# GitLab Knowledge Engine - Spec Document

## Executive Summary

A self-hosted tool to extract, index, and semantically search 2+ years of GitLab data (issues, MRs, comments/notes, and MR file-change links) from 2 main repositories (~10K items). The MVP delivers semantic search as a foundational capability that enables future specialized views (file history, personal tracking, person context). Commit-level indexing is explicitly post-MVP.

---

## Discovery Summary

### Pain Points Identified
1. **Knowledge discovery** - Tribal knowledge buried in old MRs/issues that nobody can find
2. **Decision traceability** - Hard to find *why* decisions were made; context scattered across issue comments and MR discussions

### Constraints
| Constraint | Detail |
|------------|--------|
| Hosting | Self-hosted only, no external APIs |
| Compute | Local dev machine (M-series Mac assumed) |
| GitLab Access | Self-hosted instance, PAT access, no webhooks (could request) |
| Build Method | AI agents will implement; user is TypeScript expert for review |

### Target Use Cases (Priority Order)
1. **MVP: Semantic Search** - "Find discussions about authentication redesign"
2. **Future: File/Feature History** - "What decisions were made about src/auth/login.ts?"
3. **Future: Personal Tracking** - "What am I assigned to or mentioned in?"
4. **Future: Person Context** - "What's @johndoe's background in this project?"

---

## Architecture Overview

```
┌─────────────────────────────────────────────────────────────────┐
│                        GitLab API                                │
│                    (Issues, MRs, Notes)                          │
└─────────────────────────────────────────────────────────────────┘
  (Commit-level indexing explicitly post-MVP)
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│                     Data Ingestion Layer                         │
│  - Incremental sync (PAT-based polling)                         │
│  - Rate limiting / backoff                                       │
│  - Raw JSON storage for replay                                   │
│  - Dependent resource fetching (notes, MR changes)              │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│                    Data Processing Layer                        │
│  - Normalize artifacts to unified schema                        │
│  - Extract searchable documents (canonical text + metadata)     │
│  - Content hashing for change detection                         │
│  - Build relationship graph (issue↔MR↔note↔file)               │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│                      Storage Layer                               │
│  - SQLite + sqlite-vss + FTS5 (hybrid search)                   │
│  - Structured metadata in relational tables                      │
│  - Vector embeddings for semantic search                         │
│  - Full-text index for lexical search fallback                  │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│                      Query Interface                             │
│  - CLI for human testing                                         │
│  - JSON API for AI agent testing                                 │
│  - Semantic search with filters (author, date, type, label)     │
└─────────────────────────────────────────────────────────────────┘
```

### Technology Choices

| Component | Recommendation | Rationale |
|-----------|---------------|-----------|
| Language | TypeScript/Node.js | User expertise, good GitLab libs, AI agent friendly |
| Database | SQLite + sqlite-vss | Zero-config, portable, vector search built-in |
| Embeddings | Ollama + nomic-embed-text | Self-hosted, runs well on Apple Silicon, 768-dim vectors |
| CLI Framework | Commander.js or oclif | Standard, well-documented |

### Alternative Considered: Postgres + pgvector
- Pros: More scalable, better for production multi-user
- Cons: Requires running Postgres, heavier setup
- Decision: Start with SQLite for simplicity; migration path exists if needed

---

## Checkpoint Structure

Each checkpoint is a **testable milestone** where a human can validate the system works before proceeding.

### Checkpoint 0: Project Setup
**Deliverable:** Scaffolded project with GitLab API connection verified

**Tests:**
1. Run `gitlab-engine auth-test` → returns authenticated user info
2. Run `gitlab-engine doctor` → verifies:
   - Can reach GitLab baseUrl
   - PAT is present and can read configured projects
   - SQLite opens DB and migrations apply
   - Ollama reachable OR embedding disabled with clear warning

**Scope:**
- Project structure (TypeScript, ESLint, Vitest)
- GitLab API client with PAT authentication
- Environment and project configuration
- Basic CLI scaffold with `auth-test` command
- `doctor` command for environment verification
- Projects table and initial sync

