlin doesn't ship prebuilt binaries for win32-x64, causing
npm install to fail on Windows without Visual Studio. All grammars are now
optional since the runtime already handles missing parsers gracefully.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add 'svelte' to Language type, DEFAULT_CONFIG includes, grammars, and config validation
- Add SvelteExtractor that extracts <script> blocks and delegates to TS/JS TreeSitterExtractor
- Add Svelte framework resolver for runes ($state, $derived, $effect, etc.), store auto-subscriptions, SvelteKit module aliases ($app/*, $env/*, $lib/*), and SvelteKit route detection
- Update README to list Svelte and Dart in supported languages
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
PostToolUse(Edit|Write) marks the project dirty via .codegraph/.dirty,
and Stop syncs only if dirty — batching all edits into one sync per
Claude response. The installer now writes these hooks to settings.json.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Node insertion used plain INSERT which crashes on duplicate IDs.
In large C/C++ projects, tree-sitter can produce duplicate nodes for
the same symbol (e.g. typedef struct where both struct_specifier and
type_definition resolve to the same name/kind/line, or multiple
anonymous constructs on the same line).
- Change nodes INSERT to INSERT OR REPLACE (idempotent, same data)
- Change edges INSERT to INSERT OR IGNORE (skip duplicate edges)
The node ID is sha256(filePath:kind:name:line) which already uses full
relative paths, so cross-directory collisions are not the issue.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
sqlite-vss fails to compile on Windows — moving it to optional lets
install succeed while the code already falls back to brute-force
vector search. tree-sitter-liquid is removed entirely as it has ABI
incompatibility with tree-sitter 0.22+ and Liquid is handled by the
built-in regex extractor.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Covers arrow function extraction, best-candidate resolution, graph
traversal direction fix, MCP symbol disambiguation, output truncation,
CLI uninit command, and more. Tests requiring better-sqlite3 native
bindings are conditionally skipped.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add findSymbol() helper that prefers exact name matches and notes
alternatives when multiple symbols share the same name
- Add output truncation (15K char cap) to prevent context window bloat
- Apply to callers, callees, impact, node, search, and files tools
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Exposes the existing uninitialize() method via `codegraph uninit [path]`.
Includes confirmation prompt (skippable with --force) before deleting
the .codegraph/ directory.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix arrow function extraction: explicitly call extractFunction() for
arrow functions/function expressions in variable declarations instead
of silently skipping them (all 6 arrow function tests now pass)
- Best-candidate resolution: collect candidates from all strategies and
return highest confidence match instead of first match
- Fix graph traversal 'both' direction: correctly determine next node
for mixed incoming/outgoing edges in BFS and DFS
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- SQLite performance pragmas: synchronous=NORMAL, 64MB cache,
memory temp store, 256MB mmap (safe with WAL mode)
- Batch insert for unresolved refs: single transaction instead of
N individual inserts per file
- Symbol caching (warmCaches): pre-load all nodes into memory maps
before resolution, eliminating repeated SQLite queries per ref
- Async file I/O: fs.stat/readFile in indexFile() are now non-blocking
- Denormalize filePath/language onto UnresolvedReference: avoids N
node lookups during resolution, with schema migration v2
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix Float32Array embedder bug: was creating zero-filled array instead
of copying data from TypedArray-like objects
- Fix VSS search query: use subquery pattern so LIMIT applies before JOIN
- Pin tree-sitter versions: remove caret ranges for ABI stability, add
overrides to lock tree-sitter core at 0.22.4
- Lazy grammar loading: load native bindings on first use per language
instead of all at startup, so one missing grammar doesn't affect others
- Remove stale src/extraction/queries copy from copy-assets script
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Implements security improvements inspired by PR #16 (credit: MO2k4):
- Add validatePathWithinRoot() to prevent path traversal attacks in
extraction and context building
- Clamp MCP tool inputs (limit, depth, maxDepth) to sane ranges
- Use atomic writes (temp file + rename) for config saves
- Add symlink cycle detection in directory scanning to prevent infinite loops
- Replace all JSON.parse calls in db/queries.ts with safeJsonParse fallbacks
to handle corrupted database metadata gracefully
- Add cross-process FileLock for DB write operations (indexAll, indexFiles,
sync) to prevent concurrent writes from CLI, MCP server, and git hooks
- Remove unused path import from context/index.ts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds support for Dart and Liquid languages with tree-sitter parsing.
Improves accuracy of code symbol extraction for existing languages.
Indexes project files to enhance code navigation features.
Migrates build system to facilitate code contributions.
Removes git hook functionality.
Integrates Sentry for error tracking and reporting.
Enhances project initialization and configuration loading.
The nomic-ai model is now downloaded during npm install via a postinstall
script and stored globally in ~/.codegraph/models (shared across projects)
instead of per-project in .codegraph/models.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add note that installer updates ~/.claude/CLAUDE.md in Quick Start
- Rename "Recommended: Add Global Instructions" to "Global Instructions Reference"
- Clarify that instructions are added automatically, shown for reference
- Bump version to 0.2.7
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The hybrid approach (Claude's native Explore agents using codegraph tools)
is more effective than a custom explore tool because Explore agents already
know what format the main session needs.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add 'liquid' to Language type and default include patterns
- Create LiquidExtractor with regex-based extraction (tree-sitter-liquid has ABI issues)
- Extract render/include/section references as component nodes
- Extract schema blocks as constant nodes with parsed names
- Extract assign statements as variable nodes
- Create file relationship edges for snippet/section references
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added claude-md-template.ts with the instructions template
- Installer writes to ~/.claude/CLAUDE.md (global) or ./.claude/CLAUDE.md (local)
- Smart detection: updates existing CodeGraph section or appends if not found
- Uses HTML comment markers for reliable section replacement on upgrades
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Colby McHenryandClaude Opus 4.6
