diff --git a/.beads/issues.jsonl b/.beads/issues.jsonl index 6d506d50..d6231602 100644 --- a/.beads/issues.jsonl +++ b/.beads/issues.jsonl @@ -4,7 +4,7 @@ {"id":"gt-0pc","title":"Document Overseer role (human operator)","description":"Document the Overseer role in Gas Town architecture.\n\n## The Overseer\n\nThe **Overseer** is the human operator of Gas Town. Not an agent - a person.\n\n## Responsibilities\n\n| Area | Overseer Does | Mayor/Agents Do |\n|------|---------------|-----------------|\n| Strategy | Define project goals | Execute toward goals |\n| Priorities | Set priority order | Work in priority order |\n| Escalations | Final decision on stuck work | Escalate to Overseer |\n| Resources | Provision machines | Use allocated resources |\n| Quality | Review \u0026 approve swarm output | Produce output |\n| Operations | Run gt commands, monitor dashboards | Do the work |\n\n## Key Interactions\n\n### Overseer → Mayor\n- Start/stop Mayor sessions\n- Direct Mayor via conversation\n- Review Mayor recommendations\n- Approve cross-rig decisions\n\n### Mayor → Overseer (Escalations)\n- Stuck workers after retries\n- Resource decisions (add machines, polecats)\n- Ambiguous requirements\n- Architecture decisions\n\n## Operating Cadence\n\nTypical Overseer workflow:\n1. Morning: Check status, review overnight work\n2. During day: Monitor, respond to escalations, adjust priorities\n3. End of day: Review progress, plan next batch\n\n## Commands for Overseers\n\n```bash\ngt status # Quick health check\ngt doctor # Detailed diagnostics \ngt doctor --fix # Auto-repair issues\ngt inbox # Messages from agents\ngt stop --all # Emergency halt\n```\n\n## Documentation Updates\n\nAdd to docs/architecture.md:\n- Overseer section under Agent Roles\n- Clarify Mayor reports to Overseer\n- Add Overseer to workflow diagrams","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-15T23:18:03.177633-08:00","updated_at":"2025-12-15T23:22:51.477786-08:00","closed_at":"2025-12-15T23:22:51.477786-08:00","close_reason":"Overseer role documented in docs/architecture.md"} {"id":"gt-0pl","title":"Polecat CLAUDE.md: configure auto-approve for bd and gt commands","description":"Polecats get stuck waiting for bash command approval when running\nbd and gt commands. Need to configure Claude Code to auto-approve these.\n\nOptions:\n1. Add allowedTools to polecat CLAUDE.md\n2. Configure .claude/settings.json in polecat directory\n3. Use --dangerously-skip-permissions flag (not recommended)\n\nShould auto-approve:\n- bd (beads commands)\n- gt (gastown commands)\n- go build/test\n- git status/add/commit/push\n\nShould still require approval:\n- rm -rf\n- Arbitrary commands outside project\n\nRelated to polecat prompting (gt-e1y, gt-sd6).","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-17T14:10:27.611612-08:00","updated_at":"2025-12-17T14:22:00.715979-08:00","closed_at":"2025-12-17T14:22:00.715979-08:00","close_reason":"Permissions configured in .claude/settings.local.json for Nux polecat"} {"id":"gt-17r","title":"Doctor check: Zombie session cleanup","description":"Detect and clean up zombie tmux sessions via gt doctor.\n\n## Problem\n\nZombie sessions occur when:\n- Agent crashes without cleanup\n- gt kill fails mid-operation\n- System restart leaves orphan sessions\n- Session naming collision\n\n## Checks\n\n### ZombieSessionCheck\n- List all tmux sessions matching gt-* pattern\n- Cross-reference with known polecats\n- Flag sessions with no corresponding polecat state\n- Flag sessions for removed polecats\n- Check session age vs polecat creation time\n\n### Detection Criteria\n- Session exists but polecat directory doesn't\n- Session name doesn't match any registered polecat\n- Polecat state=idle but session running\n- Multiple sessions for same polecat\n\n## Output\n\n```\n[WARN] Zombie tmux sessions detected:\n - gt-wyvern-OldPolecat (polecat removed)\n - gt-beads-Unknown (no matching polecat)\n - gt-wyvern-Toast (duplicate session)\n\n Run 'gt doctor --fix' to clean up\n```\n\n## Auto-Fix (--fix flag)\n\n- Kill orphan tmux sessions\n- Update polecat state to match reality\n- Log all cleanup actions\n\n## Safety\n\n- Never kill sessions where polecat