**Configuration (MVP):**
```json
// gitlab-engine.config.json
{
  "gitlab": {
    "baseUrl": "https://gitlab.example.com",
    "tokenEnvVar": "GITLAB_TOKEN"
  },
  "projects": [
    { "path": "group/project-one" },
    { "path": "group/project-two" }
  ],
  "embedding": {
    "provider": "ollama",
    "model": "nomic-embed-text",
    "baseUrl": "http://localhost:11434"
  }
}
```

**DB Runtime Defaults (Checkpoint 0):**
- On every connection:
  - `PRAGMA journal_mode=WAL;`
  - `PRAGMA foreign_keys=ON;`

**Schema (Checkpoint 0):**
```sql
-- Projects table (configured targets)
CREATE TABLE projects (
  id INTEGER PRIMARY KEY,
  gitlab_project_id INTEGER UNIQUE NOT NULL,
  path_with_namespace TEXT NOT NULL,
  default_branch TEXT,
  web_url TEXT,
  created_at INTEGER,
  updated_at INTEGER,
  raw_payload_id INTEGER REFERENCES raw_payloads(id)
);
CREATE INDEX idx_projects_path ON projects(path_with_namespace);

-- Sync tracking for reliability
CREATE TABLE sync_runs (
  id INTEGER PRIMARY KEY,
  started_at INTEGER NOT NULL,
  finished_at INTEGER,
  status TEXT NOT NULL,          -- 'running' | 'succeeded' | 'failed'
  command TEXT NOT NULL,         -- 'ingest issues' | 'sync' | etc.
  error TEXT
);

-- Sync cursors for primary resources only
-- Notes and MR changes are dependent resources (fetched via parent updates)
CREATE TABLE sync_cursors (
  project_id INTEGER NOT NULL REFERENCES projects(id),
  resource_type TEXT NOT NULL,   -- 'issues' | 'merge_requests'
  updated_at_cursor INTEGER,     -- last fully processed updated_at (ms epoch)
  tie_breaker_id INTEGER,        -- last fully processed gitlab_id (for stable ordering)
  PRIMARY KEY(project_id, resource_type)
);

-- Raw payload storage (decoupled from entity tables)
CREATE TABLE raw_payloads (
  id INTEGER PRIMARY KEY,
  source TEXT NOT NULL,          -- 'gitlab'
  resource_type TEXT NOT NULL,   -- 'project' | 'issue' | 'mr' | 'note'
  gitlab_id INTEGER NOT NULL,
  fetched_at INTEGER NOT NULL,
  json TEXT NOT NULL
);
CREATE INDEX idx_raw_payloads_lookup ON raw_payloads(resource_type, gitlab_id);
```

---

### Checkpoint 1: Issue Ingestion
**Deliverable:** All issues from target repos stored locally

**Test:** Run `gitlab-engine ingest --type=issues` → count matches GitLab; run `gitlab-engine list issues --limit=10` → displays issues correctly

**Scope:**
- Issue fetcher with pagination handling
- Raw JSON storage in raw_payloads table
- Normalized issue schema in SQLite
- Labels ingestion derived from issue payload:
  - Always persist label names from `labels: string[]`
  - Optionally request `with_labels_details=true` to capture color/description when available
- Incremental sync support (run tracking + per-project cursor)
- Basic list/count CLI commands

**Reliability/Idempotency Rules:**
- Every ingest/sync creates a `sync_runs` row
- Single-flight: refuse to start if an existing run is `running` (unless `--force`)
- Cursor advances only after successful transaction commit per page/batch
- Ordering: `updated_at ASC`, tie-breaker `gitlab_id ASC`
- Use explicit transactions for batch inserts

