mirror of
https://github.com/Gitlawb/openclaude.git
synced 2026-08-24 02:34:15 -05:00
fb40d49e68
* feat: add Codebase Intelligence — repo map with PageRank-ranked structural summaries
Adds a new module that builds a structural map of the repository by parsing
source files with tree-sitter, building a cross-file reference graph weighted
by IDF, ranking files with PageRank, and rendering a token-budgeted summary
of the most important files and their signatures.
Surface:
- RepoMap tool the model can call on-demand, with focus_files / focus_symbols
- /repomap slash command with --tokens, --focus, --stats, --invalidate
- Auto-injection into session system context, gated by REPO_MAP=1 env var
(compile-time feature('REPO_MAP') flag stays off in scripts/build.ts)
How it works:
git ls-files → tree-sitter WASM parse → extract defs/refs →
IDF-weighted directed graph → PageRank → render top files until token budget
Files imported by many others rank highest. Common symbol names (get, set,
map, value) are down-weighted via IDF. Results cached to disk keyed by
(path, mtime, size) — only changed files are re-parsed.
Supported languages: TypeScript, JavaScript, Python.
Tree-sitter tag queries are inlined as string constants in queries.ts so
they ship inside dist/cli.mjs and work after npm install — the .scm source
files are kept for readability/Aider attribution but are not required at
runtime. A drift-guard test (queries.test.ts) asserts byte-equality between
the inlined strings and the .scm source files.
Dependencies added: web-tree-sitter, tree-sitter-wasms, graphology,
graphology-pagerank, graphology-operators, js-tiktoken.
* fix(repomap): invalidate rendered cache on file edits + Windows test fix
- computeMapHash now folds per-file mtime+size into the cache key so a
source edit (without changing the file list) no longer returns the
prior rendered map. Adds a regression test that edits a file and
confirms the second build reflects the new symbol without manual
invalidateCache().
- queries.test.ts byte-for-byte drift guard normalizes CRLF -> LF when
reading the .scm source so Windows checkouts pass. .gitattributes
also pins *.scm to LF on future checkouts.
- Externals: declare web-tree-sitter, tree-sitter-wasms, graphology*,
and js-tiktoken in scripts/externals.ts so build validation passes.
* fix(repomap): expand directory focus paths
* fix(repomap): satisfy deadcode check
* Fix repo map review findings
* Resolve remaining repo map review findings
* fix(repomap): address review findings
* fix(repomap): address review findings
* fix(repomap): resolve smoke and review follow-ups
* fix(repomap): preserve cached tag order
* fix(repomap): resolve review follow-ups
* fix(repomap): satisfy query promise lint
* Fix repo map context timeout cleanup
* fix: address repo map review findings
* fix: cancel timed-out repo map context builds
* fix(repomap): preserve git file path whitespace
* fix(repomap): handle graph and parsing edge cases
* fix(repomap): preserve shell token positions
* fix(repomap): respect configured cache home
* fix(repomap): address review findings
- Add explicit 10000ms timeout to the feature-flag-off context test to avoid cold-import flakes.
- Add --focus-symbols flag to /repomap and forward it to buildRepoMap, matching the RepoMap tool.
- Add parsing/command tests and docs coverage for --focus-symbols.
---------
Co-authored-by: gnanam1990 <gnanasekaran.sekareee@gmail.com>
140 lines
4.0 KiB
TypeScript
140 lines
4.0 KiB
TypeScript
/**
|
|
* Shared external dependency lists for CLI and SDK bundles.
|
|
*
|
|
* Used by build.ts and validate-externals.ts.
|
|
* When adding a new dependency to package.json, check if it should be
|
|
* added here (large packages, native modules, or packages with many exports).
|
|
*/
|
|
|
|
// Packages that should be kept external in ALL bundles (CLI + SDK)
|
|
export const COMMON_EXTERNALS: string[] = [
|
|
// Native image processing
|
|
'sharp',
|
|
// Cloud provider SDKs
|
|
'@aws-sdk/client-bedrock',
|
|
'@aws-sdk/client-bedrock-runtime',
|
|
'@aws-sdk/client-sts',
|
|
'@aws-sdk/credential-providers',
|
|
'@azure/identity',
|
|
'google-auth-library',
|
|
// @vscode/ripgrep ships a platform-specific binary alongside its
|
|
// index.js and resolves the path via __dirname at runtime. Bundling
|
|
// would freeze the build host's absolute path into dist/cli.mjs, so we
|
|
// keep it external and rely on the npm package being installed.