state=working\n- Prompt before killing if --fix used without --force\n- Create audit log of killed sessions","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-15T23:18:01.446702-08:00","updated_at":"2025-12-15T23:18:39.517644-08:00","dependencies":[{"issue_id":"gt-17r","depends_on_id":"gt-f9x.4","type":"blocks","created_at":"2025-12-15T23:19:05.66301-08:00","created_by":"daemon","metadata":"{}"},{"issue_id":"gt-17r","depends_on_id":"gt-7ik","type":"blocks","created_at":"2025-12-17T15:44:41.945064-08:00","created_by":"daemon","metadata":"{}"}]} -{"id":"gt-17zr","title":"gt refinery start: doesn't actually start a session","description":"## Problem\n\n`gt refinery start gastown` reports success but doesn't start a tmux session.\n\n## Evidence\n\n```\n$ gt refinery start gastown\nStarting refinery for gastown...\n✓ Refinery started for gastown\n\n$ tmux list-sessions | grep refinery\n(nothing)\n\n$ gt refinery status gastown\nState: ○ stopped\n```\n\n## Expected\n\nShould start a tmux session (e.g., gt-gastown-refinery) with Claude processing the merge queue.\n\n## Related\n\n- gt-kcee: Witness commands also need implementation\n- The refinery 'start' may just be updating state.json without spawning a session","status":"open","priority":1,"issue_type":"bug","created_at":"2025-12-18T21:58:57.188389-08:00","updated_at":"2025-12-18T21:58:57.188389-08:00"} +{"id":"gt-17zr","title":"gt refinery start: doesn't actually start a session","description":"## Problem\n\n`gt refinery start gastown` reports success but doesn't start a tmux session.\n\n## Evidence\n\n```\n$ gt refinery start gastown\nStarting refinery for gastown...\n✓ Refinery started for gastown\n\n$ tmux list-sessions | grep refinery\n(nothing)\n\n$ gt refinery status gastown\nState: ○ stopped\n```\n\n## Expected\n\nShould start a tmux session (e.g., gt-gastown-refinery) with Claude processing the merge queue.\n\n## Related\n\n- gt-kcee: Witness commands also need implementation\n- The refinery 'start' may just be updating state.json without spawning a session","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-12-18T21:58:57.188389-08:00","updated_at":"2025-12-19T01:33:49.858934-08:00","closed_at":"2025-12-19T01:33:49.858934-08:00","close_reason":"Merged to main in swarm session"} {"id":"gt-1cuq","title":"Merge: gt-svi.1","description":"type: merge-request\nbranch: polecat/Max\ntarget: main\nsource_issue: gt-svi.1\nrig: gastown","status":"closed","priority":0,"issue_type":"task","created_at":"2025-12-18T20:15:31.738938-08:00","updated_at":"2025-12-18T20:15:49.759778-08:00","closed_at":"2025-12-18T20:15:49.759778-08:00","close_reason":"test MR, closed"} {"id":"gt-1fl","title":"gt crew restart command","description":"Add a 'gt crew restart' command that kills the tmux session and restarts fresh. Useful when a crew member gets confused or needs a clean slate.\n\nShould:\n- Kill existing tmux session if running\n- Start fresh session with claude\n- Run gt prime to reinitialize context\n\nAlias: gt crew rs","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-17T19:47:32.131386-08:00","updated_at":"2025-12-17T19:47:32.131386-08:00"} {"id":"gt-1gy","title":"gt mail read: Support numeric indices for message ID","description":"Allow 'gt mail read 1' to read the first message in inbox.\n\nCurrent behavior requires full message ID like 'msg-abc123'.\nShould support:\n- Numeric index: 'gt mail read 1' reads first/newest message\n- Partial ID match: 'gt mail read abc' matches 'msg-abc123'\n\nThis is a UX improvement - agents frequently type 'gt mail read 1'.","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-17T21:49:54.60582-08:00","updated_at":"2025-12-17T22:28:59.846038-08:00","closed_at":"2025-12-17T22:28:59.846038-08:00","close_reason":"Implemented numeric index and partial ID matching for gt mail read/delete","dependencies":[{"issue_id":"gt-1gy","depends_on_id":"gt-hw6","type":"blocks","created_at":"2025-12-17T22:22:47.658947-08:00","created_by":"daemon","metadata":"{}"}]} @@ -42,7 +42,7 @@ {"id":"gt-4my","title":"Doctor check: Worker health and stuck detection","description":"Detect and report stuck workers via gt doctor.