**Schema Preview:**
```sql
CREATE TABLE issues (
  id INTEGER PRIMARY KEY,
  gitlab_id INTEGER UNIQUE NOT NULL,
  project_id INTEGER NOT NULL REFERENCES projects(id),
  iid INTEGER NOT NULL,
  title TEXT,
  description TEXT,
  state TEXT,
  author_username TEXT,
  created_at INTEGER,
  updated_at INTEGER,
  web_url TEXT,
  raw_payload_id INTEGER REFERENCES raw_payloads(id)
);
CREATE INDEX idx_issues_project_updated ON issues(project_id, updated_at);
CREATE INDEX idx_issues_author ON issues(author_username);

-- Labels are derived from issue payloads (string array)
-- Uniqueness is (project_id, name) since gitlab_id isn't always available
CREATE TABLE labels (
  id INTEGER PRIMARY KEY,
  gitlab_id INTEGER,                  -- optional (only if available)
  project_id INTEGER NOT NULL REFERENCES projects(id),
  name TEXT NOT NULL,
  color TEXT,
  description TEXT
);
CREATE UNIQUE INDEX uq_labels_project_name ON labels(project_id, name);
CREATE INDEX idx_labels_name ON labels(name);

CREATE TABLE issue_labels (
  issue_id INTEGER REFERENCES issues(id),
  label_id INTEGER REFERENCES labels(id),
  PRIMARY KEY(issue_id, label_id)
);
CREATE INDEX idx_issue_labels_label ON issue_labels(label_id);
```

---

### Checkpoint 2: MR + Comments + File Links Ingestion
**Deliverable:** All MRs, discussion threads, and file-change links stored locally

**Test:** Run `gitlab-engine ingest --type=merge_requests` → count matches; run `gitlab-engine show mr 1234` → displays MR with comments and files changed

**Scope:**
- MR fetcher with pagination
- Notes fetcher (issue notes + MR notes) as a dependent resource:
  - During initial ingest: fetch notes for every issue/MR
  - During sync: refetch notes only for issues/MRs updated since cursor
- MR changes/diffs fetcher as a dependent resource:
  - During initial ingest: fetch changes for every MR
  - During sync: refetch changes only for MRs updated since cursor
- Relationship linking (note → parent issue/MR via foreign keys, MR → files)
- Extended CLI commands for MR display

**Schema Additions:**
```sql
CREATE TABLE merge_requests (
  id INTEGER PRIMARY KEY,
  gitlab_id INTEGER UNIQUE NOT NULL,
  project_id INTEGER NOT NULL REFERENCES projects(id),
  iid INTEGER NOT NULL,
  title TEXT,
  description TEXT,
  state TEXT,
  author_username TEXT,
  source_branch TEXT,
  target_branch TEXT,
  created_at INTEGER,
  updated_at INTEGER,
  merged_at INTEGER,
  web_url TEXT,
  raw_payload_id INTEGER REFERENCES raw_payloads(id)
);
CREATE INDEX idx_mrs_project_updated ON merge_requests(project_id, updated_at);
CREATE INDEX idx_mrs_author ON merge_requests(author_username);

-- Notes with explicit parent foreign keys for referential integrity
CREATE TABLE notes (
  id INTEGER PRIMARY KEY,
  gitlab_id INTEGER UNIQUE NOT NULL,
  project_id INTEGER NOT NULL REFERENCES projects(id),
  issue_id INTEGER REFERENCES issues(id),
  merge_request_id INTEGER REFERENCES merge_requests(id),
  noteable_type TEXT NOT NULL,      -- 'Issue' | 'MergeRequest'
  noteable_iid INTEGER NOT NULL,    -- parent IID (from API path)
  author_username TEXT,
  body TEXT,
  created_at INTEGER,
  updated_at INTEGER,
  system BOOLEAN,
  raw_payload_id INTEGER REFERENCES raw_payloads(id),
  -- Exactly one parent FK must be set
  CHECK (
    (noteable_type='Issue' AND issue_id IS NOT NULL AND merge_request_id IS NULL) OR
    (noteable_type='MergeRequest' AND merge_request_id IS NOT NULL AND issue_id IS NULL)
  )
);
CREATE INDEX idx_notes_issue ON notes(issue_id);
CREATE INDEX idx_notes_mr ON notes(merge_request_id);
CREATE INDEX idx_notes_author ON notes(author_username);

-- File linkage for "what MRs touched this file?" queries (with rename support)
CREATE TABLE mr_files (
  id INTEGER PRIMARY KEY,
  merge_request_id INTEGER REFERENCES merge_requests(id),
  old_path TEXT,
  new_path TEXT,
  new_file BOOLEAN,
  deleted_file BOOLEAN,
  renamed_file BOOLEAN,
  UNIQUE(merge_request_id, old_path, new_path)
);
CREATE INDEX idx_mr_files_old_path ON mr_files(old_path);
CREATE INDEX idx_mr_files_new_path ON mr_files(new_path);

-- MR labels (reuse same labels table)
CREATE TABLE mr_labels (
  merge_request_id INTEGER REFERENCES merge_requests(id),
  label_id INTEGER REFERENCES labels(id),
  PRIMARY KEY(merge_request_id, label_id)
);
CREATE INDEX idx_mr_labels_label ON mr_labels(label_id);
```

