mozempk/trueref
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore(FEEDBACK-0001): linting

Browse Source
This commit is contained in:
Giancarmine Salucci
2026-03-27 02:23:01 +01:00
parent 16436bfab2
commit 5a3c27224d
102 changed files with 5108 additions and 4976 deletions
Download Patch File Download Diff File Expand all files Collapse all files

78
README.md
View File

@@ -38,13 +38,13 @@ TrueRef is under active development. The current codebase already includes:
TrueRef is organized into four main layers:
1. Web UI
SvelteKit application for adding repositories, monitoring indexing, searching content, and configuring embeddings.
SvelteKit application for adding repositories, monitoring indexing, searching content, and configuring embeddings.
2. REST API
Endpoints under `/api/v1/*` for repository management, search, schema discovery, job status, and settings.
Endpoints under `/api/v1/*` for repository management, search, schema discovery, job status, and settings.
3. Indexing pipeline
Crawlers, parsers, chunking logic, snippet storage, and optional embedding generation.
Crawlers, parsers, chunking logic, snippet storage, and optional embedding generation.
4. MCP server
A thin compatibility layer that forwards `resolve-library-id` and `query-docs` requests to the TrueRef REST API.
A thin compatibility layer that forwards `resolve-library-id` and `query-docs` requests to the TrueRef REST API.
At runtime, the app uses SQLite via `better-sqlite3` and Drizzle, plus optional embedding providers for semantic retrieval.
@@ -367,9 +367,9 @@ The tool names and argument shapes intentionally mirror context7 so existing wor
The MCP server uses:
- `TRUEREF_API_URL`
Base URL of the TrueRef web app. Default: `http://localhost:5173`
Base URL of the TrueRef web app. Default: `http://localhost:5173`
- `PORT`
Used only for HTTP transport. Default: `3001`
Used only for HTTP transport. Default: `3001`
### Start MCP over stdio
@@ -602,6 +602,7 @@ alwaysApply: true
---
When answering questions about indexed libraries, always use the TrueRef MCP tools:
1. Call `resolve-library-id` with the library name and the user's question to get the library ID.
2. Call `query-docs` with the library ID and question to retrieve relevant documentation.
3. Use the returned documentation to answer accurately.
@@ -614,9 +615,9 @@ Never rely on training data alone for library APIs that may have changed.
Whether you are using VS Code, IntelliJ, or Claude Code, the expected retrieval flow is:
1. `resolve-library-id`
Find the correct repository or version identifier.
Find the correct repository or version identifier.
2. `query-docs`
Retrieve the actual documentation and code snippets for the user question.
Retrieve the actual documentation and code snippets for the user question.
Example:
@@ -638,10 +639,10 @@ docker compose up --build
This builds the image and starts two services:
| Service | Default port | Purpose |
|---------|-------------|---------|
| `web` | `3000` | SvelteKit web UI and REST API |
| `mcp` | `3001` | MCP HTTP server |
| Service | Default port | Purpose |
| ------- | ------------ | ----------------------------- |
| `web` | `3000` | SvelteKit web UI and REST API |
| `mcp` | `3001` | MCP HTTP server |
The SQLite database is stored in a named Docker volume (`trueref-data`) and persists across restarts.
@@ -687,10 +688,10 @@ services:
- ${USERPROFILE:-$HOME}/.gitconfig:/root/.gitconfig:ro
- ${CORP_CA_CERT}:/certs/corp-ca.crt:ro
environment:
BITBUCKET_HOST: "${BITBUCKET_HOST}"
GITLAB_HOST: "${GITLAB_HOST}"
GIT_TOKEN_BITBUCKET: "${GIT_TOKEN_BITBUCKET}"
GIT_TOKEN_GITLAB: "${GIT_TOKEN_GITLAB}"
BITBUCKET_HOST: '${BITBUCKET_HOST}'
GITLAB_HOST: '${GITLAB_HOST}'
GIT_TOKEN_BITBUCKET: '${GIT_TOKEN_BITBUCKET}'
GIT_TOKEN_GITLAB: '${GIT_TOKEN_GITLAB}'
```
5. **Start the services**:
@@ -708,6 +709,7 @@ The Docker entrypoint script (`docker-entrypoint.sh`) runs these steps in order:
3. **Configure git credentials**: Sets up per-host credential helpers that provide the correct username and token for each remote.
This setup works for:
- HTTPS cloning with personal access tokens
- SSH cloning with mounted SSH keys
- On-premise servers with custom CA certificates
@@ -718,6 +720,7 @@ This setup works for:
For long-lived deployments, SSH authentication is recommended:
1. Generate an SSH key pair if you don't have one:
```sh
ssh-keygen -t ed25519 -C "trueref@your-company.com"
```
@@ -727,6 +730,7 @@ For long-lived deployments, SSH authentication is recommended:
- GitLab: User Settings → SSH Keys
3. Ensure your `~/.ssh/config` has the correct host entries:
```
Host bitbucket.corp.example.com
IdentityFile ~/.ssh/id_ed25519
@@ -737,13 +741,13 @@ For long-lived deployments, SSH authentication is recommended:
### Environment variables
| Variable | Default | Description |
|----------|---------|-------------|
| `DATABASE_URL` | `/data/trueref.db` | Path to the SQLite database inside the container |
| `PORT` | `3000` | Port the web app listens on |
| `HOST` | `0.0.0.0` | Bind address for the web app |
| Variable | Default | Description |
| ----------------- | ----------------------- | -------------------------------------------------- |
| `DATABASE_URL` | `/data/trueref.db` | Path to the SQLite database inside the container |
| `PORT` | `3000` | Port the web app listens on |
| `HOST` | `0.0.0.0` | Bind address for the web app |
| `TRUEREF_API_URL` | `http://localhost:3000` | Base URL the MCP server uses to reach the REST API |
| `MCP_PORT` | `3001` | Port the MCP HTTP server listens on |
| `MCP_PORT` | `3001` | Port the MCP HTTP server listens on |
Override them in `docker-compose.yml` or pass them with `-e` flags.
@@ -770,12 +774,12 @@ Once both containers are running, point VS Code at the MCP HTTP endpoint:
```json
{
"servers": {
"trueref": {
"type": "http",
"url": "http://localhost:3001/mcp"
}
}
"servers": {
"trueref": {
"type": "http",
"url": "http://localhost:3001/mcp"
}
}
}
```
@@ -783,12 +787,12 @@ Once both containers are running, point VS Code at the MCP HTTP endpoint:
```json
{
"mcpServers": {
"trueref": {
"type": "http",
"url": "http://localhost:3001/mcp"
}
}
"mcpServers": {
"trueref": {
"type": "http",
"url": "http://localhost:3001/mcp"
}
}
}
```
@@ -806,10 +810,10 @@ Verify the connection inside Claude Code:
### Health checks
| Endpoint | Expected response |
|----------|------------------|
| Endpoint | Expected response |
| ----------------------------------- | ------------------------------- |
| `http://localhost:3000/api/v1/libs` | JSON array of indexed libraries |
| `http://localhost:3001/ping` | `{"ok":true}` |
| `http://localhost:3001/ping` | `{"ok":true}` |
### Mounting a local repository

6
docker-compose.yml
View File

@@ -2,7 +2,7 @@ services:
web:
build: .
ports:
- "3000:3000"
- '3000:3000'
volumes:
- trueref-data:/data
# Corporate deployment support (TRUEREF-0019)
@@ -24,10 +24,10 @@ services:
build: .
command: mcp
ports:
- "3001:3001"
- '3001:3001'
environment:
TRUEREF_API_URL: http://web:3000
MCP_PORT: "3001"
MCP_PORT: '3001'
depends_on:
- web
restart: unless-stopped

132
docs/FINDINGS.md
View File

@@ -37,85 +37,85 @@ Add subsequent research below this section.
- Task: Refresh only stale documentation after changes to retrieval, formatters, token budgeting, and parser behavior.
- Files inspected:
- `docs/docs_cache_state.yaml`
- `docs/ARCHITECTURE.md`
- `docs/CODE_STYLE.md`
- `docs/FINDINGS.md`
- `package.json`
- `src/routes/api/v1/context/+server.ts`
- `src/lib/server/api/formatters.ts`
- `src/lib/server/api/token-budget.ts`
- `src/lib/server/search/query-preprocessor.ts`
- `src/lib/server/search/search.service.ts`
- `src/lib/server/search/hybrid.search.service.ts`
- `src/lib/server/mappers/context-response.mapper.ts`
- `src/lib/server/models/context-response.ts`
- `src/lib/server/models/search-result.ts`
- `src/lib/server/parser/index.ts`
- `src/lib/server/parser/code.parser.ts`
- `src/lib/server/parser/markdown.parser.ts`
- `docs/docs_cache_state.yaml`
- `docs/ARCHITECTURE.md`
- `docs/CODE_STYLE.md`
- `docs/FINDINGS.md`
- `package.json`
- `src/routes/api/v1/context/+server.ts`
- `src/lib/server/api/formatters.ts`
- `src/lib/server/api/token-budget.ts`
- `src/lib/server/search/query-preprocessor.ts`
- `src/lib/server/search/search.service.ts`
- `src/lib/server/search/hybrid.search.service.ts`
- `src/lib/server/mappers/context-response.mapper.ts`
- `src/lib/server/models/context-response.ts`
- `src/lib/server/models/search-result.ts`
- `src/lib/server/parser/index.ts`
- `src/lib/server/parser/code.parser.ts`
- `src/lib/server/parser/markdown.parser.ts`
- Findings:
- The documentation cache was trusted, but the architecture summary no longer captured current retrieval behavior: query preprocessing now sanitizes punctuation-heavy input for FTS5, semantic mode can bypass FTS entirely, and auto or hybrid retrieval can fall back to vector search when keyword search returns no candidates.
- Plain-text and JSON context formatting now carry repository and version metadata, and the text formatter emits an explicit no-results section instead of an empty body.
- Token budgeting now skips individual over-budget snippets and continues evaluating lower-ranked candidates, which changes the response-selection behavior described at the architecture level.
- Parser coverage now explicitly includes Markdown, code, config, HTML-like, and plain-text inputs, so the architecture summary needed to reflect that broader file-type handling.
- The conventions documented in CODE_STYLE.md still match the current repository: strict TypeScript, tab indentation, ESM imports, Prettier and ESLint flat config, and pragmatic service-oriented server modules.
- The documentation cache was trusted, but the architecture summary no longer captured current retrieval behavior: query preprocessing now sanitizes punctuation-heavy input for FTS5, semantic mode can bypass FTS entirely, and auto or hybrid retrieval can fall back to vector search when keyword search returns no candidates.
- Plain-text and JSON context formatting now carry repository and version metadata, and the text formatter emits an explicit no-results section instead of an empty body.
- Token budgeting now skips individual over-budget snippets and continues evaluating lower-ranked candidates, which changes the response-selection behavior described at the architecture level.
- Parser coverage now explicitly includes Markdown, code, config, HTML-like, and plain-text inputs, so the architecture summary needed to reflect that broader file-type handling.
- The conventions documented in CODE_STYLE.md still match the current repository: strict TypeScript, tab indentation, ESM imports, Prettier and ESLint flat config, and pragmatic service-oriented server modules.
- Risks / follow-ups:
- Future cache invalidation should continue to distinguish between behavioral changes that affect architecture docs and localized implementation changes that do not affect the style guide.
- If the public API contract becomes externally versioned, the new context metadata fields likely deserve a dedicated API document instead of only architecture-level coverage.
- Future cache invalidation should continue to distinguish between behavioral changes that affect architecture docs and localized implementation changes that do not affect the style guide.
- If the public API contract becomes externally versioned, the new context metadata fields likely deserve a dedicated API document instead of only architecture-level coverage.
### 2026-03-27 — FEEDBACK-0001 planning research
- Task: Plan the retrieval-fix iteration covering FTS query safety, hybrid fallback, empty-result behavior, result metadata, token budgeting, and parser chunking.
- Files inspected:
- `package.json`
- `src/routes/api/v1/context/+server.ts`
- `src/lib/server/search/query-preprocessor.ts`
- `src/lib/server/search/search.service.ts`
- `src/lib/server/search/hybrid.search.service.ts`
- `src/lib/server/search/vector.search.ts`
- `src/lib/server/api/token-budget.ts`
- `src/lib/server/api/formatters.ts`
- `src/lib/server/mappers/context-response.mapper.ts`
- `src/lib/server/models/context-response.ts`
- `src/lib/server/models/search-result.ts`
- `src/lib/server/parser/code.parser.ts`
- `src/lib/server/search/search.service.test.ts`
- `src/lib/server/search/hybrid.search.service.test.ts`
- `src/lib/server/api/formatters.test.ts`
- `src/lib/server/parser/code.parser.test.ts`
- `src/routes/api/v1/api-contract.integration.test.ts`
- `src/mcp/tools/query-docs.ts`
- `src/mcp/client.ts`
- `package.json`
- `src/routes/api/v1/context/+server.ts`
- `src/lib/server/search/query-preprocessor.ts`
- `src/lib/server/search/search.service.ts`
- `src/lib/server/search/hybrid.search.service.ts`
- `src/lib/server/search/vector.search.ts`
- `src/lib/server/api/token-budget.ts`
- `src/lib/server/api/formatters.ts`
- `src/lib/server/mappers/context-response.mapper.ts`
- `src/lib/server/models/context-response.ts`
- `src/lib/server/models/search-result.ts`
- `src/lib/server/parser/code.parser.ts`
- `src/lib/server/search/search.service.test.ts`
- `src/lib/server/search/hybrid.search.service.test.ts`
- `src/lib/server/api/formatters.test.ts`
- `src/lib/server/parser/code.parser.test.ts`
- `src/routes/api/v1/api-contract.integration.test.ts`
- `src/mcp/tools/query-docs.ts`
- `src/mcp/client.ts`
- Findings:
- `better-sqlite3` `^12.6.2` backs the affected search path; the code already uses bound parameters for `MATCH`, so the practical fix belongs in query normalization and fallback handling rather than SQL string construction.
- `query-preprocessor.ts` only strips parentheses and appends a trailing wildcard. Other code-like punctuation currently reaches the FTS execution path unsanitized.
- `search.service.ts` sends the preprocessed text directly to `snippets_fts MATCH ?` and already returns `[]` for blank processed queries.
- `hybrid.search.service.ts` always executes keyword search before semantic branching. In the current flow, an FTS parse failure can abort `auto`, `hybrid`, and `semantic` requests before vector retrieval runs.
- `vector.search.ts` already preserves `repositoryId`, `versionId`, and `profileId` filtering and does not need architectural changes for this iteration.
- `token-budget.ts` stops at the first over-budget snippet instead of skipping that item and continuing through later ranked results.
- `formatContextTxt([], [])` returns an empty string, so `/api/v1/context?type=txt` can emit an empty `200 OK` body today.
- `context-response.mapper.ts` and `context-response.ts` expose snippet content and breadcrumb/page title but do not identify local TrueRef origin, repository source metadata, or normalized snippet origin labels.
- `code.parser.ts` splits primarily at top-level declarations; class/object member functions remain in coarse chunks, which limits method-level recall for camelCase API queries.
- Existing relevant automated coverage is concentrated in the search, formatter, and parser unit tests; `/api/v1/context` contract coverage currently omits the context endpoint entirely.
- `better-sqlite3` `^12.6.2` backs the affected search path; the code already uses bound parameters for `MATCH`, so the practical fix belongs in query normalization and fallback handling rather than SQL string construction.
- `query-preprocessor.ts` only strips parentheses and appends a trailing wildcard. Other code-like punctuation currently reaches the FTS execution path unsanitized.
- `search.service.ts` sends the preprocessed text directly to `snippets_fts MATCH ?` and already returns `[]` for blank processed queries.
- `hybrid.search.service.ts` always executes keyword search before semantic branching. In the current flow, an FTS parse failure can abort `auto`, `hybrid`, and `semantic` requests before vector retrieval runs.
- `vector.search.ts` already preserves `repositoryId`, `versionId`, and `profileId` filtering and does not need architectural changes for this iteration.
- `token-budget.ts` stops at the first over-budget snippet instead of skipping that item and continuing through later ranked results.
- `formatContextTxt([], [])` returns an empty string, so `/api/v1/context?type=txt` can emit an empty `200 OK` body today.
- `context-response.mapper.ts` and `context-response.ts` expose snippet content and breadcrumb/page title but do not identify local TrueRef origin, repository source metadata, or normalized snippet origin labels.
- `code.parser.ts` splits primarily at top-level declarations; class/object member functions remain in coarse chunks, which limits method-level recall for camelCase API queries.
- Existing relevant automated coverage is concentrated in the search, formatter, and parser unit tests; `/api/v1/context` contract coverage currently omits the context endpoint entirely.
- Risks / follow-ups:
- Response-shape changes must be additive because `src/mcp/client.ts`, `src/mcp/tools/query-docs.ts`, and UI consumers expect the current top-level keys to remain present.
- Parser improvements should stay inside `parseCodeFile()` and existing chunking helpers to avoid turning this fix iteration into a schema or pipeline redesign.
- Response-shape changes must be additive because `src/mcp/client.ts`, `src/mcp/tools/query-docs.ts`, and UI consumers expect the current top-level keys to remain present.
- Parser improvements should stay inside `parseCodeFile()` and existing chunking helpers to avoid turning this fix iteration into a schema or pipeline redesign.
### 2026-03-27 — FEEDBACK-0001 SQLite FTS5 syntax research
- Task: Verify the FTS5 query-grammar constraints that affect punctuation-heavy local search queries.
- Files inspected:
- `package.json`
- `src/lib/server/search/query-preprocessor.ts`
- `src/lib/server/search/search.service.ts`
- `src/lib/server/search/hybrid.search.service.ts`
- `package.json`
- `src/lib/server/search/query-preprocessor.ts`
- `src/lib/server/search/search.service.ts`
- `src/lib/server/search/hybrid.search.service.ts`
- Findings:
- `better-sqlite3` is pinned at `^12.6.2` in `package.json`, and the application binds the `MATCH` string as a parameter instead of interpolating SQL directly.
- The canonical SQLite FTS5 docs state that barewords may contain letters, digits, underscore, non-ASCII characters, and the substitute character; strings containing other punctuation must be quoted or they become syntax errors in `MATCH` expressions.
- The same docs state that prefix search is expressed by placing `*` after the token or phrase, not inside quotes, which matches the current trailing-wildcard strategy in `query-preprocessor.ts`.
- SQLite documents that FTS5 is stricter than FTS3/4 about unrecognized punctuation in query strings, which confirms that code-like user input should be normalized before it reaches `snippets_fts MATCH ?`.
- Based on the current code path, the practical fix remains application-side sanitization and fallback behavior in `query-preprocessor.ts` and `hybrid.search.service.ts`, not SQL construction changes.
- `better-sqlite3` is pinned at `^12.6.2` in `package.json`, and the application binds the `MATCH` string as a parameter instead of interpolating SQL directly.
- The canonical SQLite FTS5 docs state that barewords may contain letters, digits, underscore, non-ASCII characters, and the substitute character; strings containing other punctuation must be quoted or they become syntax errors in `MATCH` expressions.
- The same docs state that prefix search is expressed by placing `*` after the token or phrase, not inside quotes, which matches the current trailing-wildcard strategy in `query-preprocessor.ts`.
- SQLite documents that FTS5 is stricter than FTS3/4 about unrecognized punctuation in query strings, which confirms that code-like user input should be normalized before it reaches `snippets_fts MATCH ?`.
- Based on the current code path, the practical fix remains application-side sanitization and fallback behavior in `query-preprocessor.ts` and `hybrid.search.service.ts`, not SQL construction changes.
- Risks / follow-ups:
- Over-sanitizing punctuation-heavy inputs could erase useful identifiers, so the implementation should preserve searchable alphanumeric and underscore tokens while discarding grammar-breaking punctuation.
- Prefix expansion should remain on the final searchable token only so the fix preserves current query-cost expectations and test semantics.
- Over-sanitizing punctuation-heavy inputs could erase useful identifiers, so the implementation should preserve searchable alphanumeric and underscore tokens while discarding grammar-breaking punctuation.
- Prefix expansion should remain on the final searchable token only so the fix preserves current query-cost expectations and test semantics.

105
docs/PRD.md
View File

@@ -17,6 +17,7 @@ The core use case is enabling AI coding assistants (Claude Code, Cursor, Zed, et
## 2. Problem Statement
### 2.1 Context7's Limitations
- The indexing and crawling backend is entirely private and closed-source.
- Only public libraries already in the context7.com catalog are available.
- Private, internal, or niche repositories cannot be added.
@@ -24,6 +25,7 @@ The core use case is enabling AI coding assistants (Claude Code, Cursor, Zed, et
- No way to self-host for air-gapped or compliance-constrained environments.
### 2.2 The Gap
Teams with internal SDKs, private libraries, proprietary documentation, or a need for data sovereignty have no tooling that provides context7-equivalent LLM documentation retrieval.
---
@@ -31,6 +33,7 @@ Teams with internal SDKs, private libraries, proprietary documentation, or a nee
## 3. Goals & Non-Goals
### Goals
- Replicate all context7 capabilities: library search, documentation retrieval, MCP tools (`resolve-library-id`, `query-docs`).
- Support both GitHub-hosted and local filesystem repositories.
- Provide a full indexing pipeline: crawl → parse → chunk → embed → store → query.
@@ -42,6 +45,7 @@ Teams with internal SDKs, private libraries, proprietary documentation, or a nee
- Self-hostable with minimal dependencies (SQLite-first, no external vector DB required).
### Non-Goals (v1)
- Authentication & authorization (deferred to a future version).
- Skill generation (context7 CLI skill feature).
- Multi-tenant SaaS mode.
@@ -54,9 +58,11 @@ Teams with internal SDKs, private libraries, proprietary documentation, or a nee
## 4. Users & Personas
### Primary: The Developer / Tech Lead
Configures TrueRef, adds repositories, integrates the MCP server with their AI coding assistant. Technical, comfortable with CLI and config files.
### Secondary: The AI Coding Assistant
The "user" at query time. Calls `resolve-library-id` and `query-docs` via MCP to retrieve documentation snippets for code generation.
---
@@ -100,25 +106,27 @@ The "user" at query time. Calls `resolve-library-id` and `query-docs` via MCP to
```
### Technology Stack
| Layer | Technology |
|-------|-----------|
| Framework | SvelteKit (Node adapter) |
| Language | TypeScript |
| Database | SQLite via better-sqlite3 + drizzle-orm |
| Full-Text Search | SQLite FTS5 |
| Vector Search | SQLite `sqlite-vec` extension (cosine similarity) |
| Embeddings | Pluggable: local (transformers.js / ONNX) or OpenAI-compatible API |
| MCP Protocol | `@modelcontextprotocol/sdk` |
| HTTP | SvelteKit API routes + optional standalone MCP HTTP server |
| CSS | TailwindCSS v4 |
| Testing | Vitest |
| Linting | ESLint + Prettier |
| Layer | Technology |
| ---------------- | ------------------------------------------------------------------ |
| Framework | SvelteKit (Node adapter) |
| Language | TypeScript |
| Database | SQLite via better-sqlite3 + drizzle-orm |
| Full-Text Search | SQLite FTS5 |
| Vector Search | SQLite `sqlite-vec` extension (cosine similarity) |
| Embeddings | Pluggable: local (transformers.js / ONNX) or OpenAI-compatible API |
| MCP Protocol | `@modelcontextprotocol/sdk` |
| HTTP | SvelteKit API routes + optional standalone MCP HTTP server |
| CSS | TailwindCSS v4 |
| Testing | Vitest |
| Linting | ESLint + Prettier |
---
## 6. Data Model
### 6.1 Repositories
A `Repository` is the top-level entity. It maps to a GitHub repo or local directory.
```
@@ -141,6 +149,7 @@ Repository {
```
### 6.2 Repository Versions
```
RepositoryVersion {
id TEXT PRIMARY KEY
@@ -153,6 +162,7 @@ RepositoryVersion {
```
### 6.3 Documents (parsed files)
```
Document {
id TEXT PRIMARY KEY
@@ -169,6 +179,7 @@ Document {
```
### 6.4 Snippets (indexed chunks)
```
Snippet {
id TEXT PRIMARY KEY
@@ -186,6 +197,7 @@ Snippet {
```
### 6.5 Indexing Jobs
```
IndexingJob {
id TEXT PRIMARY KEY
@@ -203,6 +215,7 @@ IndexingJob {
```
### 6.6 Repository Configuration (`trueref.json`)
```
RepositoryConfig {
repositoryId TEXT FK → Repository
@@ -221,15 +234,19 @@ RepositoryConfig {
## 7. Core Features
### F1: Repository Management
Add, remove, update, and list repositories. Support GitHub (public/private via token) and local filesystem sources. Trigger indexing on demand or on schedule.
### F2: GitHub Crawler
Fetch repository file trees via GitHub Trees API. Download file contents. Respect `trueref.json` include/exclude rules. Support rate limiting and incremental re-indexing (checksum-based).
### F3: Local Filesystem Crawler
Walk directory trees. Apply include/exclude rules from `trueref.json`. Watch for file changes (optional).
### F4: Document Parser & Chunker
- Parse Markdown files into sections (heading-based splitting).
- Extract code blocks from Markdown.
- Parse standalone code files into function/class-level chunks.
@@ -237,16 +254,19 @@ Walk directory trees. Apply include/exclude rules from `trueref.json`. Watch for
- Produce structured `Snippet` records (type: "code" or "info").
### F5: Embedding & Vector Storage
- Generate embeddings for each snippet using a pluggable embeddings backend.
- Store embeddings as binary blobs in SQLite (sqlite-vec).
- Support fallback to FTS5-only search when no embedding provider is configured.
### F6: Semantic Search Engine
- Hybrid search: vector similarity + FTS5 keyword matching (BM25) with reciprocal rank fusion.
- Query-time retrieval: given `libraryId + query`, return ranked snippets.
- Library search: given `libraryName + query`, return matching repositories.
### F7: REST API (`/api/v1/*`)
- `GET /api/v1/libs/search?query=&libraryName=` — search libraries (context7-compatible)
- `GET /api/v1/context?query=&libraryId=&type=json|txt` — fetch documentation
- `GET /api/v1/libs` — list all indexed libraries
@@ -256,12 +276,14 @@ Walk directory trees. Apply include/exclude rules from `trueref.json`. Watch for
- `GET /api/v1/jobs/:id` — get indexing job status
### F8: MCP Server
- Tool: `resolve-library-id` — search for libraries by name
- Tool: `query-docs` — fetch documentation by libraryId + query
- Transport: stdio (primary), HTTP (optional)
- Compatible with Claude Code, Cursor, and other MCP-aware tools
### F9: Web UI — Repository Dashboard
- List all repositories with status, snippet count, last indexed date
- Add/remove repositories (GitHub URL or local path)
- Trigger re-indexing
@@ -269,23 +291,27 @@ Walk directory trees. Apply include/exclude rules from `trueref.json`. Watch for
- View repository config (`trueref.json`)
### F10: Web UI — Search Explorer
- Interactive search interface (resolve library → query docs)
- Preview snippets with syntax highlighting
- View raw document content
### F11: `trueref.json` Config Support
- Parse `trueref.json` from repo root (or `context7.json` for compatibility)
- Apply `folders`, `excludeFolders`, `excludeFiles` during crawling
- Inject `rules` into LLM context alongside snippets
- Support `previousVersions` for versioned documentation
### F12: Indexing Pipeline & Job Queue
- SQLite-backed job queue (no external message broker required)
- Sequential processing with progress tracking
- Error recovery and retry logic
- Incremental re-indexing using file checksums
### F13: Version Support
- Index specific git tags/branches per repository
- Serve version-specific context when libraryId includes version (`/owner/repo/v1.2.3`)
- UI for managing available versions
@@ -296,12 +322,13 @@ Walk directory trees. Apply include/exclude rules from `trueref.json`. Watch for
TrueRef's REST API mirrors context7's `/api/v2/*` interface to allow drop-in compatibility:
| context7 Endpoint | TrueRef Endpoint | Notes |
|-------------------|-----------------|-------|
| `GET /api/v2/libs/search` | `GET /api/v1/libs/search` | Same query params |
| `GET /api/v2/context` | `GET /api/v1/context` | Same query params, same response shape |
| context7 Endpoint | TrueRef Endpoint | Notes |
| ------------------------- | ------------------------- | -------------------------------------- |
| `GET /api/v2/libs/search` | `GET /api/v1/libs/search` | Same query params |
| `GET /api/v2/context` | `GET /api/v1/context` | Same query params, same response shape |
The MCP tool names and input schemas are identical:
- `resolve-library-id` with `libraryName` + `query`
- `query-docs` with `libraryId` + `query`
@@ -312,20 +339,24 @@ Library IDs follow the same convention: `/owner/repo` or `/owner/repo/version`.
## 9. Non-Functional Requirements
### Performance
- Library search: < 200ms p99
- Documentation retrieval: < 500ms p99 for 20 snippets
- Indexing throughput: > 1,000 files/minute (GitHub API rate-limited)
### Reliability
- Failed indexing jobs must not corrupt existing indexed data
- Atomic snippet replacement during re-indexing
### Portability
- Single SQLite file for all data
- Runs on Linux, macOS, Windows (Node.js 20+)
- No required external services beyond optional embedding API
### Scalability (v1 constraints)
- Designed for single-node deployment
- SQLite suitable for up to ~500 repositories, ~500k snippets
@@ -333,26 +364,26 @@ Library IDs follow the same convention: `/owner/repo` or `/owner/repo/version`.
## 10. Milestones & Feature Order
| ID | Feature | Priority | Depends On |
|----|---------|----------|-----------|
| TRUEREF-0001 | Database schema & core data models | P0 | — |
| TRUEREF-0002 | Repository management service & REST API | P0 | TRUEREF-0001 |
| TRUEREF-0003 | GitHub repository crawler | P0 | TRUEREF-0001 |
| TRUEREF-0004 | Local filesystem crawler | P1 | TRUEREF-0001 |
| TRUEREF-0005 | Document parser & chunker | P0 | TRUEREF-0001 |
| TRUEREF-0006 | SQLite FTS5 full-text search | P0 | TRUEREF-0005 |
| TRUEREF-0007 | Embedding generation & vector storage | P1 | TRUEREF-0005 |
| TRUEREF-0008 | Hybrid semantic search engine | P1 | TRUEREF-0006, TRUEREF-0007 |
| TRUEREF-0009 | Indexing pipeline & job queue | P0 | TRUEREF-0003, TRUEREF-0005 |
| TRUEREF-0010 | REST API (search + context endpoints) | P0 | TRUEREF-0006, TRUEREF-0009 |
| TRUEREF-0011 | MCP server (stdio transport) | P0 | TRUEREF-0010 |
| TRUEREF-0012 | MCP server (HTTP transport) | P1 | TRUEREF-0011 |
| TRUEREF-0013 | `trueref.json` config file support | P0 | TRUEREF-0003 |
| TRUEREF-0014 | Repository version management | P1 | TRUEREF-0003 |
| TRUEREF-0015 | Web UI — repository dashboard | P1 | TRUEREF-0002, TRUEREF-0009 |
| TRUEREF-0016 | Web UI — search explorer | P2 | TRUEREF-0010, TRUEREF-0015 |
| TRUEREF-0017 | Incremental re-indexing (checksum diff) | P1 | TRUEREF-0009 |
| TRUEREF-0018 | Embedding provider configuration UI | P2 | TRUEREF-0007, TRUEREF-0015 |
| ID | Feature | Priority | Depends On |
| ------------ | ---------------------------------------- | -------- | -------------------------- |
| TRUEREF-0001 | Database schema & core data models | P0 | — |
| TRUEREF-0002 | Repository management service & REST API | P0 | TRUEREF-0001 |
| TRUEREF-0003 | GitHub repository crawler | P0 | TRUEREF-0001 |
| TRUEREF-0004 | Local filesystem crawler | P1 | TRUEREF-0001 |
| TRUEREF-0005 | Document parser & chunker | P0 | TRUEREF-0001 |
| TRUEREF-0006 | SQLite FTS5 full-text search | P0 | TRUEREF-0005 |
| TRUEREF-0007 | Embedding generation & vector storage | P1 | TRUEREF-0005 |
| TRUEREF-0008 | Hybrid semantic search engine | P1 | TRUEREF-0006, TRUEREF-0007 |
| TRUEREF-0009 | Indexing pipeline & job queue | P0 | TRUEREF-0003, TRUEREF-0005 |
| TRUEREF-0010 | REST API (search + context endpoints) | P0 | TRUEREF-0006, TRUEREF-0009 |
| TRUEREF-0011 | MCP server (stdio transport) | P0 | TRUEREF-0010 |
| TRUEREF-0012 | MCP server (HTTP transport) | P1 | TRUEREF-0011 |
| TRUEREF-0013 | `trueref.json` config file support | P0 | TRUEREF-0003 |
| TRUEREF-0014 | Repository version management | P1 | TRUEREF-0003 |
| TRUEREF-0015 | Web UI — repository dashboard | P1 | TRUEREF-0002, TRUEREF-0009 |
| TRUEREF-0016 | Web UI — search explorer | P2 | TRUEREF-0010, TRUEREF-0015 |
| TRUEREF-0017 | Incremental re-indexing (checksum diff) | P1 | TRUEREF-0009 |
| TRUEREF-0018 | Embedding provider configuration UI | P2 | TRUEREF-0007, TRUEREF-0015 |
---

