johno/gastown
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

bd sync: 2025-12-21 22:18:15

Browse Source
This commit is contained in:
Steve Yegge
2025-12-21 22:18:15 -08:00
parent 2a8ae43041
commit 61d1973c6d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.beads/issues.jsonl
View File

@@ -250,7 +250,7 @@
{"id":"gt-ct0u","title":"Merge: gt-3x1.4","description":"branch: polecat/Nux\ntarget: main\nsource_issue: gt-3x1.4\nrig: gastown","status":"closed","priority":1,"issue_type":"merge-request","created_at":"2025-12-19T14:53:53.140259-08:00","updated_at":"2025-12-19T18:26:14.104002-08:00","closed_at":"2025-12-19T17:49:09.234713-08:00"}
{"id":"gt-ctr","title":"GGT vs PGT Gap Analysis Summary","description":"Summary of gaps comparing GGT (~4,500 LOC) to PGT (~27,700 LOC).\n\n## Critical Gaps (P1) - Existing Issues\n- gt-u1j.17: Polecat CLI (add, list, wake, sleep) - DETAILED\n- gt-u1j.16: Rig CLI (add, list, show, remove) - DETAILED\n- gt-u1j.18: Witness CLI (start, stop, status) - DETAILED\n- gt-f9x.4: Doctor framework - DETAILED\n- gt-f9x.5: Workspace doctor checks - DETAILED\n- gt-f9x.6: Rig doctor checks - DETAILED\n\n## Critical Gaps (P1) - New Issues\n- gt-a95: Refinery background daemon mode - ENHANCED\n- gt-hgk: Mail message types and threading - ENHANCED\n\n## Significant Gaps (P2) - New Issues\n- gt-d46: Mail CLI archive/purge/search - ENHANCED\n- gt-e9k: Swarm preflight/postflight - ENHANCED\n- gt-662: Swarm report generation - ENHANCED\n- gt-69l: Hook system - ENHANCED\n- gt-3yj: Agent monitoring - ENHANCED\n- gt-1ky: Workspace CLI (may overlap f9x.3) - ENHANCED\n- gt-9j9: Worker status reporting - ENHANCED\n- gt-qao: Mayor CLI - ENHANCED\n- gt-7o7: Session pre-shutdown checks - ENHANCED\n- gt-c92: Batch all command - ENHANCED\n- gt-lno: Swarm state persistence - ENHANCED\n- gt-a9y: File locking - ENHANCED\n- gt-30o: Error handling improvements - ENHANCED\n\n## Significant Gaps (P2) - Existing Issues\n- gt-kmn.12: Ephemeral rig support - DETAILED\n\n## Lower Priority (P3) - New Issues\n- gt-3fm: Mail orchestrator daemon - ENHANCED\n- gt-2kz: Cleanup commands - ENHANCED\n- gt-ebl: Names commands - ENHANCED\n- gt-1u9: Interactive prompts - ENHANCED\n- gt-8lz: Help text improvements - ENHANCED\n\n## Closed as Duplicates\n- gt-3tz → gt-u1j.17 (polecat CLI)\n- gt-e1r → gt-u1j.16 (rig CLI)\n- gt-86w → gt-f9x.4/5/6 (doctor)\n- gt-alx → gt-kmn.12 (ephemeral rigs)\n\n## Execution Order Recommendation\n1. P1 CLI commands (existing detailed issues ready to implement)\n2. gt-a95: Refinery daemon (blocks autonomous operation)\n3. gt-7o7: Pre-shutdown checks (prevents data loss)\n4. gt-a9y: File locking (prevents corruption)\n5. gt-hgk + gt-d46: Mail improvements\n6. gt-69l: Hook system (enables extensibility)\n7. Remaining P2s in any order\n8. P3s as time permits","status":"open","priority":1,"issue_type":"epic","created_at":"2025-12-16T14:49:09.555759-08:00","updated_at":"2025-12-16T16:07:58.413016-08:00"}
{"id":"gt-cu7r","title":"Implement handoffs using pinned beads","description":"Replace the current mail-based handoff system with pinned beads.\n\n## Current Problem\n\nHandoff messages get closed before the successor can read them because:\n1. `gt mail read` auto-acks (closes) messages\n2. `bd mail inbox` only shows open messages\n3. Successor sees empty inbox\n\n## Solution\n\nUse pinned beads for handoffs:\n- One pinned bead per role: `mayor-handoff`, `\u003crig\u003e-refinery-handoff`, etc.\n- Predecessor updates the content before cycling\n- Successor reads on startup via `gt prime`\n- Never closes - always available\n\n## Implementation\n\n### 1. Create handoff beads on first cycle\n- `bd create --title='Mayor Handoff' --type=task --status=pinned --assignee=mayor`\n- Store ID in role config or use well-known naming convention\n\n### 2. Update gt handoff command\n- Instead of `bd mail send`, update the pinned handoff bead\n- `bd update \u003chandoff-id\u003e --description='...handoff content...'`\n\n### 3. Update gt prime\n- Read the role's handoff bead\n- Display content to successor\n\n### 4. Compression/reset\n- `gt rig reset` clears handoff content\n- Or manual: `bd update \u003chandoff-id\u003e --description=''`\n\n## Dependencies\n\nRequires beads-6v2 (StatusPinned) to be implemented first.","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-18T21:28:05.738035-08:00","updated_at":"2025-12-19T01:57:17.034513-08:00","closed_at":"2025-12-19T01:57:17.034513-08:00"}