---

### Checkpoint 3: Embedding Generation
**Deliverable:** Vector embeddings generated for all text content

**Test:** Run `gitlab-engine embed --all` → progress indicator; run `gitlab-engine stats` → shows embedding coverage percentage

**Scope:**
- Ollama integration (nomic-embed-text model)
- Embedding generation pipeline (batch processing)
- Vector storage in SQLite (sqlite-vss extension)
- Progress tracking and resumability
- Document extraction layer:
  - Canonical "search documents" derived from issues/MRs/notes
  - Stable content hashing for change detection (SHA-256 of content_text)
  - Single embedding per document (chunking deferred to post-MVP)
- Denormalized metadata for fast filtering (author, labels, dates)
- Fast label filtering via `document_labels` join table

**Schema Additions:**
```sql
-- Unified searchable documents (derived from issues/MRs/notes)
CREATE TABLE documents (
  id INTEGER PRIMARY KEY,
  source_type TEXT NOT NULL,     -- 'issue' | 'merge_request' | 'note'
  source_id INTEGER NOT NULL,    -- local DB id in the source table
  project_id INTEGER NOT NULL REFERENCES projects(id),
  author_username TEXT,
  label_names TEXT,              -- JSON array (display/debug only)
  created_at INTEGER,
  updated_at INTEGER,
  url TEXT,
  title TEXT,                    -- null for notes
  content_text TEXT NOT NULL,    -- canonical text for embedding/snippets
  content_hash TEXT NOT NULL,    -- SHA-256 for change detection
  UNIQUE(source_type, source_id)
);
CREATE INDEX idx_documents_project_updated ON documents(project_id, updated_at);
CREATE INDEX idx_documents_author ON documents(author_username);
CREATE INDEX idx_documents_source ON documents(source_type, source_id);

-- Fast label filtering for documents (indexed exact-match)
CREATE TABLE document_labels (
  document_id INTEGER NOT NULL REFERENCES documents(id),
  label_name TEXT NOT NULL,
  PRIMARY KEY(document_id, label_name)
);
CREATE INDEX idx_document_labels_label ON document_labels(label_name);

-- sqlite-vss virtual table
-- Storage rule: embeddings.rowid = documents.id
CREATE VIRTUAL TABLE embeddings USING vss0(
  embedding(768)
);

-- Embedding provenance + change detection
-- document_id is PRIMARY KEY and equals embeddings.rowid
CREATE TABLE embedding_metadata (
  document_id INTEGER PRIMARY KEY REFERENCES documents(id),
  model TEXT NOT NULL,           -- 'nomic-embed-text'
  dims INTEGER NOT NULL,         -- 768
  content_hash TEXT NOT NULL,    -- copied from documents.content_hash
  created_at INTEGER NOT NULL
);
```

**Storage Rule (MVP):**
- Insert embedding with `rowid = documents.id`
- Upsert `embedding_metadata` by `document_id`
- This alignment simplifies joins and eliminates rowid mapping fragility

**Document Extraction Rules:**
- Issue → title + "\n\n" + description
- MR → title + "\n\n" + description
- Note → body (skip system notes unless they contain meaningful content)

---

### Checkpoint 4: Semantic Search
**Deliverable:** Working semantic search across all indexed content

**Tests:**
1. Run `gitlab-engine search "authentication redesign"` → returns ranked results with snippets
2. Golden queries: curated list of 10 queries with expected result *containment* (e.g., "at least one of these 3 known URLs appears in top 10")
3. `gitlab-engine search "..." --json` validates against JSON schema (stable fields present)