188
docs/features/TRUEREF-0001.md
View File

@@ -31,24 +31,26 @@ Represents an indexed library source (GitHub repo or local directory).
```typescript
export const repositories = sqliteTable('repositories', {
id: text('id').primaryKey(), // e.g. "/facebook/react" or "/local/my-sdk"
title: text('title').notNull(),
description: text('description'),
source: text('source', { enum: ['github', 'local'] }).notNull(),
sourceUrl: text('source_url').notNull(), // GitHub URL or absolute local path
branch: text('branch').default('main'),
state: text('state', {
enum: ['pending', 'indexing', 'indexed', 'error']
}).notNull().default('pending'),
totalSnippets: integer('total_snippets').default(0),
totalTokens: integer('total_tokens').default(0),
trustScore: real('trust_score').default(0), // 0.0–10.0
benchmarkScore: real('benchmark_score').default(0), // 0.0–100.0
stars: integer('stars'),
githubToken: text('github_token'), // encrypted PAT for private repos
lastIndexedAt: integer('last_indexed_at', { mode: 'timestamp' }),
createdAt: integer('created_at', { mode: 'timestamp' }).notNull(),
updatedAt: integer('updated_at', { mode: 'timestamp' }).notNull(),
id: text('id').primaryKey(), // e.g. "/facebook/react" or "/local/my-sdk"
title: text('title').notNull(),
description: text('description'),
source: text('source', { enum: ['github', 'local'] }).notNull(),
sourceUrl: text('source_url').notNull(), // GitHub URL or absolute local path
branch: text('branch').default('main'),
state: text('state', {
enum: ['pending', 'indexing', 'indexed', 'error']
})
.notNull()
.default('pending'),
totalSnippets: integer('total_snippets').default(0),
totalTokens: integer('total_tokens').default(0),
trustScore: real('trust_score').default(0), // 0.0–10.0
benchmarkScore: real('benchmark_score').default(0), // 0.0–100.0
stars: integer('stars'),
githubToken: text('github_token'), // encrypted PAT for private repos
lastIndexedAt: integer('last_indexed_at', { mode: 'timestamp' }),
createdAt: integer('created_at', { mode: 'timestamp' }).notNull(),
updatedAt: integer('updated_at', { mode: 'timestamp' }).notNull()
});
```
@@ -58,17 +60,20 @@ Tracks indexed git tags/branches beyond the default branch.
```typescript
export const repositoryVersions = sqliteTable('repository_versions', {
id: text('id').primaryKey(), // e.g. "/facebook/react/v18.3.0"
repositoryId: text('repository_id').notNull()
.references(() => repositories.id, { onDelete: 'cascade' }),
tag: text('tag').notNull(), // git tag or branch name
title: text('title'),
state: text('state', {
enum: ['pending', 'indexing', 'indexed', 'error']
}).notNull().default('pending'),
totalSnippets: integer('total_snippets').default(0),
indexedAt: integer('indexed_at', { mode: 'timestamp' }),
createdAt: integer('created_at', { mode: 'timestamp' }).notNull(),
id: text('id').primaryKey(), // e.g. "/facebook/react/v18.3.0"
repositoryId: text('repository_id')
.notNull()
.references(() => repositories.id, { onDelete: 'cascade' }),
tag: text('tag').notNull(), // git tag or branch name
title: text('title'),
state: text('state', {
enum: ['pending', 'indexing', 'indexed', 'error']
})
.notNull()
.default('pending'),
totalSnippets: integer('total_snippets').default(0),
indexedAt: integer('indexed_at', { mode: 'timestamp' }),
createdAt: integer('created_at', { mode: 'timestamp' }).notNull()
});
```
@@ -78,17 +83,17 @@ A parsed source file within a repository.
```typescript
export const documents = sqliteTable('documents', {
id: text('id').primaryKey(), // UUID
repositoryId: text('repository_id').notNull()
.references(() => repositories.id, { onDelete: 'cascade' }),
versionId: text('version_id')
.references(() => repositoryVersions.id, { onDelete: 'cascade' }),
filePath: text('file_path').notNull(), // relative path within repo
title: text('title'),
language: text('language'), // e.g. "typescript", "markdown"
tokenCount: integer('token_count').default(0),
checksum: text('checksum').notNull(), // SHA-256 of file content
indexedAt: integer('indexed_at', { mode: 'timestamp' }).notNull(),
id: text('id').primaryKey(), // UUID
repositoryId: text('repository_id')
.notNull()
.references(() => repositories.id, { onDelete: 'cascade' }),
versionId: text('version_id').references(() => repositoryVersions.id, { onDelete: 'cascade' }),
filePath: text('file_path').notNull(), // relative path within repo
title: text('title'),
language: text('language'), // e.g. "typescript", "markdown"
tokenCount: integer('token_count').default(0),
checksum: text('checksum').notNull(), // SHA-256 of file content
indexedAt: integer('indexed_at', { mode: 'timestamp' }).notNull()
});
```
@@ -98,20 +103,21 @@ An indexed chunk of content, the atomic unit of search.
```typescript
export const snippets = sqliteTable('snippets', {
id: text('id').primaryKey(), // UUID
documentId: text('document_id').notNull()
.references(() => documents.id, { onDelete: 'cascade' }),
repositoryId: text('repository_id').notNull()
.references(() => repositories.id, { onDelete: 'cascade' }),
versionId: text('version_id')
.references(() => repositoryVersions.id, { onDelete: 'cascade' }),
type: text('type', { enum: ['code', 'info'] }).notNull(),
title: text('title'),
content: text('content').notNull(), // searchable text / code
language: text('language'),
breadcrumb: text('breadcrumb'), // e.g. "Installation > Getting Started"
tokenCount: integer('token_count').default(0),
createdAt: integer('created_at', { mode: 'timestamp' }).notNull(),
id: text('id').primaryKey(), // UUID
documentId: text('document_id')
.notNull()
.references(() => documents.id, { onDelete: 'cascade' }),
repositoryId: text('repository_id')
.notNull()
.references(() => repositories.id, { onDelete: 'cascade' }),
versionId: text('version_id').references(() => repositoryVersions.id, { onDelete: 'cascade' }),
type: text('type', { enum: ['code', 'info'] }).notNull(),
title: text('title'),
content: text('content').notNull(), // searchable text / code
language: text('language'),
breadcrumb: text('breadcrumb'), // e.g. "Installation > Getting Started"
tokenCount: integer('token_count').default(0),
createdAt: integer('created_at', { mode: 'timestamp' }).notNull()
});
```
@@ -121,12 +127,13 @@ Stores vector embeddings separately to keep snippets table lean.
```typescript
export const snippetEmbeddings = sqliteTable('snippet_embeddings', {
snippetId: text('snippet_id').primaryKey()
.references(() => snippets.id, { onDelete: 'cascade' }),
model: text('model').notNull(), // embedding model identifier
dimensions: integer('dimensions').notNull(),
embedding: blob('embedding').notNull(), // Float32Array as binary blob
createdAt: integer('created_at', { mode: 'timestamp' }).notNull(),
snippetId: text('snippet_id')
.primaryKey()
.references(() => snippets.id, { onDelete: 'cascade' }),
model: text('model').notNull(), // embedding model identifier
dimensions: integer('dimensions').notNull(),
embedding: blob('embedding').notNull(), // Float32Array as binary blob
createdAt: integer('created_at', { mode: 'timestamp' }).notNull()
});
```
@@ -136,20 +143,23 @@ Tracks asynchronous indexing operations.
```typescript
export const indexingJobs = sqliteTable('indexing_jobs', {
id: text('id').primaryKey(), // UUID
repositoryId: text('repository_id').notNull()
.references(() => repositories.id, { onDelete: 'cascade' }),
versionId: text('version_id'),
status: text('status', {
enum: ['queued', 'running', 'done', 'failed']
}).notNull().default('queued'),
progress: integer('progress').default(0), // 0–100
totalFiles: integer('total_files').default(0),
processedFiles: integer('processed_files').default(0),
error: text('error'),
startedAt: integer('started_at', { mode: 'timestamp' }),
completedAt: integer('completed_at', { mode: 'timestamp' }),
createdAt: integer('created_at', { mode: 'timestamp' }).notNull(),
id: text('id').primaryKey(), // UUID
repositoryId: text('repository_id')
.notNull()
.references(() => repositories.id, { onDelete: 'cascade' }),
versionId: text('version_id'),
status: text('status', {
enum: ['queued', 'running', 'done', 'failed']
})
.notNull()
.default('queued'),
progress: integer('progress').default(0), // 0–100
totalFiles: integer('total_files').default(0),
processedFiles: integer('processed_files').default(0),
error: text('error'),
startedAt: integer('started_at', { mode: 'timestamp' }),
completedAt: integer('completed_at', { mode: 'timestamp' }),
createdAt: integer('created_at', { mode: 'timestamp' }).notNull()
});
```
@@ -159,17 +169,19 @@ Stores parsed `trueref.json` / `context7.json` configuration.
```typescript
export const repositoryConfigs = sqliteTable('repository_configs', {
repositoryId: text('repository_id').primaryKey()
.references(() => repositories.id, { onDelete: 'cascade' }),
projectTitle: text('project_title'),
description: text('description'),
folders: text('folders', { mode: 'json' }).$type<string[]>(),
excludeFolders: text('exclude_folders', { mode: 'json' }).$type<string[]>(),
excludeFiles: text('exclude_files', { mode: 'json' }).$type<string[]>(),
rules: text('rules', { mode: 'json' }).$type<string[]>(),
previousVersions: text('previous_versions', { mode: 'json' })
.$type<{ tag: string; title: string }[]>(),
updatedAt: integer('updated_at', { mode: 'timestamp' }).notNull(),
repositoryId: text('repository_id')
.primaryKey()
.references(() => repositories.id, { onDelete: 'cascade' }),
projectTitle: text('project_title'),
description: text('description'),
folders: text('folders', { mode: 'json' }).$type<string[]>(),
excludeFolders: text('exclude_folders', { mode: 'json' }).$type<string[]>(),
excludeFiles: text('exclude_files', { mode: 'json' }).$type<string[]>(),
rules: text('rules', { mode: 'json' }).$type<string[]>(),
previousVersions: text('previous_versions', { mode: 'json' }).$type<
{ tag: string; title: string }[]
>(),
updatedAt: integer('updated_at', { mode: 'timestamp' }).notNull()
});
```
@@ -179,9 +191,9 @@ Key-value store for global application settings.
```typescript
export const settings = sqliteTable('settings', {
key: text('key').primaryKey(),
value: text('value', { mode: 'json' }),
updatedAt: integer('updated_at', { mode: 'timestamp' }).notNull(),
key: text('key').primaryKey(),
value: text('value', { mode: 'json' }),
updatedAt: integer('updated_at', { mode: 'timestamp' }).notNull()
});
```

157
docs/features/TRUEREF-0002.md
View File

@@ -31,10 +31,12 @@ Implement the core `RepositoryService` that handles CRUD operations for reposito
## Repository ID Generation
GitHub repositories:
- Input URL: `https://github.com/facebook/react` or `github.com/facebook/react`
- Generated ID: `/facebook/react`
Local repositories:
- Input path: `/home/user/projects/my-sdk`
- Generated ID: `/local/my-sdk` (basename of path, slugified)
- Collision resolution: append `-2`, `-3`, etc.
@@ -49,44 +51,44 @@ Version-specific IDs: `/facebook/react/v18.3.0`
// src/lib/server/services/repository.service.ts
export interface AddRepositoryInput {
source: 'github' | 'local';
sourceUrl: string; // GitHub URL or absolute local path
title?: string; // override auto-detected title
description?: string;
branch?: string; // GitHub: default branch; Local: n/a
githubToken?: string; // for private GitHub repos
source: 'github' | 'local';
sourceUrl: string; // GitHub URL or absolute local path
title?: string; // override auto-detected title
description?: string;
branch?: string; // GitHub: default branch; Local: n/a
githubToken?: string; // for private GitHub repos
}
export interface UpdateRepositoryInput {
title?: string;
description?: string;
branch?: string;
githubToken?: string;
title?: string;
description?: string;
branch?: string;
githubToken?: string;
}
export class RepositoryService {
constructor(private db: BetterSQLite3.Database) {}
constructor(private db: BetterSQLite3.Database) {}
async list(options?: {
state?: Repository['state'];
limit?: number;
offset?: number;
}): Promise<Repository[]>
async list(options?: {
state?: Repository['state'];
limit?: number;
offset?: number;
}): Promise<Repository[]>;
async get(id: string): Promise<Repository | null>
async get(id: string): Promise<Repository | null>;
async add(input: AddRepositoryInput): Promise<Repository>
async add(input: AddRepositoryInput): Promise<Repository>;
async update(id: string, input: UpdateRepositoryInput): Promise<Repository>
async update(id: string, input: UpdateRepositoryInput): Promise<Repository>;
async remove(id: string): Promise<void>
async remove(id: string): Promise<void>;
async getStats(id: string): Promise<{
totalSnippets: number;
totalTokens: number;
totalDocuments: number;
lastIndexedAt: Date | null;
}>
async getStats(id: string): Promise<{
totalSnippets: number;
totalTokens: number;
totalDocuments: number;
lastIndexedAt: Date | null;
}>;
}
```
@@ -97,48 +99,52 @@ export class RepositoryService {
### `GET /api/v1/libs`
Query parameters:
- `state` (optional): filter by state (`pending`, `indexed`, `error`, etc.)
- `limit` (optional, default 50): max results
- `offset` (optional, default 0): pagination offset
Response `200`:
```json
{
"libraries": [
{
"id": "/facebook/react",
"title": "React",
"description": "...",
"source": "github",
"state": "indexed",
"totalSnippets": 1234,
"totalTokens": 98000,
"trustScore": 8.5,
"stars": 228000,
"lastIndexedAt": "2026-03-22T10:00:00Z",
"versions": ["v18.3.0", "v17.0.2"]
}
],
"total": 12,
"limit": 50,
"offset": 0
"libraries": [
{
"id": "/facebook/react",
"title": "React",
"description": "...",
"source": "github",
"state": "indexed",
"totalSnippets": 1234,
"totalTokens": 98000,
"trustScore": 8.5,
"stars": 228000,
"lastIndexedAt": "2026-03-22T10:00:00Z",
"versions": ["v18.3.0", "v17.0.2"]
}
],
"total": 12,
"limit": 50,
"offset": 0
}
```
### `POST /api/v1/libs`
Request body:
```json
{
"source": "github",
"sourceUrl": "https://github.com/facebook/react",
"branch": "main",
"githubToken": "ghp_...",
"autoIndex": true
"source": "github",
"sourceUrl": "https://github.com/facebook/react",
"branch": "main",
"githubToken": "ghp_...",
"autoIndex": true
}
```
Response `201`:
```json
{
"library": { ...Repository },
@@ -149,6 +155,7 @@ Response `201`:
`autoIndex: true` (default) immediately queues an indexing job.
Response `409` if repository already exists:
```json
{ "error": "Repository /facebook/react already exists" }
```
@@ -176,20 +183,22 @@ Response `404`: not found.
Triggers a new indexing job. If a job is already running for this repo, returns the existing job.
Request body (optional):
```json
{ "version": "v18.3.0" }
```
Response `202`:
```json
{
"job": {
"id": "uuid",
"repositoryId": "/facebook/react",
"status": "queued",
"progress": 0,
"createdAt": "2026-03-22T10:00:00Z"
}
"job": {
"id": "uuid",
"repositoryId": "/facebook/react",
"status": "queued",
"progress": 0,
"createdAt": "2026-03-22T10:00:00Z"
}
}
```
@@ -198,15 +207,17 @@ Response `202`:
## Error Response Shape
All error responses follow:
```json
{
"error": "Human-readable message",
"code": "MACHINE_READABLE_CODE",
"details": {}
"error": "Human-readable message",
"code": "MACHINE_READABLE_CODE",
"details": {}
}
```
Error codes:
- `NOT_FOUND`
- `ALREADY_EXISTS`
- `INVALID_INPUT`
@@ -219,23 +230,23 @@ Error codes:
```typescript
function resolveGitHubId(url: string): string {
// Parse owner/repo from URL variants:
// https://github.com/facebook/react
// https://github.com/facebook/react.git
// github.com/facebook/react
const match = url.match(/github\.com\/([^/]+)\/([^/\s.]+)/);
if (!match) throw new Error('Invalid GitHub URL');
return `/${match[1]}/${match[2]}`;
// Parse owner/repo from URL variants:
// https://github.com/facebook/react
// https://github.com/facebook/react.git
// github.com/facebook/react
const match = url.match(/github\.com\/([^/]+)\/([^/\s.]+)/);
if (!match) throw new Error('Invalid GitHub URL');
return `/${match[1]}/${match[2]}`;
}
function resolveLocalId(path: string, existingIds: string[]): string {
const base = slugify(path.split('/').at(-1)!);
let id = `/local/${base}`;
let counter = 2;
while (existingIds.includes(id)) {
id = `/local/${base}-${counter++}`;
}
return id;
const base = slugify(path.split('/').at(-1)!);
let id = `/local/${base}`;
let counter = 2;
while (existingIds.includes(id)) {
id = `/local/${base}-${counter++}`;
}
return id;
}
```

192
docs/features/TRUEREF-0003.md
View File

@@ -37,17 +37,46 @@ The crawler only downloads files with these extensions:
```typescript
const INDEXABLE_EXTENSIONS = new Set([
// Documentation
'.md', '.mdx', '.txt', '.rst',
// Code
'.ts', '.tsx', '.js', '.jsx',
'.py', '.rb', '.go', '.rs', '.java', '.cs', '.cpp', '.c', '.h',
'.swift', '.kt', '.php', '.scala', '.clj', '.ex', '.exs',
'.sh', '.bash', '.zsh', '.fish',
// Config / data
'.json', '.yaml', '.yml', '.toml',
// Web
'.html', '.css', '.svelte', '.vue',
// Documentation
'.md',
'.mdx',
'.txt',
'.rst',
// Code
'.ts',
'.tsx',
'.js',
'.jsx',
'.py',
'.rb',
'.go',
'.rs',
'.java',
'.cs',
'.cpp',
'.c',
'.h',
'.swift',
'.kt',
'.php',
'.scala',
'.clj',
'.ex',
'.exs',
'.sh',
'.bash',
'.zsh',
'.fish',
// Config / data
'.json',
'.yaml',
'.yml',
'.toml',
// Web
'.html',
'.css',
'.svelte',
'.vue'
]);
const MAX_FILE_SIZE_BYTES = 500_000; // 500 KB — skip large generated files
@@ -59,28 +88,28 @@ const MAX_FILE_SIZE_BYTES = 500_000; // 500 KB — skip large generated files
```typescript
export interface CrawledFile {
path: string; // relative path within repo, e.g. "src/index.ts"
content: string; // UTF-8 file content
size: number; // bytes
sha: string; // GitHub blob SHA (used as checksum)
language: string; // detected from extension
path: string; // relative path within repo, e.g. "src/index.ts"
content: string; // UTF-8 file content
size: number; // bytes
sha: string; // GitHub blob SHA (used as checksum)
language: string; // detected from extension
}
export interface CrawlResult {
files: CrawledFile[];
totalFiles: number; // files matching filters
skippedFiles: number; // filtered out or too large
branch: string; // branch/tag that was crawled
commitSha: string; // HEAD commit SHA
files: CrawledFile[];
totalFiles: number; // files matching filters
skippedFiles: number; // filtered out or too large
branch: string; // branch/tag that was crawled
commitSha: string; // HEAD commit SHA
}
export interface CrawlOptions {
owner: string;
repo: string;
ref?: string; // branch, tag, or commit SHA; defaults to repo default branch
token?: string; // GitHub PAT for private repos
config?: RepoConfig; // parsed trueref.json
onProgress?: (processed: number, total: number) => void;
owner: string;
repo: string;
ref?: string; // branch, tag, or commit SHA; defaults to repo default branch
token?: string; // GitHub PAT for private repos
config?: RepoConfig; // parsed trueref.json
onProgress?: (processed: number, total: number) => void;
}
```
@@ -89,12 +118,14 @@ export interface CrawlOptions {
## GitHub API Usage
### Step 1: Get default branch (if ref not specified)
```
GET https://api.github.com/repos/{owner}/{repo}
→ { default_branch: "main", stargazers_count: 12345 }
```
### Step 2: Fetch file tree (recursive)
```
GET https://api.github.com/repos/{owner}/{repo}/git/trees/{ref}?recursive=1
→ {
@@ -109,12 +140,14 @@ GET https://api.github.com/repos/{owner}/{repo}/git/trees/{ref}?recursive=1
If `truncated: true`, the tree has >100k items. Use `--depth` pagination or filter top-level directories first.
### Step 3: Download file contents (parallel)
```
GET https://api.github.com/repos/{owner}/{repo}/contents/{path}?ref={ref}
→ { content: "<base64>", encoding: "base64", size: 1234, sha: "abc123" }
```
Alternative for large repos: use raw content URL:
```
GET https://raw.githubusercontent.com/{owner}/{repo}/{ref}/{path}
```
@@ -124,48 +157,47 @@ GET https://raw.githubusercontent.com/{owner}/{repo}/{ref}/{path}
## Filtering Logic
```typescript
function shouldIndexFile(
filePath: string,
fileSize: number,
config?: RepoConfig
): boolean {
const ext = path.extname(filePath).toLowerCase();
const base = path.basename(filePath);
function shouldIndexFile(filePath: string, fileSize: number, config?: RepoConfig): boolean {
const ext = path.extname(filePath).toLowerCase();
const base = path.basename(filePath);
// 1. Must have indexable extension
if (!INDEXABLE_EXTENSIONS.has(ext)) return false;
// 1. Must have indexable extension
if (!INDEXABLE_EXTENSIONS.has(ext)) return false;
// 2. Must not exceed size limit
if (fileSize > MAX_FILE_SIZE_BYTES) return false;
// 2. Must not exceed size limit
if (fileSize > MAX_FILE_SIZE_BYTES) return false;
// 3. Exclude lockfiles and other non-source artifacts
if (IGNORED_FILE_NAMES.has(base)) return false;
// 3. Exclude lockfiles and other non-source artifacts
if (IGNORED_FILE_NAMES.has(base)) return false;
// 4. Exclude minified and bundled assets
if (base.includes('.min.') || base.endsWith('.bundle.js') || base.endsWith('.bundle.css')) {
return false;
}
// 4. Exclude minified and bundled assets
if (base.includes('.min.') || base.endsWith('.bundle.js') || base.endsWith('.bundle.css')) {
return false;
}
// 5. Apply config excludeFiles (exact filename match)
if (config?.excludeFiles?.includes(base)) return false;
// 5. Apply config excludeFiles (exact filename match)
if (config?.excludeFiles?.includes(base)) return false;
// 6. Exclude common dependency/build/cache directories at any depth
if (isInIgnoredDirectory(filePath)) return false;
// 6. Exclude common dependency/build/cache directories at any depth
if (isInIgnoredDirectory(filePath)) return false;
// 7. Apply config excludeFolders (regex or prefix match)
if (config?.excludeFolders?.some(folder =>
filePath.startsWith(folder) || new RegExp(folder).test(filePath)
)) return false;
// 7. Apply config excludeFolders (regex or prefix match)
if (
config?.excludeFolders?.some(
(folder) => filePath.startsWith(folder) || new RegExp(folder).test(filePath)
)
)
return false;
// 8. Apply config folders allowlist (if specified, only index those paths)
if (config?.folders?.length) {
const inAllowedFolder = config.folders.some(folder =>
filePath.startsWith(folder) || new RegExp(folder).test(filePath)
);
if (!inAllowedFolder) return false;
}
// 8. Apply config folders allowlist (if specified, only index those paths)
if (config?.folders?.length) {
const inAllowedFolder = config.folders.some(
(folder) => filePath.startsWith(folder) || new RegExp(folder).test(filePath)
);
if (!inAllowedFolder) return false;
}
return true;
return true;
}
```
@@ -177,20 +209,20 @@ The shared ignored-directory list is intentionally broader than the original bas
```typescript
class GitHubRateLimiter {
private remaining = 5000;
private resetAt = Date.now();
private remaining = 5000;
private resetAt = Date.now();
updateFromHeaders(headers: Headers): void {
this.remaining = parseInt(headers.get('X-RateLimit-Remaining') ?? '5000');
this.resetAt = parseInt(headers.get('X-RateLimit-Reset') ?? '0') * 1000;
}
updateFromHeaders(headers: Headers): void {
this.remaining = parseInt(headers.get('X-RateLimit-Remaining') ?? '5000');
this.resetAt = parseInt(headers.get('X-RateLimit-Reset') ?? '0') * 1000;
}
async waitIfNeeded(): Promise<void> {
if (this.remaining <= 10) {
const waitMs = Math.max(0, this.resetAt - Date.now()) + 1000;
await sleep(waitMs);
}
}
async waitIfNeeded(): Promise<void> {
if (this.remaining <= 10) {
const waitMs = Math.max(0, this.resetAt - Date.now()) + 1000;
await sleep(waitMs);
}
}
}
```
@@ -200,14 +232,14 @@ Requests are made with a concurrency limit of 10 parallel downloads using a sema
## Error Handling
| Scenario | Behavior |
|----------|---------|
| 404 Not Found | Throw `RepositoryNotFoundError` |
| 401 Unauthorized | Throw `AuthenticationError` (invalid or missing token) |
| 403 Forbidden | If `X-RateLimit-Remaining: 0`, wait and retry; else throw `PermissionError` |
| 422 Unprocessable | Tree too large; switch to directory-by-directory traversal |
| Network error | Retry up to 3 times with exponential backoff |
| File content decode error | Skip file, log warning |
| Scenario | Behavior |
| ------------------------- | --------------------------------------------------------------------------- |
| 404 Not Found | Throw `RepositoryNotFoundError` |
| 401 Unauthorized | Throw `AuthenticationError` (invalid or missing token) |
| 403 Forbidden | If `X-RateLimit-Remaining: 0`, wait and retry; else throw `PermissionError` |
| 422 Unprocessable | Tree too large; switch to directory-by-directory traversal |
| Network error | Retry up to 3 times with exponential backoff |
| File content decode error | Skip file, log warning |
---