|
|
'@vscode/ripgrep',
|
|
// Orama search engine
|
|
'@orama/orama',
|
|
'@orama/plugin-data-persistence',
|
|
// web-tree-sitter ships a WASM file alongside its JS and resolves the
|
|
// path via require.resolve at runtime; bundling would freeze the build
|
|
// host's absolute path, so keep it external.
|
|
'web-tree-sitter',
|
|
// tree-sitter-wasms ships per-language .wasm files resolved via
|
|
// require.resolve at runtime — same bundling concern as web-tree-sitter.
|
|
'tree-sitter-wasms',
|
|
]
|
|
|
|
// Additional packages external only in the SDK bundle (TUI + heavy deps)
|
|
export const SDK_ONLY_EXTERNALS: string[] = [
|
|
'react',
|
|
'react-reconciler',
|
|
'@anthropic-ai/sdk',
|
|
'@modelcontextprotocol/sdk',
|
|
]
|
|
|
|
// Packages kept external but NOT listed in package.json dependencies.
|
|
// These are dynamically imported at runtime — they're optional and resolved
|
|
// from transitive deps or installed by users who need that provider/protocol.
|
|
export const OPTIONAL_RUNTIME_EXTERNALS: string[] = [
|
|
// Cloud provider SDKs (dynamically imported per-provider)
|
|
'@aws-sdk/client-bedrock',
|
|
'@aws-sdk/client-bedrock-runtime',
|
|
'@aws-sdk/client-sts',
|
|
'@aws-sdk/credential-providers',
|
|
'@azure/identity',
|
|
]
|
|
|
|
// Computed full lists
|
|
export const CLI_EXTERNALS: string[] = COMMON_EXTERNALS
|
|
export const SDK_EXTERNALS: string[] = [...COMMON_EXTERNALS, ...SDK_ONLY_EXTERNALS]
|
|
|
|
// Packages intentionally bundled (not external, not flagged by validation)
|
|
// These are small utilities that are fine to inline into the output bundle.
|
|
export const INTENTIONALLY_BUNDLED: string[] = [
|
|
// Test utilities (bundled, not external)
|
|
// Anthropic provider variants (bundled, not the main SDK)
|
|
'@anthropic-ai/bedrock-sdk',
|
|
'@anthropic-ai/foundry-sdk',
|
|
'@anthropic-ai/sandbox-runtime',
|
|
// CLI / TUI utilities
|
|
'@alcalzone/ansi-tokenize',
|
|
'@commander-js/extra-typings',
|
|
'bidi-js',
|
|
'chalk',
|
|
'cli-boxes',
|
|
'cli-highlight',
|
|
'commander',
|
|
'emoji-regex',
|
|
'env-paths',
|
|
'figures',
|
|
'get-east-asian-width',
|
|
'indent-string',
|
|
'supports-hyperlinks',
|
|
'wrap-ansi',
|
|
// Data formats
|
|
'jsonc-parser',
|
|
'yaml',
|
|
'marked',
|
|
'turndown',
|
|
'xss',
|
|
// Data utilities
|
|
'ajv',
|
|
'auto-bind',
|
|
'diff',
|
|
'fflate',
|
|
'fuse.js',
|
|
'ignore',
|
|
'lodash-es',
|
|
'lru-cache',
|
|
'p-map',
|
|
'picomatch',
|
|
'proper-lockfile',
|
|
'qrcode',
|
|
'semver',
|
|
'shell-quote',
|
|
'signal-exit',
|
|
'type-fest',
|
|
// Networking
|
|
'axios',
|
|
'cross-spawn',
|
|
'duck-duck-scrape',
|
|
'execa',
|
|
'https-proxy-agent',
|
|
'tree-kill',
|
|
'undici',
|
|
'ws',
|
|
// React ecosystem (react/react-reconciler are SDK_ONLY_EXTERNALS, bundled in CLI)
|
|
'react',
|
|
'react-compiler-runtime',
|
|
'react-reconciler',
|
|
'usehooks-ts',
|
|
// Anthropic SDK (external in SDK bundle, bundled in CLI)
|
|
'@anthropic-ai/sdk',
|
|
// MCP SDK (external in SDK bundle, bundled in CLI)
|
|
'@modelcontextprotocol/sdk',
|
|
// Schema validation
|
|
'zod',
|
|
// gRPC (bundled into CLI, not external)
|
|
'@grpc/grpc-js',
|
|
'@grpc/proto-loader',
|
|
// Language server protocol
|
|
'vscode-languageserver-protocol',
|
|
// File watching
|
|
'chokidar',
|
|
// Graph algorithms (repo map PageRank)
|
|
'graphology',
|
|
'graphology-metrics',
|
|
// Tokenizer for repo map token budgeting
|
|
'js-tiktoken',
|
|
]
|