**Scope:**
- Hybrid retrieval:
  - Vector recall (sqlite-vss) + FTS lexical recall (fts5)
  - Merge + rerank results using Reciprocal Rank Fusion (RRF)
- Result ranking and scoring (document-level)
- Search filters: `--type=issue|mr|note`, `--author=username`, `--after=date`, `--label=name`
  - Label filtering operates on `document_labels` (indexed, exact-match)
- Output formatting: ranked list with title, snippet, score, URL
- JSON output mode for AI agent consumption

**Schema Additions:**
```sql
-- Full-text search for hybrid retrieval
CREATE VIRTUAL TABLE documents_fts USING fts5(
  title,
  content_text,
  content='documents',
  content_rowid='id'
);

-- Triggers to keep FTS in sync
CREATE TRIGGER documents_ai AFTER INSERT ON documents BEGIN
  INSERT INTO documents_fts(rowid, title, content_text)
  VALUES (new.id, new.title, new.content_text);
END;

CREATE TRIGGER documents_ad AFTER DELETE ON documents BEGIN
  INSERT INTO documents_fts(documents_fts, rowid, title, content_text)
  VALUES('delete', old.id, old.title, old.content_text);
END;

CREATE TRIGGER documents_au AFTER UPDATE ON documents BEGIN
  INSERT INTO documents_fts(documents_fts, rowid, title, content_text)
  VALUES('delete', old.id, old.title, old.content_text);
  INSERT INTO documents_fts(rowid, title, content_text)
  VALUES (new.id, new.title, new.content_text);
END;
```

**Hybrid Search Algorithm (MVP) - Reciprocal Rank Fusion:**
1. Query both vector index (top 50) and FTS5 (top 50)
2. Merge results by document_id
3. Combine with Reciprocal Rank Fusion (RRF):
   - For each retriever list, assign ranks (1..N)
   - `rrf_score = Σ 1 / (k + rank)` with k=60 (tunable)
   - RRF is simpler than weighted sums and doesn't require score normalization
4. Apply filters (type, author, date, label)
5. Return top K

**Why RRF over Weighted Sums:**
- FTS5 BM25 scores and vector distances use different scales
- Weighted sums (`0.7 * vector + 0.3 * fts`) require careful normalization
- RRF operates on ranks, not scores, making it robust to scale differences
- Well-established in information retrieval literature

**CLI Interface:**
```bash
# Basic semantic search
gitlab-engine search "why did we choose Redis"

# Pure FTS search (fallback if embeddings unavailable)
gitlab-engine search "redis" --mode=lexical

# Filtered search
gitlab-engine search "authentication" --type=mr --after=2024-01-01

# Filter by label
gitlab-engine search "performance" --label=bug --label=critical

# JSON output for programmatic use
gitlab-engine search "payment processing" --json
```

---

### Checkpoint 5: Incremental Sync
**Deliverable:** Efficient ongoing synchronization with GitLab

**Test:** Make a change in GitLab; run `gitlab-engine sync` → only fetches changed items; verify change appears in search

**Scope:**
- Delta sync based on stable cursor (updated_at + tie-breaker id)
- Dependent resources sync strategy (notes, MR changes)
- Webhook handler (optional, if webhook access granted)
- Re-embedding based on content_hash change (documents.content_hash != embedding_metadata.content_hash)
- Sync status reporting

**Correctness Rules (MVP):**
1. Fetch pages ordered by `updated_at ASC`, within identical timestamps advance by `gitlab_id ASC`
2. Cursor advances only after successful DB commit for that page
3. Dependent resources:
   - For each updated issue/MR, refetch its notes (sorted by `updated_at`)
   - For each updated MR, refetch its file changes
4. A document is queued for embedding iff `documents.content_hash != embedding_metadata.content_hash`
5. Sync run is marked 'failed' with error message if any page fails (can resume from cursor)

**Why Dependent Resource Model:**
- GitLab Notes API doesn't provide a clean global `updated_after` stream
- Notes are listed per-issue or per-MR, not as a top-level resource
- Treating notes as dependent resources (refetch when parent updates) is simpler and more correct
- Same applies to MR changes/diffs

**CLI Commands:**
```bash
# Full sync (respects cursors, only fetches new/updated)
gitlab-engine sync

# Force full re-sync (resets cursors)
gitlab-engine sync --full

# Override stale 'running' run after operator review
gitlab-engine sync --force

# Show sync status
gitlab-engine sync-status
```