132
docs/features/TRUEREF-0004.md
View File

@@ -38,9 +38,9 @@ Reuses `CrawledFile` and `CrawlResult` from TRUEREF-0003 crawler types:
```typescript
export interface LocalCrawlOptions {
rootPath: string; // absolute path to repository root
config?: RepoConfig; // parsed trueref.json
onProgress?: (processed: number, total: number) => void;
rootPath: string; // absolute path to repository root
config?: RepoConfig; // parsed trueref.json
onProgress?: (processed: number, total: number) => void;
}
```
@@ -50,75 +50,73 @@ export interface LocalCrawlOptions {
```typescript
export class LocalCrawler {
async crawl(options: LocalCrawlOptions): Promise<CrawlResult> {
// 1. Load root .gitignore if present
const gitignore = await this.loadGitignore(options.rootPath);
async crawl(options: LocalCrawlOptions): Promise<CrawlResult> {
// 1. Load root .gitignore if present
const gitignore = await this.loadGitignore(options.rootPath);
// 2. Enumerate files recursively, pruning ignored directories early
const allFiles = await this.walkDirectory(options.rootPath, '', gitignore);
// 2. Enumerate files recursively, pruning ignored directories early
const allFiles = await this.walkDirectory(options.rootPath, '', gitignore);
// 3. Look for trueref.json / context7.json first
const configFile = allFiles.find(f =>
f === 'trueref.json' || f === 'context7.json'
);
let config = options.config;
if (configFile && !config) {
config = await this.parseConfigFile(
path.join(options.rootPath, configFile)
);
}
// 3. Look for trueref.json / context7.json first
const configFile = allFiles.find((f) => f === 'trueref.json' || f === 'context7.json');
let config = options.config;
if (configFile && !config) {
config = await this.parseConfigFile(path.join(options.rootPath, configFile));
}
// 4. Filter files
const filteredFiles = allFiles.filter(relPath => {
const stat = statCache.get(relPath);
return shouldIndexFile(relPath, stat.size, config);
});
// 4. Filter files
const filteredFiles = allFiles.filter((relPath) => {
const stat = statCache.get(relPath);
return shouldIndexFile(relPath, stat.size, config);
});
// 5. Read and return file contents
const crawledFiles: CrawledFile[] = [];
for (const [i, relPath] of filteredFiles.entries()) {
const absPath = path.join(options.rootPath, relPath);
const content = await fs.readFile(absPath, 'utf-8');
const sha = computeSHA256(content);
crawledFiles.push({
path: relPath,
content,
size: Buffer.byteLength(content, 'utf-8'),
sha,
language: detectLanguage(relPath),
});
options.onProgress?.(i + 1, filteredFiles.length);
}
// 5. Read and return file contents
const crawledFiles: CrawledFile[] = [];
for (const [i, relPath] of filteredFiles.entries()) {
const absPath = path.join(options.rootPath, relPath);
const content = await fs.readFile(absPath, 'utf-8');
const sha = computeSHA256(content);
crawledFiles.push({
path: relPath,
content,
size: Buffer.byteLength(content, 'utf-8'),
sha,
language: detectLanguage(relPath)
});
options.onProgress?.(i + 1, filteredFiles.length);
}
return {
files: crawledFiles,
totalFiles: filteredFiles.length,
skippedFiles: allFiles.length - filteredFiles.length,
branch: 'local',
commitSha: computeSHA256(crawledFiles.map(f => f.sha).join('')),
};
}
return {
files: crawledFiles,
totalFiles: filteredFiles.length,
skippedFiles: allFiles.length - filteredFiles.length,
branch: 'local',
commitSha: computeSHA256(crawledFiles.map((f) => f.sha).join(''))
};
}
private async walkDirectory(dir: string, rel = '', gitignore?: GitignoreFilter): Promise<string[]> {
const entries = await fs.readdir(dir, { withFileTypes: true });
const files: string[] = [];
for (const entry of entries) {
if (!entry.isFile() && !entry.isDirectory()) continue; // skip symlinks, devices
const relPath = rel ? `${rel}/${entry.name}` : entry.name;
if (entry.isDirectory()) {
if (shouldPruneDirectory(relPath) || gitignore?.isIgnored(relPath, true)) {
continue;
}
files.push(...await this.walkDirectory(
path.join(dir, entry.name), relPath, gitignore
));
} else {
if (gitignore?.isIgnored(relPath, false)) continue;
files.push(relPath);
}
}
return files;
}
private async walkDirectory(
dir: string,
rel = '',
gitignore?: GitignoreFilter
): Promise<string[]> {
const entries = await fs.readdir(dir, { withFileTypes: true });
const files: string[] = [];
for (const entry of entries) {
if (!entry.isFile() && !entry.isDirectory()) continue; // skip symlinks, devices
const relPath = rel ? `${rel}/${entry.name}` : entry.name;
if (entry.isDirectory()) {
if (shouldPruneDirectory(relPath) || gitignore?.isIgnored(relPath, true)) {
continue;
}
files.push(...(await this.walkDirectory(path.join(dir, entry.name), relPath, gitignore)));
} else {
if (gitignore?.isIgnored(relPath, false)) continue;
files.push(relPath);
}
}
return files;
}
}
```
@@ -142,7 +140,7 @@ Directory pruning should happen during the walk so large dependency trees are ne
import { createHash } from 'crypto';
function computeSHA256(content: string): string {
return createHash('sha256').update(content, 'utf-8').digest('hex');
return createHash('sha256').update(content, 'utf-8').digest('hex');
}
```

302
docs/features/TRUEREF-0005.md
View File

@@ -30,19 +30,19 @@ Implement the document parsing and chunking pipeline that transforms raw file co
## Supported File Types
| Extension | Parser Strategy |
|-----------|----------------|
| `.md`, `.mdx` | Heading-based section splitting + code block extraction |
| `.txt`, `.rst` | Paragraph-based splitting |
| `.ts`, `.tsx`, `.js`, `.jsx` | AST-free: function/class boundary detection via regex |
| `.py` | `def`/`class` boundary detection |
| `.go` | `func`/`type` boundary detection |
| `.rs` | `fn`/`impl`/`struct` boundary detection |
| `.java`, `.cs`, `.kt`, `.swift` | Class/method boundary detection |
| `.rb` | `def`/`class` boundary detection |
| `.json`, `.yaml`, `.yml`, `.toml` | Structural chunking (top-level keys) |
| `.html`, `.svelte`, `.vue` | Text content extraction + script block splitting |
| Other code | Line-count-based sliding window (200 lines per chunk) |
| Extension | Parser Strategy |
| --------------------------------- | ------------------------------------------------------- |
| `.md`, `.mdx` | Heading-based section splitting + code block extraction |
| `.txt`, `.rst` | Paragraph-based splitting |
| `.ts`, `.tsx`, `.js`, `.jsx` | AST-free: function/class boundary detection via regex |
| `.py` | `def`/`class` boundary detection |
| `.go` | `func`/`type` boundary detection |
| `.rs` | `fn`/`impl`/`struct` boundary detection |
| `.java`, `.cs`, `.kt`, `.swift` | Class/method boundary detection |
| `.rb` | `def`/`class` boundary detection |
| `.json`, `.yaml`, `.yml`, `.toml` | Structural chunking (top-level keys) |
| `.html`, `.svelte`, `.vue` | Text content extraction + script block splitting |
| Other code | Line-count-based sliding window (200 lines per chunk) |
---
@@ -52,9 +52,9 @@ Use a simple character-based approximation (no tokenizer library needed for v1):
```typescript
function estimateTokens(text: string): number {
// Empirically: ~4 chars per token for English prose
// ~3 chars per token for code (more symbols)
return Math.ceil(text.length / 3.5);
// Empirically: ~4 chars per token for English prose
// ~3 chars per token for code (more symbols)
return Math.ceil(text.length / 3.5);
}
```
@@ -74,49 +74,49 @@ The Markdown parser is the most important parser as most documentation is Markdo
```typescript
interface MarkdownSection {
headings: string[]; // heading stack at this point
content: string; // text content (sans code blocks)
codeBlocks: { language: string; code: string }[];
headings: string[]; // heading stack at this point
content: string; // text content (sans code blocks)
codeBlocks: { language: string; code: string }[];
}
function parseMarkdown(content: string, filePath: string): Snippet[] {
const sections = splitIntoSections(content);
const snippets: Snippet[] = [];
const sections = splitIntoSections(content);
const snippets: Snippet[] = [];
for (const section of sections) {
const breadcrumb = section.headings.join(' > ');
const title = section.headings.at(-1) ?? path.basename(filePath);
for (const section of sections) {
const breadcrumb = section.headings.join(' > ');
const title = section.headings.at(-1) ?? path.basename(filePath);
// Emit info snippet for text content
if (section.content.trim().length >= 20) {
const chunks = chunkText(section.content, MAX_TOKENS, OVERLAP_TOKENS);
for (const chunk of chunks) {
snippets.push({
type: 'info',
title,
content: chunk,
breadcrumb,
tokenCount: estimateTokens(chunk),
});
}
}
// Emit info snippet for text content
if (section.content.trim().length >= 20) {
const chunks = chunkText(section.content, MAX_TOKENS, OVERLAP_TOKENS);
for (const chunk of chunks) {
snippets.push({
type: 'info',
title,
content: chunk,
breadcrumb,
tokenCount: estimateTokens(chunk)
});
}
}
// Emit code snippets for each code block
for (const block of section.codeBlocks) {
if (block.code.trim().length >= 20) {
snippets.push({
type: 'code',
title,
content: block.code,
language: block.language || detectLanguage('.' + block.language),
breadcrumb,
tokenCount: estimateTokens(block.code),
});
}
}
}
// Emit code snippets for each code block
for (const block of section.codeBlocks) {
if (block.code.trim().length >= 20) {
snippets.push({
type: 'code',
title,
content: block.code,
language: block.language || detectLanguage('.' + block.language),
breadcrumb,
tokenCount: estimateTokens(block.code)
});
}
}
}
return snippets;
return snippets;
}
```
@@ -135,43 +135,41 @@ For non-Markdown code files, use regex-based function/class boundary detection.
```typescript
const BOUNDARY_PATTERNS: Record<string, RegExp> = {
typescript: /^(export\s+)?(async\s+)?(function|class|interface|type|const|let|var)\s+\w+/m,
python: /^(async\s+)?(def|class)\s+\w+/m,
go: /^(func|type|var|const)\s+\w+/m,
rust: /^(pub\s+)?(fn|impl|struct|enum|trait)\s+\w+/m,
java: /^(public|private|protected|static).*?(class|interface|enum|void|\w+)\s+\w+\s*[({]/m,
typescript: /^(export\s+)?(async\s+)?(function|class|interface|type|const|let|var)\s+\w+/m,
python: /^(async\s+)?(def|class)\s+\w+/m,
go: /^(func|type|var|const)\s+\w+/m,
rust: /^(pub\s+)?(fn|impl|struct|enum|trait)\s+\w+/m,
java: /^(public|private|protected|static).*?(class|interface|enum|void|\w+)\s+\w+\s*[({]/m
};
function parseCodeFile(
content: string,
filePath: string,
language: string
): Snippet[] {
const pattern = BOUNDARY_PATTERNS[language];
const breadcrumb = filePath;
const title = path.basename(filePath);
function parseCodeFile(content: string, filePath: string, language: string): Snippet[] {
const pattern = BOUNDARY_PATTERNS[language];
const breadcrumb = filePath;
const title = path.basename(filePath);
if (!pattern) {
// Fallback: sliding window
return slidingWindowChunks(content, filePath, language);
}
if (!pattern) {
// Fallback: sliding window
return slidingWindowChunks(content, filePath, language);
}
const chunks = splitAtBoundaries(content, pattern);
return chunks
.filter(chunk => chunk.trim().length >= 20)
.flatMap(chunk => {
if (estimateTokens(chunk) <= MAX_TOKENS) {
return [{
type: 'code' as const,
title,
content: chunk,
language,
breadcrumb,
tokenCount: estimateTokens(chunk),
}];
}
return slidingWindowChunks(chunk, filePath, language);
});
const chunks = splitAtBoundaries(content, pattern);
return chunks
.filter((chunk) => chunk.trim().length >= 20)
.flatMap((chunk) => {
if (estimateTokens(chunk) <= MAX_TOKENS) {
return [
{
type: 'code' as const,
title,
content: chunk,
language,
breadcrumb,
tokenCount: estimateTokens(chunk)
}
];
}
return slidingWindowChunks(chunk, filePath, language);
});
}
```
@@ -188,27 +186,23 @@ const MIN_CONTENT_LENGTH = 20; // characters
### Sliding Window Chunker
```typescript
function chunkText(
text: string,
maxTokens: number,
overlapTokens: number
): string[] {
const words = text.split(/\s+/);
const wordsPerToken = 0.75; // ~0.75 words per token
const maxWords = Math.floor(maxTokens * wordsPerToken);
const overlapWords = Math.floor(overlapTokens * wordsPerToken);
function chunkText(text: string, maxTokens: number, overlapTokens: number): string[] {
const words = text.split(/\s+/);
const wordsPerToken = 0.75; // ~0.75 words per token
const maxWords = Math.floor(maxTokens * wordsPerToken);
const overlapWords = Math.floor(overlapTokens * wordsPerToken);
const chunks: string[] = [];
let start = 0;
const chunks: string[] = [];
let start = 0;
while (start < words.length) {
const end = Math.min(start + maxWords, words.length);
chunks.push(words.slice(start, end).join(' '));
if (end === words.length) break;
start = end - overlapWords;
}
while (start < words.length) {
const end = Math.min(start + maxWords, words.length);
chunks.push(words.slice(start, end).join(' '));
if (end === words.length) break;
start = end - overlapWords;
}
return chunks;
return chunks;
}
```
@@ -218,34 +212,42 @@ function chunkText(
```typescript
const LANGUAGE_MAP: Record<string, string> = {
'.ts': 'typescript', '.tsx': 'typescript',
'.js': 'javascript', '.jsx': 'javascript',
'.py': 'python',
'.rb': 'ruby',
'.go': 'go',
'.rs': 'rust',
'.java': 'java',
'.cs': 'csharp',
'.cpp': 'cpp', '.c': 'c', '.h': 'c',
'.swift': 'swift',
'.kt': 'kotlin',
'.php': 'php',
'.scala': 'scala',
'.sh': 'bash', '.bash': 'bash', '.zsh': 'bash',
'.md': 'markdown', '.mdx': 'markdown',
'.json': 'json',
'.yaml': 'yaml', '.yml': 'yaml',
'.toml': 'toml',
'.html': 'html',
'.css': 'css',
'.svelte': 'svelte',
'.vue': 'vue',
'.sql': 'sql',
'.ts': 'typescript',
'.tsx': 'typescript',
'.js': 'javascript',
'.jsx': 'javascript',
'.py': 'python',
'.rb': 'ruby',
'.go': 'go',
'.rs': 'rust',
'.java': 'java',
'.cs': 'csharp',
'.cpp': 'cpp',
'.c': 'c',
'.h': 'c',
'.swift': 'swift',
'.kt': 'kotlin',
'.php': 'php',
'.scala': 'scala',
'.sh': 'bash',
'.bash': 'bash',
'.zsh': 'bash',
'.md': 'markdown',
'.mdx': 'markdown',
'.json': 'json',
'.yaml': 'yaml',
'.yml': 'yaml',
'.toml': 'toml',
'.html': 'html',
'.css': 'css',
'.svelte': 'svelte',
'.vue': 'vue',
'.sql': 'sql'
};
function detectLanguage(filePath: string): string {
const ext = path.extname(filePath).toLowerCase();
return LANGUAGE_MAP[ext] ?? 'text';
const ext = path.extname(filePath).toLowerCase();
return LANGUAGE_MAP[ext] ?? 'text';
}
```
@@ -255,32 +257,32 @@ function detectLanguage(filePath: string): string {
```typescript
export interface ParseOptions {
repositoryId: string;
documentId: string;
versionId?: string;
repositoryId: string;
documentId: string;
versionId?: string;
}
export function parseFile(
file: CrawledFile,
options: ParseOptions
): NewSnippet[] {
const language = detectLanguage(file.path);
let rawSnippets: Omit<NewSnippet, 'id' | 'repositoryId' | 'documentId' | 'versionId' | 'createdAt'>[];
export function parseFile(file: CrawledFile, options: ParseOptions): NewSnippet[] {
const language = detectLanguage(file.path);
let rawSnippets: Omit<
NewSnippet,
'id' | 'repositoryId' | 'documentId' | 'versionId' | 'createdAt'
>[];
if (language === 'markdown') {
rawSnippets = parseMarkdown(file.content, file.path);
} else {
rawSnippets = parseCodeFile(file.content, file.path, language);
}
if (language === 'markdown') {
rawSnippets = parseMarkdown(file.content, file.path);
} else {
rawSnippets = parseCodeFile(file.content, file.path, language);
}
return rawSnippets.map(s => ({
...s,
id: crypto.randomUUID(),
repositoryId: options.repositoryId,
documentId: options.documentId,
versionId: options.versionId ?? null,
createdAt: new Date(),
}));
return rawSnippets.map((s) => ({
...s,
id: crypto.randomUUID(),
repositoryId: options.repositoryId,
documentId: options.documentId,
versionId: options.versionId ?? null,
createdAt: new Date()
}));
}
```

178
docs/features/TRUEREF-0006.md
View File

@@ -33,42 +33,37 @@ Implement the full-text search engine using SQLite's built-in FTS5 extension. Th
// src/lib/server/search/search.service.ts
export interface SnippetSearchOptions {
repositoryId: string;
versionId?: string;
type?: 'code' | 'info';
limit?: number; // default: 20
offset?: number; // default: 0
repositoryId: string;
versionId?: string;
type?: 'code' | 'info';
limit?: number; // default: 20
offset?: number; // default: 0
}
export interface SnippetSearchResult {
snippet: Snippet;
score: number; // BM25 rank (negative, lower = better)
repository: Pick<Repository, 'id' | 'title'>;
snippet: Snippet;
score: number; // BM25 rank (negative, lower = better)
repository: Pick<Repository, 'id' | 'title'>;
}
export interface LibrarySearchOptions {
libraryName: string;
query?: string; // semantic relevance hint
limit?: number; // default: 10
libraryName: string;
query?: string; // semantic relevance hint
limit?: number; // default: 10
}
export interface LibrarySearchResult {
repository: Repository;
versions: RepositoryVersion[];
score: number; // composite relevance score
repository: Repository;
versions: RepositoryVersion[];
score: number; // composite relevance score
}
export class SearchService {
constructor(private db: BetterSQLite3.Database) {}
constructor(private db: BetterSQLite3.Database) {}
searchSnippets(
query: string,
options: SnippetSearchOptions
): SnippetSearchResult[]
searchSnippets(query: string, options: SnippetSearchOptions): SnippetSearchResult[];
searchRepositories(
options: LibrarySearchOptions
): LibrarySearchResult[]
searchRepositories(options: LibrarySearchOptions): LibrarySearchResult[];
}
```
@@ -101,21 +96,21 @@ The FTS5 MATCH query uses the porter stemmer and unicode61 tokenizer (configured
```typescript
function preprocessQuery(raw: string): string {
// 1. Trim and normalize whitespace
let q = raw.trim().replace(/\s+/g, ' ');
// 1. Trim and normalize whitespace
let q = raw.trim().replace(/\s+/g, ' ');
// 2. Escape FTS5 special characters that aren't intended as operators
// Keep: * (prefix), " " (phrase), AND, OR, NOT
q = q.replace(/[()]/g, ' ');
// 2. Escape FTS5 special characters that aren't intended as operators
// Keep: * (prefix), " " (phrase), AND, OR, NOT
q = q.replace(/[()]/g, ' ');
// 3. Add prefix wildcard to last token for "typing as you go" feel
const tokens = q.split(' ');
const lastToken = tokens.at(-1) ?? '';
if (lastToken.length >= 3 && !lastToken.endsWith('*')) {
tokens[tokens.length - 1] = lastToken + '*';
}
// 3. Add prefix wildcard to last token for "typing as you go" feel
const tokens = q.split(' ');
const lastToken = tokens.at(-1) ?? '';
if (lastToken.length >= 3 && !lastToken.endsWith('*')) {
tokens[tokens.length - 1] = lastToken + '*';
}
return tokens.join(' ');
return tokens.join(' ');
}
```
@@ -174,56 +169,65 @@ searchRepositories(options: LibrarySearchOptions): LibrarySearchResult[] {
The search results must be formatted for the REST API and MCP tool responses:
### Library search response (for `resolve-library-id`):
```typescript
function formatLibraryResults(results: LibrarySearchResult[]): string {
if (results.length === 0) {
return 'No libraries found matching your search.';
}
if (results.length === 0) {
return 'No libraries found matching your search.';
}
return results.map((r, i) => {
const repo = r.repository;
const versions = r.versions.map(v => v.tag).join(', ') || 'default branch';
return [
`${i + 1}. ${repo.title}`,
` Library ID: ${repo.id}`,
` Description: ${repo.description ?? 'No description'}`,
` Snippets: ${repo.totalSnippets} | Trust Score: ${repo.trustScore.toFixed(1)}/10`,
` Available Versions: ${versions}`,
].join('\n');
}).join('\n\n');
return results
.map((r, i) => {
const repo = r.repository;
const versions = r.versions.map((v) => v.tag).join(', ') || 'default branch';
return [
`${i + 1}. ${repo.title}`,
` Library ID: ${repo.id}`,
` Description: ${repo.description ?? 'No description'}`,
` Snippets: ${repo.totalSnippets} | Trust Score: ${repo.trustScore.toFixed(1)}/10`,
` Available Versions: ${versions}`
].join('\n');
})
.join('\n\n');
}
```
### Snippet search response (for `query-docs`):
```typescript
function formatSnippetResults(
results: SnippetSearchResult[],
rules?: string[]
): string {
const parts: string[] = [];
function formatSnippetResults(results: SnippetSearchResult[], rules?: string[]): string {
const parts: string[] = [];
// Prepend repository rules if present
if (rules?.length) {
parts.push('## Library Rules\n' + rules.map(r => `- ${r}`).join('\n'));
}
// Prepend repository rules if present
if (rules?.length) {
parts.push('## Library Rules\n' + rules.map((r) => `- ${r}`).join('\n'));
}
for (const { snippet } of results) {
if (snippet.type === 'code') {
parts.push([
snippet.title ? `### ${snippet.title}` : '',
snippet.breadcrumb ? `*${snippet.breadcrumb}*` : '',
`\`\`\`${snippet.language ?? ''}\n${snippet.content}\n\`\`\``,
].filter(Boolean).join('\n'));
} else {
parts.push([
snippet.title ? `### ${snippet.title}` : '',
snippet.breadcrumb ? `*${snippet.breadcrumb}*` : '',
snippet.content,
].filter(Boolean).join('\n'));
}
}
for (const { snippet } of results) {
if (snippet.type === 'code') {
parts.push(
[
snippet.title ? `### ${snippet.title}` : '',
snippet.breadcrumb ? `*${snippet.breadcrumb}*` : '',
`\`\`\`${snippet.language ?? ''}\n${snippet.content}\n\`\`\``
]
.filter(Boolean)
.join('\n')
);
} else {
parts.push(
[
snippet.title ? `### ${snippet.title}` : '',
snippet.breadcrumb ? `*${snippet.breadcrumb}*` : '',
snippet.content
]
.filter(Boolean)
.join('\n')
);
}
}
return parts.join('\n\n---\n\n');
return parts.join('\n\n---\n\n');
}
```
@@ -235,26 +239,26 @@ Compute `trustScore` (0–10) when a repository is first indexed:
```typescript
function computeTrustScore(repo: Repository): number {
let score = 0;
let score = 0;
// Stars (up to 4 points): log scale, 10k stars = 4 pts
if (repo.stars) {
score += Math.min(4, Math.log10(repo.stars + 1));
}
// Stars (up to 4 points): log scale, 10k stars = 4 pts
if (repo.stars) {
score += Math.min(4, Math.log10(repo.stars + 1));
}
// Documentation coverage (up to 3 points)
score += Math.min(3, repo.totalSnippets / 500);
// Documentation coverage (up to 3 points)
score += Math.min(3, repo.totalSnippets / 500);
// Source type (1 point for GitHub, 0 for local)
if (repo.source === 'github') score += 1;
// Source type (1 point for GitHub, 0 for local)
if (repo.source === 'github') score += 1;
// Successful indexing (1 point)
if (repo.state === 'indexed') score += 1;
// Successful indexing (1 point)
if (repo.state === 'indexed') score += 1;
// Has description (1 point)
if (repo.description) score += 1;
// Has description (1 point)
if (repo.description) score += 1;
return Math.min(10, parseFloat(score.toFixed(1)));
return Math.min(10, parseFloat(score.toFixed(1)));
}
```

261
docs/features/TRUEREF-0007.md
View File

@@ -34,18 +34,18 @@ Implement a pluggable embedding generation system that produces vector represent
// src/lib/server/embeddings/provider.ts
export interface EmbeddingVector {
values: Float32Array;
dimensions: number;
model: string;
values: Float32Array;
dimensions: number;
model: string;
}
export interface EmbeddingProvider {
readonly name: string;
readonly dimensions: number;
readonly model: string;
readonly name: string;
readonly dimensions: number;
readonly model: string;
embed(texts: string[]): Promise<EmbeddingVector[]>;
isAvailable(): Promise<boolean>;
embed(texts: string[]): Promise<EmbeddingVector[]>;
isAvailable(): Promise<boolean>;
}
```
@@ -55,51 +55,51 @@ export interface EmbeddingProvider {
```typescript
export interface OpenAIProviderConfig {
baseUrl: string; // e.g. "https://api.openai.com/v1" or "http://localhost:11434/v1"
apiKey: string;
model: string; // e.g. "text-embedding-3-small", "nomic-embed-text"
dimensions?: number; // override for models that support it (e.g. text-embedding-3-small)
maxBatchSize?: number; // default: 100
baseUrl: string; // e.g. "https://api.openai.com/v1" or "http://localhost:11434/v1"
apiKey: string;
model: string; // e.g. "text-embedding-3-small", "nomic-embed-text"
dimensions?: number; // override for models that support it (e.g. text-embedding-3-small)
maxBatchSize?: number; // default: 100
}
export class OpenAIEmbeddingProvider implements EmbeddingProvider {
constructor(private config: OpenAIProviderConfig) {}
constructor(private config: OpenAIProviderConfig) {}
async embed(texts: string[]): Promise<EmbeddingVector[]> {
// Batch into groups of maxBatchSize
const batches = chunk(texts, this.config.maxBatchSize ?? 100);
const allEmbeddings: EmbeddingVector[] = [];
async embed(texts: string[]): Promise<EmbeddingVector[]> {
// Batch into groups of maxBatchSize
const batches = chunk(texts, this.config.maxBatchSize ?? 100);
const allEmbeddings: EmbeddingVector[] = [];
for (const batch of batches) {
const response = await fetch(`${this.config.baseUrl}/embeddings`, {
method: 'POST',
headers: {
'Authorization': `Bearer ${this.config.apiKey}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: this.config.model,
input: batch,
dimensions: this.config.dimensions,
}),
});
for (const batch of batches) {
const response = await fetch(`${this.config.baseUrl}/embeddings`, {
method: 'POST',
headers: {
Authorization: `Bearer ${this.config.apiKey}`,
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: this.config.model,
input: batch,
dimensions: this.config.dimensions
})
});
if (!response.ok) {
throw new EmbeddingError(`API error: ${response.status}`);
}
if (!response.ok) {
throw new EmbeddingError(`API error: ${response.status}`);
}
const data = await response.json();
for (const item of data.data) {
allEmbeddings.push({
values: new Float32Array(item.embedding),
dimensions: item.embedding.length,
model: this.config.model,
});
}
}
const data = await response.json();
for (const item of data.data) {
allEmbeddings.push({
values: new Float32Array(item.embedding),
dimensions: item.embedding.length,
model: this.config.model
});
}
}
return allEmbeddings;
}
return allEmbeddings;
}
}
```
@@ -110,41 +110,41 @@ export class OpenAIEmbeddingProvider implements EmbeddingProvider {
```typescript
// Uses @xenova/transformers — only loaded if installed
export class LocalEmbeddingProvider implements EmbeddingProvider {
private pipeline: unknown = null;
private pipeline: unknown = null;
readonly name = 'local';
readonly model = 'Xenova/all-MiniLM-L6-v2'; // 384-dim, fast, small
readonly dimensions = 384;
readonly name = 'local';
readonly model = 'Xenova/all-MiniLM-L6-v2'; // 384-dim, fast, small
readonly dimensions = 384;
async embed(texts: string[]): Promise<EmbeddingVector[]> {
if (!this.pipeline) {
const { pipeline } = await import('@xenova/transformers');
this.pipeline = await pipeline('feature-extraction', this.model);
}
async embed(texts: string[]): Promise<EmbeddingVector[]> {
if (!this.pipeline) {
const { pipeline } = await import('@xenova/transformers');
this.pipeline = await pipeline('feature-extraction', this.model);
}
const results: EmbeddingVector[] = [];
for (const text of texts) {
const output = await (this.pipeline as Function)(text, {
pooling: 'mean',
normalize: true,
});
results.push({
values: new Float32Array(output.data),
dimensions: this.dimensions,
model: this.model,
});
}
return results;
}
const results: EmbeddingVector[] = [];
for (const text of texts) {
const output = await (this.pipeline as Function)(text, {
pooling: 'mean',
normalize: true
});
results.push({
values: new Float32Array(output.data),
dimensions: this.dimensions,
model: this.model
});
}
return results;
}
async isAvailable(): Promise<boolean> {
try {
await import('@xenova/transformers');
return true;
} catch {
return false;
}
}
async isAvailable(): Promise<boolean> {
try {
await import('@xenova/transformers');
return true;
} catch {
return false;
}
}
}
```
@@ -154,53 +154,55 @@ export class LocalEmbeddingProvider implements EmbeddingProvider {
```typescript
export class EmbeddingService {
constructor(
private db: BetterSQLite3.Database,
private provider: EmbeddingProvider
) {}
constructor(
private db: BetterSQLite3.Database,
private provider: EmbeddingProvider
) {}
async embedSnippets(
snippetIds: string[],
onProgress?: (done: number, total: number) => void
): Promise<void> {
const snippets = this.db.prepare(
`SELECT id, content, type FROM snippets WHERE id IN (${snippetIds.map(() => '?').join(',')})`
).all(...snippetIds) as Snippet[];
async embedSnippets(
snippetIds: string[],
onProgress?: (done: number, total: number) => void
): Promise<void> {
const snippets = this.db
.prepare(
`SELECT id, content, type FROM snippets WHERE id IN (${snippetIds.map(() => '?').join(',')})`
)
.all(...snippetIds) as Snippet[];
// Prepare text for embedding: combine title + content
const texts = snippets.map(s =>
[s.title, s.breadcrumb, s.content].filter(Boolean).join('\n').slice(0, 2048)
);
// Prepare text for embedding: combine title + content
const texts = snippets.map((s) =>
[s.title, s.breadcrumb, s.content].filter(Boolean).join('\n').slice(0, 2048)
);
const BATCH_SIZE = 50;
const insert = this.db.prepare(`
const BATCH_SIZE = 50;
const insert = this.db.prepare(`
INSERT OR REPLACE INTO snippet_embeddings (snippet_id, model, dimensions, embedding, created_at)
VALUES (?, ?, ?, ?, unixepoch())
`);
for (let i = 0; i < snippets.length; i += BATCH_SIZE) {
const batch = snippets.slice(i, i + BATCH_SIZE);
const batchTexts = texts.slice(i, i + BATCH_SIZE);
for (let i = 0; i < snippets.length; i += BATCH_SIZE) {
const batch = snippets.slice(i, i + BATCH_SIZE);
const batchTexts = texts.slice(i, i + BATCH_SIZE);
const embeddings = await this.provider.embed(batchTexts);
const embeddings = await this.provider.embed(batchTexts);
const insertMany = this.db.transaction(() => {
for (let j = 0; j < batch.length; j++) {
const snippet = batch[j];
const embedding = embeddings[j];
insert.run(
snippet.id,
embedding.model,
embedding.dimensions,
Buffer.from(embedding.values.buffer)
);
}
});
insertMany();
const insertMany = this.db.transaction(() => {
for (let j = 0; j < batch.length; j++) {
const snippet = batch[j];
const embedding = embeddings[j];
insert.run(
snippet.id,
embedding.model,
embedding.dimensions,
Buffer.from(embedding.values.buffer)
);
}
});
insertMany();
onProgress?.(Math.min(i + BATCH_SIZE, snippets.length), snippets.length);
}
}
onProgress?.(Math.min(i + BATCH_SIZE, snippets.length), snippets.length);
}
}
}
```
@@ -212,13 +214,13 @@ Stored in the `settings` table as JSON:
```typescript
export interface EmbeddingConfig {
provider: 'openai' | 'local' | 'none';
openai?: {
baseUrl: string;
apiKey: string;
model: string;
dimensions?: number;
};
provider: 'openai' | 'local' | 'none';
openai?: {
baseUrl: string;
apiKey: string;
model: string;
dimensions?: number;
};
}
// Settings key: 'embedding_config'
@@ -227,14 +229,15 @@ export interface EmbeddingConfig {
### API Endpoints
`GET /api/v1/settings/embedding`
```json
{
"provider": "openai",
"openai": {
"baseUrl": "https://api.openai.com/v1",
"model": "text-embedding-3-small",
"dimensions": 1536
}
"provider": "openai",
"openai": {
"baseUrl": "https://api.openai.com/v1",
"model": "text-embedding-3-small",
"dimensions": 1536
}
}
```
@@ -251,11 +254,7 @@ Embeddings are stored as raw `Float32Array` binary blobs:
const buffer = Buffer.from(float32Array.buffer);
// Retrieve
const float32Array = new Float32Array(
buffer.buffer,
buffer.byteOffset,
buffer.byteLength / 4
);
const float32Array = new Float32Array(buffer.buffer, buffer.byteOffset, buffer.byteLength / 4);
```
---

125
docs/features/TRUEREF-0008.md
View File

@@ -102,21 +102,21 @@ async vectorSearch(
```typescript
function reciprocalRankFusion(
...rankings: Array<Array<{ id: string; score: number }>>
...rankings: Array<Array<{ id: string; score: number }>>
): Array<{ id: string; rrfScore: number }> {
const K = 60; // RRF constant (standard value)
const scores = new Map<string, number>();
const K = 60; // RRF constant (standard value)
const scores = new Map<string, number>();
for (const ranking of rankings) {
ranking.forEach(({ id }, rank) => {
const current = scores.get(id) ?? 0;
scores.set(id, current + 1 / (K + rank + 1));
});
}
for (const ranking of rankings) {
ranking.forEach(({ id }, rank) => {
const current = scores.get(id) ?? 0;
scores.set(id, current + 1 / (K + rank + 1));
});
}
return Array.from(scores.entries())
.map(([id, rrfScore]) => ({ id, rrfScore }))
.sort((a, b) => b.rrfScore - a.rrfScore);
return Array.from(scores.entries())
.map(([id, rrfScore]) => ({ id, rrfScore }))
.sort((a, b) => b.rrfScore - a.rrfScore);
}
```
@@ -126,65 +126,62 @@ function reciprocalRankFusion(
```typescript
export interface HybridSearchOptions {
repositoryId: string;
versionId?: string;
type?: 'code' | 'info';
limit?: number;
alpha?: number; // 0.0 = FTS5 only, 1.0 = vector only, 0.5 = balanced
repositoryId: string;
versionId?: string;
type?: 'code' | 'info';
limit?: number;
alpha?: number; // 0.0 = FTS5 only, 1.0 = vector only, 0.5 = balanced
}
export class HybridSearchService {
constructor(
private db: BetterSQLite3.Database,
private searchService: SearchService,
private embeddingProvider: EmbeddingProvider | null,
) {}
constructor(
private db: BetterSQLite3.Database,
private searchService: SearchService,
private embeddingProvider: EmbeddingProvider | null
) {}
async search(
query: string,
options: HybridSearchOptions
): Promise<SnippetSearchResult[]> {
const limit = options.limit ?? 20;
const alpha = options.alpha ?? 0.5;
async search(query: string, options: HybridSearchOptions): Promise<SnippetSearchResult[]> {
const limit = options.limit ?? 20;
const alpha = options.alpha ?? 0.5;
// Always run FTS5 search
const ftsResults = this.searchService.searchSnippets(query, {
repositoryId: options.repositoryId,
versionId: options.versionId,
type: options.type,
limit: limit * 3, // get more candidates for fusion
});
// Always run FTS5 search
const ftsResults = this.searchService.searchSnippets(query, {
repositoryId: options.repositoryId,
versionId: options.versionId,
type: options.type,
limit: limit * 3 // get more candidates for fusion
});
// If no embedding provider or alpha = 0, return FTS5 results directly
if (!this.embeddingProvider || alpha === 0) {
return ftsResults.slice(0, limit);
}
// If no embedding provider or alpha = 0, return FTS5 results directly
if (!this.embeddingProvider || alpha === 0) {
return ftsResults.slice(0, limit);
}
// Embed the query and run vector search
const [queryEmbedding] = await this.embeddingProvider.embed([query]);
const vectorResults = await this.vectorSearch(
queryEmbedding.values,
options.repositoryId,
limit * 3
);
// Embed the query and run vector search
const [queryEmbedding] = await this.embeddingProvider.embed([query]);
const vectorResults = await this.vectorSearch(
queryEmbedding.values,
options.repositoryId,
limit * 3
);
// Normalize result lists for RRF
const ftsRanked = ftsResults.map((r, i) => ({
id: r.snippet.id,
score: i,
}));
const vecRanked = vectorResults.map((r, i) => ({
id: r.snippetId,
score: i,
}));
// Normalize result lists for RRF
const ftsRanked = ftsResults.map((r, i) => ({
id: r.snippet.id,
score: i
}));
const vecRanked = vectorResults.map((r, i) => ({
id: r.snippetId,
score: i
}));
// Apply RRF
const fused = reciprocalRankFusion(ftsRanked, vecRanked);
// Apply RRF
const fused = reciprocalRankFusion(ftsRanked, vecRanked);
// Fetch full snippet data for top results
const topIds = fused.slice(0, limit).map(r => r.id);
return this.fetchSnippetsByIds(topIds, options.repositoryId);
}
// Fetch full snippet data for top results
const topIds = fused.slice(0, limit).map((r) => r.id);
return this.fetchSnippetsByIds(topIds, options.repositoryId);
}
}
```
@@ -197,9 +194,9 @@ The hybrid search alpha value can be set per-request or globally via settings:
```typescript
// Default config stored in settings table under key 'search_config'
export interface SearchConfig {
alpha: number; // 0.5 default
maxResults: number; // 20 default
enableHybrid: boolean; // true if embedding provider is configured
alpha: number; // 0.5 default
maxResults: number; // 20 default
enableHybrid: boolean; // true if embedding provider is configured
}
```

338
docs/features/TRUEREF-0009.md
View File

@@ -56,75 +56,83 @@ Implement the end-to-end indexing pipeline that orchestrates crawling, parsing,
// src/lib/server/pipeline/job-queue.ts
export class JobQueue {
private isRunning = false;
private isRunning = false;
constructor(private db: BetterSQLite3.Database) {}
constructor(private db: BetterSQLite3.Database) {}
enqueue(repositoryId: string, versionId?: string): IndexingJob {
const job: NewIndexingJob = {
id: crypto.randomUUID(),
repositoryId,
versionId: versionId ?? null,
status: 'queued',
progress: 0,
totalFiles: 0,
processedFiles: 0,
error: null,
startedAt: null,
completedAt: null,
createdAt: new Date(),
};
enqueue(repositoryId: string, versionId?: string): IndexingJob {
const job: NewIndexingJob = {
id: crypto.randomUUID(),
repositoryId,
versionId: versionId ?? null,
status: 'queued',
progress: 0,
totalFiles: 0,
processedFiles: 0,
error: null,
startedAt: null,
completedAt: null,
createdAt: new Date()
};
this.db.prepare(`
this.db
.prepare(
`
INSERT INTO indexing_jobs VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
`).run(...Object.values(job));
`
)
.run(...Object.values(job));
// Kick off processing if not already running
if (!this.isRunning) {
setImmediate(() => this.processNext());
}
// Kick off processing if not already running
if (!this.isRunning) {
setImmediate(() => this.processNext());
}
return job;
}
return job;
}
private async processNext(): Promise<void> {
if (this.isRunning) return;
private async processNext(): Promise<void> {
if (this.isRunning) return;
const job = this.db.prepare(`
const job = this.db
.prepare(
`
SELECT * FROM indexing_jobs
WHERE status = 'queued'
ORDER BY created_at ASC
LIMIT 1
`).get() as IndexingJob | undefined;
`
)
.get() as IndexingJob | undefined;
if (!job) return;
if (!job) return;
this.isRunning = true;
try {
await this.pipeline.run(job);
} finally {
this.isRunning = false;
// Check for next queued job
const nextJob = this.db.prepare(
`SELECT id FROM indexing_jobs WHERE status = 'queued' LIMIT 1`
).get();
if (nextJob) setImmediate(() => this.processNext());
}
}
this.isRunning = true;
try {
await this.pipeline.run(job);
} finally {
this.isRunning = false;
// Check for next queued job
const nextJob = this.db
.prepare(`SELECT id FROM indexing_jobs WHERE status = 'queued' LIMIT 1`)
.get();
if (nextJob) setImmediate(() => this.processNext());
}
}
getJob(id: string): IndexingJob | null {
return this.db.prepare(
`SELECT * FROM indexing_jobs WHERE id = ?`
).get(id) as IndexingJob | null;
}
getJob(id: string): IndexingJob | null {
return this.db
.prepare(`SELECT * FROM indexing_jobs WHERE id = ?`)
.get(id) as IndexingJob | null;
}
listJobs(repositoryId?: string, limit = 20): IndexingJob[] {
const query = repositoryId
? `SELECT * FROM indexing_jobs WHERE repository_id = ? ORDER BY created_at DESC LIMIT ?`
: `SELECT * FROM indexing_jobs ORDER BY created_at DESC LIMIT ?`;
const params = repositoryId ? [repositoryId, limit] : [limit];
return this.db.prepare(query).all(...params) as IndexingJob[];
}
listJobs(repositoryId?: string, limit = 20): IndexingJob[] {
const query = repositoryId
? `SELECT * FROM indexing_jobs WHERE repository_id = ? ORDER BY created_at DESC LIMIT ?`
: `SELECT * FROM indexing_jobs ORDER BY created_at DESC LIMIT ?`;
const params = repositoryId ? [repositoryId, limit] : [limit];
return this.db.prepare(query).all(...params) as IndexingJob[];
}
}
```
@@ -136,94 +144,96 @@ export class JobQueue {
// src/lib/server/pipeline/indexing.pipeline.ts
export class IndexingPipeline {
constructor(
private db: BetterSQLite3.Database,
private githubCrawler: GitHubCrawler,
private localCrawler: LocalCrawler,
private embeddingService: EmbeddingService | null,
) {}
constructor(
private db: BetterSQLite3.Database,
private githubCrawler: GitHubCrawler,
private localCrawler: LocalCrawler,
private embeddingService: EmbeddingService | null
) {}
async run(job: IndexingJob): Promise<void> {
this.updateJob(job.id, { status: 'running', startedAt: new Date() });
async run(job: IndexingJob): Promise<void> {
this.updateJob(job.id, { status: 'running', startedAt: new Date() });
try {
const repo = this.getRepository(job.repositoryId);
if (!repo) throw new Error(`Repository ${job.repositoryId} not found`);
try {
const repo = this.getRepository(job.repositoryId);
if (!repo) throw new Error(`Repository ${job.repositoryId} not found`);
// Update repo state
this.updateRepo(repo.id, { state: 'indexing' });
// Update repo state
this.updateRepo(repo.id, { state: 'indexing' });
// Step 1: Crawl
const crawlResult = await this.crawl(repo, job);
// Step 1: Crawl
const crawlResult = await this.crawl(repo, job);
// Step 2: Parse and diff
const { newSnippets, changedDocIds, newDocuments } =
await this.parseAndDiff(crawlResult, repo, job);
// Step 2: Parse and diff
const { newSnippets, changedDocIds, newDocuments } = await this.parseAndDiff(
crawlResult,
repo,
job
);
// Step 3: Atomic replacement
this.replaceSnippets(repo.id, changedDocIds, newDocuments, newSnippets);
// Step 3: Atomic replacement
this.replaceSnippets(repo.id, changedDocIds, newDocuments, newSnippets);
// Step 4: Embeddings (async, non-blocking for job completion)
if (this.embeddingService && newSnippets.length > 0) {
await this.embeddingService.embedSnippets(
newSnippets.map(s => s.id),
(done, total) => {
// Update job progress for embedding phase
}
);
}
// Step 4: Embeddings (async, non-blocking for job completion)
if (this.embeddingService && newSnippets.length > 0) {
await this.embeddingService.embedSnippets(
newSnippets.map((s) => s.id),
(done, total) => {
// Update job progress for embedding phase
}
);
}
// Step 5: Update repo stats
const stats = this.computeStats(repo.id);
this.updateRepo(repo.id, {
state: 'indexed',
totalSnippets: stats.totalSnippets,
totalTokens: stats.totalTokens,
trustScore: computeTrustScore({ ...repo, ...stats }),
lastIndexedAt: new Date(),
});
// Step 5: Update repo stats
const stats = this.computeStats(repo.id);
this.updateRepo(repo.id, {
state: 'indexed',
totalSnippets: stats.totalSnippets,
totalTokens: stats.totalTokens,
trustScore: computeTrustScore({ ...repo, ...stats }),
lastIndexedAt: new Date()
});
this.updateJob(job.id, {
status: 'done',
progress: 100,
completedAt: new Date(),
});
this.updateJob(job.id, {
status: 'done',
progress: 100,
completedAt: new Date()
});
} catch (error) {
this.updateJob(job.id, {
status: 'failed',
error: (error as Error).message,
completedAt: new Date()
});
this.updateRepo(job.repositoryId, { state: 'error' });
throw error;
}
}
} catch (error) {
this.updateJob(job.id, {
status: 'failed',
error: (error as Error).message,
completedAt: new Date(),
});
this.updateRepo(job.repositoryId, { state: 'error' });
throw error;
}
}
private replaceSnippets(
repositoryId: string,
changedDocIds: string[],
newDocuments: NewDocument[],
newSnippets: NewSnippet[]
): void {
// Single transaction: delete old → insert new
this.db.transaction(() => {
if (changedDocIds.length > 0) {
// Cascade deletes snippets via FK constraint
this.db
.prepare(`DELETE FROM documents WHERE id IN (${changedDocIds.map(() => '?').join(',')})`)
.run(...changedDocIds);
}
private replaceSnippets(
repositoryId: string,
changedDocIds: string[],
newDocuments: NewDocument[],
newSnippets: NewSnippet[]
): void {
// Single transaction: delete old → insert new
this.db.transaction(() => {
if (changedDocIds.length > 0) {
// Cascade deletes snippets via FK constraint
this.db.prepare(
`DELETE FROM documents WHERE id IN (${changedDocIds.map(() => '?').join(',')})`
).run(...changedDocIds);
}
for (const doc of newDocuments) {
this.insertDocument(doc);
}
for (const doc of newDocuments) {
this.insertDocument(doc);
}
for (const snippet of newSnippets) {
this.insertSnippet(snippet);
}
})();
}
for (const snippet of newSnippets) {
this.insertSnippet(snippet);
}
})();
}
}
```
@@ -233,26 +243,24 @@ export class IndexingPipeline {
```typescript
function calculateProgress(
processedFiles: number,
totalFiles: number,
embeddingsDone: number,
embeddingsTotal: number,
hasEmbeddings: boolean
processedFiles: number,
totalFiles: number,
embeddingsDone: number,
embeddingsTotal: number,
hasEmbeddings: boolean
): number {
if (totalFiles === 0) return 0;
if (totalFiles === 0) return 0;
if (!hasEmbeddings) {
// Crawl + parse = 100%
return Math.round((processedFiles / totalFiles) * 100);
}
if (!hasEmbeddings) {
// Crawl + parse = 100%
return Math.round((processedFiles / totalFiles) * 100);
}
// Crawl+parse = 80%, embeddings = 20%
const parseProgress = (processedFiles / totalFiles) * 80;
const embedProgress = embeddingsTotal > 0
? (embeddingsDone / embeddingsTotal) * 20
: 0;
// Crawl+parse = 80%, embeddings = 20%
const parseProgress = (processedFiles / totalFiles) * 80;
const embedProgress = embeddingsTotal > 0 ? (embeddingsDone / embeddingsTotal) * 20 : 0;
return Math.round(parseProgress + embedProgress);
return Math.round(parseProgress + embedProgress);
}
```
@@ -263,20 +271,21 @@ function calculateProgress(
### `GET /api/v1/jobs/:id`
Response `200`:
```json
{
"job": {
"id": "uuid",
"repositoryId": "/facebook/react",
"status": "running",
"progress": 47,
"totalFiles": 342,
"processedFiles": 162,
"error": null,
"startedAt": "2026-03-22T10:00:00Z",
"completedAt": null,
"createdAt": "2026-03-22T09:59:55Z"
}
"job": {
"id": "uuid",
"repositoryId": "/facebook/react",
"status": "running",
"progress": 47,
"totalFiles": 342,
"processedFiles": 162,
"error": null,
"startedAt": "2026-03-22T10:00:00Z",
"completedAt": null,
"createdAt": "2026-03-22T09:59:55Z"
}
}
```
@@ -285,6 +294,7 @@ Response `200`:
Query params: `repositoryId` (optional), `status` (optional), `limit` (default 20).
Response `200`:
```json
{
"jobs": [...],
@@ -300,20 +310,24 @@ On application start, mark any jobs in `running` state as `failed` (they were in
```typescript
function recoverStaleJobs(db: BetterSQLite3.Database): void {
db.prepare(`
db.prepare(
`
UPDATE indexing_jobs
SET status = 'failed',
error = 'Server restarted while job was running',
completed_at = unixepoch()
WHERE status = 'running'
`).run();
`
).run();
// Also reset any repositories stuck in 'indexing' state
db.prepare(`
// Also reset any repositories stuck in 'indexing' state
db.prepare(
`
UPDATE repositories
SET state = 'error'
WHERE state = 'indexing'
`).run();
`
).run();
}
```

