Document merge command and AI duplicate detection workflow (bd-29)

- Add comprehensive merge command documentation to README.md
- Add AI agent duplicate detection workflow to AGENTS.md
- Include command syntax, examples, and best practices
- Close bd-29

Amp-Thread-ID: https://ampcode.com/threads/T-95a37593-fd67-4e99-bc84-ace580b4776d
Co-authored-by: Amp <amp@ampcode.com>

.beads/issues.jsonl

@@ -19,7 +19,7 @@
 {"id":"bd-26","title":"Make merge command idempotent for safe retry after partial failures","description":"The merge command currently performs 3 operations without an outer transaction:\n1. Migrate dependencies from source → target\n2. Update text references across all issues\n3. Close source issues\n\nIf merge fails mid-operation (network issue, daemon crash, etc.), a retry will fail or produce incorrect results because some operations already succeeded.\n\n**Goal:** Make merge idempotent so retrying after partial failure is safe and completes the remaining work.\n\n**Idempotency checks needed:**\n- Skip dependency migration if target already has the dependency\n- Skip text reference updates if already updated\n- Skip closing source issues if already closed\n- Report which operations were skipped vs performed\n\n**Example output:**\n```\n✓ Merged 2 issue(s) into bd-78\n  - Dependencies: 3 migrated, 2 already existed\n  - Text references: 5 updated, 0 already correct\n  - Source issues: 1 closed, 1 already closed\n```\n\n**Related:** bd-23 originally requested transaction support, but idempotency is a better solution for this use case since individual operations are already atomic.","design":"Current merge code already has some idempotency:\n- Dependency migration checks `alreadyExists` before adding (line ~145-151 in merge.go)\n- Text reference updates are naturally idempotent (replacing bd-X with bd-Y twice has same result)\n\nMissing idempotency:\n- CloseIssue fails if source already closed\n- Error messages don't distinguish \"already done\" from \"real failure\"\n\nImplementation:\n1. Check source issue status before closing - skip if already closed\n2. Track which operations succeeded/skipped\n3. Return detailed results for user visibility\n4. Consider adding --dry-run output showing what would be done vs skipped","status":"open","priority":2,"issue_type":"feature","created_at":"2025-10-21T23:53:44.31362-07:00","updated_at":"2025-10-22T01:03:24.905087-07:00"}
 {"id":"bd-27","title":"bd sync crashes with nil pointer when daemon is running","description":"The 'bd sync' command crashes with a nil pointer dereference when the daemon is running.\n\n**Reproduction:**\n```bash\n# With daemon running\n./bd sync\n```\n\n**Error:**\n```\npanic: runtime error: invalid memory address or nil pointer dereference\n[signal SIGSEGV: segmentation violation code=0x2 addr=0x120 pc=0x1012314ac]\n\ngoroutine 1 [running]:\nmain.exportToJSONL({0x1014ec2e0, 0x101a49900}, {0x14000028db0, 0x30})\n        /Users/stevey/src/fred/beads/cmd/bd/sync.go:245 +0x4c\n```\n\n**Root cause:**\nThe sync command's `exportToJSONL` function directly accesses `store.SearchIssues()` at line 245, but when daemon mode is active, the global `store` variable is nil. The sync command should either:\n1. Use daemon RPC when daemon is running, or\n2. Force direct mode for sync operations\n\n**Workaround:**\nUse `--no-daemon` flag: `bd sync --no-daemon`","status":"closed","priority":0,"issue_type":"bug","created_at":"2025-10-21T23:53:44.31362-07:00","updated_at":"2025-10-22T01:03:24.90534-07:00","closed_at":"2025-10-22T00:09:12.615536-07:00"}
 {"id":"bd-28","title":"Add cross-repo issue references (future enhancement)","description":"Support referencing issues across different beads repositories. Useful for tracking dependencies between separate projects.\n\nProposed syntax:\n- Local reference: bd-78 (current behavior)\n- Cross-repo by path: ~/src/other-project#bd-456\n- Cross-repo by workspace name: @project2:bd-789\n\nUse cases:\n1. Frontend project depends on backend API issue\n2. Shared library changes blocking multiple projects\n3. System administrator tracking work across machines\n4. Monorepo with separate beads databases per component\n\nImplementation challenges:\n- Storage layer needs to query external databases\n- Dependency resolution across repos\n- What if external repo not available?\n- How to handle in JSONL export/import?