---

## Future Checkpoints (Post-MVP)

### Checkpoint 6: File/Feature History View
- Map commits to MRs to discussions
- Query: "Show decision history for src/auth/login.ts"
- Ship `gitlab-engine file-history <path>` as a first-class feature here
- This command is deferred from MVP to sharpen checkpoint focus

### Checkpoint 7: Personal Dashboard
- Filter by assigned/mentioned
- Integrate with existing gitlab-inbox tool

### Checkpoint 8: Person Context
- Aggregate contributions by author
- Expertise inference from activity

### Checkpoint 9: Decision Graph
- Extract decisions from discussions (LLM-assisted)
- Visualize decision relationships

---

## Verification Strategy

Each checkpoint includes:

1. **Automated tests** - Unit tests for data transformations, integration tests for API calls
2. **CLI smoke tests** - Manual commands with expected outputs documented
3. **Data integrity checks** - Count verification against GitLab, schema validation
4. **Search quality tests** - Known queries with expected results (for Checkpoint 4+)

---

## Risk Mitigation

| Risk | Mitigation |
|------|------------|
| GitLab rate limiting | Exponential backoff, respect Retry-After headers, incremental sync |
| Embedding model quality | Start with nomic-embed-text; architecture allows model swap |
| SQLite scale limits | Monitor performance; Postgres migration path documented |
| Stale data | Incremental sync with change detection |
| Mid-sync failures | Cursor-based resumption, sync_runs audit trail |
| Search quality | Hybrid (vector + FTS5) retrieval with RRF, golden query test suite |
| Concurrent sync corruption | Single-flight protection (refuse if existing run is `running`) |

**SQLite Performance Defaults (MVP):**
- Enable `PRAGMA journal_mode=WAL;` on every connection
- Enable `PRAGMA foreign_keys=ON;` on every connection
- Use explicit transactions for page/batch inserts
- Targeted indexes on `(project_id, updated_at)` for primary resources

---

## Schema Summary

| Table | Checkpoint | Purpose |
|-------|------------|---------|
| projects | 0 | Configured GitLab projects |
| sync_runs | 0 | Audit trail of sync operations |
| sync_cursors | 0 | Resumable sync state per primary resource |
| raw_payloads | 0 | Decoupled raw JSON storage |
| issues | 1 | Normalized issues |
| labels | 1 | Label definitions (unique by project + name) |
| issue_labels | 1 | Issue-label junction |
| merge_requests | 2 | Normalized MRs |
| notes | 2 | Issue and MR comments (with parent FKs) |
| mr_files | 2 | MR file changes (with rename tracking) |
| mr_labels | 2 | MR-label junction |
| documents | 3 | Unified searchable documents |
| document_labels | 3 | Document-label junction for fast filtering |
| embeddings | 3 | Vector embeddings (sqlite-vss, rowid=document_id) |
| embedding_metadata | 3 | Embedding provenance + change detection |
| documents_fts | 4 | Full-text search index (fts5) |

---

## Resolved Decisions

| Question | Decision | Rationale |
|----------|----------|-----------|
| Commit/file linkage | **Include MR→file links** | Enables "what MRs touched this file?" without full commit history |
| Labels | **Index as filters** | Labels are well-used; `document_labels` table enables fast `--label=X` filtering |
| Labels uniqueness | **By (project_id, name)** | GitLab API returns labels as strings; gitlab_id isn't always available |
| Sync method | **Polling for MVP** | Decide on webhooks after using the system |
| Notes sync | **Dependent resource** | Notes API is per-parent, not global; refetch on parent update |
| Hybrid ranking | **RRF over weighted sums** | Simpler, no score normalization needed |
| Embedding rowid | **rowid = documents.id** | Eliminates fragile rowid mapping during upserts |
| file-history CLI | **Post-MVP (CP6)** | Sharpens MVP checkpoint focus |

---

## Next Steps

1. User approves this spec
2. Generate Checkpoint 0 PRD for project setup
3. Implement Checkpoint 0
4. Human validates → proceed to Checkpoint 1
5. Repeat for each checkpoint