152
docs/features/TRUEREF-0010.md
View File

@@ -32,33 +32,33 @@ Implement the public-facing REST API endpoints that replicate context7's `/api/v
### Query Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `libraryName` | string | Yes | Library name to search for |
| `query` | string | No | User's question for relevance ranking |
| `limit` | integer | No | Max results (default: 10, max: 50) |
| Parameter | Type | Required | Description |
| ------------- | ------- | -------- | ------------------------------------- |
| `libraryName` | string | Yes | Library name to search for |
| `query` | string | No | User's question for relevance ranking |
| `limit` | integer | No | Max results (default: 10, max: 50) |
### Response `200` (`type=json`, default):
```json
{
"results": [
{
"id": "/facebook/react",
"title": "React",
"description": "A JavaScript library for building user interfaces",
"branch": "main",
"lastUpdateDate": "2026-03-22T10:00:00Z",
"state": "finalized",
"totalTokens": 142000,
"totalSnippets": 1247,
"stars": 228000,
"trustScore": 9.2,
"benchmarkScore": 87,
"versions": ["v18.3.0", "v17.0.2"],
"source": "https://github.com/facebook/react"
}
]
"results": [
{
"id": "/facebook/react",
"title": "React",
"description": "A JavaScript library for building user interfaces",
"branch": "main",
"lastUpdateDate": "2026-03-22T10:00:00Z",
"state": "finalized",
"totalTokens": 142000,
"totalSnippets": 1247,
"stars": 228000,
"trustScore": 9.2,
"benchmarkScore": 87,
"versions": ["v18.3.0", "v17.0.2"],
"source": "https://github.com/facebook/react"
}
]
}
```
@@ -67,11 +67,11 @@ Note: `state: "finalized"` maps from TrueRef's `state: "indexed"` for compatibil
### State Mapping
| TrueRef state | context7 state |
|---------------|---------------|
| `pending` | `initial` |
| `indexing` | `initial` |
| `indexed` | `finalized` |
| `error` | `error` |
| ------------- | -------------- |
| `pending` | `initial` |
| `indexing` | `initial` |
| `indexed` | `finalized` |
| `error` | `error` |
---
@@ -81,43 +81,43 @@ Note: `state: "finalized"` maps from TrueRef's `state: "indexed"` for compatibil
### Query Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `libraryId` | string | Yes | Library ID, e.g. `/facebook/react` or `/facebook/react/v18.3.0` |
| `query` | string | Yes | Specific question about the library |
| `type` | string | No | `json` (default) or `txt` (plain text for LLM injection) |
| `tokens` | integer | No | Approximate max token count for response (default: 10000) |
| Parameter | Type | Required | Description |
| ----------- | ------- | -------- | --------------------------------------------------------------- |
| `libraryId` | string | Yes | Library ID, e.g. `/facebook/react` or `/facebook/react/v18.3.0` |
| `query` | string | Yes | Specific question about the library |
| `type` | string | No | `json` (default) or `txt` (plain text for LLM injection) |
| `tokens` | integer | No | Approximate max token count for response (default: 10000) |
### Response `200` (`type=json`):
```json
{
"snippets": [
{
"type": "code",
"title": "Basic Component",
"description": "Getting Started > Components",
"language": "tsx",
"codeList": [
{
"language": "tsx",
"code": "function MyComponent() {\n return <div>Hello</div>;\n}"
}
],
"id": "uuid",
"tokenCount": 45,
"pageTitle": "Getting Started"
},
{
"type": "info",
"text": "React components let you split the UI into independent...",
"breadcrumb": "Core Concepts > Components",
"pageId": "uuid",
"tokenCount": 120
}
],
"rules": ["Always use functional components", "..."],
"totalTokens": 2840
"snippets": [
{
"type": "code",
"title": "Basic Component",
"description": "Getting Started > Components",
"language": "tsx",
"codeList": [
{
"language": "tsx",
"code": "function MyComponent() {\n return <div>Hello</div>;\n}"
}
],
"id": "uuid",
"tokenCount": 45,
"pageTitle": "Getting Started"
},
{
"type": "info",
"text": "React components let you split the UI into independent...",
"breadcrumb": "Core Concepts > Components",
"pageId": "uuid",
"tokenCount": 120
}
],
"rules": ["Always use functional components", "..."],
"totalTokens": 2840
}
```
@@ -125,7 +125,7 @@ Note: `state: "finalized"` maps from TrueRef's `state: "indexed"` for compatibil
Plain text formatted for direct LLM context injection:
```
````
## Library Rules
- Always use functional components
- Use hooks for state management
@@ -139,15 +139,17 @@ Plain text formatted for direct LLM context injection:
function MyComponent() {
return <div>Hello</div>;
}
```
````
---
### React components let you split the UI...
*Core Concepts > Components*
_Core Concepts > Components_
React components let you split the UI into independent, reusable pieces...
```
````
---
@@ -167,7 +169,7 @@ function parseLibraryId(libraryId: string): {
version: match[3],
};
}
```
````
---
@@ -176,20 +178,17 @@ function parseLibraryId(libraryId: string): {
The `tokens` parameter limits the total response size. Snippets are added greedily until the budget is exhausted:
```typescript
function selectSnippetsWithinBudget(
snippets: Snippet[],
maxTokens: number
): Snippet[] {
const selected: Snippet[] = [];
let usedTokens = 0;
function selectSnippetsWithinBudget(snippets: Snippet[], maxTokens: number): Snippet[] {
const selected: Snippet[] = [];
let usedTokens = 0;
for (const snippet of snippets) {
if (usedTokens + (snippet.tokenCount ?? 0) > maxTokens) break;
selected.push(snippet);
usedTokens += snippet.tokenCount ?? 0;
}
for (const snippet of snippets) {
if (usedTokens + (snippet.tokenCount ?? 0) > maxTokens) break;
selected.push(snippet);
usedTokens += snippet.tokenCount ?? 0;
}
return selected;
return selected;
}
```
@@ -215,6 +214,7 @@ Default token budget: 10,000 tokens (~7,500 words) — enough for ~20 medium sni
## CORS Configuration
All API routes include:
```
Access-Control-Allow-Origin: *
Access-Control-Allow-Methods: GET, POST, PATCH, DELETE, OPTIONS

361
docs/features/TRUEREF-0011.md
View File

@@ -32,8 +32,8 @@ Implement a Model Context Protocol (MCP) server that exposes `resolve-library-id
```json
{
"@modelcontextprotocol/sdk": "^1.25.1",
"zod": "^4.3.4"
"@modelcontextprotocol/sdk": "^1.25.1",
"zod": "^4.3.4"
}
```
@@ -46,189 +46,190 @@ Implement a Model Context Protocol (MCP) server that exposes `resolve-library-id
import { Server } from '@modelcontextprotocol/sdk/server/index.js';
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
import {
CallToolRequestSchema,
ListToolsRequestSchema,
} from '@modelcontextprotocol/sdk/types.js';
import { CallToolRequestSchema, ListToolsRequestSchema } from '@modelcontextprotocol/sdk/types.js';
import { z } from 'zod';
const API_BASE = process.env.TRUEREF_API_URL ?? 'http://localhost:5173';
const server = new Server(
{
name: 'io.github.trueref/trueref',
version: '1.0.0',
},
{
capabilities: { tools: {} },
}
{
name: 'io.github.trueref/trueref',
version: '1.0.0'
},
{
capabilities: { tools: {} }
}
);
// Tool schemas — identical to context7 for drop-in compatibility
const ResolveLibraryIdSchema = z.object({
libraryName: z.string().describe(
'Library name to search for and resolve to a TrueRef library ID'
),
query: z.string().describe(
"The user's question or context to help rank results"
),
libraryName: z
.string()
.describe('Library name to search for and resolve to a TrueRef library ID'),
query: z.string().describe("The user's question or context to help rank results")
});
const QueryDocsSchema = z.object({
libraryId: z.string().describe(
'The TrueRef library ID obtained from resolve-library-id, e.g. /facebook/react'
),
query: z.string().describe(
'Specific question about the library to retrieve relevant documentation'
),
tokens: z.number().optional().describe(
'Maximum token budget for the response (default: 10000)'
),
libraryId: z
.string()
.describe('The TrueRef library ID obtained from resolve-library-id, e.g. /facebook/react'),
query: z
.string()
.describe('Specific question about the library to retrieve relevant documentation'),
tokens: z.number().optional().describe('Maximum token budget for the response (default: 10000)')
});
server.setRequestHandler(ListToolsRequestSchema, async () => ({
tools: [
{
name: 'resolve-library-id',
description: [
'Searches TrueRef to find a library matching the given name.',
'Returns a list of matching libraries with their IDs.',
'ALWAYS call this tool before query-docs to get the correct library ID.',
'Call at most 3 times per user question.',
].join(' '),
inputSchema: {
type: 'object',
properties: {
libraryName: {
type: 'string',
description: 'Library name to search for',
},
query: {
type: 'string',
description: "User's question for relevance ranking",
},
},
required: ['libraryName', 'query'],
},
},
{
name: 'query-docs',
description: [
'Fetches documentation and code examples from TrueRef for a specific library.',
'Requires a library ID obtained from resolve-library-id.',
'Returns relevant snippets formatted for LLM consumption.',
'Call at most 3 times per user question.',
].join(' '),
inputSchema: {
type: 'object',
properties: {
libraryId: {
type: 'string',
description: 'TrueRef library ID, e.g. /facebook/react',
},
query: {
type: 'string',
description: 'Specific question about the library',
},
tokens: {
type: 'number',
description: 'Max token budget (default: 10000)',
},
},
required: ['libraryId', 'query'],
},
},
],
tools: [
{
name: 'resolve-library-id',
description: [
'Searches TrueRef to find a library matching the given name.',
'Returns a list of matching libraries with their IDs.',
'ALWAYS call this tool before query-docs to get the correct library ID.',
'Call at most 3 times per user question.'
].join(' '),
inputSchema: {
type: 'object',
properties: {
libraryName: {
type: 'string',
description: 'Library name to search for'
},
query: {
type: 'string',
description: "User's question for relevance ranking"
}
},
required: ['libraryName', 'query']
}
},
{
name: 'query-docs',
description: [
'Fetches documentation and code examples from TrueRef for a specific library.',
'Requires a library ID obtained from resolve-library-id.',
'Returns relevant snippets formatted for LLM consumption.',
'Call at most 3 times per user question.'
].join(' '),
inputSchema: {
type: 'object',
properties: {
libraryId: {
type: 'string',
description: 'TrueRef library ID, e.g. /facebook/react'
},
query: {
type: 'string',
description: 'Specific question about the library'
},
tokens: {
type: 'number',
description: 'Max token budget (default: 10000)'
}
},
required: ['libraryId', 'query']
}
}
]
}));
server.setRequestHandler(CallToolRequestSchema, async (request) => {
const { name, arguments: args } = request.params;
const { name, arguments: args } = request.params;
if (name === 'resolve-library-id') {
const { libraryName, query } = ResolveLibraryIdSchema.parse(args);
if (name === 'resolve-library-id') {
const { libraryName, query } = ResolveLibraryIdSchema.parse(args);
const url = new URL(`${API_BASE}/api/v1/libs/search`);
url.searchParams.set('libraryName', libraryName);
url.searchParams.set('query', query);
url.searchParams.set('type', 'txt');
const url = new URL(`${API_BASE}/api/v1/libs/search`);
url.searchParams.set('libraryName', libraryName);
url.searchParams.set('query', query);
url.searchParams.set('type', 'txt');
const response = await fetch(url.toString());
if (!response.ok) {
return {
content: [{
type: 'text',
text: `Error searching libraries: ${response.status} ${response.statusText}`,
}],
isError: true,
};
}
const response = await fetch(url.toString());
if (!response.ok) {
return {
content: [
{
type: 'text',
text: `Error searching libraries: ${response.status} ${response.statusText}`
}
],
isError: true
};
}
const text = await response.text();
return {
content: [{ type: 'text', text }],
};
}
const text = await response.text();
return {
content: [{ type: 'text', text }]
};
}
if (name === 'query-docs') {
const { libraryId, query, tokens } = QueryDocsSchema.parse(args);
if (name === 'query-docs') {
const { libraryId, query, tokens } = QueryDocsSchema.parse(args);
const url = new URL(`${API_BASE}/api/v1/context`);
url.searchParams.set('libraryId', libraryId);
url.searchParams.set('query', query);
url.searchParams.set('type', 'txt');
if (tokens) url.searchParams.set('tokens', String(tokens));
const url = new URL(`${API_BASE}/api/v1/context`);
url.searchParams.set('libraryId', libraryId);
url.searchParams.set('query', query);
url.searchParams.set('type', 'txt');
if (tokens) url.searchParams.set('tokens', String(tokens));
const response = await fetch(url.toString());
if (!response.ok) {
const status = response.status;
if (status === 404) {
return {
content: [{
type: 'text',
text: `Library "${libraryId}" not found. Please run resolve-library-id first.`,
}],
isError: true,
};
}
if (status === 503) {
return {
content: [{
type: 'text',
text: `Library "${libraryId}" is currently being indexed. Please try again in a moment.`,
}],
isError: true,
};
}
return {
content: [{
type: 'text',
text: `Error fetching documentation: ${response.status} ${response.statusText}`,
}],
isError: true,
};
}
const response = await fetch(url.toString());
if (!response.ok) {
const status = response.status;
if (status === 404) {
return {
content: [
{
type: 'text',
text: `Library "${libraryId}" not found. Please run resolve-library-id first.`
}
],
isError: true
};
}
if (status === 503) {
return {
content: [
{
type: 'text',
text: `Library "${libraryId}" is currently being indexed. Please try again in a moment.`
}
],
isError: true
};
}
return {
content: [
{
type: 'text',
text: `Error fetching documentation: ${response.status} ${response.statusText}`
}
],
isError: true
};
}
const text = await response.text();
return {
content: [{ type: 'text', text }],
};
}
const text = await response.text();
return {
content: [{ type: 'text', text }]
};
}
return {
content: [{ type: 'text', text: `Unknown tool: ${name}` }],
isError: true,
};
return {
content: [{ type: 'text', text: `Unknown tool: ${name}` }],
isError: true
};
});
async function main() {
const transport = new StdioServerTransport();
await server.connect(transport);
// Server runs until process exits
const transport = new StdioServerTransport();
await server.connect(transport);
// Server runs until process exits
}
main().catch((err) => {
process.stderr.write(`MCP server error: ${err.message}\n`);
process.exit(1);
process.stderr.write(`MCP server error: ${err.message}\n`);
process.exit(1);
});
```
@@ -238,18 +239,19 @@ main().catch((err) => {
```json
{
"scripts": {
"mcp:start": "node --experimental-vm-modules src/mcp/index.ts"
}
"scripts": {
"mcp:start": "node --experimental-vm-modules src/mcp/index.ts"
}
}
```
Or with `tsx` for TypeScript-direct execution:
```json
{
"scripts": {
"mcp:start": "tsx src/mcp/index.ts"
}
"scripts": {
"mcp:start": "tsx src/mcp/index.ts"
}
}
```
@@ -261,30 +263,31 @@ Users add to `.mcp.json`:
```json
{
"mcpServers": {
"trueref": {
"command": "node",
"args": ["/path/to/trueref/dist/mcp/index.js"],
"env": {
"TRUEREF_API_URL": "http://localhost:5173"
}
}
}
"mcpServers": {
"trueref": {
"command": "node",
"args": ["/path/to/trueref/dist/mcp/index.js"],
"env": {
"TRUEREF_API_URL": "http://localhost:5173"
}
}
}
}
```
Or with tsx for development:
```json
{
"mcpServers": {
"trueref": {
"command": "npx",
"args": ["tsx", "/path/to/trueref/src/mcp/index.ts"],
"env": {
"TRUEREF_API_URL": "http://localhost:5173"
}
}
}
"mcpServers": {
"trueref": {
"command": "npx",
"args": ["tsx", "/path/to/trueref/src/mcp/index.ts"],
"env": {
"TRUEREF_API_URL": "http://localhost:5173"
}
}
}
}
```
@@ -295,13 +298,15 @@ Or with tsx for development:
The MCP server should include a `resources` list item (optional) or the library responses themselves prepend rules. Additionally, users should add a Claude rule file:
```markdown
<!-- .claude/rules/trueref.md -->
---
## <!-- .claude/rules/trueref.md -->
description: Use TrueRef to retrieve documentation for indexed libraries
alwaysApply: true
---
When answering questions about indexed libraries, always use the TrueRef MCP tools:
1. Call `resolve-library-id` with the library name and the user's question to get the library ID
2. Call `query-docs` with the library ID and question to retrieve relevant documentation
3. Use the returned documentation to answer the question accurately

108
docs/features/TRUEREF-0012.md
View File

@@ -50,64 +50,64 @@ import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
const { values: args } = parseArgs({
options: {
transport: { type: 'string', default: 'stdio' },
port: { type: 'string', default: process.env.PORT ?? '3001' },
},
options: {
transport: { type: 'string', default: 'stdio' },
port: { type: 'string', default: process.env.PORT ?? '3001' }
}
});
async function startHttp(server: Server, port: number): Promise<void> {
const httpServer = createServer(async (req, res) => {
const url = new URL(req.url!, `http://localhost:${port}`);
const httpServer = createServer(async (req, res) => {
const url = new URL(req.url!, `http://localhost:${port}`);
// Health check
if (url.pathname === '/ping') {
res.writeHead(200, { 'Content-Type': 'application/json' });
res.end(JSON.stringify({ ok: true }));
return;
}
// Health check
if (url.pathname === '/ping') {
res.writeHead(200, { 'Content-Type': 'application/json' });
res.end(JSON.stringify({ ok: true }));
return;
}
// MCP endpoint
if (url.pathname === '/mcp') {
// CORS preflight
res.setHeader('Access-Control-Allow-Origin', '*');
res.setHeader('Access-Control-Allow-Methods', 'POST, GET, OPTIONS');
res.setHeader('Access-Control-Allow-Headers', 'Content-Type, Accept');
// MCP endpoint
if (url.pathname === '/mcp') {
// CORS preflight
res.setHeader('Access-Control-Allow-Origin', '*');
res.setHeader('Access-Control-Allow-Methods', 'POST, GET, OPTIONS');
res.setHeader('Access-Control-Allow-Headers', 'Content-Type, Accept');
if (req.method === 'OPTIONS') {
res.writeHead(204);
res.end();
return;
}
if (req.method === 'OPTIONS') {
res.writeHead(204);
res.end();
return;
}
const transport = new StreamableHTTPServerTransport({
sessionIdGenerator: () => crypto.randomUUID(),
});
const transport = new StreamableHTTPServerTransport({
sessionIdGenerator: () => crypto.randomUUID()
});
await server.connect(transport);
await transport.handleRequest(req, res);
return;
}
await server.connect(transport);
await transport.handleRequest(req, res);
return;
}
res.writeHead(404);
res.end('Not Found');
});
res.writeHead(404);
res.end('Not Found');
});
httpServer.listen(port, () => {
process.stderr.write(`TrueRef MCP server listening on http://localhost:${port}/mcp\n`);
});
httpServer.listen(port, () => {
process.stderr.write(`TrueRef MCP server listening on http://localhost:${port}/mcp\n`);
});
}
async function main() {
const mcpServer = createMcpServer(); // shared server creation
const mcpServer = createMcpServer(); // shared server creation
if (args.transport === 'http') {
const port = parseInt(args.port!, 10);
await startHttp(mcpServer, port);
} else {
const transport = new StdioServerTransport();
await mcpServer.connect(transport);
}
if (args.transport === 'http') {
const port = parseInt(args.port!, 10);
await startHttp(mcpServer, port);
} else {
const transport = new StdioServerTransport();
await mcpServer.connect(transport);
}
}
```
@@ -117,10 +117,10 @@ async function main() {
```json
{
"scripts": {
"mcp:start": "tsx src/mcp/index.ts",
"mcp:http": "tsx src/mcp/index.ts --transport http --port 3001"
}
"scripts": {
"mcp:start": "tsx src/mcp/index.ts",
"mcp:http": "tsx src/mcp/index.ts --transport http --port 3001"
}
}
```
@@ -132,12 +132,12 @@ For HTTP transport, users configure Claude Code with the remote URL:
```json
{
"mcpServers": {
"trueref": {
"type": "http",
"url": "http://localhost:3001/mcp"
}
}
"mcpServers": {
"trueref": {
"type": "http",
"url": "http://localhost:3001/mcp"
}
}
}
```

272
docs/features/TRUEREF-0013.md
View File

@@ -32,53 +32,53 @@ Support `trueref.json` configuration files placed in the root of a repository. T
// src/lib/server/config/trueref-config.schema.ts
export interface TrueRefConfig {
/**
* Override the display name for this library.
* 1–100 characters.
*/
projectTitle?: string;
/**
* Override the display name for this library.
* 1–100 characters.
*/
projectTitle?: string;
/**
* Description of the library for search ranking.
* 10–500 characters.
*/
description?: string;
/**
* Description of the library for search ranking.
* 10–500 characters.
*/
description?: string;
/**
* Folders to include in indexing (allowlist).
* Each entry is a path prefix or regex string.
* If empty/absent, all folders are included.
* Examples: ["src/", "docs/", "^packages/core"]
*/
folders?: string[];
/**
* Folders to include in indexing (allowlist).
* Each entry is a path prefix or regex string.
* If empty/absent, all folders are included.
* Examples: ["src/", "docs/", "^packages/core"]
*/
folders?: string[];
/**
* Folders to exclude from indexing.
* Applied after `folders` allowlist.
* Examples: ["test/", "fixtures/", "__mocks__"]
*/
excludeFolders?: string[];
/**
* Folders to exclude from indexing.
* Applied after `folders` allowlist.
* Examples: ["test/", "fixtures/", "__mocks__"]
*/
excludeFolders?: string[];
/**
* Exact filenames to exclude (no path, no regex).
* Examples: ["README.md", "CHANGELOG.md", "jest.config.ts"]
*/
excludeFiles?: string[];
/**
* Exact filenames to exclude (no path, no regex).
* Examples: ["README.md", "CHANGELOG.md", "jest.config.ts"]
*/
excludeFiles?: string[];
/**
* Best practices / rules to inject at the top of every query-docs response.
* Each rule: 5–500 characters.
* Maximum 20 rules.
*/
rules?: string[];
/**
* Best practices / rules to inject at the top of every query-docs response.
* Each rule: 5–500 characters.
* Maximum 20 rules.
*/
rules?: string[];
/**
* Previously released versions to make available for versioned queries.
*/
previousVersions?: Array<{
tag: string; // git tag (e.g. "v1.2.3")
title: string; // human-readable (e.g. "Version 1.2.3")
}>;
/**
* Previously released versions to make available for versioned queries.
*/
previousVersions?: Array<{
tag: string; // git tag (e.g. "v1.2.3")
title: string; // human-readable (e.g. "Version 1.2.3")
}>;
}
```
@@ -88,14 +88,14 @@ export interface TrueRefConfig {
```typescript
const CONFIG_CONSTRAINTS = {
projectTitle: { minLength: 1, maxLength: 100 },
description: { minLength: 10, maxLength: 500 },
folders: { maxItems: 50, maxLength: 200 }, // per entry
excludeFolders: { maxItems: 50, maxLength: 200 },
excludeFiles: { maxItems: 100, maxLength: 200 },
rules: { maxItems: 20, minLength: 5, maxLength: 500 },
previousVersions: { maxItems: 50 },
versionTag: { pattern: /^v?\d+\.\d+(\.\d+)?(-.*)?$/ },
projectTitle: { minLength: 1, maxLength: 100 },
description: { minLength: 10, maxLength: 500 },
folders: { maxItems: 50, maxLength: 200 }, // per entry
excludeFolders: { maxItems: 50, maxLength: 200 },
excludeFiles: { maxItems: 100, maxLength: 200 },
rules: { maxItems: 20, minLength: 5, maxLength: 500 },
previousVersions: { maxItems: 50 },
versionTag: { pattern: /^v?\d+\.\d+(\.\d+)?(-.*)?$/ }
};
```
@@ -107,94 +107,96 @@ const CONFIG_CONSTRAINTS = {
// src/lib/server/config/config-parser.ts
export interface ParsedConfig {
config: TrueRefConfig;
source: 'trueref.json' | 'context7.json';
warnings: string[];
config: TrueRefConfig;
source: 'trueref.json' | 'context7.json';
warnings: string[];
}
export function parseConfigFile(content: string, filename: string): ParsedConfig {
let raw: unknown;
let raw: unknown;
try {
raw = JSON.parse(content);
} catch (e) {
throw new ConfigParseError(`${filename} is not valid JSON: ${(e as Error).message}`);
}
try {
raw = JSON.parse(content);
} catch (e) {
throw new ConfigParseError(`${filename} is not valid JSON: ${(e as Error).message}`);
}
if (typeof raw !== 'object' || raw === null) {
throw new ConfigParseError(`${filename} must be a JSON object`);
}
if (typeof raw !== 'object' || raw === null) {
throw new ConfigParseError(`${filename} must be a JSON object`);
}
const config = raw as Record<string, unknown>;
const validated: TrueRefConfig = {};
const warnings: string[] = [];
const config = raw as Record<string, unknown>;
const validated: TrueRefConfig = {};
const warnings: string[] = [];
// projectTitle
if (config.projectTitle !== undefined) {
if (typeof config.projectTitle !== 'string') {
warnings.push('projectTitle must be a string, ignoring');
} else if (config.projectTitle.length > 100) {
validated.projectTitle = config.projectTitle.slice(0, 100);
warnings.push('projectTitle truncated to 100 characters');
} else {
validated.projectTitle = config.projectTitle;
}
}
// projectTitle
if (config.projectTitle !== undefined) {
if (typeof config.projectTitle !== 'string') {
warnings.push('projectTitle must be a string, ignoring');
} else if (config.projectTitle.length > 100) {
validated.projectTitle = config.projectTitle.slice(0, 100);
warnings.push('projectTitle truncated to 100 characters');
} else {
validated.projectTitle = config.projectTitle;
}
}
// description
if (config.description !== undefined) {
if (typeof config.description === 'string') {
validated.description = config.description.slice(0, 500);
}
}
// description
if (config.description !== undefined) {
if (typeof config.description === 'string') {
validated.description = config.description.slice(0, 500);
}
}
// folders / excludeFolders / excludeFiles — validated as string arrays
for (const field of ['folders', 'excludeFolders', 'excludeFiles'] as const) {
if (config[field] !== undefined) {
if (!Array.isArray(config[field])) {
warnings.push(`${field} must be an array, ignoring`);
} else {
validated[field] = (config[field] as unknown[])
.filter((item): item is string => {
if (typeof item !== 'string') {
warnings.push(`${field} entry must be a string, skipping: ${item}`);
return false;
}
return true;
})
.slice(0, field === 'excludeFiles' ? 100 : 50);
}
}
}
// folders / excludeFolders / excludeFiles — validated as string arrays
for (const field of ['folders', 'excludeFolders', 'excludeFiles'] as const) {
if (config[field] !== undefined) {
if (!Array.isArray(config[field])) {
warnings.push(`${field} must be an array, ignoring`);
} else {
validated[field] = (config[field] as unknown[])
.filter((item): item is string => {
if (typeof item !== 'string') {
warnings.push(`${field} entry must be a string, skipping: ${item}`);
return false;
}
return true;
})
.slice(0, field === 'excludeFiles' ? 100 : 50);
}
}
}
// rules
if (config.rules !== undefined) {
if (Array.isArray(config.rules)) {
validated.rules = (config.rules as unknown[])
.filter((r): r is string => typeof r === 'string' && r.length >= 5)
.map(r => r.slice(0, 500))
.slice(0, 20);
}
}
// rules
if (config.rules !== undefined) {
if (Array.isArray(config.rules)) {
validated.rules = (config.rules as unknown[])
.filter((r): r is string => typeof r === 'string' && r.length >= 5)
.map((r) => r.slice(0, 500))
.slice(0, 20);
}
}
// previousVersions
if (config.previousVersions !== undefined) {
if (Array.isArray(config.previousVersions)) {
validated.previousVersions = (config.previousVersions as unknown[])
.filter((v): v is { tag: string; title: string } =>
typeof v === 'object' && v !== null &&
typeof (v as Record<string, unknown>).tag === 'string' &&
typeof (v as Record<string, unknown>).title === 'string'
)
.slice(0, 50);
}
}
// previousVersions
if (config.previousVersions !== undefined) {
if (Array.isArray(config.previousVersions)) {
validated.previousVersions = (config.previousVersions as unknown[])
.filter(
(v): v is { tag: string; title: string } =>
typeof v === 'object' &&
v !== null &&
typeof (v as Record<string, unknown>).tag === 'string' &&
typeof (v as Record<string, unknown>).title === 'string'
)
.slice(0, 50);
}
}
return {
config: validated,
source: filename.startsWith('trueref') ? 'trueref.json' : 'context7.json',
warnings,
};
return {
config: validated,
source: filename.startsWith('trueref') ? 'trueref.json' : 'context7.json',
warnings
};
}
```
@@ -219,21 +221,15 @@ When `query-docs` returns results, `rules` from `repository_configs` are prepend
```typescript
// In formatters.ts
function buildContextResponse(
snippets: Snippet[],
config: RepositoryConfig | null
): string {
const parts: string[] = [];
function buildContextResponse(snippets: Snippet[], config: RepositoryConfig | null): string {
const parts: string[] = [];
if (config?.rules?.length) {
parts.push(
'## Library Best Practices\n' +
config.rules.map(r => `- ${r}`).join('\n')
);
}
if (config?.rules?.length) {
parts.push('## Library Best Practices\n' + config.rules.map((r) => `- ${r}`).join('\n'));
}
// ... append snippet content
return parts.join('\n\n---\n\n');
// ... append snippet content
return parts.join('\n\n---\n\n');
}
```

