bd sync: 2025-12-21 21:45:59

.beads/issues.jsonl

@@ -139,7 +139,7 @@
 {"id":"gt-7o7","title":"Session pre-shutdown checks","description":"Session stop should verify clean state before killing, like PGT.\n\n## Pre-Shutdown Checks\n\n### 1. Git Working Tree Clean\n```go\nfunc checkGitClean(clonePath string) error {\n    // git status --porcelain\n    // Fail if any output\n}\n```\n\n### 2. All Commits Pushed\n```go\nfunc checkCommitsPushed(clonePath string) error {\n    // git log origin/HEAD..HEAD\n    // Fail if any unpushed commits\n}\n```\n\n### 3. Assigned Issues Handled\n```go\nfunc checkIssuesHandled(polecat *Polecat) error {\n    // If polecat.Issue != \"\", check if closed or reassigned\n}\n```\n\n### 4. Beads Synced\n```go\nfunc checkBeadsSynced(clonePath string) error {\n    // bd sync --status in clone directory\n}\n```\n\n## Behavior on Failure\n1. First attempt: Nudge worker to fix\n2. Retry up to 3 times with delay\n3. After retries: Escalate to Witness/Mayor\n\n## Integration\nModify internal/session/manager.go Stop():\n```go\nfunc (m *Manager) Stop(polecat string, force bool) error {\n    if !force {\n        if err := m.runPreShutdownChecks(polecat); err != nil {\n            return fmt.Errorf(\"pre-shutdown checks failed: %w\", err)\n        }\n    }\n    // existing stop logic\n}\n```\n\n## Flags\n- --force: Skip checks\n- --grace-period N: Time to wait for fixes\n\n## Dependencies\n- Ties into gt-69l (hook system) - can be hook-based\n- Ties into gt-f8v (Witness pre-kill verification)\n\n## Acceptance Criteria\n- [ ] Stop fails if uncommitted changes (without --force)\n- [ ] Stop fails if unpushed commits\n- [ ] Clear error messages with fix instructions\n- [ ] --force bypasses all checks","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-16T14:47:55.968983-08:00","updated_at":"2025-12-16T16:05:02.795812-08:00"}
 {"id":"gt-7oow","title":"gt mail: Cross-level routing is broken","description":"**Problem:**\nWhen Mayor (at ~/gt) sends mail to a rig worker (gastown/crew/max), the message lands in town-level beads (~/.beads/) but the recipient checks rig-level beads (crew/max/.beads/).\n\n**Reproduction:**\n```bash\ncd ~/gt\ngt mail send gastown/crew/max -s 'Test' -m 'body'\n# Message goes to ~/gt/.beads/ with prefix hq-*\n\ncd ~/gt/gastown/crew/max  \ngt mail inbox\n# Does NOT see the message - it's looking in crew/max/.beads/\n```\n\n**Root cause:**\n`findBeadsWorkDir()` walks up from CWD to find .beads. `Router.Send()` runs `bd create` in that directory. This means messages always go to the sender's beads, not the recipient's.\n\n**Fix options:**\n1. Route based on recipient address - if sending to rig/*, use that rig's .beads\n2. Use a single shared beads database for all mail (simpler but less isolated)\n3. Teach agents to check both levels (workaround, not fix)\n\n**Related:**\n- gt-ngu1: Pinned beads sorting (done but pointless if mail doesn't route)\n- This blocks all cross-level mail functionality","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-12-20T17:57:30.258991-08:00","updated_at":"2025-12-20T18:35:54.390121-08:00","closed_at":"2025-12-20T18:35:54.390121-08:00"}
 {"id":"gt-7q4","title":"HOP: Skill vectors on work items","description":"Add skill embeddings to work items for capability-based matching. See ~/ai/stevey-gastown/hop/CONTEXT.md. Post-v0.1 work.","status":"open","priority":3,"issue_type":"feature","created_at":"2025-12-17T01:00:43.251085-08:00","updated_at":"2025-12-17T01:00:43.251085-08:00"}
-{"id":"gt-7sqi","title":"Refactor: Extract common manager creation boilerplate","description":"Five nearly identical functions exist for creating managers:\n- getPolecatManager (polecat.go:241)\n- getSessionManager (session.go:183)\n- getCrewManager (crew_helpers.go:44)\n- getRefineryManager (refinery.go:116)\n- getWitnessManager (witness.go:102)\n\nAll follow the same pattern: find workspace, load config, get rig, create manager. Should extract to a common helper that takes a factory function.","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-21T21:34:30.495275-08:00","updated_at":"2025-12-21T21:34:30.495275-08:00"}
