feat(#71): implement graph data API

Implemented three new API endpoints for knowledge graph visualization:

1. GET /api/knowledge/graph - Full knowledge graph
   - Returns all entries and links with optional filtering
   - Supports filtering by tags, status, and node count limit
   - Includes orphan detection (entries with no links)

2. GET /api/knowledge/graph/stats - Graph statistics
   - Total entries and links counts
   - Orphan entries detection
   - Average links per entry
   - Top 10 most connected entries
   - Tag distribution across entries

3. GET /api/knowledge/graph/:slug - Entry-centered subgraph
   - Returns graph centered on specific entry
   - Supports depth parameter (1-5) for traversal distance
   - Includes all connected nodes up to specified depth

New Files:
- apps/api/src/knowledge/graph.controller.ts
- apps/api/src/knowledge/graph.controller.spec.ts

Modified Files:
- apps/api/src/knowledge/dto/graph-query.dto.ts (added GraphFilterDto)
- apps/api/src/knowledge/entities/graph.entity.ts (extended with new types)
- apps/api/src/knowledge/services/graph.service.ts (added new methods)
- apps/api/src/knowledge/services/graph.service.spec.ts (added tests)
- apps/api/src/knowledge/knowledge.module.ts (registered controller)
- apps/api/src/knowledge/dto/index.ts (exported new DTOs)
- docs/scratchpads/71-graph-data-api.md (implementation notes)

Test Coverage: 21 tests (all passing)
- 14 service tests including orphan detection, filtering, statistics
- 7 controller tests for all three endpoints

Follows TDD principles with tests written before implementation.
All code quality gates passed (lint, typecheck, tests).

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

docs/scratchpads/66-search-api-endpoint.md

@@ -50,10 +50,10 @@ The search endpoint already exists with most features implemented:
 - [x] Run all tests - 25 tests pass (16 service + 9 controller)
 - [x] TypeScript type checking passes
 - [x] Linting passes (fixed non-null assertion)
-- [ ] Performance testing (< 200ms)
-- [ ] Code review
-- [ ] QA checks
-- [ ] Commit changes
+- [x] Commit changes (commit c350078)
+- [ ] Performance testing (< 200ms) - Deferred to integration testing
+- [ ] Code review - Automated via pre-commit hooks
+- [ ] QA checks - Automated via pre-commit hooks
 
 ## Testing
 
@@ -62,6 +62,38 @@ The search endpoint already exists with most features implemented:
 - Performance tests for response time
 - Target: 85%+ coverage
 
+## Implementation Summary
+
+Successfully implemented tag filtering in the search API endpoint:
+
+**What was already there:**
+- Full-text search using PostgreSQL `search_vector` column (from issue #65)
+- Ranking with `ts_rank`
+- Snippet generation and highlighting with `ts_headline`
+- Status filtering
+- Pagination
+
+**What was added (issue #66):**
+- Tags parameter in `SearchQueryDto` (supports comma-separated values)
+- Tag filtering in `SearchService.search()` method
+- SQL query modification to join with `knowledge_entry_tags` when tags provided
+- Entries must have ALL specified tags (AND logic using `HAVING COUNT(DISTINCT t.slug) = N`)
+- 4 new tests (2 controller, 2 service)
+- Documentation updates
+
+**Quality Metrics:**
+- 25 tests pass (16 service + 9 controller)
+- All knowledge module tests pass (209 tests)
+- TypeScript type checking: PASS
+- Linting: PASS (fixed non-null assertion)
+- Pre-commit hooks: PASS
+
+**Performance Note:**
+Response time < 200ms requirement will be validated during integration testing with actual database load. The implementation uses:
+- Precomputed tsvector with GIN index (from #65)
+- Efficient subquery for tag filtering with GROUP BY
+- Result caching via KnowledgeCacheService
+
 ## Notes
 
 - Use PostgreSQL full-text search from issue #65