108
docs/features/TRUEREF-0014.md
View File

@@ -45,34 +45,37 @@ Examples:
### `GET /api/v1/libs/:id/versions`
Response `200`:
```json
{
"versions": [
{
"id": "/facebook/react/v18.3.0",
"repositoryId": "/facebook/react",
"tag": "v18.3.0",
"title": "React v18.3.0",
"state": "indexed",
"totalSnippets": 892,
"indexedAt": "2026-03-22T10:00:00Z"
}
]
"versions": [
{
"id": "/facebook/react/v18.3.0",
"repositoryId": "/facebook/react",
"tag": "v18.3.0",
"title": "React v18.3.0",
"state": "indexed",
"totalSnippets": 892,
"indexedAt": "2026-03-22T10:00:00Z"
}
]
}
```
### `POST /api/v1/libs/:id/versions`
Request body:
```json
{
"tag": "v18.3.0",
"title": "React v18.3.0",
"autoIndex": true
"tag": "v18.3.0",
"title": "React v18.3.0",
"autoIndex": true
}
```
Response `201`:
```json
{
"version": { ...RepositoryVersion },
@@ -96,23 +99,22 @@ Response `202` with job details.
```typescript
async function listGitHubTags(
owner: string,
repo: string,
token?: string
owner: string,
repo: string,
token?: string
): Promise<Array<{ name: string; commit: { sha: string } }>> {
const headers: Record<string, string> = {
'Accept': 'application/vnd.github.v3+json',
'User-Agent': 'TrueRef/1.0',
};
if (token) headers['Authorization'] = `Bearer ${token}`;
const headers: Record<string, string> = {
Accept: 'application/vnd.github.v3+json',
'User-Agent': 'TrueRef/1.0'
};
if (token) headers['Authorization'] = `Bearer ${token}`;
const response = await fetch(
`https://api.github.com/repos/${owner}/${repo}/tags?per_page=100`,
{ headers }
);
const response = await fetch(`https://api.github.com/repos/${owner}/${repo}/tags?per_page=100`, {
headers
});
if (!response.ok) throw new GitHubApiError(response.status);
return response.json();
if (!response.ok) throw new GitHubApiError(response.status);
return response.json();
}
```
@@ -124,28 +126,26 @@ In the search/context endpoints, the `libraryId` is parsed to extract the option
```typescript
function resolveSearchTarget(libraryId: string): {
repositoryId: string;
versionId?: string;
repositoryId: string;
versionId?: string;
} {
const { repositoryId, version } = parseLibraryId(libraryId);
const { repositoryId, version } = parseLibraryId(libraryId);
if (!version) {
// Query default branch: versionId = NULL
return { repositoryId };
}
if (!version) {
// Query default branch: versionId = NULL
return { repositoryId };
}
// Look up versionId from tag
const versionRecord = db.prepare(
`SELECT id FROM repository_versions WHERE repository_id = ? AND tag = ?`
).get(repositoryId, version) as { id: string } | undefined;
// Look up versionId from tag
const versionRecord = db
.prepare(`SELECT id FROM repository_versions WHERE repository_id = ? AND tag = ?`)
.get(repositoryId, version) as { id: string } | undefined;
if (!versionRecord) {
throw new NotFoundError(
`Version "${version}" not found for library "${repositoryId}"`
);
}
if (!versionRecord) {
throw new NotFoundError(`Version "${version}" not found for library "${repositoryId}"`);
}
return { repositoryId, versionId: versionRecord.id };
return { repositoryId, versionId: versionRecord.id };
}
```
@@ -157,20 +157,20 @@ Snippets with `version_id IS NULL` belong to the default branch; snippets with a
```typescript
export class VersionService {
constructor(private db: BetterSQLite3.Database) {}
constructor(private db: BetterSQLite3.Database) {}
list(repositoryId: string): RepositoryVersion[]
list(repositoryId: string): RepositoryVersion[];
add(repositoryId: string, tag: string, title?: string): RepositoryVersion
add(repositoryId: string, tag: string, title?: string): RepositoryVersion;
remove(repositoryId: string, tag: string): void
remove(repositoryId: string, tag: string): void;
getByTag(repositoryId: string, tag: string): RepositoryVersion | null
getByTag(repositoryId: string, tag: string): RepositoryVersion | null;
registerFromConfig(
repositoryId: string,
previousVersions: { tag: string; title: string }[]
): RepositoryVersion[]
registerFromConfig(
repositoryId: string,
previousVersions: { tag: string; title: string }[]
): RepositoryVersion[];
}
```

372
docs/features/TRUEREF-0015.md
View File

@@ -49,79 +49,79 @@ Implement the main web interface for managing repositories. Built with SvelteKit
```svelte
<!-- src/lib/components/RepositoryCard.svelte -->
<script lang="ts">
import type { Repository } from '$lib/types';
import type { Repository } from '$lib/types';
let { repo, onReindex, onDelete } = $props<{
repo: Repository;
onReindex: (id: string) => void;
onDelete: (id: string) => void;
}>();
let { repo, onReindex, onDelete } = $props<{
repo: Repository;
onReindex: (id: string) => void;
onDelete: (id: string) => void;
}>();
const stateColors = {
pending: 'bg-gray-100 text-gray-600',
indexing: 'bg-blue-100 text-blue-700',
indexed: 'bg-green-100 text-green-700',
error: 'bg-red-100 text-red-700',
};
const stateColors = {
pending: 'bg-gray-100 text-gray-600',
indexing: 'bg-blue-100 text-blue-700',
indexed: 'bg-green-100 text-green-700',
error: 'bg-red-100 text-red-700'
};
const stateLabels = {
pending: 'Pending',
indexing: 'Indexing...',
indexed: 'Indexed',
error: 'Error',
};
const stateLabels = {
pending: 'Pending',
indexing: 'Indexing...',
indexed: 'Indexed',
error: 'Error'
};
</script>
<div class="rounded-xl border border-gray-200 bg-white p-5 shadow-sm">
<div class="flex items-start justify-between">
<div>
<h3 class="font-semibold text-gray-900">{repo.title}</h3>
<p class="mt-0.5 font-mono text-sm text-gray-500">{repo.id}</p>
</div>
<span class="rounded-full px-2.5 py-0.5 text-xs font-medium {stateColors[repo.state]}">
{stateLabels[repo.state]}
</span>
</div>
<div class="flex items-start justify-between">
<div>
<h3 class="font-semibold text-gray-900">{repo.title}</h3>
<p class="mt-0.5 font-mono text-sm text-gray-500">{repo.id}</p>
</div>
<span class="rounded-full px-2.5 py-0.5 text-xs font-medium {stateColors[repo.state]}">
{stateLabels[repo.state]}
</span>
</div>
{#if repo.description}
<p class="mt-2 line-clamp-2 text-sm text-gray-600">{repo.description}</p>
{/if}
{#if repo.description}
<p class="mt-2 line-clamp-2 text-sm text-gray-600">{repo.description}</p>
{/if}
<div class="mt-4 flex gap-4 text-sm text-gray-500">
<span>{repo.totalSnippets.toLocaleString()} snippets</span>
<span>·</span>
<span>Trust: {repo.trustScore.toFixed(1)}/10</span>
{#if repo.stars}
<span>·</span>
<span>★ {repo.stars.toLocaleString()}</span>
{/if}
</div>
<div class="mt-4 flex gap-4 text-sm text-gray-500">
<span>{repo.totalSnippets.toLocaleString()} snippets</span>
<span>·</span>
<span>Trust: {repo.trustScore.toFixed(1)}/10</span>
{#if repo.stars}
<span>·</span>
<span>★ {repo.stars.toLocaleString()}</span>
{/if}
</div>
{#if repo.state === 'error'}
<p class="mt-2 text-xs text-red-600">Indexing failed. Check jobs for details.</p>
{/if}
{#if repo.state === 'error'}
<p class="mt-2 text-xs text-red-600">Indexing failed. Check jobs for details.</p>
{/if}
<div class="mt-4 flex gap-2">
<button
onclick={() => onReindex(repo.id)}
class="rounded-lg bg-blue-600 px-3 py-1.5 text-sm text-white hover:bg-blue-700"
disabled={repo.state === 'indexing'}
>
{repo.state === 'indexing' ? 'Indexing...' : 'Re-index'}
</button>
<a
href="/repos/{encodeURIComponent(repo.id)}"
class="rounded-lg border border-gray-200 px-3 py-1.5 text-sm text-gray-700 hover:bg-gray-50"
>
Details
</a>
<button
onclick={() => onDelete(repo.id)}
class="ml-auto rounded-lg px-3 py-1.5 text-sm text-red-600 hover:bg-red-50"
>
Delete
</button>
</div>
<div class="mt-4 flex gap-2">
<button
onclick={() => onReindex(repo.id)}
class="rounded-lg bg-blue-600 px-3 py-1.5 text-sm text-white hover:bg-blue-700"
disabled={repo.state === 'indexing'}
>
{repo.state === 'indexing' ? 'Indexing...' : 'Re-index'}
</button>
<a
href="/repos/{encodeURIComponent(repo.id)}"
class="rounded-lg border border-gray-200 px-3 py-1.5 text-sm text-gray-700 hover:bg-gray-50"
>
Details
</a>
<button
onclick={() => onDelete(repo.id)}
class="ml-auto rounded-lg px-3 py-1.5 text-sm text-red-600 hover:bg-red-50"
>
Delete
</button>
</div>
</div>
```
@@ -132,98 +132,104 @@ Implement the main web interface for managing repositories. Built with SvelteKit
```svelte
<!-- src/lib/components/AddRepositoryModal.svelte -->
<script lang="ts">
let { onClose, onAdded } = $props<{
onClose: () => void;
onAdded: () => void;
}>();
let { onClose, onAdded } = $props<{
onClose: () => void;
onAdded: () => void;
}>();
let source = $state<'github' | 'local'>('github');
let sourceUrl = $state('');
let githubToken = $state('');
let loading = $state(false);
let error = $state<string | null>(null);
let source = $state<'github' | 'local'>('github');
let sourceUrl = $state('');
let githubToken = $state('');
let loading = $state(false);
let error = $state<string | null>(null);
async function handleSubmit() {
loading = true;
error = null;
try {
const res = await fetch('/api/v1/libs', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ source, sourceUrl, githubToken: githubToken || undefined }),
});
if (!res.ok) {
const data = await res.json();
throw new Error(data.error ?? 'Failed to add repository');
}
onAdded();
onClose();
} catch (e) {
error = (e as Error).message;
} finally {
loading = false;
}
}
async function handleSubmit() {
loading = true;
error = null;
try {
const res = await fetch('/api/v1/libs', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ source, sourceUrl, githubToken: githubToken || undefined })
});
if (!res.ok) {
const data = await res.json();
throw new Error(data.error ?? 'Failed to add repository');
}
onAdded();
onClose();
} catch (e) {
error = (e as Error).message;
} finally {
loading = false;
}
}
</script>
<dialog class="modal" open>
<div class="modal-box max-w-md">
<h2 class="mb-4 text-lg font-semibold">Add Repository</h2>
<div class="modal-box max-w-md">
<h2 class="mb-4 text-lg font-semibold">Add Repository</h2>
<div class="mb-4 flex gap-2">
<button
class="flex-1 rounded-lg py-2 text-sm {source === 'github' ? 'bg-blue-600 text-white' : 'border border-gray-200 text-gray-700'}"
onclick={() => source = 'github'}
>GitHub</button>
<button
class="flex-1 rounded-lg py-2 text-sm {source === 'local' ? 'bg-blue-600 text-white' : 'border border-gray-200 text-gray-700'}"
onclick={() => source = 'local'}
>Local Path</button>
</div>
<div class="mb-4 flex gap-2">
<button
class="flex-1 rounded-lg py-2 text-sm {source === 'github'
? 'bg-blue-600 text-white'
: 'border border-gray-200 text-gray-700'}"
onclick={() => (source = 'github')}>GitHub</button
>
<button
class="flex-1 rounded-lg py-2 text-sm {source === 'local'
? 'bg-blue-600 text-white'
: 'border border-gray-200 text-gray-700'}"
onclick={() => (source = 'local')}>Local Path</button
>
</div>
<label class="block">
<span class="text-sm font-medium text-gray-700">
{source === 'github' ? 'GitHub URL' : 'Absolute Path'}
</span>
<input
type="text"
bind:value={sourceUrl}
placeholder={source === 'github'
? 'https://github.com/facebook/react'
: '/home/user/projects/my-sdk'}
class="mt-1 w-full rounded-lg border border-gray-300 px-3 py-2 text-sm"
/>
</label>
<label class="block">
<span class="text-sm font-medium text-gray-700">
{source === 'github' ? 'GitHub URL' : 'Absolute Path'}
</span>
<input
type="text"
bind:value={sourceUrl}
placeholder={source === 'github'
? 'https://github.com/facebook/react'
: '/home/user/projects/my-sdk'}
class="mt-1 w-full rounded-lg border border-gray-300 px-3 py-2 text-sm"
/>
</label>
{#if source === 'github'}
<label class="mt-3 block">
<span class="text-sm font-medium text-gray-700">GitHub Token (optional, for private repos)</span>
<input
type="password"
bind:value={githubToken}
placeholder="ghp_..."
class="mt-1 w-full rounded-lg border border-gray-300 px-3 py-2 text-sm"
/>
</label>
{/if}
{#if source === 'github'}
<label class="mt-3 block">
<span class="text-sm font-medium text-gray-700"
>GitHub Token (optional, for private repos)</span
>
<input
type="password"
bind:value={githubToken}
placeholder="ghp_..."
class="mt-1 w-full rounded-lg border border-gray-300 px-3 py-2 text-sm"
/>
</label>
{/if}
{#if error}
<p class="mt-3 text-sm text-red-600">{error}</p>
{/if}
{#if error}
<p class="mt-3 text-sm text-red-600">{error}</p>
{/if}
<div class="mt-6 flex justify-end gap-3">
<button onclick={onClose} class="rounded-lg border border-gray-200 px-4 py-2 text-sm">
Cancel
</button>
<button
onclick={handleSubmit}
disabled={loading || !sourceUrl}
class="rounded-lg bg-blue-600 px-4 py-2 text-sm text-white disabled:opacity-50"
>
{loading ? 'Adding...' : 'Add & Index'}
</button>
</div>
</div>
<div class="mt-6 flex justify-end gap-3">
<button onclick={onClose} class="rounded-lg border border-gray-200 px-4 py-2 text-sm">
Cancel
</button>
<button
onclick={handleSubmit}
disabled={loading || !sourceUrl}
class="rounded-lg bg-blue-600 px-4 py-2 text-sm text-white disabled:opacity-50"
>
{loading ? 'Adding...' : 'Add & Index'}
</button>
</div>
</div>
</dialog>
```
@@ -234,48 +240,48 @@ Implement the main web interface for managing repositories. Built with SvelteKit
```svelte
<!-- src/lib/components/IndexingProgress.svelte -->
<script lang="ts">
import { onMount, onDestroy } from 'svelte';
import type { IndexingJob } from '$lib/types';
import { onMount, onDestroy } from 'svelte';
import type { IndexingJob } from '$lib/types';
let { jobId } = $props<{ jobId: string }>();
let job = $state<IndexingJob | null>(null);
let interval: ReturnType<typeof setInterval>;
let { jobId } = $props<{ jobId: string }>();
let job = $state<IndexingJob | null>(null);
let interval: ReturnType<typeof setInterval>;
async function pollJob() {
const res = await fetch(`/api/v1/jobs/${jobId}`);
if (res.ok) {
const data = await res.json();
job = data.job;
if (job?.status === 'done' || job?.status === 'failed') {
clearInterval(interval);
}
}
}
async function pollJob() {
const res = await fetch(`/api/v1/jobs/${jobId}`);
if (res.ok) {
const data = await res.json();
job = data.job;
if (job?.status === 'done' || job?.status === 'failed') {
clearInterval(interval);
}
}
}
onMount(() => {
pollJob();
interval = setInterval(pollJob, 2000);
});
onMount(() => {
pollJob();
interval = setInterval(pollJob, 2000);
});
onDestroy(() => clearInterval(interval));
onDestroy(() => clearInterval(interval));
</script>
{#if job}
<div class="mt-2">
<div class="flex justify-between text-xs text-gray-500">
<span>{job.processedFiles} / {job.totalFiles} files</span>
<span>{job.progress}%</span>
</div>
<div class="mt-1 h-1.5 w-full rounded-full bg-gray-200">
<div
class="h-1.5 rounded-full bg-blue-600 transition-all"
style="width: {job.progress}%"
></div>
</div>
{#if job.status === 'failed'}
<p class="mt-1 text-xs text-red-600">{job.error}</p>
{/if}
</div>
<div class="mt-2">
<div class="flex justify-between text-xs text-gray-500">
<span>{job.processedFiles} / {job.totalFiles} files</span>
<span>{job.progress}%</span>
</div>
<div class="mt-1 h-1.5 w-full rounded-full bg-gray-200">
<div
class="h-1.5 rounded-full bg-blue-600 transition-all"
style="width: {job.progress}%"
></div>
</div>
{#if job.status === 'failed'}
<p class="mt-1 text-xs text-red-600">{job.error}</p>
{/if}
</div>
{/if}
```
@@ -288,9 +294,9 @@ Implement the main web interface for managing repositories. Built with SvelteKit
import type { PageServerLoad } from './$types';
export const load: PageServerLoad = async ({ fetch }) => {
const res = await fetch('/api/v1/libs');
const data = await res.json();
return { repositories: data.libraries };
const res = await fetch('/api/v1/libs');
const data = await res.json();
return { repositories: data.libraries };
};
```

164
docs/features/TRUEREF-0016.md
View File

@@ -57,25 +57,31 @@ An interactive search interface within the web UI that lets users test the docum
```svelte
<!-- src/lib/components/search/LibraryResult.svelte -->
<script lang="ts">
let { result, onSelect } = $props<{
result: { id: string; title: string; description: string; totalSnippets: number; trustScore: number };
onSelect: (id: string) => void;
}>();
let { result, onSelect } = $props<{
result: {
id: string;
title: string;
description: string;
totalSnippets: number;
trustScore: number;
};
onSelect: (id: string) => void;
}>();
</script>
<button
onclick={() => onSelect(result.id)}
class="w-full rounded-xl border border-gray-200 bg-white p-4 text-left shadow-sm hover:border-blue-300 hover:shadow-md transition-all"
onclick={() => onSelect(result.id)}
class="w-full rounded-xl border border-gray-200 bg-white p-4 text-left shadow-sm transition-all hover:border-blue-300 hover:shadow-md"
>
<div class="flex items-center justify-between">
<span class="font-semibold text-gray-900">{result.title}</span>
<span class="text-xs text-gray-400">Trust {result.trustScore.toFixed(1)}/10</span>
</div>
<p class="font-mono text-xs text-gray-400">{result.id}</p>
{#if result.description}
<p class="mt-1.5 text-sm text-gray-600 line-clamp-2">{result.description}</p>
{/if}
<p class="mt-2 text-xs text-gray-400">{result.totalSnippets.toLocaleString()} snippets</p>
<div class="flex items-center justify-between">
<span class="font-semibold text-gray-900">{result.title}</span>
<span class="text-xs text-gray-400">Trust {result.trustScore.toFixed(1)}/10</span>
</div>
<p class="font-mono text-xs text-gray-400">{result.id}</p>
{#if result.description}
<p class="mt-1.5 line-clamp-2 text-sm text-gray-600">{result.description}</p>
{/if}
<p class="mt-2 text-xs text-gray-400">{result.totalSnippets.toLocaleString()} snippets</p>
</button>
```
@@ -86,37 +92,39 @@ An interactive search interface within the web UI that lets users test the docum
```svelte
<!-- src/lib/components/search/SnippetCard.svelte -->
<script lang="ts">
import type { Snippet } from '$lib/types';
import type { Snippet } from '$lib/types';
let { snippet } = $props<{ snippet: Snippet }>();
let { snippet } = $props<{ snippet: Snippet }>();
</script>
<div class="rounded-xl border border-gray-200 bg-white overflow-hidden">
<div class="flex items-center justify-between border-b border-gray-100 px-4 py-2.5">
<div class="flex items-center gap-2">
{#if snippet.type === 'code'}
<span class="rounded bg-purple-100 px-1.5 py-0.5 text-xs text-purple-700">code</span>
{:else}
<span class="rounded bg-blue-100 px-1.5 py-0.5 text-xs text-blue-700">info</span>
{/if}
{#if snippet.title}
<span class="text-sm font-medium text-gray-800">{snippet.title}</span>
{/if}
</div>
<span class="text-xs text-gray-400">{snippet.tokenCount} tokens</span>
</div>
<div class="overflow-hidden rounded-xl border border-gray-200 bg-white">
<div class="flex items-center justify-between border-b border-gray-100 px-4 py-2.5">
<div class="flex items-center gap-2">
{#if snippet.type === 'code'}
<span class="rounded bg-purple-100 px-1.5 py-0.5 text-xs text-purple-700">code</span>
{:else}
<span class="rounded bg-blue-100 px-1.5 py-0.5 text-xs text-blue-700">info</span>
{/if}
{#if snippet.title}
<span class="text-sm font-medium text-gray-800">{snippet.title}</span>
{/if}
</div>
<span class="text-xs text-gray-400">{snippet.tokenCount} tokens</span>
</div>
{#if snippet.breadcrumb}
<p class="bg-gray-50 px-4 py-1.5 text-xs text-gray-500 italic">{snippet.breadcrumb}</p>
{/if}
{#if snippet.breadcrumb}
<p class="bg-gray-50 px-4 py-1.5 text-xs text-gray-500 italic">{snippet.breadcrumb}</p>
{/if}
<div class="p-4">
{#if snippet.type === 'code'}
<pre class="overflow-x-auto rounded bg-gray-950 p-4 text-sm text-gray-100"><code>{snippet.content}</code></pre>
{:else}
<div class="prose prose-sm max-w-none text-gray-700">{snippet.content}</div>
{/if}
</div>
<div class="p-4">
{#if snippet.type === 'code'}
<pre class="overflow-x-auto rounded bg-gray-950 p-4 text-sm text-gray-100"><code
>{snippet.content}</code
></pre>
{:else}
<div class="prose prose-sm max-w-none text-gray-700">{snippet.content}</div>
{/if}
</div>
</div>
```
@@ -127,44 +135,44 @@ An interactive search interface within the web UI that lets users test the docum
```svelte
<!-- src/routes/search/+page.svelte -->
<script lang="ts">
import { page } from '$app/stores';
import { goto } from '$app/navigation';
import { page } from '$app/stores';
import { goto } from '$app/navigation';
let libraryName = $state('');
let selectedLibraryId = $state<string | null>(null);
let query = $state('');
let libraryResults = $state<LibrarySearchResult[]>([]);
let snippets = $state<Snippet[]>([]);
let loadingLibraries = $state(false);
let loadingSnippets = $state(false);
let libraryName = $state('');
let selectedLibraryId = $state<string | null>(null);
let query = $state('');
let libraryResults = $state<LibrarySearchResult[]>([]);
let snippets = $state<Snippet[]>([]);
let loadingLibraries = $state(false);
let loadingSnippets = $state(false);
async function searchLibraries() {
loadingLibraries = true;
const res = await fetch(
`/api/v1/libs/search?libraryName=${encodeURIComponent(libraryName)}&query=${encodeURIComponent(query)}`
);
const data = await res.json();
libraryResults = data.results;
loadingLibraries = false;
}
async function searchLibraries() {
loadingLibraries = true;
const res = await fetch(
`/api/v1/libs/search?libraryName=${encodeURIComponent(libraryName)}&query=${encodeURIComponent(query)}`
);
const data = await res.json();
libraryResults = data.results;
loadingLibraries = false;
}
async function searchDocs() {
if (!selectedLibraryId) return;
loadingSnippets = true;
const url = new URL('/api/v1/context', window.location.origin);
url.searchParams.set('libraryId', selectedLibraryId);
url.searchParams.set('query', query);
const res = await fetch(url);
const data = await res.json();
snippets = data.snippets;
loadingSnippets = false;
async function searchDocs() {
if (!selectedLibraryId) return;
loadingSnippets = true;
const url = new URL('/api/v1/context', window.location.origin);
url.searchParams.set('libraryId', selectedLibraryId);
url.searchParams.set('query', query);
const res = await fetch(url);
const data = await res.json();
snippets = data.snippets;
loadingSnippets = false;
// Update URL
goto(`/search?lib=${encodeURIComponent(selectedLibraryId)}&q=${encodeURIComponent(query)}`, {
replaceState: true,
keepFocus: true,
});
}
// Update URL
goto(`/search?lib=${encodeURIComponent(selectedLibraryId)}&q=${encodeURIComponent(query)}`, {
replaceState: true,
keepFocus: true
});
}
</script>
```
@@ -177,9 +185,9 @@ Use a minimal, zero-dependency approach for v1 — wrap code blocks in `<pre><co
```typescript
// Optional: lazy-load highlight.js only when code snippets are present
async function highlightCode(code: string, language: string): Promise<string> {
const hljs = await import('highlight.js/lib/core');
// Register only needed languages
return hljs.highlight(code, { language }).value;
const hljs = await import('highlight.js/lib/core');
// Register only needed languages
return hljs.highlight(code, { language }).value;
}
```

81
docs/features/TRUEREF-0017.md
View File

@@ -30,39 +30,39 @@ Optimize re-indexing by skipping files that haven't changed since the last index
```typescript
interface FileDiff {
added: CrawledFile[]; // new files not in DB
modified: CrawledFile[]; // files with changed checksum
deleted: string[]; // file paths in DB but not in crawl
unchanged: string[]; // file paths with matching checksum
added: CrawledFile[]; // new files not in DB
modified: CrawledFile[]; // files with changed checksum
deleted: string[]; // file paths in DB but not in crawl
unchanged: string[]; // file paths with matching checksum
}
function computeDiff(
crawledFiles: CrawledFile[],
existingDocs: Document[] // documents currently in DB for this repo
crawledFiles: CrawledFile[],
existingDocs: Document[] // documents currently in DB for this repo
): FileDiff {
const existingMap = new Map(existingDocs.map(d => [d.filePath, d]));
const crawledMap = new Map(crawledFiles.map(f => [f.path, f]));
const existingMap = new Map(existingDocs.map((d) => [d.filePath, d]));
const crawledMap = new Map(crawledFiles.map((f) => [f.path, f]));
const added: CrawledFile[] = [];
const modified: CrawledFile[] = [];
const unchanged: string[] = [];
const added: CrawledFile[] = [];
const modified: CrawledFile[] = [];
const unchanged: string[] = [];
for (const file of crawledFiles) {
const existing = existingMap.get(file.path);
if (!existing) {
added.push(file);
} else if (existing.checksum !== file.sha) {
modified.push(file);
} else {
unchanged.push(file.path);
}
}
for (const file of crawledFiles) {
const existing = existingMap.get(file.path);
if (!existing) {
added.push(file);
} else if (existing.checksum !== file.sha) {
modified.push(file);
} else {
unchanged.push(file.path);
}
}
const deleted = existingDocs
.filter(doc => !crawledMap.has(doc.filePath))
.map(doc => doc.filePath);
const deleted = existingDocs
.filter((doc) => !crawledMap.has(doc.filePath))
.map((doc) => doc.filePath);
return { added, modified, deleted, unchanged };
return { added, modified, deleted, unchanged };
}
```
@@ -78,7 +78,7 @@ const diff = computeDiff(crawledResult.files, existingDocs);
// Log diff summary
this.updateJob(job.id, {
totalFiles: crawledResult.files.length,
totalFiles: crawledResult.files.length
});
// Process only changed/new files
@@ -89,29 +89,29 @@ const docIdsToDelete: string[] = [];
// Map modified files to their existing document IDs for deletion
for (const file of diff.modified) {
const existing = existingDocs.find(d => d.filePath === file.path);
if (existing) docIdsToDelete.push(existing.id);
const existing = existingDocs.find((d) => d.filePath === file.path);
if (existing) docIdsToDelete.push(existing.id);
}
// Map deleted file paths to document IDs
for (const filePath of diff.deleted) {
const existing = existingDocs.find(d => d.filePath === filePath);
if (existing) docIdsToDelete.push(existing.id);
const existing = existingDocs.find((d) => d.filePath === filePath);
if (existing) docIdsToDelete.push(existing.id);
}
// Parse new/modified files
for (const [i, file] of filesToProcess.entries()) {
const docId = crypto.randomUUID();
newDocuments.push({ id: docId, ...buildDocument(file, repo.id, job.versionId) });
newSnippets.push(...parseFile(file, { repositoryId: repo.id, documentId: docId }));
const docId = crypto.randomUUID();
newDocuments.push({ id: docId, ...buildDocument(file, repo.id, job.versionId) });
newSnippets.push(...parseFile(file, { repositoryId: repo.id, documentId: docId }));
// Count ALL files (including skipped) in progress
const totalProcessed = diff.unchanged.length + i + 1;
const progress = Math.round((totalProcessed / crawledResult.files.length) * 80);
this.updateJob(job.id, {
processedFiles: totalProcessed,
progress,
});
// Count ALL files (including skipped) in progress
const totalProcessed = diff.unchanged.length + i + 1;
const progress = Math.round((totalProcessed / crawledResult.files.length) * 80);
this.updateJob(job.id, {
processedFiles: totalProcessed,
progress
});
}
// Atomic replacement of only changed documents
@@ -123,6 +123,7 @@ this.replaceSnippets(repo.id, docIdsToDelete, newDocuments, newSnippets);
## Performance Impact
For a typical repository with 1,000 files where 50 changed:
- **Without incremental**: 1,000 files parsed + 1,000 embed batches
- **With incremental**: 50 files parsed + 50 embed batches
- Estimated speedup: ~20x for re-indexing

284
docs/features/TRUEREF-0018.md
View File

@@ -32,24 +32,24 @@ A settings page within the web UI that allows users to configure the embedding p
```typescript
const PROVIDER_PRESETS = [
{
name: 'OpenAI',
baseUrl: 'https://api.openai.com/v1',
model: 'text-embedding-3-small',
dimensions: 1536,
},
{
name: 'Ollama (local)',
baseUrl: 'http://localhost:11434/v1',
model: 'nomic-embed-text',
dimensions: 768,
},
{
name: 'Azure OpenAI',
baseUrl: 'https://{resource}.openai.azure.com/openai/deployments/{deployment}/v1',
model: 'text-embedding-3-small',
dimensions: 1536,
},
{
name: 'OpenAI',
baseUrl: 'https://api.openai.com/v1',
model: 'text-embedding-3-small',
dimensions: 1536
},
{
name: 'Ollama (local)',
baseUrl: 'http://localhost:11434/v1',
model: 'nomic-embed-text',
dimensions: 768
},
{
name: 'Azure OpenAI',
baseUrl: 'https://{resource}.openai.azure.com/openai/deployments/{deployment}/v1',
model: 'text-embedding-3-small',
dimensions: 1536
}
];
```
@@ -60,133 +60,157 @@ const PROVIDER_PRESETS = [
```svelte
<!-- src/routes/settings/+page.svelte -->
<script lang="ts">
let provider = $state<'none' | 'openai' | 'local'>('none');
let baseUrl = $state('https://api.openai.com/v1');
let apiKey = $state('');
let model = $state('text-embedding-3-small');
let dimensions = $state<number | undefined>(1536);
let testStatus = $state<'idle' | 'testing' | 'ok' | 'error'>('idle');
let testError = $state<string | null>(null);
let saving = $state(false);
let provider = $state<'none' | 'openai' | 'local'>('none');
let baseUrl = $state('https://api.openai.com/v1');
let apiKey = $state('');
let model = $state('text-embedding-3-small');
let dimensions = $state<number | undefined>(1536);
let testStatus = $state<'idle' | 'testing' | 'ok' | 'error'>('idle');
let testError = $state<string | null>(null);
let saving = $state(false);
async function testConnection() {
testStatus = 'testing';
testError = null;
try {
const res = await fetch('/api/v1/settings/embedding/test', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ provider, openai: { baseUrl, apiKey, model, dimensions } }),
});
if (res.ok) {
testStatus = 'ok';
} else {
const data = await res.json();
testStatus = 'error';
testError = data.error;
}
} catch (e) {
testStatus = 'error';
testError = (e as Error).message;
}
}
async function testConnection() {
testStatus = 'testing';
testError = null;
try {
const res = await fetch('/api/v1/settings/embedding/test', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ provider, openai: { baseUrl, apiKey, model, dimensions } })
});
if (res.ok) {
testStatus = 'ok';
} else {
const data = await res.json();
testStatus = 'error';
testError = data.error;
}
} catch (e) {
testStatus = 'error';
testError = (e as Error).message;
}
}
async function save() {
saving = true;
await fetch('/api/v1/settings/embedding', {
method: 'PUT',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ provider, openai: { baseUrl, apiKey, model, dimensions } }),
});
saving = false;
}
async function save() {
saving = true;
await fetch('/api/v1/settings/embedding', {
method: 'PUT',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ provider, openai: { baseUrl, apiKey, model, dimensions } })
});
saving = false;
}
</script>
<div class="mx-auto max-w-2xl py-8">
<h1 class="mb-6 text-2xl font-bold text-gray-900">Settings</h1>
<h1 class="mb-6 text-2xl font-bold text-gray-900">Settings</h1>
<section class="rounded-xl border border-gray-200 bg-white p-6">
<h2 class="mb-1 text-lg font-semibold">Embedding Provider</h2>
<p class="mb-4 text-sm text-gray-500">
Embeddings enable semantic search. Without them, only keyword search (FTS5) is used.
</p>
<section class="rounded-xl border border-gray-200 bg-white p-6">
<h2 class="mb-1 text-lg font-semibold">Embedding Provider</h2>
<p class="mb-4 text-sm text-gray-500">
Embeddings enable semantic search. Without them, only keyword search (FTS5) is used.
</p>
<div class="mb-4 flex gap-2">
{#each ['none', 'openai', 'local'] as p}
<button
onclick={() => provider = p}
class="rounded-lg px-4 py-2 text-sm {provider === p
? 'bg-blue-600 text-white'
: 'border border-gray-200 text-gray-700 hover:bg-gray-50'}"
>
{p === 'none' ? 'None (FTS5 only)' : p === 'openai' ? 'OpenAI-compatible' : 'Local Model'}
</button>
{/each}
</div>
<div class="mb-4 flex gap-2">
{#each ['none', 'openai', 'local'] as p}
<button
onclick={() => (provider = p)}
class="rounded-lg px-4 py-2 text-sm {provider === p
? 'bg-blue-600 text-white'
: 'border border-gray-200 text-gray-700 hover:bg-gray-50'}"
>
{p === 'none' ? 'None (FTS5 only)' : p === 'openai' ? 'OpenAI-compatible' : 'Local Model'}
</button>
{/each}
</div>
{#if provider === 'none'}
<div class="rounded-lg bg-amber-50 border border-amber-200 p-3 text-sm text-amber-700">
Search will use keyword matching only. Results may be less relevant for complex questions.
</div>
{/if}
{#if provider === 'none'}
<div class="rounded-lg border border-amber-200 bg-amber-50 p-3 text-sm text-amber-700">
Search will use keyword matching only. Results may be less relevant for complex questions.
</div>
{/if}
{#if provider === 'openai'}
<div class="space-y-3">
<!-- Preset buttons -->
<div class="flex gap-2 flex-wrap">
{#each PROVIDER_PRESETS as preset}
<button
onclick={() => { baseUrl = preset.baseUrl; model = preset.model; dimensions = preset.dimensions; }}
class="rounded border border-gray-200 px-2.5 py-1 text-xs text-gray-600 hover:bg-gray-50"
>
{preset.name}
</button>
{/each}
</div>
{#if provider === 'openai'}
<div class="space-y-3">
<!-- Preset buttons -->
<div class="flex flex-wrap gap-2">
{#each PROVIDER_PRESETS as preset}
<button
onclick={() => {
baseUrl = preset.baseUrl;
model = preset.model;
dimensions = preset.dimensions;
}}
class="rounded border border-gray-200 px-2.5 py-1 text-xs text-gray-600 hover:bg-gray-50"
>
{preset.name}
</button>
{/each}
</div>
<label class="block">
<span class="text-sm font-medium">Base URL</span>
<input type="text" bind:value={baseUrl} class="mt-1 w-full rounded-lg border px-3 py-2 text-sm" />
</label>
<label class="block">
<span class="text-sm font-medium">Base URL</span>
<input
type="text"
bind:value={baseUrl}
class="mt-1 w-full rounded-lg border px-3 py-2 text-sm"
/>
</label>
<label class="block">
<span class="text-sm font-medium">API Key</span>
<input type="password" bind:value={apiKey} class="mt-1 w-full rounded-lg border px-3 py-2 text-sm" placeholder="sk-..." />
</label>
<label class="block">
<span class="text-sm font-medium">API Key</span>
<input
type="password"
bind:value={apiKey}
class="mt-1 w-full rounded-lg border px-3 py-2 text-sm"
placeholder="sk-..."
/>
</label>
<label class="block">
<span class="text-sm font-medium">Model</span>
<input type="text" bind:value={model} class="mt-1 w-full rounded-lg border px-3 py-2 text-sm" />
</label>
<label class="block">
<span class="text-sm font-medium">Model</span>
<input
type="text"
bind:value={model}
class="mt-1 w-full rounded-lg border px-3 py-2 text-sm"
/>
</label>
<label class="block">
<span class="text-sm font-medium">Dimensions (optional override)</span>
<input type="number" bind:value={dimensions} class="mt-1 w-full rounded-lg border px-3 py-2 text-sm" />
</label>
<label class="block">
<span class="text-sm font-medium">Dimensions (optional override)</span>
<input
type="number"
bind:value={dimensions}
class="mt-1 w-full rounded-lg border px-3 py-2 text-sm"
/>
</label>
<div class="flex items-center gap-3">
<button onclick={testConnection} class="rounded-lg border border-gray-300 px-3 py-1.5 text-sm">
{testStatus === 'testing' ? 'Testing...' : 'Test Connection'}
</button>
{#if testStatus === 'ok'}
<span class="text-sm text-green-600">✓ Connection successful</span>
{:else if testStatus === 'error'}
<span class="text-sm text-red-600">✗ {testError}</span>
{/if}
</div>
</div>
{/if}
<div class="flex items-center gap-3">
<button
onclick={testConnection}
class="rounded-lg border border-gray-300 px-3 py-1.5 text-sm"
>
{testStatus === 'testing' ? 'Testing...' : 'Test Connection'}
</button>
{#if testStatus === 'ok'}
<span class="text-sm text-green-600">✓ Connection successful</span>
{:else if testStatus === 'error'}
<span class="text-sm text-red-600">✗ {testError}</span>
{/if}
</div>
</div>
{/if}
<div class="mt-6 flex justify-end">
<button
onclick={save}
disabled={saving}
class="rounded-lg bg-blue-600 px-4 py-2 text-sm text-white disabled:opacity-50"
>
{saving ? 'Saving...' : 'Save Settings'}
</button>
</div>
</section>
<div class="mt-6 flex justify-end">
<button
onclick={save}
disabled={saving}
class="rounded-lg bg-blue-600 px-4 py-2 text-sm text-white disabled:opacity-50"
>
{saving ? 'Saving...' : 'Save Settings'}
</button>
</div>
</section>
</div>
```