{"id":"gt-cvfg","title":"Use cmd.OutOrStdout instead of fmt.Print in refinery","description":"refinery/manager.go and refinery/engineer.go use fmt.Print/Println directly for user output (30+ occurrences). This breaks testability and doesn't follow cobra best practices. Should use cmd.OutOrStdout() or pass an io.Writer.\n\nAffected files:\n- internal/refinery/manager.go (lines 222, 360-361, 369, 387-393, 519, 537, 672)\n- internal/refinery/engineer.go (lines 190-211, 249, 294-297, 325-353, 362-366)","status":"open","priority":3,"issue_type":"task","created_at":"2025-12-21T21:35:08.080292-08:00","updated_at":"2025-12-21T21:35:08.080292-08:00"}
{"id":"gt-cvfg","title":"Use cmd.OutOrStdout instead of fmt.Print in refinery","description":"refinery/manager.go and refinery/engineer.go use fmt.Print/Println directly for user output (30+ occurrences). This breaks testability and doesn't follow cobra best practices. Should use cmd.OutOrStdout() or pass an io.Writer.\n\nAffected files:\n- internal/refinery/manager.go (lines 222, 360-361, 369, 387-393, 519, 537, 672)\n- internal/refinery/engineer.go (lines 190-211, 249, 294-297, 325-353, 362-366)","status":"closed","priority":3,"issue_type":"task","created_at":"2025-12-21T21:35:08.080292-08:00","updated_at":"2025-12-21T22:18:10.18202-08:00","closed_at":"2025-12-21T22:18:10.18202-08:00","close_reason":"Added io.Writer field to Manager and Engineer structs with SetOutput() methods for testability. Replaced all 30+ fmt.Print calls with fmt.Fprintf using the configurable output writer."}
{"id":"gt-cxtu","title":"Implement shared beads architecture for rig","description":"Implement redirect-based shared beads to eliminate git sync overhead within a rig.\n\n## Background\nEach polecat currently has its own .beads/ directory synced via git. This burns tokens on sync operations.\n\n## Solution\nUse bd's redirect feature:\n1. Create single shared .beads/ at rig root\n2. Polecats get redirect files pointing to shared location\n3. All agents connect to same daemon\n4. SQLite WAL + daemon serialization handles concurrency\n\n## Implementation\n1. Create shared .beads/ at rig root (e.g., ~/gt/gastown/.beads/)\n2. Update gt spawn to create redirect files:\n mkdir -p polecats/nux/.beads\n echo ../../.beads \u003e polecats/nux/.beads/redirect\n3. Test that all polecats connect to same daemon\n4. Remove git sync from intra-rig workflow\n5. Keep JSONL export for backup/cross-rig only\n\n## Reference\nbeads/polecats/rictus/internal/beads/beads.go:45 - followRedirect()","status":"closed","priority":1,"issue_type":"feature","created_at":"2025-12-20T20:19:53.6549-08:00","updated_at":"2025-12-21T14:27:43.957132-08:00","closed_at":"2025-12-21T14:27:43.957132-08:00","close_reason":"Shared beads architecture implemented: crew/polecats use redirects to mayor/rig/.beads. Also fixed mail identity format to use slashes (rig/role/name) instead of dashes."}
{"id":"gt-cxx","title":"Swarm learning: Witness needs automated context cycling","description":"Furiosa hit 2% context during swarm work. Witness role needs automated detection of low context and should trigger session cycling before agents get stuck. Add to Witness responsibilities in prompts.md.","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-16T01:21:49.67756-08:00","updated_at":"2025-12-16T01:51:39.2553-08:00","closed_at":"2025-12-16T01:51:39.2553-08:00"}
{"id":"gt-d0a","title":"Haiku-based smart stuck detection","description":"Use Haiku to analyze tmux state when signals are ambiguous.\n\n## When to Invoke\n\nOnly as escalation tier:\n1. Keepalive is stale (\u003e 2 min)\n2. Tmux shows claude is running (not idle shell)\n3. Heuristics can't determine state\n\n## Prompt\n\nCapture last 50 lines of tmux pane, ask Haiku:\n'Is this Claude agent: WORKING | STUCK | IDLE | WAITING_FOR_HUMAN?'\n\n## Cost\n\n~$0.001 per check. At 1 check/min worst case = $0.06/hour.\nIn practice, most checks avoided by keepalive signal.\n\n## Configuration\n\n```toml\n[daemon]\nsmart_detection = true\nsmart_model = \"haiku\"\nsmart_threshold = \"2m\" # only check if stale \u003e 2min\n```","status":"open","priority":3,"issue_type":"task","created_at":"2025-12-18T14:19:31.287215-08:00","updated_at":"2025-12-18T14:19:31.287215-08:00","dependencies":[{"issue_id":"gt-d0a","depends_on_id":"gt-bfd","type":"blocks","created_at":"2025-12-18T14:19:46.788667-08:00","created_by":"daemon"}]}