\n- Security: should repos be able to read others?\n\nDesign questions to resolve first:\n1. Read-only references vs full cross-repo dependencies?\n2. How to handle repo renames/moves?\n3. Absolute paths vs workspace names vs git remotes?\n4. Should bd-77 auto-discover related repos?\n\nRecommendation: \n- Gather user feedback first\n- Start with read-only references\n- Implement as plugin/extension?\n\nContext: This is mentioned in bd-77 as approach #2. Much more complex than daemon multi-repo approach. Only implement if there's strong user demand.\n\nPriority: Backlog (4) - wait for user feedback before designing","status":"closed","priority":4,"issue_type":"feature","created_at":"2025-10-21T23:53:44.31362-07:00","updated_at":"2025-10-22T01:03:24.905617-07:00","closed_at":"2025-10-20T22:00:31.966891-07:00"}
-{"id":"bd-29","title":"Document merge command and AI integration","description":"Update README, AGENTS.md with merge command examples. Document AI agent duplicate detection workflow.","status":"open","priority":1,"issue_type":"task","created_at":"2025-10-21T23:53:44.31362-07:00","updated_at":"2025-10-22T01:03:24.905923-07:00"}
+{"id":"bd-29","title":"Document merge command and AI integration","description":"Update README, AGENTS.md with merge command examples. Document AI agent duplicate detection workflow.","status":"closed","priority":1,"issue_type":"task","created_at":"2025-10-21T23:53:44.31362-07:00","updated_at":"2025-10-22T11:37:41.104918-07:00","closed_at":"2025-10-22T11:37:41.104918-07:00"}
 {"id":"bd-3","title":"Add godoc comments for auto-flush functions","description":"Add comprehensive godoc comments for findJSONLPath(), markDirtyAndScheduleFlush(), and flushToJSONL() explaining behavior, concurrency considerations, and error handling. Include notes about debouncing behavior (timer resets on each write, flush occurs 5s after LAST operation) and flush-on-exit guarantees. Located in cmd/bd/main.go:188-307.","status":"closed","priority":4,"issue_type":"chore","created_at":"2025-10-21T23:53:44.31362-07:00","updated_at":"2025-10-22T01:03:24.906177-07:00","closed_at":"2025-10-19T19:22:19.172983-07:00"}
 {"id":"bd-30","title":"Optimize export dependency queries (N+1 problem)","description":"Export triggers separate GetDependencyRecords() per issue. For large DBs (1000+ issues), this is N+1 queries. Add GetAllDependencyRecords() to fetch all dependencies in one query. Location: cmd/bd/export.go:52-59, import.go:138-142","status":"closed","priority":3,"issue_type":"task","created_at":"2025-10-21T23:53:44.31362-07:00","updated_at":"2025-10-22T01:03:24.906463-07:00","closed_at":"2025-10-14T02:51:52.19905-07:00"}
 {"id":"bd-31","title":"Add workspace config file for multi-repo management (optional enhancement)","description":"For users who want explicit control over multi-repo setup without daemon, add optional workspace config file.\n\nConfig file: ~/.beads/workspaces.toml\n\nExample:\n[workspaces]\ncurrent = \"global\"\n\n[workspace.global]\ndb = \"~/.beads/global.db\"\ndescription = \"System-wide tasks\"\n\n[workspace.project1]  \ndb = \"~/src/project1/.beads/db.sqlite\"\ndescription = \"Main product\"\n\n[workspace.project2]\ndb = \"~/src/project2/.beads/db.sqlite\"\ndescription = \"Internal tools\"\n\nCommands:\nbd workspace list                    # Show all workspaces\nbd workspace add NAME PATH           # Add workspace\nbd workspace remove NAME             # Remove workspace  \nbd workspace use NAME                # Switch active workspace\nbd workspace current                 # Show current workspace\nbd --workspace NAME \u003ccommand\u003e        # Override for single command\n\nImplementation:\n- Load config in PersistentPreRun\n- Override dbPath based on current workspace\n- Store workspace state in config file\n- Support both workspace config AND auto-discovery\n- Workspace config takes precedence over auto-discovery\n\nPriority rationale:\n- Priority 3 (low) because daemon approach already solves this\n- Only implement if users request explicit workspace management\n- Adds complexity vs daemon's automatic discovery\n\nAlternative: Users can use BEADS_DB env var for manual workspace switching today.","status":"closed","priority":3,"issue_type":"feature","created_at":"2025-10-21T23:53:44.31362-07:00","updated_at":"2025-10-22T01:03:24.906689-07:00","closed_at":"2025-10-20T16:04:27.216482-07:00"}