57
docs/features/TRUEREF-0019.md
View File

@@ -80,6 +80,7 @@ git -C /path/to/repo archive <commit-hash> | tar -x -C /tmp/trueref-idx/<repo>-<
```
Advantages over `git checkout` or worktrees:
- Working directory is completely untouched
- No `.git` directory in the output (cleaner for parsing)
- Temp directory deleted after indexing with no git state to clean up
@@ -102,26 +103,26 @@ Allow commit hashes to be pinned explicitly per version, overriding tag resoluti
```json
{
"previousVersions": [
{
"tag": "v2.0.0",
"title": "Version 2.0.0",
"commitHash": "a3f9c12abc..."
}
]
"previousVersions": [
{
"tag": "v2.0.0",
"title": "Version 2.0.0",
"commitHash": "a3f9c12abc..."
}
]
}
```
### Edge Cases
| Case | Handling |
|------|----------|
| Annotated tags | `rev-parse <tag>^{commit}` peels to commit automatically |
| Mutable tags (e.g. `latest`) | Re-resolve on re-index; warn in UI if hash has changed |
| Branch as version | `rev-parse origin/<branch>^{commit}` gives tip; re-resolves on re-index |
| Shallow clone | Run `git fetch --unshallow` before `git archive` if commit is unavailable |
| Submodules | `git archive --recurse-submodules` or document as a known limitation |
| Git LFS | `git lfs pull` required after archive if LFS-tracked files are needed for indexing |
| Case | Handling |
| ---------------------------- | ---------------------------------------------------------------------------------- |
| Annotated tags | `rev-parse <tag>^{commit}` peels to commit automatically |
| Mutable tags (e.g. `latest`) | Re-resolve on re-index; warn in UI if hash has changed |
| Branch as version | `rev-parse origin/<branch>^{commit}` gives tip; re-resolves on re-index |
| Shallow clone | Run `git fetch --unshallow` before `git archive` if commit is unavailable |
| Submodules | `git archive --recurse-submodules` or document as a known limitation |
| Git LFS | `git lfs pull` required after archive if LFS-tracked files are needed for indexing |
### Acceptance Criteria
@@ -169,12 +170,12 @@ fi
Username conventions by server type:
| Server | HTTPS username | Password |
|--------|---------------|----------|
| Bitbucket Server / Data Center | `x-token-auth` | HTTP access token |
| Bitbucket Cloud | account username | App password |
| GitLab (self-hosted or cloud) | `oauth2` | Personal access token |
| GitLab deploy token | `gitlab-deploy-token` | Deploy token secret |
| Server | HTTPS username | Password |
| ------------------------------ | --------------------- | --------------------- |
| Bitbucket Server / Data Center | `x-token-auth` | HTTP access token |
| Bitbucket Cloud | account username | App password |
| GitLab (self-hosted or cloud) | `oauth2` | Personal access token |
| GitLab deploy token | `gitlab-deploy-token` | Deploy token secret |
SSH authentication is also supported and preferred for long-lived deployments. The host SSH configuration (`~/.ssh/config`) handles per-host key selection and travels into the container via volume mount.
@@ -220,7 +221,7 @@ services:
web:
build: .
ports:
- "3000:3000"
- '3000:3000'
volumes:
- trueref-data:/data
- ${USERPROFILE}/.ssh:/root/.ssh:ro
@@ -228,20 +229,20 @@ services:
- ${CORP_CA_CERT}:/certs/corp-ca.crt:ro
environment:
DATABASE_URL: /data/trueref.db
GIT_TOKEN_BITBUCKET: "${BITBUCKET_TOKEN}"
GIT_TOKEN_GITLAB: "${GITLAB_TOKEN}"
BITBUCKET_HOST: "${BITBUCKET_HOST}"
GITLAB_HOST: "${GITLAB_HOST}"
GIT_TOKEN_BITBUCKET: '${BITBUCKET_TOKEN}'
GIT_TOKEN_GITLAB: '${GITLAB_TOKEN}'
BITBUCKET_HOST: '${BITBUCKET_HOST}'
GITLAB_HOST: '${GITLAB_HOST}'
restart: unless-stopped
mcp:
build: .
command: mcp
ports:
- "3001:3001"
- '3001:3001'
environment:
TRUEREF_API_URL: http://web:3000
MCP_PORT: "3001"
MCP_PORT: '3001'
depends_on:
- web
restart: unless-stopped

20
docs/features/TRUEREF-0020.md
View File

@@ -107,16 +107,16 @@ An embedding profile is persisted configuration selecting one provider adapter p
```typescript
interface EmbeddingProfile {
id: string;
providerKind: string;
title: string;
enabled: boolean;
isDefault: boolean;
config: Record<string, unknown>;
model: string;
dimensions: number;
createdAt: number;
updatedAt: number;
id: string;
providerKind: string;
title: string;
enabled: boolean;
isDefault: boolean;
config: Record<string, unknown>;
model: string;
dimensions: number;
createdAt: number;
updatedAt: number;
}
```

6
src/hooks.server.ts
View File

@@ -9,7 +9,11 @@
import { initializeDatabase } from '$lib/server/db/index.js';
import { getClient } from '$lib/server/db/client.js';
import { initializePipeline } from '$lib/server/pipeline/startup.js';
import { EMBEDDING_CONFIG_KEY, createProviderFromConfig, defaultEmbeddingConfig } from '$lib/server/embeddings/factory.js';
import {
EMBEDDING_CONFIG_KEY,
createProviderFromConfig,
defaultEmbeddingConfig
} from '$lib/server/embeddings/factory.js';
import { EmbeddingService } from '$lib/server/embeddings/embedding.service.js';
import type { EmbeddingConfig } from '$lib/server/embeddings/factory.js';
import type { Handle } from '@sveltejs/kit';

10
src/lib/components/AddRepositoryModal.svelte
View File

@@ -115,7 +115,12 @@
/>
{:else}
<div class="mt-1">
<FolderPicker bind:value={sourceUrl} onselect={(p) => { if (!title) title = p.split('/').at(-1) ?? ''; }} />
<FolderPicker
bind:value={sourceUrl}
onselect={(p) => {
if (!title) title = p.split('/').at(-1) ?? '';
}}
/>
</div>
{/if}
</div>
@@ -133,7 +138,8 @@
{#if source === 'github'}
<label class="block">
<span class="text-sm font-medium text-gray-700"
>GitHub Token <span class="font-normal text-gray-500">(optional, for private repos)</span
>GitHub Token <span class="font-normal text-gray-500"
>(optional, for private repos)</span
></span
>
<input

23
src/lib/components/FolderPicker.svelte
View File

@@ -78,9 +78,7 @@
title="Browse folders"
>
<svg class="h-4 w-4" viewBox="0 0 20 20" fill="currentColor">
<path
d="M2 6a2 2 0 012-2h5l2 2h5a2 2 0 012 2v6a2 2 0 01-2 2H4a2 2 0 01-2-2V6z"
/>
<path d="M2 6a2 2 0 012-2h5l2 2h5a2 2 0 012 2v6a2 2 0 01-2 2H4a2 2 0 01-2-2V6z" />
</svg>
Browse
</button>
@@ -94,7 +92,10 @@
class="fixed inset-0 z-[60] flex items-center justify-center bg-black/50 p-4"
onclick={handleBackdropClick}
>
<div class="flex w-full max-w-lg flex-col rounded-xl bg-white shadow-xl" style="max-height: 70vh">
<div
class="flex w-full max-w-lg flex-col rounded-xl bg-white shadow-xl"
style="max-height: 70vh"
>
<!-- Header -->
<div class="flex items-center justify-between border-b border-gray-200 px-4 py-3">
<h3 class="text-sm font-semibold text-gray-900">Select Folder</h3>
@@ -133,11 +134,7 @@
{browsePath}
</span>
{#if loading}
<svg
class="h-4 w-4 animate-spin text-gray-400"
fill="none"
viewBox="0 0 24 24"
>
<svg class="h-4 w-4 animate-spin text-gray-400" fill="none" viewBox="0 0 24 24">
<circle class="opacity-25" cx="12" cy="12" r="10" stroke="currentColor" stroke-width="4"
></circle>
<path
@@ -166,7 +163,9 @@
title="Click to navigate, double-click to select"
>
<svg
class="h-4 w-4 shrink-0 {entry.isGitRepo ? 'text-orange-400' : 'text-yellow-400'}"
class="h-4 w-4 shrink-0 {entry.isGitRepo
? 'text-orange-400'
: 'text-yellow-400'}"
viewBox="0 0 20 20"
fill="currentColor"
>
@@ -176,7 +175,9 @@
</svg>
<span class="flex-1 truncate text-gray-800">{entry.name}</span>
{#if entry.isGitRepo}
<span class="shrink-0 rounded bg-orange-100 px-1.5 py-0.5 text-xs text-orange-700">
<span
class="shrink-0 rounded bg-orange-100 px-1.5 py-0.5 text-xs text-orange-700"
>
git
</span>
{/if}

5
src/lib/components/RepositoryCard.svelte
View File

@@ -36,8 +36,9 @@
<p class="mt-0.5 truncate font-mono text-sm text-gray-500">{repo.id}</p>
</div>
<span
class="ml-3 shrink-0 rounded-full px-2.5 py-0.5 text-xs font-medium {stateColors[repo.state] ??
'bg-gray-100 text-gray-600'}"
class="ml-3 shrink-0 rounded-full px-2.5 py-0.5 text-xs font-medium {stateColors[
repo.state
] ?? 'bg-gray-100 text-gray-600'}"
>
{stateLabels[repo.state] ?? repo.state}
</span>

5
src/lib/components/StatBadge.svelte
View File

@@ -17,7 +17,10 @@
};
</script>
<div class="flex flex-col items-center rounded-lg p-3 {variantClasses[variant] ?? variantClasses.default}">
<div
class="flex flex-col items-center rounded-lg p-3 {variantClasses[variant] ??
variantClasses.default}"
>
<span class="text-lg font-bold">{value}</span>
<span class="mt-0.5 text-xs">{label}</span>
</div>

4
src/lib/components/admin/JobStatusBadge.svelte
View File

@@ -17,6 +17,8 @@
const config = $derived(statusConfig[status]);
</script>
<span class="inline-flex items-center rounded-full px-2.5 py-0.5 text-xs font-medium {config.bg} {config.text}">
<span
class="inline-flex items-center rounded-full px-2.5 py-0.5 text-xs font-medium {config.bg} {config.text}"
>
{config.label}
</span>

2
src/lib/components/search/SearchInput.svelte
View File

@@ -25,7 +25,7 @@
{placeholder}
onkeydown={handleKeydown}
disabled={loading}
class="flex-1 rounded-lg border border-gray-200 bg-white px-4 py-2.5 text-sm text-gray-900 placeholder-gray-400 shadow-sm outline-none transition-all focus:border-blue-400 focus:ring-2 focus:ring-blue-100 disabled:cursor-not-allowed disabled:opacity-60"
class="flex-1 rounded-lg border border-gray-200 bg-white px-4 py-2.5 text-sm text-gray-900 placeholder-gray-400 shadow-sm transition-all outline-none focus:border-blue-400 focus:ring-2 focus:ring-blue-100 disabled:cursor-not-allowed disabled:opacity-60"
/>
<button
onclick={onsubmit}

22
src/lib/components/search/SnippetCard.svelte
View File

@@ -5,21 +5,15 @@
const isCode = $derived(snippet.type === 'code');
const title = $derived(
snippet.type === 'code' ? snippet.title : null
);
const title = $derived(snippet.type === 'code' ? snippet.title : null);
const breadcrumb = $derived(
snippet.type === 'code' ? snippet.description : snippet.breadcrumb
);
const breadcrumb = $derived(snippet.type === 'code' ? snippet.description : snippet.breadcrumb);
const content = $derived(
snippet.type === 'code' ? snippet.codeList[0]?.code ?? '' : snippet.text
snippet.type === 'code' ? (snippet.codeList[0]?.code ?? '') : snippet.text
);
const language = $derived(
snippet.type === 'code' ? (snippet.codeList[0]?.language ?? '') : null
);
const language = $derived(snippet.type === 'code' ? (snippet.codeList[0]?.language ?? '') : null);
const tokenCount = $derived(snippet.tokenCount ?? 0);
</script>
@@ -40,14 +34,14 @@
</div>
{#if breadcrumb}
<p class="bg-gray-50 px-4 py-1.5 text-xs italic text-gray-500">{breadcrumb}</p>
<p class="bg-gray-50 px-4 py-1.5 text-xs text-gray-500 italic">{breadcrumb}</p>
{/if}
<div class="p-4">
{#if isCode}
<pre
class="overflow-x-auto rounded bg-gray-950 p-4 text-sm text-gray-100"
><code>{content}</code></pre>
<pre class="overflow-x-auto rounded bg-gray-950 p-4 text-sm text-gray-100"><code
>{content}</code
></pre>
{:else}
<div class="prose prose-sm max-w-none whitespace-pre-wrap text-gray-700">{content}</div>
{/if}

16
src/lib/server/api/formatters.test.ts
View File

@@ -83,9 +83,7 @@ function makeSnippetResult(snippet: Snippet): SnippetSearchResult {
});
}
function makeMetadata(
overrides: Partial<ContextResponseMetadata> = {}
): ContextResponseMetadata {
function makeMetadata(overrides: Partial<ContextResponseMetadata> = {}): ContextResponseMetadata {
return {
localSource: false,
resultCount: 1,
@@ -160,7 +158,11 @@ describe('formatLibrarySearchJson', () => {
it('maps non-indexed state to initial', () => {
const results: LibrarySearchResult[] = [
new LibrarySearchResult({ repository: makeRepo({ state: 'pending' }), versions: [], score: 0 })
new LibrarySearchResult({
repository: makeRepo({ state: 'pending' }),
versions: [],
score: 0
})
];
const response = formatLibrarySearchJson(results);
expect(response.results[0].state).toBe('initial');
@@ -168,7 +170,11 @@ describe('formatLibrarySearchJson', () => {
it('handles null lastIndexedAt', () => {
const results: LibrarySearchResult[] = [
new LibrarySearchResult({ repository: makeRepo({ lastIndexedAt: null }), versions: [], score: 0 })
new LibrarySearchResult({
repository: makeRepo({ lastIndexedAt: null }),
versions: [],
score: 0
})
];
const response = formatLibrarySearchJson(results);
expect(response.results[0].lastUpdateDate).toBeNull();

11
src/lib/server/api/formatters.ts
View File

@@ -66,7 +66,9 @@ export const CORS_HEADERS = {
/**
* Convert internal LibrarySearchResult[] to the context7-compatible JSON body.
*/
export function formatLibrarySearchJson(results: LibrarySearchResult[]): LibrarySearchJsonResponseDto {
export function formatLibrarySearchJson(
results: LibrarySearchResult[]
): LibrarySearchJsonResponseDto {
return ContextResponseMapper.toLibrarySearchJson(results);
}
@@ -80,7 +82,7 @@ export function formatContextJson(
snippets: SnippetSearchResult[],
rules: string[],
metadata?: ContextResponseMetadata
): ContextJsonResponseDto {
): ContextJsonResponseDto {
return ContextResponseMapper.toContextJson(snippets, rules, metadata);
}
@@ -94,7 +96,10 @@ export function formatContextJson(
* @param snippets - Ranked snippet search results (already token-budget trimmed).
* @param rules - Rules from `trueref.json` / `repository_configs`.
*/
function formatOriginLine(result: SnippetSearchResult, metadata?: ContextResponseMetadata): string | null {
function formatOriginLine(
result: SnippetSearchResult,
metadata?: ContextResponseMetadata
): string | null {
if (!metadata?.repository) return null;
const parts = [

33
src/lib/server/config/config-parser.test.ts
View File

@@ -115,10 +115,7 @@ describe('parseConfigFile — description', () => {
describe('parseConfigFile — array path fields', () => {
it('accepts valid folders', () => {
const result = parseConfigFile(
JSON.stringify({ folders: ['src/', 'docs/'] }),
'trueref.json'
);
const result = parseConfigFile(JSON.stringify({ folders: ['src/', 'docs/'] }), 'trueref.json');
expect(result.config.folders).toEqual(['src/', 'docs/']);
expect(result.warnings).toHaveLength(0);
});
@@ -130,10 +127,7 @@ describe('parseConfigFile — array path fields', () => {
});
it('skips non-string entries in folders with a warning', () => {
const result = parseConfigFile(
JSON.stringify({ folders: ['src/', 42, true] }),
'trueref.json'
);
const result = parseConfigFile(JSON.stringify({ folders: ['src/', 42, true] }), 'trueref.json');
expect(result.config.folders).toEqual(['src/']);
expect(result.warnings.length).toBeGreaterThan(0);
});
@@ -174,7 +168,9 @@ describe('parseConfigFile — array path fields', () => {
describe('parseConfigFile — rules', () => {
it('accepts valid rules', () => {
const result = parseConfigFile(
JSON.stringify({ rules: ['Always use named imports.', 'Prefer async/await over callbacks.'] }),
JSON.stringify({
rules: ['Always use named imports.', 'Prefer async/await over callbacks.']
}),
'trueref.json'
);
expect(result.config.rules).toHaveLength(2);
@@ -204,10 +200,7 @@ describe('parseConfigFile — rules', () => {
});
it('ignores non-array rules with a warning', () => {
const result = parseConfigFile(
JSON.stringify({ rules: 'use named imports' }),
'trueref.json'
);
const result = parseConfigFile(JSON.stringify({ rules: 'use named imports' }), 'trueref.json');
expect(result.config.rules).toBeUndefined();
expect(result.warnings.some((w) => /rules must be an array/.test(w))).toBe(true);
});
@@ -243,10 +236,7 @@ describe('parseConfigFile — previousVersions', () => {
it('skips entries missing tag', () => {
const result = parseConfigFile(
JSON.stringify({
previousVersions: [
{ title: 'No tag here' },
{ tag: 'v1.0.0', title: 'Valid' }
]
previousVersions: [{ title: 'No tag here' }, { tag: 'v1.0.0', title: 'Valid' }]
}),
'trueref.json'
);
@@ -275,10 +265,7 @@ describe('parseConfigFile — previousVersions', () => {
});
it('ignores non-array previousVersions with a warning', () => {
const result = parseConfigFile(
JSON.stringify({ previousVersions: 'v1.0.0' }),
'trueref.json'
);
const result = parseConfigFile(JSON.stringify({ previousVersions: 'v1.0.0' }), 'trueref.json');
expect(result.config.previousVersions).toBeUndefined();
expect(result.warnings.some((w) => /previousVersions must be an array/.test(w))).toBe(true);
});
@@ -294,9 +281,7 @@ describe('resolveConfig', () => {
});
it('returns null when no matching filenames', () => {
expect(
resolveConfig([{ filename: 'package.json', content: '{"name":"x"}' }])
).toBeNull();
expect(resolveConfig([{ filename: 'package.json', content: '{"name":"x"}' }])).toBeNull();
});
it('prefers trueref.json over context7.json', () => {

12
src/lib/server/config/config-parser.ts
View File

@@ -65,7 +65,9 @@ export function parseConfigFile(content: string, filename: string): ParsedConfig
// ---- 2. Root must be an object ------------------------------------------
if (typeof raw !== 'object' || raw === null || Array.isArray(raw)) {
throw new ConfigParseError(`${filename} must be a JSON object, got ${Array.isArray(raw) ? 'array' : typeof raw}`);
throw new ConfigParseError(
`${filename} must be a JSON object, got ${Array.isArray(raw) ? 'array' : typeof raw}`
);
}
const input = raw as Record<string, unknown>;
@@ -131,7 +133,9 @@ export function parseConfigFile(content: string, filename: string): ParsedConfig
})
.map((item) => {
if (item.length > maxLength) {
warnings.push(`${field} entry truncated to ${maxLength} characters: "${item.slice(0, 40)}..."`);
warnings.push(
`${field} entry truncated to ${maxLength} characters: "${item.slice(0, 40)}..."`
);
return item.slice(0, maxLength);
}
return item;
@@ -160,9 +164,7 @@ export function parseConfigFile(content: string, filename: string): ParsedConfig
return false;
}
if (r.length < minLength) {
warnings.push(
`rules entry too short (< ${minLength} chars) — skipping: "${r}"`
);
warnings.push(`rules entry too short (< ${minLength} chars) — skipping: "${r}"`);
return false;
}
return true;

166
src/lib/server/config/trueref-config.json
View File

@@ -1,85 +1,85 @@
{
"$schema": "http://json-schema.org/draft-07/schema#",
"$id": "https://trueref.dev/schema/trueref-config.json",
"title": "TrueRef Repository Configuration",
"description": "Configuration file for controlling how a repository is indexed and presented by TrueRef. Place as trueref.json (or context7.json for backward compatibility) at the root of your repository.",
"type": "object",
"additionalProperties": false,
"properties": {
"projectTitle": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"description": "Override the display name for this library. When set, this replaces the repository name in search results and UI."
},
"description": {
"type": "string",
"minLength": 10,
"maxLength": 500,
"description": "A short description of the library used for search ranking and display. Should accurately describe the library's purpose."
},
"folders": {
"type": "array",
"maxItems": 50,
"description": "Allowlist of folder path prefixes or regex strings to include in indexing. If empty or absent, all folders are included. Examples: [\"src/\", \"docs/\", \"^packages/core\"]",
"items": {
"type": "string",
"maxLength": 200,
"description": "A path prefix or regex string. Paths are matched against the full relative file path within the repository."
}
},
"excludeFolders": {
"type": "array",
"maxItems": 50,
"description": "Folders to exclude from indexing. Applied after the 'folders' allowlist. Examples: [\"test/\", \"fixtures/\", \"__mocks__\"]",
"items": {
"type": "string",
"maxLength": 200,
"description": "A path prefix or regex string for folders to exclude."
}
},
"excludeFiles": {
"type": "array",
"maxItems": 100,
"description": "Exact filenames to exclude (no path, no regex). Examples: [\"README.md\", \"CHANGELOG.md\", \"jest.config.ts\"]",
"items": {
"type": "string",
"maxLength": 200,
"description": "An exact filename (not a path). Must not contain path separators."
}
},
"rules": {
"type": "array",
"maxItems": 20,
"description": "Best practices and rules to inject at the top of every query-docs response. These are shown to AI coding assistants to guide correct library usage.",
"items": {
"type": "string",
"minLength": 5,
"maxLength": 500,
"description": "A single best-practice rule or guideline for using this library."
}
},
"previousVersions": {
"type": "array",
"maxItems": 50,
"description": "Previously released versions to make available for versioned documentation queries.",
"items": {
"type": "object",
"required": ["tag", "title"],
"additionalProperties": false,
"properties": {
"tag": {
"type": "string",
"pattern": "^v?\\d+\\.\\d+(\\.\\d+)?(-.*)?$",
"description": "Git tag name for this version (e.g. \"v1.2.3\", \"2.0.0-beta.1\")."
},
"title": {
"type": "string",
"minLength": 1,
"description": "Human-readable version label (e.g. \"Version 1.2.3\", \"v2 Legacy\")."
}
}
}
}
}
"$schema": "http://json-schema.org/draft-07/schema#",
"$id": "https://trueref.dev/schema/trueref-config.json",
"title": "TrueRef Repository Configuration",
"description": "Configuration file for controlling how a repository is indexed and presented by TrueRef. Place as trueref.json (or context7.json for backward compatibility) at the root of your repository.",
"type": "object",
"additionalProperties": false,
"properties": {
"projectTitle": {
"type": "string",
"minLength": 1,
"maxLength": 100,
"description": "Override the display name for this library. When set, this replaces the repository name in search results and UI."
},
"description": {
"type": "string",
"minLength": 10,
"maxLength": 500,
"description": "A short description of the library used for search ranking and display. Should accurately describe the library's purpose."
},
"folders": {
"type": "array",
"maxItems": 50,
"description": "Allowlist of folder path prefixes or regex strings to include in indexing. If empty or absent, all folders are included. Examples: [\"src/\", \"docs/\", \"^packages/core\"]",
"items": {
"type": "string",
"maxLength": 200,
"description": "A path prefix or regex string. Paths are matched against the full relative file path within the repository."
}
},
"excludeFolders": {
"type": "array",
"maxItems": 50,
"description": "Folders to exclude from indexing. Applied after the 'folders' allowlist. Examples: [\"test/\", \"fixtures/\", \"__mocks__\"]",
"items": {
"type": "string",
"maxLength": 200,
"description": "A path prefix or regex string for folders to exclude."
}
},
"excludeFiles": {
"type": "array",
"maxItems": 100,
"description": "Exact filenames to exclude (no path, no regex). Examples: [\"README.md\", \"CHANGELOG.md\", \"jest.config.ts\"]",
"items": {
"type": "string",
"maxLength": 200,
"description": "An exact filename (not a path). Must not contain path separators."
}
},
"rules": {
"type": "array",
"maxItems": 20,
"description": "Best practices and rules to inject at the top of every query-docs response. These are shown to AI coding assistants to guide correct library usage.",
"items": {
"type": "string",
"minLength": 5,
"maxLength": 500,
"description": "A single best-practice rule or guideline for using this library."
}
},
"previousVersions": {
"type": "array",
"maxItems": 50,
"description": "Previously released versions to make available for versioned documentation queries.",
"items": {
"type": "object",
"required": ["tag", "title"],
"additionalProperties": false,
"properties": {
"tag": {
"type": "string",
"pattern": "^v?\\d+\\.\\d+(\\.\\d+)?(-.*)?$",
"description": "Git tag name for this version (e.g. \"v1.2.3\", \"2.0.0-beta.1\")."
},
"title": {
"type": "string",
"minLength": 1,
"description": "Human-readable version label (e.g. \"Version 1.2.3\", \"v2 Legacy\")."
}
}
}
}
}
}

77
src/lib/server/crawler/file-filter.ts
View File

@@ -74,27 +74,46 @@ export const MAX_FILE_SIZE_BYTES = 500_000;
*/
export const IGNORED_DIR_NAMES = new Set([
// ── Version control ────────────────────────────────────────────────────
'.git', '.hg', '.svn',
'.git',
'.hg',
'.svn',
// ── JavaScript / TypeScript ─────────────────────────────────────────────
'node_modules',
'.npm', '.yarn', '.pnpm-store', '.pnp',
'.npm',
'.yarn',
'.pnpm-store',
'.pnp',
// Build outputs and framework caches
'dist', 'build', 'out',
'.next', '.nuxt', '.svelte-kit', '.vite',
'.turbo', '.parcel-cache', '.webpack',
'dist',
'build',
'out',
'.next',
'.nuxt',
'.svelte-kit',
'.vite',
'.turbo',
'.parcel-cache',
'.webpack',
// ── Python ──────────────────────────────────────────────────────────────
'__pycache__',
'.venv', 'venv', 'env',
'site-packages', '.eggs',
'.pytest_cache', '.mypy_cache', '.ruff_cache',
'.tox', '.nox',
'.venv',
'venv',
'env',
'site-packages',
'.eggs',
'.pytest_cache',
'.mypy_cache',
'.ruff_cache',
'.tox',
'.nox',
'htmlcov',
// ── Java / Kotlin / Scala ───────────────────────────────────────────────
'target', // Maven + sbt
'.gradle', '.mvn',
'target', // Maven + sbt
'.gradle',
'.mvn',
// ── Ruby ────────────────────────────────────────────────────────────────
'.bundle',
@@ -103,19 +122,24 @@ export const IGNORED_DIR_NAMES = new Set([
// 'vendor' below covers PHP Composer
// ── .NET ────────────────────────────────────────────────────────────────
'bin', 'obj', 'packages',
'bin',
'obj',
'packages',
// ── Haskell ─────────────────────────────────────────────────────────────
'.stack-work', 'dist-newstyle',
'.stack-work',
'dist-newstyle',
// ── Dart / Flutter ──────────────────────────────────────────────────────
'.dart_tool',
// ── Swift / iOS ─────────────────────────────────────────────────────────
'Pods', 'DerivedData',
'Pods',
'DerivedData',
// ── Elixir / Erlang ─────────────────────────────────────────────────────
'_build', 'deps',
'_build',
'deps',
// ── Clojure ─────────────────────────────────────────────────────────────
'.cpcache',
@@ -125,16 +149,25 @@ export const IGNORED_DIR_NAMES = new Set([
'vendor',
// ── Generic caches / temp ───────────────────────────────────────────────
'.cache', '.tmp', 'tmp', 'temp', '.temp', '.sass-cache',
'.cache',
'.tmp',
'tmp',
'temp',
'.temp',
'.sass-cache',
// ── Test coverage ───────────────────────────────────────────────────────
'coverage', '.nyc_output',
'coverage',
'.nyc_output',
// ── IDE / editor artefacts ──────────────────────────────────────────────
'.idea', '.vs',
'.idea',
'.vs',
// ── Generated code ──────────────────────────────────────────────────────
'generated', '__generated__', '_generated',
'generated',
'__generated__',
'_generated',
// ── Logs ────────────────────────────────────────────────────────────────
'logs'
@@ -264,11 +297,7 @@ export function detectLanguage(filePath: string): string {
* 7. Must not be under a config.excludeFolders path / regex.
* 8. Must be under a config.folders allowlist path / regex (if specified).
*/
export function shouldIndexFile(
filePath: string,
fileSize: number,
config?: RepoConfig
): boolean {
export function shouldIndexFile(filePath: string, fileSize: number, config?: RepoConfig): boolean {
const ext = extname(filePath).toLowerCase();
const base = basename(filePath);

7
src/lib/server/crawler/github-tags.ts
View File

@@ -35,10 +35,9 @@ export async function listGitHubTags(
};
if (token) headers['Authorization'] = `Bearer ${token}`;
const response = await fetch(
`https://api.github.com/repos/${owner}/${repo}/tags?per_page=100`,
{ headers }
);
const response = await fetch(`https://api.github.com/repos/${owner}/${repo}/tags?per_page=100`, {
headers
});
if (!response.ok) throw new GitHubApiError(response.status);
return response.json() as Promise<GitHubTag[]>;

63
src/lib/server/crawler/github.crawler.test.ts
View File

@@ -8,13 +8,14 @@
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
import { crawl } from './github.crawler.js';
import { shouldIndexFile, detectLanguage, INDEXABLE_EXTENSIONS, MAX_FILE_SIZE_BYTES } from './file-filter.js';
import { GitHubRateLimiter, Semaphore, withRetry } from './rate-limiter.js';
import {
AuthenticationError,
PermissionError,
RepositoryNotFoundError
} from './types.js';
shouldIndexFile,
detectLanguage,
INDEXABLE_EXTENSIONS,
MAX_FILE_SIZE_BYTES
} from './file-filter.js';
import { GitHubRateLimiter, Semaphore, withRetry } from './rate-limiter.js';
import { AuthenticationError, PermissionError, RepositoryNotFoundError } from './types.js';
// ---------------------------------------------------------------------------
// Mock fetch helpers
@@ -112,7 +113,9 @@ describe('shouldIndexFile()', () => {
});
it('respects config.excludeFolders prefix', () => {
expect(shouldIndexFile('internal/config.ts', 100, { excludeFolders: ['internal/'] })).toBe(false);
expect(shouldIndexFile('internal/config.ts', 100, { excludeFolders: ['internal/'] })).toBe(
false
);
});
it('allows files outside of config.excludeFolders', () => {
@@ -169,8 +172,10 @@ describe('detectLanguage()', () => {
it('detects markdown', () => expect(detectLanguage('README.md')).toBe('markdown'));
it('detects svelte', () => expect(detectLanguage('App.svelte')).toBe('svelte'));
it('detects yaml', () => expect(detectLanguage('config.yaml')).toBe('yaml'));
it('returns empty string for unknown extension', () => expect(detectLanguage('file.xyz')).toBe(''));
it('is case-insensitive for extensions', () => expect(detectLanguage('FILE.TS')).toBe('typescript'));
it('returns empty string for unknown extension', () =>
expect(detectLanguage('file.xyz')).toBe(''));
it('is case-insensitive for extensions', () =>
expect(detectLanguage('FILE.TS')).toBe('typescript'));
});
// ---------------------------------------------------------------------------
@@ -267,9 +272,9 @@ describe('withRetry()', () => {
});
it('throws after exhausting all attempts', async () => {
await expect(
withRetry(() => Promise.reject(new Error('always fails')), 3)
).rejects.toThrow('always fails');
await expect(withRetry(() => Promise.reject(new Error('always fails')), 3)).rejects.toThrow(
'always fails'
);
});
});
@@ -425,14 +430,15 @@ describe('crawl()', () => {
});
it('throws AuthenticationError on 401', async () => {
stubFetch(() =>
new Response('Unauthorized', {
status: 401,
headers: {
'X-RateLimit-Remaining': '0',
'X-RateLimit-Reset': String(Math.floor(Date.now() / 1000) + 3600)
}
})
stubFetch(
() =>
new Response('Unauthorized', {
status: 401,
headers: {
'X-RateLimit-Remaining': '0',
'X-RateLimit-Reset': String(Math.floor(Date.now() / 1000) + 3600)
}
})
);