+{"id":"gt-7sqi","title":"Refactor: Extract common manager creation boilerplate","description":"Five nearly identical functions exist for creating managers:\n- getPolecatManager (polecat.go:241)\n- getSessionManager (session.go:183)\n- getCrewManager (crew_helpers.go:44)\n- getRefineryManager (refinery.go:116)\n- getWitnessManager (witness.go:102)\n\nAll follow the same pattern: find workspace, load config, get rig, create manager. Should extract to a common helper that takes a factory function.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-21T21:34:30.495275-08:00","updated_at":"2025-12-21T21:45:39.65029-08:00","closed_at":"2025-12-21T21:45:39.65029-08:00","close_reason":"Extracted common getRig() helper in internal/cmd/rig_helpers.go, updated all 5 manager creation functions to use it"}
 {"id":"gt-7tt8","title":"Default crew name should be something better than 'main'","description":"When creating a new rig, the default crew worker name is 'main'. This is confusing since:\n\n1. 'main' is also the git branch name\n2. It doesn't convey that this is the user's personal workspace\n3. Crew names should feel more personal/distinct\n\nConsider alternatives like:\n- 'home' - the user's home base\n- 'desk' - their personal desk\n- 'joe/max/etc' - actual name-based defaults\n- Let user pick during rig init","status":"open","priority":3,"issue_type":"task","created_at":"2025-12-21T16:46:51.049367-08:00","updated_at":"2025-12-21T16:46:59.133599-08:00"}
 {"id":"gt-7we","title":"Swarms of One: Lightweight single-worker task dispatch","description":"Design and implement a lightweight pattern for firing off single workers to handle tasks without full swarm overhead.\n\n## Context\n\nCurrently we have:\n- town spawn: Creates a polecat in a rig with issue assignment\n- Swarms (sw-*): Full lifecycle tracking with manifest, state, events, reports\n- Ephemeral rigs (rig-*): Temporary worker groups for swarms\n\nWhat's missing: A simple way to say 'fire off a worker to do X' without swarm ceremony.\n\n## Design Questions\n\n1. Should this be a new command like 'gt fire' or an option on existing commands?\n2. Should single tasks still get swarm IDs (sw-N) for consistency/queryability?\n3. Should it default to creating new workers or support --reuse for idle polecats?\n4. How does this relate to crew workers (gt-cik)?\n\n## Possible Interface\n\ngt fire --rig gastown --issue gt-xyz [--prompt '...']\ngt fire gastown/QuickTask --issue gt-xyz\n\n## Related\n\n- gt-cik: Overseer Crew (user-managed persistent workspaces)\n- gt-kmn: Swarm System epic","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-16T16:51:02.716629-08:00","updated_at":"2025-12-16T17:23:18.589027-08:00","closed_at":"2025-12-16T17:23:18.589027-08:00"}
 {"id":"gt-82y","title":"Design: Swarm shutdown and worker cleanup","description":"Design for graceful swarm shutdown, worker cleanup, and session cycling.\n\n## Key Decisions\n\n1. Pre-kill verification uses model intelligence (not framework rules)\n2. Witness can request restart when context filling (mail self, exit)\n3. Mayor NOT involved in per-worker cleanup (Witness responsibility)\n4. Clear responsibility boundaries between Mayor/Witness/Polecat\n\n## Subtasks (implementation)\n\n- gt-sd6: Polecat decommission checklist prompting\n- gt-f8v: Witness pre-kill verification protocol\n- gt-eu9: Witness session cycling and handoff\n- gt-gl2: Mayor vs Witness cleanup responsibilities\n\n**Design complete.** Each subtask has full specification in its description.","status":"closed","priority":1,"issue_type":"epic","created_at":"2025-12-15T19:47:44.936374-08:00","updated_at":"2025-12-15T20:49:22.849598-08:00","closed_at":"2025-12-15T20:12:05.441911-08:00"}