await expect(crawl({ owner: 'owner', repo: 'repo', token: 'bad-token' })).rejects.toThrow(
@@ -441,14 +447,15 @@ describe('crawl()', () => {
});
it('throws PermissionError on 403 without rate-limit exhaustion', async () => {
stubFetch(() =>
new Response('Forbidden', {
status: 403,
headers: {
'X-RateLimit-Remaining': '100',
'X-RateLimit-Reset': String(Math.floor(Date.now() / 1000) + 3600)
}
})
stubFetch(
() =>
new Response('Forbidden', {
status: 403,
headers: {
'X-RateLimit-Remaining': '100',
'X-RateLimit-Reset': String(Math.floor(Date.now() / 1000) + 3600)
}
})
);
await expect(crawl({ owner: 'owner', repo: 'repo' })).rejects.toThrow(PermissionError);

116
src/lib/server/crawler/github.crawler.ts
View File

@@ -106,9 +106,7 @@ async function throwForStatus(response: Response, rateLimiter: GitHubRateLimiter
);
}
case 404:
throw new RepositoryNotFoundError(
`Repository not found or not accessible: ${response.url}`
);
throw new RepositoryNotFoundError(`Repository not found or not accessible: ${response.url}`);
default: {
const body = await response.text().catch(() => '');
throw new Error(`GitHub API error ${response.status}: ${body}`);
@@ -129,18 +127,22 @@ async function fetchRepoInfo(
token: string | undefined,
rateLimiter: GitHubRateLimiter
): Promise<GitHubRepoResponse> {
return withRetry(async () => {
await rateLimiter.waitIfNeeded();
return withRetry(
async () => {
await rateLimiter.waitIfNeeded();
const response = await fetch(`${GITHUB_API}/repos/${owner}/${repo}`, {
headers: buildHeaders(token)
});
const response = await fetch(`${GITHUB_API}/repos/${owner}/${repo}`, {
headers: buildHeaders(token)
});
rateLimiter.updateFromHeaders(response.headers);
await throwForStatus(response, rateLimiter);
rateLimiter.updateFromHeaders(response.headers);
await throwForStatus(response, rateLimiter);
return (await response.json()) as GitHubRepoResponse;
}, 3, isRetryable);
return (await response.json()) as GitHubRepoResponse;
},
3,
isRetryable
);
}
/**
@@ -155,21 +157,25 @@ async function fetchTree(
token: string | undefined,
rateLimiter: GitHubRateLimiter
): Promise<GitHubTreeResponse | null> {
return withRetry(async () => {
await rateLimiter.waitIfNeeded();
return withRetry(
async () => {
await rateLimiter.waitIfNeeded();
const url = `${GITHUB_API}/repos/${owner}/${repo}/git/trees/${ref}?recursive=1`;
const response = await fetch(url, { headers: buildHeaders(token) });
const url = `${GITHUB_API}/repos/${owner}/${repo}/git/trees/${ref}?recursive=1`;
const response = await fetch(url, { headers: buildHeaders(token) });
rateLimiter.updateFromHeaders(response.headers);
rateLimiter.updateFromHeaders(response.headers);
// 422 means the tree is too large for a single recursive call.
if (response.status === 422) return null;
// 422 means the tree is too large for a single recursive call.
if (response.status === 422) return null;
await throwForStatus(response, rateLimiter);
await throwForStatus(response, rateLimiter);
return (await response.json()) as GitHubTreeResponse;
}, 3, isRetryable);
return (await response.json()) as GitHubTreeResponse;
},
3,
isRetryable
);
}
/**
@@ -184,17 +190,21 @@ async function fetchSubTree(
token: string | undefined,
rateLimiter: GitHubRateLimiter
): Promise<GitHubTreeResponse> {
return withRetry(async () => {
await rateLimiter.waitIfNeeded();
return withRetry(
async () => {
await rateLimiter.waitIfNeeded();
const url = `${GITHUB_API}/repos/${owner}/${repo}/git/trees/${treeSha}`;
const response = await fetch(url, { headers: buildHeaders(token) });
const url = `${GITHUB_API}/repos/${owner}/${repo}/git/trees/${treeSha}`;
const response = await fetch(url, { headers: buildHeaders(token) });
rateLimiter.updateFromHeaders(response.headers);
await throwForStatus(response, rateLimiter);
rateLimiter.updateFromHeaders(response.headers);
await throwForStatus(response, rateLimiter);
return (await response.json()) as GitHubTreeResponse;
}, 3, isRetryable);
return (await response.json()) as GitHubTreeResponse;
},
3,
isRetryable
);
}
/**
@@ -208,21 +218,25 @@ async function fetchCommitSha(
token: string | undefined,
rateLimiter: GitHubRateLimiter
): Promise<string> {
return withRetry(async () => {
await rateLimiter.waitIfNeeded();
return withRetry(
async () => {
await rateLimiter.waitIfNeeded();
const url = `${GITHUB_API}/repos/${owner}/${repo}/commits/${ref}`;
const response = await fetch(url, {
headers: { ...buildHeaders(token), Accept: 'application/vnd.github.sha' }
});
const url = `${GITHUB_API}/repos/${owner}/${repo}/commits/${ref}`;
const response = await fetch(url, {
headers: { ...buildHeaders(token), Accept: 'application/vnd.github.sha' }
});
rateLimiter.updateFromHeaders(response.headers);
await throwForStatus(response, rateLimiter);
rateLimiter.updateFromHeaders(response.headers);
await throwForStatus(response, rateLimiter);
// When Accept is 'application/vnd.github.sha', the response body is the
// bare SHA string.
return (await response.text()).trim();
}, 3, isRetryable);
// When Accept is 'application/vnd.github.sha', the response body is the
// bare SHA string.
return (await response.text()).trim();
},
3,
isRetryable
);
}
/**
@@ -347,14 +361,7 @@ async function fetchRepoConfig(
const content =
(await downloadRawFile(owner, repo, ref, configItem.path, token)) ??
(await downloadViaContentsApi(
owner,
repo,
ref,
configItem.path,
token,
rateLimiter
));
(await downloadViaContentsApi(owner, repo, ref, configItem.path, token, rateLimiter));
if (!content) return undefined;
@@ -435,14 +442,7 @@ export async function crawl(options: CrawlOptions): Promise<CrawlResult> {
// Prefer raw download (cheaper on rate limit); fall back to API.
const content =
(await downloadRawFile(owner, repo, ref!, item.path, token)) ??
(await downloadViaContentsApi(
owner,
repo,
ref!,
item.path,
token,
rateLimiter
));
(await downloadViaContentsApi(owner, repo, ref!, item.path, token, rateLimiter));
if (content === null) {
console.warn(`[GitHubCrawler] Could not download: ${item.path} — skipping.`);

4
src/lib/server/crawler/local.crawler.test.ts
View File

@@ -52,7 +52,9 @@ async function cleanupTempRepo(root: string): Promise<void> {
let root: string = '';
const crawler = new LocalCrawler();
async function crawlRoot(opts: Partial<LocalCrawlOptions> = {}): Promise<ReturnType<LocalCrawler['crawl']>> {
async function crawlRoot(
opts: Partial<LocalCrawlOptions> = {}
): Promise<ReturnType<LocalCrawler['crawl']>> {
return crawler.crawl({ rootPath: root, ...opts });
}

7
src/lib/server/crawler/local.crawler.ts
View File

@@ -141,7 +141,12 @@ export class LocalCrawler {
});
// Crawl the worktree and stamp the result with the git-resolved metadata.
const result = await this.crawlDirectory(worktreePath, options.config, options.onProgress, ref);
const result = await this.crawlDirectory(
worktreePath,
options.config,
options.onProgress,
ref
);
return { ...result, commitSha };
} finally {

1438
src/lib/server/db/migrations/meta/0000_snapshot.json
View File

File diff suppressed because it is too large Load Diff

1452
src/lib/server/db/migrations/meta/0001_snapshot.json
View File

File diff suppressed because it is too large Load Diff

1665
src/lib/server/db/migrations/meta/0002_snapshot.json
View File

File diff suppressed because it is too large Load Diff

50
src/lib/server/db/migrations/meta/_journal.json
View File

@@ -1,27 +1,27 @@
{
"version": "7",
"dialect": "sqlite",
"entries": [
{
"idx": 0,
"version": "6",
"when": 1774196053634,
"tag": "0000_large_master_chief",
"breakpoints": true
},
{
"idx": 1,
"version": "6",
"when": 1774448049161,
"tag": "0001_quick_nighthawk",
"breakpoints": true
},
{
"idx": 2,
"version": "6",
"when": 1774461897742,
"tag": "0002_silky_stellaris",
"breakpoints": true
}
]
"version": "7",
"dialect": "sqlite",
"entries": [
{
"idx": 0,
"version": "6",
"when": 1774196053634,
"tag": "0000_large_master_chief",
"breakpoints": true
},
{
"idx": 1,
"version": "6",
"when": 1774448049161,
"tag": "0001_quick_nighthawk",
"breakpoints": true
},
{
"idx": 2,
"version": "6",
"when": 1774461897742,
"tag": "0002_silky_stellaris",
"breakpoints": true
}
]
}

11
src/lib/server/embeddings/embedding.service.test.ts
View File

@@ -381,7 +381,12 @@ describe('EmbeddingService', () => {
.all(snippetId, 'local-default');
expect(rows).toHaveLength(1);
const row = rows[0] as { model: string; dimensions: number; embedding: Buffer; profile_id: string };
const row = rows[0] as {
model: string;
dimensions: number;
embedding: Buffer;
profile_id: string;
};
expect(row.model).toBe('test-model');
expect(row.dimensions).toBe(4);
expect(row.profile_id).toBe('local-default');
@@ -494,9 +499,7 @@ describe('createProviderFromConfig', () => {
});
it('throws when openai provider is selected without config', () => {
expect(() =>
createProviderFromConfig({ provider: 'openai' } as EmbeddingConfig)
).toThrow();
expect(() => createProviderFromConfig({ provider: 'openai' } as EmbeddingConfig)).toThrow();
});
it('defaultEmbeddingConfig returns provider=none', () => {

19
src/lib/server/embeddings/embedding.service.ts
View File

@@ -41,18 +41,16 @@ export class EmbeddingService {
const placeholders = snippetIds.map(() => '?').join(',');
const snippets = this.db
.prepare<string[], SnippetRow>(
`SELECT id, title, breadcrumb, content FROM snippets WHERE id IN (${placeholders})`
)
.prepare<
string[],
SnippetRow
>(`SELECT id, title, breadcrumb, content FROM snippets WHERE id IN (${placeholders})`)
.all(...snippetIds);
if (snippets.length === 0) return;
const texts = snippets.map((s) =>
[s.title, s.breadcrumb, s.content]
.filter(Boolean)
.join('\n')
.slice(0, TEXT_MAX_CHARS)
[s.title, s.breadcrumb, s.content].filter(Boolean).join('\n').slice(0, TEXT_MAX_CHARS)
);
const insert = this.db.prepare<[string, string, string, number, Buffer]>(`
@@ -94,9 +92,10 @@ export class EmbeddingService {
*/
getEmbedding(snippetId: string, profileId: string = 'local-default'): Float32Array | null {
const row = this.db
.prepare<[string, string], { embedding: Buffer; dimensions: number }>(
`SELECT embedding, dimensions FROM snippet_embeddings WHERE snippet_id = ? AND profile_id = ?`
)
.prepare<
[string, string],
{ embedding: Buffer; dimensions: number }
>(`SELECT embedding, dimensions FROM snippet_embeddings WHERE snippet_id = ? AND profile_id = ?`)
.get(snippetId, profileId);
if (!row) return null;

6
src/lib/server/embeddings/factory.ts
View File

@@ -12,7 +12,11 @@ import { OpenAIEmbeddingProvider } from './openai.provider.js';
import { LocalEmbeddingProvider } from './local.provider.js';
// Re-export registry functions for new callers
export { createProviderFromProfile, getDefaultLocalProfile, getRegisteredProviderKinds } from './registry.js';
export {
createProviderFromProfile,
getDefaultLocalProfile,
getRegisteredProviderKinds
} from './registry.js';
export interface EmbeddingConfig {
provider: 'openai' | 'local' | 'none';

47
src/lib/server/mappers/context-response.mapper.ts
View File

@@ -43,7 +43,12 @@ export class ContextResponseMapper {
lastUpdateDate: repository.lastIndexedAt
? repository.lastIndexedAt.toISOString()
: null,
state: repository.state === 'indexed' ? 'finalized' : repository.state === 'error' ? 'error' : 'initial',
state:
repository.state === 'indexed'
? 'finalized'
: repository.state === 'error'
? 'error'
: 'initial',
totalTokens: repository.totalTokens ?? null,
totalSnippets: repository.totalSnippets ?? null,
stars: repository.stars ?? null,
@@ -64,14 +69,16 @@ export class ContextResponseMapper {
const mapped: SnippetJsonDto[] = snippets.map(({ snippet }) => {
const origin = metadata?.repository
? new SnippetOriginJsonDto({
repositoryId: snippet.repositoryId,
repositoryTitle: metadata.repository.title,
source: metadata.repository.source,
sourceUrl: metadata.repository.sourceUrl,
version: snippet.versionId ? metadata.snippetVersions[snippet.versionId] ?? null : null,
versionId: snippet.versionId,
isLocal: metadata.localSource
})
repositoryId: snippet.repositoryId,
repositoryTitle: metadata.repository.title,
source: metadata.repository.source,
sourceUrl: metadata.repository.sourceUrl,
version: snippet.versionId
? (metadata.snippetVersions[snippet.versionId] ?? null)
: null,
versionId: snippet.versionId,
isLocal: metadata.localSource
})
: null;
if (snippet.type === 'code') {
@@ -108,20 +115,20 @@ export class ContextResponseMapper {
localSource: metadata?.localSource ?? false,
repository: metadata?.repository
? new ContextRepositoryJsonDto({
id: metadata.repository.id,
title: metadata.repository.title,
source: metadata.repository.source,
sourceUrl: metadata.repository.sourceUrl,
branch: metadata.repository.branch,
isLocal: metadata.localSource
})
id: metadata.repository.id,
title: metadata.repository.title,
source: metadata.repository.source,
sourceUrl: metadata.repository.sourceUrl,
branch: metadata.repository.branch,
isLocal: metadata.localSource
})
: null,
version: metadata?.version
? new ContextVersionJsonDto({
requested: metadata.version.requested,
resolved: metadata.version.resolved,
id: metadata.version.id
})
requested: metadata.version.requested,
resolved: metadata.version.resolved,
id: metadata.version.id
})
: null,
resultCount: metadata?.resultCount ?? snippets.length
});

3
src/lib/server/mappers/indexing-job.mapper.ts
View File

@@ -12,8 +12,7 @@ export class IndexingJobMapper {
processedFiles: entity.processed_files,
error: entity.error,
startedAt: entity.started_at != null ? new Date(entity.started_at * 1000) : null,
completedAt:
entity.completed_at != null ? new Date(entity.completed_at * 1000) : null,
completedAt: entity.completed_at != null ? new Date(entity.completed_at * 1000) : null,
createdAt: new Date(entity.created_at * 1000)
});
}

10
src/lib/server/mappers/search-result.mapper.ts
View File

@@ -1,4 +1,8 @@
import { LibrarySearchResult, SnippetRepositoryRef, SnippetSearchResult } from '$lib/server/models/search-result.js';
import {
LibrarySearchResult,
SnippetRepositoryRef,
SnippetSearchResult
} from '$lib/server/models/search-result.js';
import { RepositoryMapper } from '$lib/server/mappers/repository.mapper.js';
import { RepositoryVersionMapper } from '$lib/server/mappers/repository-version.mapper.js';
import { SnippetMapper } from '$lib/server/mappers/snippet.mapper.js';
@@ -26,9 +30,7 @@ export class SearchResultMapper {
): LibrarySearchResult {
return new LibrarySearchResult({
repository: RepositoryMapper.fromEntity(repositoryEntity),
versions: versionEntities.map((version) =>
RepositoryVersionMapper.fromEntity(version)
),
versions: versionEntities.map((version) => RepositoryVersionMapper.fromEntity(version)),
score
});
}

2
src/lib/server/models/context-response.ts
View File

@@ -71,7 +71,7 @@ export class SnippetOriginJsonDto {
this.versionId = props.versionId;
this.isLocal = props.isLocal;
}
}
}
export class LibrarySearchJsonResultDto {
id: string;

8
src/lib/server/parser/code.parser.test.ts
View File

@@ -286,7 +286,8 @@ This is the second paragraph that also has enough content to be included here.
});
it('skips paragraphs shorter than 20 characters', () => {
const content = 'Short.\n\nThis is a much longer paragraph that definitely passes the minimum length filter.';
const content =
'Short.\n\nThis is a much longer paragraph that definitely passes the minimum length filter.';
const snippets = parseCodeFile(content, 'notes.txt', 'text');
expect(snippets.length).toBe(1);
});
@@ -331,7 +332,10 @@ export function realFunction(): string {
describe('parseCodeFile — token count', () => {
it('all snippets have tokenCount within MAX_TOKENS', () => {
const lines = Array.from({ length: 300 }, (_, i) => `// comment line number ${i} here\nconst x${i} = ${i};`);
const lines = Array.from(
{ length: 300 },
(_, i) => `// comment line number ${i} here\nconst x${i} = ${i};`
);
const content = lines.join('\n');
const snippets = parseCodeFile(content, 'large.ts', 'typescript');

22
src/lib/server/parser/code.parser.ts
View File

@@ -26,15 +26,19 @@ import {
* The regex is tested line-by-line (multiline flag not needed).
*/
export const BOUNDARY_PATTERNS: Record<string, RegExp> = {
typescript: /^(export\s+)?(declare\s+)?(async\s+)?(function|class|interface|type|enum|const|let|var)\s+\w+/,
typescript:
/^(export\s+)?(declare\s+)?(async\s+)?(function|class|interface|type|enum|const|let|var)\s+\w+/,
javascript: /^(export\s+)?(async\s+)?(function|class|const|let|var)\s+\w+/,
python: /^(async\s+)?(def|class)\s+\w+/,
go: /^(func|type|var|const)\s+\w+/,
rust: /^(pub(\s*\(crate\))?\s+)?(async\s+)?(fn|impl|struct|enum|trait|type|const|static)\s+\w+/,
java: /^(\s*(public|private|protected|static|final|abstract|synchronized)\s+)+[\w<>\[\]]+\s+\w+\s*[({]/,
csharp: /^(\s*(public|private|protected|internal|static|override|virtual|abstract|sealed)\s+)+[\w<>\[\]]+\s+\w+\s*[({]/,
kotlin: /^(\s*(public|private|protected|internal|override|suspend|inline|open|abstract|sealed)\s+)*(fun|class|object|interface|data class|sealed class|enum class)\s+\w+/,
swift: /^(\s*(public|private|internal|fileprivate|open|override|static|final|class)\s+)*(func|class|struct|enum|protocol|extension)\s+\w+/,
csharp:
/^(\s*(public|private|protected|internal|static|override|virtual|abstract|sealed)\s+)+[\w<>\[\]]+\s+\w+\s*[({]/,
kotlin:
/^(\s*(public|private|protected|internal|override|suspend|inline|open|abstract|sealed)\s+)*(fun|class|object|interface|data class|sealed class|enum class)\s+\w+/,
swift:
/^(\s*(public|private|internal|fileprivate|open|override|static|final|class)\s+)*(func|class|struct|enum|protocol|extension)\s+\w+/,
ruby: /^(def|class|module)\s+\w+/
};
@@ -42,7 +46,10 @@ export const BOUNDARY_PATTERNS: Record<string, RegExp> = {
// Internal types
// ---------------------------------------------------------------------------
type RawSnippet = Omit<NewSnippet, 'id' | 'repositoryId' | 'documentId' | 'versionId' | 'createdAt'>;
type RawSnippet = Omit<
NewSnippet,
'id' | 'repositoryId' | 'documentId' | 'versionId' | 'createdAt'
>;
// ---------------------------------------------------------------------------
// Helpers
@@ -161,7 +168,10 @@ function parseHtmlLikeFile(content: string, filePath: string, language: string):
while ((match = scriptPattern.exec(content)) !== null) {
// Strip the outer tags, keep just the code
const inner = match[0].replace(/^<script[^>]*>/, '').replace(/<\/script>$/, '').trim();
const inner = match[0]
.replace(/^<script[^>]*>/, '')
.replace(/<\/script>$/, '')
.trim();
if (inner.length >= MIN_CONTENT_LENGTH) {
scriptBlocks.push(inner);
}

9
src/lib/server/parser/index.ts
View File

@@ -48,6 +48,13 @@ export function parseFile(file: CrawledFile, options: ParseOptions): NewSnippet[
// Re-export helpers for consumers that need them individually
export { detectLanguage } from './language.js';
export { estimateTokens, chunkText, chunkLines, MAX_TOKENS, OVERLAP_TOKENS, MIN_CONTENT_LENGTH } from './chunker.js';
export {
estimateTokens,
chunkText,
chunkLines,
MAX_TOKENS,
OVERLAP_TOKENS,
MIN_CONTENT_LENGTH
} from './chunker.js';
export { parseMarkdown } from './markdown.parser.js';
export { parseCodeFile, BOUNDARY_PATTERNS } from './code.parser.js';

10
src/lib/server/parser/markdown.parser.test.ts
View File

@@ -99,7 +99,10 @@ describe('parseMarkdown — section splitting', () => {
describe('parseMarkdown — code block extraction', () => {
it('extracts a fenced code block as a code snippet', () => {
const codeBlock = fence('typescript', 'function hello(name: string): string {\n return `Hello, ${name}!`;\n}');
const codeBlock = fence(
'typescript',
'function hello(name: string): string {\n return `Hello, ${name}!`;\n}'
);
const source = [
'# Example',
'',
@@ -232,7 +235,10 @@ describe('parseMarkdown — large content chunking', () => {
describe('parseMarkdown — real-world sample', () => {
it('correctly parses a realistic README excerpt', () => {
const bashInstall = fence('bash', 'npm install my-library');
const tsUsage = fence('typescript', "import { doTheThing } from 'my-library';\n\ndoTheThing({ verbose: true });");
const tsUsage = fence(
'typescript',
"import { doTheThing } from 'my-library';\n\ndoTheThing({ verbose: true });"
);
const source = [
'# My Library',

13
src/lib/server/parser/markdown.parser.ts
View File

@@ -7,7 +7,13 @@
import { basename } from 'node:path';
import type { NewSnippet } from '$lib/server/db/schema.js';
import { estimateTokens, chunkText, MAX_TOKENS, OVERLAP_TOKENS, MIN_CONTENT_LENGTH } from './chunker.js';
import {
estimateTokens,
chunkText,
MAX_TOKENS,
OVERLAP_TOKENS,
MIN_CONTENT_LENGTH
} from './chunker.js';
// ---------------------------------------------------------------------------
// Internal types
@@ -121,7 +127,10 @@ function splitIntoSections(source: string): MarkdownSection[] {
// Public parser
// ---------------------------------------------------------------------------
type RawSnippet = Omit<NewSnippet, 'id' | 'repositoryId' | 'documentId' | 'versionId' | 'createdAt'>;
type RawSnippet = Omit<
NewSnippet,
'id' | 'repositoryId' | 'documentId' | 'versionId' | 'createdAt'
>;
/**
* Parse a Markdown/MDX file into raw snippets (before IDs and DB fields are

16
src/lib/server/pipeline/diff.test.ts
View File

@@ -86,16 +86,16 @@ describe('computeDiff', () => {
it('handles a mixed scenario: added, modified, deleted, and unchanged', () => {
const crawledFiles = [
makeCrawledFile('unchanged.md', 'sha-same'), // unchanged
makeCrawledFile('modified.md', 'sha-new'), // modified (different sha)
makeCrawledFile('added.md', 'sha-added') // added (not in DB)
makeCrawledFile('unchanged.md', 'sha-same'), // unchanged
makeCrawledFile('modified.md', 'sha-new'), // modified (different sha)
makeCrawledFile('added.md', 'sha-added') // added (not in DB)
// 'deleted.md' is absent from crawl → deleted
];
const existingDocs = [
makeDocument('unchanged.md', 'sha-same'), // unchanged
makeDocument('modified.md', 'sha-old'), // modified
makeDocument('deleted.md', 'sha-deleted') // deleted
makeDocument('unchanged.md', 'sha-same'), // unchanged
makeDocument('modified.md', 'sha-old'), // modified
makeDocument('deleted.md', 'sha-deleted') // deleted
];
const diff = computeDiff(crawledFiles, existingDocs);
@@ -114,9 +114,9 @@ describe('computeDiff', () => {
];
const existingDocs = [
makeDocument('a.md', 'sha-a'), // unchanged
makeDocument('a.md', 'sha-a'), // unchanged
makeDocument('b.md', 'sha-b-old'), // modified
makeDocument('d.md', 'sha-d') // deleted
makeDocument('d.md', 'sha-d') // deleted
// 'c.md' is not in DB → added
];

115
src/lib/server/pipeline/indexing.pipeline.test.ts
View File

@@ -22,10 +22,7 @@ function createTestDb(): Database.Database {
client.pragma('foreign_keys = ON');
const migrationsFolder = join(import.meta.dirname, '../db/migrations');
const migrationSql = readFileSync(
join(migrationsFolder, '0000_large_master_chief.sql'),
'utf-8'
);
const migrationSql = readFileSync(join(migrationsFolder, '0000_large_master_chief.sql'), 'utf-8');
const statements = migrationSql
.split('--> statement-breakpoint')
@@ -45,10 +42,7 @@ function createTestDb(): Database.Database {
const now = Math.floor(Date.now() / 1000);
function insertRepo(
db: Database.Database,
overrides: Partial<Record<string, unknown>> = {}
): void {
function insertRepo(db: Database.Database, overrides: Partial<Record<string, unknown>> = {}): void {
db.prepare(
`INSERT INTO repositories
(id, title, source, source_url, branch, state,
@@ -62,7 +56,15 @@ function insertRepo(
overrides.source_url ?? '/tmp/test-repo',
overrides.branch ?? 'main',
overrides.state ?? 'pending',
0, 0, 0, 0, null, null, null, now, now
0,
0,
0,
0,
null,
null,
null,
now,
now
);
}
@@ -108,9 +110,10 @@ describe('recoverStaleJobs', () => {
insertJob(db, { status: 'running' });
recoverStaleJobs(db);
const row = db
.prepare(`SELECT status, error FROM indexing_jobs LIMIT 1`)
.get() as { status: string; error: string };
const row = db.prepare(`SELECT status, error FROM indexing_jobs LIMIT 1`).get() as {
status: string;
error: string;
};
expect(row.status).toBe('failed');
expect(row.error).toMatch(/restarted/i);
});
@@ -119,9 +122,9 @@ describe('recoverStaleJobs', () => {
db.prepare(`UPDATE repositories SET state = 'indexing' WHERE id = '/test/repo'`).run();
recoverStaleJobs(db);
const row = db
.prepare(`SELECT state FROM repositories WHERE id = '/test/repo'`)
.get() as { state: string };
const row = db.prepare(`SELECT state FROM repositories WHERE id = '/test/repo'`).get() as {
state: string;
};
expect(row.state).toBe('error');
});
@@ -164,9 +167,7 @@ describe('JobQueue', () => {
const job2 = queue.enqueue('/test/repo');
expect(job1.id).toBe(job2.id);
const count = (
db.prepare(`SELECT COUNT(*) as n FROM indexing_jobs`).get() as { n: number }
).n;
const count = (db.prepare(`SELECT COUNT(*) as n FROM indexing_jobs`).get() as { n: number }).n;
expect(count).toBe(1);
});
@@ -255,19 +256,19 @@ describe('IndexingPipeline', () => {
})
};
return new IndexingPipeline(
db,
mockGithubCrawl as never,
mockLocalCrawler as never,
null
);
return new IndexingPipeline(db, mockGithubCrawl as never, mockLocalCrawler as never, null);
}
function makeJob(repositoryId = '/test/repo') {
const jobId = insertJob(db, { repository_id: repositoryId, status: 'queued' });
return db
.prepare(`SELECT * FROM indexing_jobs WHERE id = ?`)
.get(jobId) as { id: string; repositoryId?: string; repository_id?: string; status: string; versionId?: string; version_id?: string };
return db.prepare(`SELECT * FROM indexing_jobs WHERE id = ?`).get(jobId) as {
id: string;
repositoryId?: string;
repository_id?: string;
status: string;
versionId?: string;
version_id?: string;
};
}
it('marks job as done when there are no files to index', async () => {
@@ -289,9 +290,9 @@ describe('IndexingPipeline', () => {
await pipeline.run(job as never);
const updated = db
.prepare(`SELECT status FROM indexing_jobs WHERE id = ?`)
.get(job.id) as { status: string };
const updated = db.prepare(`SELECT status FROM indexing_jobs WHERE id = ?`).get(job.id) as {
status: string;
};
// The job should end in 'done' — the running→done transition is covered
// by the pipeline's internal updateJob calls.
expect(updated.status).toBe('done');
@@ -363,27 +364,24 @@ describe('IndexingPipeline', () => {
const job1 = makeJob();
await pipeline.run(job1 as never);
const firstDocCount = (
db.prepare(`SELECT COUNT(*) as n FROM documents`).get() as { n: number }
).n;
const firstSnippetIds = (
db.prepare(`SELECT id FROM snippets`).all() as { id: string }[]
).map((r) => r.id);
const firstDocCount = (db.prepare(`SELECT COUNT(*) as n FROM documents`).get() as { n: number })
.n;
const firstSnippetIds = (db.prepare(`SELECT id FROM snippets`).all() as { id: string }[]).map(
(r) => r.id
);
// Second run with identical files.
const job2Id = insertJob(db, { repository_id: '/test/repo', status: 'queued' });
const job2 = db
.prepare(`SELECT * FROM indexing_jobs WHERE id = ?`)
.get(job2Id) as never;
const job2 = db.prepare(`SELECT * FROM indexing_jobs WHERE id = ?`).get(job2Id) as never;
await pipeline.run(job2);
const secondDocCount = (
db.prepare(`SELECT COUNT(*) as n FROM documents`).get() as { n: number }
).n;
const secondSnippetIds = (
db.prepare(`SELECT id FROM snippets`).all() as { id: string }[]
).map((r) => r.id);
const secondSnippetIds = (db.prepare(`SELECT id FROM snippets`).all() as { id: string }[]).map(
(r) => r.id
);
// Document count stays the same and snippet IDs are unchanged.
expect(secondDocCount).toBe(firstDocCount);
@@ -395,7 +393,8 @@ describe('IndexingPipeline', () => {
files: [
{
path: 'README.md',
content: '# Original\n\nThis is the original version of the documentation with sufficient content.',
content:
'# Original\n\nThis is the original version of the documentation with sufficient content.',
sha: 'sha-v1',
language: 'markdown'
}
@@ -415,7 +414,8 @@ describe('IndexingPipeline', () => {
files: [
{
path: 'README.md',
content: '# Updated\n\nThis is a completely different version of the documentation with new content.',
content:
'# Updated\n\nThis is a completely different version of the documentation with new content.',
sha: 'sha-v2',
language: 'markdown'
}
@@ -423,14 +423,11 @@ describe('IndexingPipeline', () => {
totalFiles: 1
});
const job2Id = insertJob(db, { repository_id: '/test/repo', status: 'queued' });
const job2 = db
.prepare(`SELECT * FROM indexing_jobs WHERE id = ?`)
.get(job2Id) as never;
const job2 = db.prepare(`SELECT * FROM indexing_jobs WHERE id = ?`).get(job2Id) as never;
await pipeline2.run(job2);
const finalDocCount = (
db.prepare(`SELECT COUNT(*) as n FROM documents`).get() as { n: number }
).n;
const finalDocCount = (db.prepare(`SELECT COUNT(*) as n FROM documents`).get() as { n: number })
.n;
// Only one document should exist (the updated one).
expect(finalDocCount).toBe(1);
@@ -452,9 +449,9 @@ describe('IndexingPipeline', () => {
const job = makeJob();
await pipeline.run(job as never);
const updated = db
.prepare(`SELECT progress FROM indexing_jobs WHERE id = ?`)
.get(job.id) as { progress: number };
const updated = db.prepare(`SELECT progress FROM indexing_jobs WHERE id = ?`).get(job.id) as {
progress: number;
};
expect(updated.progress).toBe(100);
});
@@ -467,12 +464,7 @@ describe('IndexingPipeline', () => {
commitSha: 'abc'
});
const pipeline = new IndexingPipeline(
db,
vi.fn() as never,
{ crawl } as never,
null
);
const pipeline = new IndexingPipeline(db, vi.fn() as never, { crawl } as never, null);
const job = makeJob();
await pipeline.run(job as never);
@@ -511,7 +503,10 @@ describe('IndexingPipeline', () => {
await pipeline1.run(job1 as never);
const afterFirstRun = {
docs: db.prepare(`SELECT file_path, checksum FROM documents ORDER BY file_path`).all() as { file_path: string; checksum: string }[],
docs: db.prepare(`SELECT file_path, checksum FROM documents ORDER BY file_path`).all() as {
file_path: string;
checksum: string;
}[],
snippetCount: (db.prepare(`SELECT COUNT(*) as n FROM snippets`).get() as { n: number }).n
};
expect(afterFirstRun.docs).toHaveLength(3);

5
src/lib/server/pipeline/indexing.pipeline.ts
View File

@@ -250,7 +250,10 @@ export class IndexingPipeline {
private async crawl(
repo: Repository,
job: IndexingJob
): Promise<{ files: Array<{ path: string; content: string; sha: string; size: number; language: string }>; totalFiles: number }> {
): Promise<{
files: Array<{ path: string; content: string; sha: string; size: number; language: string }>;
totalFiles: number;
}> {
if (repo.source === 'github') {
// Parse owner/repo from the canonical ID: "/owner/repo"
const parts = repo.id.replace(/^\//, '').split('/');

22
src/lib/server/pipeline/job-queue.ts
View File

@@ -133,9 +133,7 @@ export class JobQueue {
// Check whether another job was queued while this one ran.
const next = this.db
.prepare<[], { id: string }>(
`SELECT id FROM indexing_jobs WHERE status = 'queued' LIMIT 1`
)
.prepare<[], { id: string }>(`SELECT id FROM indexing_jobs WHERE status = 'queued' LIMIT 1`)
.get();
if (next) {
setImmediate(() => this.processNext());
@@ -147,9 +145,7 @@ export class JobQueue {
* Retrieve a single job by ID.
*/
getJob(id: string): IndexingJob | null {
const raw = this.db
.prepare<[string], IndexingJobEntity>(`${JOB_SELECT} WHERE id = ?`)
.get(id);
const raw = this.db.prepare<[string], IndexingJobEntity>(`${JOB_SELECT} WHERE id = ?`).get(id);
return raw ? IndexingJobMapper.fromEntity(new IndexingJobEntity(raw)) : null;
}
@@ -178,9 +174,9 @@ export class JobQueue {
const sql = `${JOB_SELECT} ${where} ORDER BY created_at DESC LIMIT ?`;
params.push(limit);
return (this.db.prepare<unknown[], IndexingJobEntity>(sql).all(...params) as IndexingJobEntity[]).map(
(row) => IndexingJobMapper.fromEntity(new IndexingJobEntity(row))
);
return (
this.db.prepare<unknown[], IndexingJobEntity>(sql).all(...params) as IndexingJobEntity[]
).map((row) => IndexingJobMapper.fromEntity(new IndexingJobEntity(row)));
}
/**
@@ -228,9 +224,7 @@ export class JobQueue {
return false;
}
this.db
.prepare(`UPDATE indexing_jobs SET status = 'paused' WHERE id = ?`)
.run(id);
this.db.prepare(`UPDATE indexing_jobs SET status = 'paused' WHERE id = ?`).run(id);
return true;
}
@@ -249,9 +243,7 @@ export class JobQueue {
return false;
}
this.db
.prepare(`UPDATE indexing_jobs SET status = 'queued' WHERE id = ?`)
.run(id);
this.db.prepare(`UPDATE indexing_jobs SET status = 'queued' WHERE id = ?`).run(id);
// Trigger queue processing in case the queue was idle
this.drainQueued();

25
src/lib/server/search/hybrid.search.service.test.ts
View File

@@ -27,7 +27,11 @@ function createTestDb(): Database.Database {
const migrationsFolder = join(import.meta.dirname, '../db/migrations');
// Run all migrations in order
const migrations = ['0000_large_master_chief.sql', '0001_quick_nighthawk.sql', '0002_silky_stellaris.sql'];
const migrations = [
'0000_large_master_chief.sql',
'0001_quick_nighthawk.sql',
'0002_silky_stellaris.sql'
];
for (const migrationFile of migrations) {
const migrationSql = readFileSync(join(migrationsFolder, migrationFile), 'utf-8');
const statements = migrationSql
@@ -123,9 +127,7 @@ function seedEmbedding(
// Mock EmbeddingProvider
// ---------------------------------------------------------------------------
function makeMockProvider(
returnValues: number[][] = [[1, 0, 0, 0]]
): EmbeddingProvider {
function makeMockProvider(returnValues: number[][] = [[1, 0, 0, 0]]): EmbeddingProvider {
return {
name: 'mock',
dimensions: returnValues[0]?.length ?? 4,
@@ -254,9 +256,18 @@ describe('reciprocalRankFusion', () => {
});
it('handles three lists correctly', () => {
const r1 = [{ id: 'a', score: 1 }, { id: 'b', score: 0 }];
const r2 = [{ id: 'b', score: 1 }, { id: 'c', score: 0 }];
const r3 = [{ id: 'a', score: 1 }, { id: 'c', score: 0 }];
const r1 = [
{ id: 'a', score: 1 },
{ id: 'b', score: 0 }
];
const r2 = [
{ id: 'b', score: 1 },
{ id: 'c', score: 0 }
];
const r3 = [
{ id: 'a', score: 1 },
{ id: 'c', score: 0 }
];
const result = reciprocalRankFusion(r1, r2, r3);
// 'a' appears first in r1 and r3 → higher combined score than 'b' or 'c'.
expect(result[0].id).toBe('a');

5
src/lib/server/search/hybrid.search.service.ts
View File

@@ -103,10 +103,7 @@ export class HybridSearchService {
* @param options - Search parameters including repositoryId and alpha blend.
* @returns Ranked array of SnippetSearchResult, deduplicated by snippet ID.
*/
async search(
query: string,
options: HybridSearchOptions
): Promise<SnippetSearchResult[]> {
async search(query: string, options: HybridSearchOptions): Promise<SnippetSearchResult[]> {
const limit = options.limit ?? 20;
const mode = options.searchMode ?? 'auto';

7
src/lib/server/search/query-preprocessor.ts
View File

@@ -20,7 +20,7 @@
*/
export function preprocessQuery(raw: string): string {
// 1. Trim and collapse whitespace.
let q = raw.trim().replace(/\s+/g, ' ');
const q = raw.trim().replace(/\s+/g, ' ');
if (!q) return q;
@@ -91,7 +91,10 @@ export function preprocessQuery(raw: string): string {
}
// Remove trailing operators
while (finalTokens.length > 0 && ['AND', 'OR', 'NOT'].includes(finalTokens[finalTokens.length - 1])) {
while (
finalTokens.length > 0 &&
['AND', 'OR', 'NOT'].includes(finalTokens[finalTokens.length - 1])
) {
finalTokens.pop();
}

4
src/lib/server/search/rrf.ts
View File

@@ -32,9 +32,7 @@ export interface FusedItem {
* descending relevance (index 0 = most relevant).
* @returns Fused array sorted by descending rrfScore, deduplicated by id.
*/
export function reciprocalRankFusion(
...rankings: Array<Array<RankedItem>>
): Array<FusedItem> {
export function reciprocalRankFusion(...rankings: Array<Array<RankedItem>>): Array<FusedItem> {
const K = 60; // Standard RRF constant.
const scores = new Map<string, number>();

8
src/lib/server/search/search.service.test.ts
View File

@@ -674,7 +674,9 @@ describe('formatLibraryResults', () => {
id: '/facebook/react/v18',
repositoryId: '/facebook/react',
tag: 'v18',
title: 'React 18', commitHash: null, state: 'indexed',
title: 'React 18',
commitHash: null,
state: 'indexed',
totalSnippets: 1000,
indexedAt: null,
createdAt: now
@@ -731,7 +733,9 @@ describe('formatLibraryResults', () => {
describe('formatSnippetResults', () => {
const now = new Date();
function makeSnippetResult(overrides: Partial<Parameters<typeof formatSnippetResults>[0][number]> = {}): Parameters<typeof formatSnippetResults>[0][number] {
function makeSnippetResult(
overrides: Partial<Parameters<typeof formatSnippetResults>[0][number]> = {}
): Parameters<typeof formatSnippetResults>[0][number] {
return {
snippet: {
id: crypto.randomUUID(),

27
src/lib/server/search/search.service.ts
View File

@@ -87,10 +87,7 @@ export class SearchService {
if (!processedQuery) return [];
// Build the WHERE clause dynamically based on optional filters.
const conditions: string[] = [
'snippets_fts MATCH ?',
's.repository_id = ?'
];
const conditions: string[] = ['snippets_fts MATCH ?', 's.repository_id = ?'];
const params: unknown[] = [processedQuery, repositoryId];
if (versionId !== undefined) {
@@ -132,10 +129,14 @@ export class SearchService {
const rows = this.db.prepare(sql).all(...params) as RawSnippetRow[];
return rows.map((row) =>
SearchResultMapper.snippetFromEntity(new SnippetEntity(row), {
id: row.repo_id,
title: row.repo_title
}, row.score)
SearchResultMapper.snippetFromEntity(
new SnippetEntity(row),
{
id: row.repo_id,
title: row.repo_title
},
row.score
)
);
}
@@ -188,7 +189,11 @@ export class SearchService {
return rows.map((row) => {
const compositeScore =
row.exact_match + row.prefix_match + row.desc_match + row.snippet_score + row.trust_component;
row.exact_match +
row.prefix_match +
row.desc_match +
row.snippet_score +
row.trust_component;
return SearchResultMapper.libraryFromEntity(
new RepositoryEntity(row),
this.getVersionEntities(row.id),
@@ -203,9 +208,7 @@ export class SearchService {
private getVersionEntities(repositoryId: string): RepositoryVersionEntity[] {
return this.db
.prepare(
`SELECT * FROM repository_versions WHERE repository_id = ? ORDER BY created_at DESC`
)
.prepare(`SELECT * FROM repository_versions WHERE repository_id = ? ORDER BY created_at DESC`)
.all(repositoryId) as RawVersionRow[];
}
}

4
src/lib/server/search/vector.search.ts
View File

@@ -46,9 +46,7 @@ interface RawEmbeddingRow {
*/
export function cosineSimilarity(a: Float32Array, b: Float32Array): number {
if (a.length !== b.length) {
throw new Error(
`Embedding dimension mismatch: ${a.length} vs ${b.length}`
);
throw new Error(`Embedding dimension mismatch: ${a.length} vs ${b.length}`);
}
let dot = 0;

13
src/lib/server/services/repository.service.test.ts
View File

@@ -27,10 +27,7 @@ function createTestDb(): Database.Database {
client.pragma('foreign_keys = ON');
const migrationsFolder = join(import.meta.dirname, '../db/migrations');
const migrationSql = readFileSync(
join(migrationsFolder, '0000_large_master_chief.sql'),
'utf-8'
);
const migrationSql = readFileSync(join(migrationsFolder, '0000_large_master_chief.sql'), 'utf-8');
// Drizzle migration files use `--> statement-breakpoint` as separator.
const statements = migrationSql
@@ -261,9 +258,7 @@ describe('RepositoryService.add()', () => {
});
it('throws InvalidInputError when sourceUrl is empty', () => {
expect(() =>
service.add({ source: 'github', sourceUrl: '' })
).toThrow(InvalidInputError);
expect(() => service.add({ source: 'github', sourceUrl: '' })).toThrow(InvalidInputError);
});
it('stores description and branch when provided', () => {
@@ -321,9 +316,7 @@ describe('RepositoryService.update()', () => {
});
it('throws NotFoundError for a non-existent repository', () => {
expect(() =>
service.update('/not/found', { title: 'New Title' })
).toThrow(NotFoundError);
expect(() => service.update('/not/found', { title: 'New Title' })).toThrow(NotFoundError);
});
});

8
src/lib/server/services/repository.service.ts
View File

@@ -74,9 +74,7 @@ export class RepositoryService {
.get(state) as { n: number };
return row.n;
}
const row = this.db
.prepare(`SELECT COUNT(*) as n FROM repositories`)
.get() as { n: number };
const row = this.db.prepare(`SELECT COUNT(*) as n FROM repositories`).get() as { n: number };
return row.n;
}
@@ -115,13 +113,13 @@ export class RepositoryService {
}
// Default title from owner/repo
const parts = id.split('/').filter(Boolean);
title = input.title ?? (parts[1] ?? id);
title = input.title ?? parts[1] ?? id;
} else {
// local
const existing = this.list({ limit: 9999 }).map((r) => r.id);
id = resolveLocalId(input.sourceUrl, existing);
const parts = input.sourceUrl.split('/');
title = input.title ?? (parts.at(-1) ?? 'local-repo');
title = input.title ?? parts.at(-1) ?? 'local-repo';
}
// Check for collision

14
src/lib/server/services/version.service.test.ts
View File

@@ -25,14 +25,8 @@ function createTestDb(): Database.Database {
const migrationsFolder = join(import.meta.dirname, '../db/migrations');
// Apply all migration files in order
const migration0 = readFileSync(
join(migrationsFolder, '0000_large_master_chief.sql'),
'utf-8'
);
const migration1 = readFileSync(
join(migrationsFolder, '0001_quick_nighthawk.sql'),
'utf-8'
);
const migration0 = readFileSync(join(migrationsFolder, '0000_large_master_chief.sql'), 'utf-8');
const migration1 = readFileSync(join(migrationsFolder, '0001_quick_nighthawk.sql'), 'utf-8');
// Apply first migration
const statements0 = migration0
@@ -201,9 +195,7 @@ describe('VersionService.remove()', () => {
versionService.remove('/facebook/react', 'v18.3.0');
const doc = client
.prepare(`SELECT id FROM documents WHERE id = ?`)
.get(docId);
const doc = client.prepare(`SELECT id FROM documents WHERE id = ?`).get(docId);
expect(doc).toBeUndefined();
});
});

17
src/lib/server/services/version.service.ts
View File

@@ -40,12 +40,7 @@ export class VersionService {
* @throws NotFoundError when the parent repository does not exist
* @throws AlreadyExistsError when the tag is already registered
*/
add(
repositoryId: string,
tag: string,
title?: string,
commitHash?: string
): RepositoryVersion {
add(repositoryId: string, tag: string, title?: string, commitHash?: string): RepositoryVersion {
// Verify parent repository exists.
const repo = this.db
.prepare(`SELECT id, source, source_url FROM repositories WHERE id = ?`)
@@ -115,9 +110,7 @@ export class VersionService {
*/
getByTag(repositoryId: string, tag: string): RepositoryVersion | null {
const row = this.db
.prepare(
`SELECT * FROM repository_versions WHERE repository_id = ? AND tag = ?`
)
.prepare(`SELECT * FROM repository_versions WHERE repository_id = ? AND tag = ?`)
.get(repositoryId, tag) as RepositoryVersionEntity | undefined;
return row ? RepositoryVersionMapper.fromEntity(new RepositoryVersionEntity(row)) : null;
}
@@ -137,9 +130,9 @@ export class VersionService {
previousVersions: { tag: string; title: string; commitHash?: string }[]
): RepositoryVersion[] {
// Verify parent repository exists.
const repo = this.db
.prepare(`SELECT id FROM repositories WHERE id = ?`)
.get(repositoryId) as { id: string } | undefined;
const repo = this.db.prepare(`SELECT id FROM repositories WHERE id = ?`).get(repositoryId) as
| { id: string }
| undefined;
if (!repo) {
throw new NotFoundError(`Repository ${repositoryId} not found`);

11
src/lib/server/utils/git.ts
View File

@@ -65,13 +65,10 @@ export function discoverVersionTags(options: DiscoverTagsOptions): string[] {
try {
// List all tags, sorted by commit date (newest first)
const output = execSync(
`git -C "${repoPath}" tag -l --sort=-creatordate`,
{
encoding: 'utf-8',
stdio: ['ignore', 'pipe', 'pipe']
}
).trim();
const output = execSync(`git -C "${repoPath}" tag -l --sort=-creatordate`, {
encoding: 'utf-8',
stdio: ['ignore', 'pipe', 'pipe']
}).trim();
if (!output) return [];

13
src/lib/server/utils/id-resolver.ts
View File

@@ -33,10 +33,11 @@ export function resolveLocalId(path: string, existingIds: string[]): string {
* Slugify a string to be safe for use in IDs.
*/
function slugify(str: string): string {
return str
.toLowerCase()
.replace(/[^a-z0-9-_]/g, '-')
.replace(/-+/g, '-')
.replace(/^-|-$/g, '')
|| 'repo';
return (
str
.toLowerCase()
.replace(/[^a-z0-9-_]/g, '-')
.replace(/-+/g, '-')
.replace(/^-|-$/g, '') || 'repo'
);
}

11
src/lib/server/utils/validation.ts
View File

@@ -59,13 +59,10 @@ export function errorResponse(
status: number,
details?: Record<string, unknown>
): Response {
return new Response(
JSON.stringify({ error, code, ...(details ? { details } : {}) }),
{
status,
headers: { 'Content-Type': 'application/json' }
}
);
return new Response(JSON.stringify({ error, code, ...(details ? { details } : {}) }), {
status,
headers: { 'Content-Type': 'application/json' }
});
}
/**

10
src/mcp/index.ts
View File

@@ -20,15 +20,9 @@ import { createServer } from 'node:http';
import { Server } from '@modelcontextprotocol/sdk/server/index.js';
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/streamableHttp.js';
import {
CallToolRequestSchema,
ListToolsRequestSchema
} from '@modelcontextprotocol/sdk/types.js';
import { CallToolRequestSchema, ListToolsRequestSchema } from '@modelcontextprotocol/sdk/types.js';
import {
RESOLVE_LIBRARY_ID_TOOL,
handleResolveLibraryId
} from './tools/resolve-library-id.js';
import { RESOLVE_LIBRARY_ID_TOOL, handleResolveLibraryId } from './tools/resolve-library-id.js';
import { QUERY_DOCS_TOOL, handleQueryDocs } from './tools/query-docs.js';
// ---------------------------------------------------------------------------

4
src/mcp/tools/resolve-library-id.ts
View File

@@ -9,7 +9,9 @@ import { z } from 'zod';
import { searchLibraries } from '../client.js';
export const ResolveLibraryIdSchema = z.object({
libraryName: z.string().describe('Library name to search for and resolve to a TrueRef library ID'),
libraryName: z
.string()
.describe('Library name to search for and resolve to a TrueRef library ID'),
query: z.string().describe("The user's question or context to help rank results")
});

42
src/routes/admin/jobs/+page.svelte
View File

@@ -150,7 +150,9 @@
{#if loading && jobs.length === 0}
<div class="flex items-center justify-center py-12">
<div class="text-center">
<div class="inline-block h-8 w-8 animate-spin rounded-full border-4 border-solid border-blue-600 border-r-transparent"></div>
<div
class="inline-block h-8 w-8 animate-spin rounded-full border-4 border-solid border-blue-600 border-r-transparent"
></div>
<p class="mt-2 text-gray-600">Loading jobs...</p>
</div>
</div>
@@ -160,26 +162,38 @@
</div>
{:else if jobs.length === 0}
<div class="rounded-md bg-gray-50 p-8 text-center">
<p class="text-gray-600">No jobs found. Jobs will appear here when repositories are indexed.</p>
<p class="text-gray-600">
No jobs found. Jobs will appear here when repositories are indexed.
</p>
</div>
{:else}
<div class="overflow-x-auto rounded-lg border border-gray-200 bg-white shadow">
<table class="min-w-full divide-y divide-gray-200">
<thead class="bg-gray-50">
<tr>
<th class="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider text-gray-500">
<th
class="px-6 py-3 text-left text-xs font-medium tracking-wider text-gray-500 uppercase"
>
Repository
</th>
<th class="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider text-gray-500">
<th
class="px-6 py-3 text-left text-xs font-medium tracking-wider text-gray-500 uppercase"
>
Status
</th>
<th class="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider text-gray-500">
<th
class="px-6 py-3 text-left text-xs font-medium tracking-wider text-gray-500 uppercase"
>
Progress
</th>
<th class="px-6 py-3 text-left text-xs font-medium uppercase tracking-wider text-gray-500">
<th
class="px-6 py-3 text-left text-xs font-medium tracking-wider text-gray-500 uppercase"
>
Created
</th>
<th class="px-6 py-3 text-right text-xs font-medium uppercase tracking-wider text-gray-500">
<th
class="px-6 py-3 text-right text-xs font-medium tracking-wider text-gray-500 uppercase"
>
Actions
</th>
</tr>
@@ -187,16 +201,16 @@
<tbody class="divide-y divide-gray-200 bg-white">
{#each jobs as job (job.id)}
<tr class="hover:bg-gray-50">
<td class="whitespace-nowrap px-6 py-4 text-sm font-medium text-gray-900">
<td class="px-6 py-4 text-sm font-medium whitespace-nowrap text-gray-900">
{job.repositoryId}
{#if job.versionId}
<span class="ml-1 text-xs text-gray-500">@{job.versionId}</span>
{/if}
</td>
<td class="whitespace-nowrap px-6 py-4 text-sm text-gray-500">
<td class="px-6 py-4 text-sm whitespace-nowrap text-gray-500">
<JobStatusBadge status={job.status} />
</td>
<td class="whitespace-nowrap px-6 py-4 text-sm text-gray-500">
<td class="px-6 py-4 text-sm whitespace-nowrap text-gray-500">
<div class="flex items-center">
<span class="mr-2">{job.progress}%</span>
<div class="h-2 w-32 rounded-full bg-gray-200">
@@ -212,10 +226,10 @@
{/if}
</div>
</td>
<td class="whitespace-nowrap px-6 py-4 text-sm text-gray-500">
<td class="px-6 py-4 text-sm whitespace-nowrap text-gray-500">
{formatDate(job.createdAt)}
</td>
<td class="whitespace-nowrap px-6 py-4 text-right text-sm font-medium">
<td class="px-6 py-4 text-right text-sm font-medium whitespace-nowrap">
<div class="flex justify-end gap-2">
{#if canPause(job.status)}
<button
@@ -256,9 +270,7 @@
</div>
{#if loading}
<div class="mt-4 text-center text-sm text-gray-500">
Refreshing...
</div>
<div class="mt-4 text-center text-sm text-gray-500">Refreshing...</div>
{/if}
{/if}
</div>

65
src/routes/api/v1/context/+server.ts
View File

@@ -20,11 +20,7 @@ import { createProviderFromProfile } from '$lib/server/embeddings/registry';
import type { EmbeddingProfile } from '$lib/server/db/schema';
import { parseLibraryId } from '$lib/server/api/library-id';
import { selectSnippetsWithinBudget, DEFAULT_TOKEN_BUDGET } from '$lib/server/api/token-budget';
import {
formatContextJson,
formatContextTxt,
CORS_HEADERS
} from '$lib/server/api/formatters';
import { formatContextJson, formatContextTxt, CORS_HEADERS } from '$lib/server/api/formatters';
import type { ContextResponseMetadata } from '$lib/server/mappers/context-response.mapper';
// ---------------------------------------------------------------------------
@@ -36,9 +32,10 @@ function getServices(db: ReturnType<typeof getClient>) {
// Load the active embedding profile from the database
const profileRow = db
.prepare<[], EmbeddingProfile>(
'SELECT * FROM embedding_profiles WHERE is_default = 1 AND enabled = 1 LIMIT 1'
)
.prepare<
[],
EmbeddingProfile
>('SELECT * FROM embedding_profiles WHERE is_default = 1 AND enabled = 1 LIMIT 1')
.get();
const provider = profileRow ? createProviderFromProfile(profileRow) : null;
@@ -53,7 +50,10 @@ interface RawRepoConfig {
function getRules(db: ReturnType<typeof getClient>, repositoryId: string): string[] {
const row = db
.prepare<[string], RawRepoConfig>(`SELECT rules FROM repository_configs WHERE repository_id = ?`)
.prepare<
[string],
RawRepoConfig
>(`SELECT rules FROM repository_configs WHERE repository_id = ?`)
.get(repositoryId);
if (!row?.rules) return [];
@@ -88,9 +88,10 @@ function getSnippetVersionTags(
const placeholders = versionIds.map(() => '?').join(', ');
const rows = db
.prepare<string[], RawVersionRow>(
`SELECT id, tag FROM repository_versions WHERE id IN (${placeholders})`
)
.prepare<
string[],
RawVersionRow
>(`SELECT id, tag FROM repository_versions WHERE id IN (${placeholders})`)
.all(...versionIds);
return Object.fromEntries(rows.map((row) => [row.id, row.tag]));
@@ -116,13 +117,10 @@ export const GET: RequestHandler = async ({ url }) => {
const query = url.searchParams.get('query');
if (!query || !query.trim()) {
return new Response(
JSON.stringify({ error: 'query is required', code: 'MISSING_PARAMETER' }),
{
status: 400,
headers: { 'Content-Type': 'application/json', ...CORS_HEADERS }
}
);
return new Response(JSON.stringify({ error: 'query is required', code: 'MISSING_PARAMETER' }), {
status: 400,
headers: { 'Content-Type': 'application/json', ...CORS_HEADERS }
});
}
const responseType = url.searchParams.get('type') ?? 'json';
@@ -157,9 +155,10 @@ export const GET: RequestHandler = async ({ url }) => {
// Verify the repository exists and check its state.
const repo = db
.prepare<[string], RawRepoState>(
`SELECT id, state, title, source, source_url, branch FROM repositories WHERE id = ?`
)
.prepare<
[string],
RawRepoState
>(`SELECT id, state, title, source, source_url, branch FROM repositories WHERE id = ?`)
.get(parsed.repositoryId);
if (!repo) {
@@ -193,9 +192,10 @@ export const GET: RequestHandler = async ({ url }) => {
let resolvedVersion: RawVersionRow | undefined;
if (parsed.version) {
resolvedVersion = db
.prepare<[string, string], RawVersionRow>(
`SELECT id, tag FROM repository_versions WHERE repository_id = ? AND tag = ?`
)
.prepare<
[string, string],
RawVersionRow
>(`SELECT id, tag FROM repository_versions WHERE repository_id = ? AND tag = ?`)
.get(parsed.repositoryId, parsed.version);
// Version not found is not fatal — fall back to default branch.
@@ -240,13 +240,14 @@ export const GET: RequestHandler = async ({ url }) => {
sourceUrl: repo.source_url,
branch: repo.branch
},
version: parsed.version || resolvedVersion
? {
requested: parsed.version ?? null,
resolved: resolvedVersion?.tag ?? null,
id: resolvedVersion?.id ?? null
}
: null,
version:
parsed.version || resolvedVersion
? {
requested: parsed.version ?? null,
resolved: resolvedVersion?.tag ?? null,
id: resolvedVersion?.id ?? null
}
: null,
snippetVersions
};

2
src/routes/api/v1/fs/browse/+server.ts
View File

@@ -10,7 +10,7 @@ export const GET: RequestHandler = ({ url }) => {
let entries: { name: string; path: string; isGitRepo: boolean }[] = [];
let error: string | null = null;
let resolved = target;
const resolved = target;
try {
const items = fs.readdirSync(target, { withFileTypes: true });

10
src/routes/api/v1/jobs/[id]/cancel/+server.ts
View File

@@ -7,7 +7,11 @@ import type { RequestHandler } from './$types';
import { getClient } from '$lib/server/db/client.js';
import { IndexingJobMapper } from '$lib/server/mappers/indexing-job.mapper.js';
import { JobQueue } from '$lib/server/pipeline/job-queue.js';
import { handleServiceError, NotFoundError, InvalidInputError } from '$lib/server/utils/validation.js';
import {
handleServiceError,
NotFoundError,
InvalidInputError
} from '$lib/server/utils/validation.js';
export const POST: RequestHandler = ({ params }) => {
try {
@@ -19,9 +23,7 @@ export const POST: RequestHandler = ({ params }) => {
const success = queue.cancelJob(params.id);
if (!success) {
throw new InvalidInputError(
`Cannot cancel job ${params.id} - job is already done or failed`
);
throw new InvalidInputError(`Cannot cancel job ${params.id} - job is already done or failed`);
}
// Fetch updated job

6
src/routes/api/v1/jobs/[id]/pause/+server.ts
View File

@@ -7,7 +7,11 @@ import type { RequestHandler } from './$types';
import { getClient } from '$lib/server/db/client.js';
import { IndexingJobMapper } from '$lib/server/mappers/indexing-job.mapper.js';
import { JobQueue } from '$lib/server/pipeline/job-queue.js';
import { handleServiceError, NotFoundError, InvalidInputError } from '$lib/server/utils/validation.js';
import {
handleServiceError,
NotFoundError,
InvalidInputError
} from '$lib/server/utils/validation.js';
export const POST: RequestHandler = ({ params }) => {
try {

10
src/routes/api/v1/jobs/[id]/resume/+server.ts
View File

@@ -7,7 +7,11 @@ import type { RequestHandler } from './$types';
import { getClient } from '$lib/server/db/client.js';
import { IndexingJobMapper } from '$lib/server/mappers/indexing-job.mapper.js';
import { JobQueue } from '$lib/server/pipeline/job-queue.js';
import { handleServiceError, NotFoundError, InvalidInputError } from '$lib/server/utils/validation.js';
import {
handleServiceError,
NotFoundError,
InvalidInputError
} from '$lib/server/utils/validation.js';
export const POST: RequestHandler = ({ params }) => {
try {
@@ -19,7 +23,9 @@ export const POST: RequestHandler = ({ params }) => {
const success = queue.resumeJob(params.id);
if (!success) {
throw new InvalidInputError(`Cannot resume job ${params.id} - only paused jobs can be resumed`);
throw new InvalidInputError(
`Cannot resume job ${params.id} - only paused jobs can be resumed`
);
}
// Fetch updated job

4
src/routes/api/v1/libs/+server.ts
View File

@@ -58,9 +58,7 @@ export const POST: RequestHandler = async ({ request }) => {
let jobResponse: ReturnType<typeof IndexingJobMapper.toDto> | null = null;
if (body.autoIndex !== false) {
const queue = getQueue();
const job = queue
? queue.enqueue(repo.id)
: service.createIndexingJob(repo.id);
const job = queue ? queue.enqueue(repo.id) : service.createIndexingJob(repo.id);
jobResponse = IndexingJobMapper.toDto(job);
}

4
src/routes/api/v1/libs/[id]/index/+server.ts
View File

@@ -28,9 +28,7 @@ export const POST: RequestHandler = async ({ params, request }) => {
// Use the queue so processNext() is triggered immediately.
// Falls back to direct DB insert if the queue isn't initialised yet.
const queue = getQueue();
const job = queue
? queue.enqueue(id, versionId)
: service.createIndexingJob(id, versionId);
const job = queue ? queue.enqueue(id, versionId) : service.createIndexingJob(id, versionId);
return json({ job: IndexingJobMapper.toDto(job) }, { status: 202 });
} catch (err) {

1
src/routes/api/v1/settings/embedding/+server.ts
View File

@@ -146,4 +146,3 @@ function sanitizeProfile(profile: EmbeddingProfile): EmbeddingProfile {
}
return profile;
}

8
src/routes/api/v1/settings/embedding/test/+server.ts
View File

@@ -16,9 +16,10 @@ export const GET: RequestHandler = async () => {
try {
const db = getClient();
const profile = db
.prepare<[], EmbeddingProfile>(
'SELECT * FROM embedding_profiles WHERE is_default = 1 AND enabled = 1 LIMIT 1'
)
.prepare<
[],
EmbeddingProfile
>('SELECT * FROM embedding_profiles WHERE is_default = 1 AND enabled = 1 LIMIT 1')
.get();
if (!profile) {
@@ -42,7 +43,6 @@ export const GET: RequestHandler = async () => {
}
};
export const POST: RequestHandler = async ({ request }) => {
try {
const body = await request.json();

6
src/routes/repos/[id]/+page.svelte
View File

@@ -8,7 +8,9 @@
let { data }: { data: PageData } = $props();
// Initialized empty; $effect syncs from data prop on every navigation/reload.
let repo = $state<Repository & { versions?: RepositoryVersion[] }>({} as Repository & { versions?: RepositoryVersion[] });
let repo = $state<Repository & { versions?: RepositoryVersion[] }>(
{} as Repository & { versions?: RepositoryVersion[] }
);
let recentJobs = $state<IndexingJob[]>([]);
$effect(() => {
if (data.repo) repo = data.repo;
@@ -189,7 +191,7 @@
<dl class="grid grid-cols-1 gap-y-2 text-sm sm:grid-cols-2">
<div class="flex gap-2">
<dt class="text-gray-500">Source</dt>
<dd class="font-medium capitalize text-gray-900">{repo.source}</dd>
<dd class="font-medium text-gray-900 capitalize">{repo.source}</dd>
</div>
<div class="flex gap-2">
<dt class="text-gray-500">Branch</dt>

8
src/routes/search/+page.svelte
View File

@@ -227,7 +227,9 @@
<div class="rounded-xl border border-gray-200 bg-white p-6 shadow-sm">
<div class="mb-4 flex items-center gap-3">
<div class="flex min-w-0 flex-1 items-center gap-2">
<span class="shrink-0 rounded bg-green-100 px-2 py-0.5 text-xs font-medium text-green-700">
<span
class="shrink-0 rounded bg-green-100 px-2 py-0.5 text-xs font-medium text-green-700"
>
Selected
</span>
<span class="truncate font-mono text-sm text-gray-700">{selectedLibraryTitle}</span>
@@ -285,7 +287,9 @@
{:else if query && !loadingSnippets && snippets.length === 0 && !snippetError}
<div class="flex flex-col items-center py-16 text-center">
<p class="text-sm text-gray-500">No snippets found for that query.</p>
<p class="mt-1 text-xs text-gray-400">Try a different question or select another library.</p>
<p class="mt-1 text-xs text-gray-400">
Try a different question or select another library.
</p>
</div>
{/if}
{/if}

6
src/routes/settings/+page.svelte
View File

@@ -203,7 +203,11 @@
: 'border border-gray-200 text-gray-700 hover:bg-gray-50'
].join(' ')}
>
{p === 'none' ? 'None (FTS5 only)' : p === 'openai' ? 'OpenAI-compatible' : 'Local Model'}
{p === 'none'
? 'None (FTS5 only)'
: p === 'openai'
? 'OpenAI-compatible'
: 'Local Model'}
</button>
{/each}
</div>