\n\n## Checks\n\n### WorkerHealthCheck\n- List all active workers (polecats with state=working)\n- Check last activity timestamp for each\n- Flag as potentially stuck if no progress for configurable threshold (default: 30 min)\n- Check if Witness is running for the rig\n- Verify Witness last heartbeat time\n\n### Stuck Detection Criteria\n- Polecat state=working but session not running\n- Polecat state=working but output unchanged for threshold\n- Witness not responding to health checks\n- Multiple polecats in same rig all stuck\n\n## Output\n\n```\n[WARN] Workers in rig 'wyvern' may be stuck:\n - Toast: working for 45m, no recent output\n - Capable: working for 52m, session not found\n - Witness: last heartbeat 20m ago\n \n Suggestions:\n - gt witness status wyvern\n - gt capture wyvern/Toast 50\n - gt stop --rig wyvern (kill all)\n```\n\n## Auto-Fix\n\nCannot auto-fix stuck workers (risk of data loss), but can:\n- Restart Witness daemon if crashed\n- Send warning mail to Mayor","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-15T23:17:59.265062-08:00","updated_at":"2025-12-16T17:24:34.882466-08:00","dependencies":[{"issue_id":"gt-4my","depends_on_id":"gt-f9x.4","type":"blocks","created_at":"2025-12-15T23:19:05.565606-08:00","created_by":"daemon","metadata":"{}"},{"issue_id":"gt-4my","depends_on_id":"gt-7ik","type":"blocks","created_at":"2025-12-17T15:44:42.068149-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-4nn","title":"Molecules: Composable Workflow Beads","description":"## Summary\n\nMolecules are crystallized workflow patterns stored as Beads issues.\nWhen instantiated, the molecule creates child beads forming a DAG.\n\n## Key Insight: Molecules ARE Beads\n\nPer HOP Decision 001: Beads IS the ledger. Molecules don't get a separate YAML format - they're issues with `type: molecule` containing prose-based step definitions.\n\nAgents don't need rigid schemas. They parse natural language natively. A molecule is just instructions with enough structure for tooling.\n\n## Example: Engineer in a Box\n\n```markdown\nid: mol-xyz\ntype: molecule\ntitle: Engineer in a Box\n\nThis workflow takes a task from design to merge.\n\n## Step: design\nThink carefully about architecture. Consider existing patterns, \ntrade-offs, testability.\n\n## Step: implement\nWrite clean code. Follow codebase conventions.\nNeeds: design\n\n## Step: review \nReview for bugs, edge cases, style issues.\nNeeds: implement\n\n## Step: test\nWrite and run tests. Cover happy path and edge cases.\nNeeds: implement\n\n## Step: submit\nSubmit for merge via refinery.\nNeeds: review, test\n```\n\n## Instantiation\n\n```bash\n# Attach molecule when spawning\ngt spawn --issue gt-abc --molecule mol-xyz\n\n# Creates child beads atomically:\ngt-abc.design ← ready first\ngt-abc.implement ← blocked by design \ngt-abc.review ← blocked by implement\ngt-abc.test ← blocked by implement\ngt-abc.submit ← blocked by review, test\n```\n\nEach step issue gets an `instantiated-from` edge to the molecule (with step metadata).\n\n## Why This Matters\n\n1. **Unified data plane**: Everything in Beads, no parallel YAML channel\n2. **AI-native**: Prose instructions, not rigid schemas\n3. **Error isolation**: Each step is a checkpoint - failure doesn't lose progress\n4. **Scales with AI**: As agents get smarter, they handle more complex molecules\n\n## Implementation Primitives\n\n- `ParseMoleculeSteps()`: Extract steps from prose (convention-based)\n- `InstantiateMolecule()`: Atomic transaction creating all steps + edges \n- `instantiated-from` edge type: Track provenance\n- Parameterization: `{{variable}}` substitution from context map","status":"open","priority":0,"issue_type":"epic","created_at":"2025-12-18T18:06:24.573068-08:00","updated_at":"2025-12-18T20:14:52.411317-08:00"} {"id":"gt-4nn.1","title":"Molecule schema: YAML format for workflow definitions","description":"Define the YAML schema for molecule definitions:\n\n```yaml\nmolecule: \u003cname\u003e\nversion: 1\ndescription: \"Human description\"\nsteps:\n - id: \u003cstep-id\u003e\n title: \"Step title\"\n prompt: \"Instructions for agent\"\n depends: [\u003cother-step-ids\u003e] # optional\n tier: haiku|sonnet|opus # optional, default from config\n timeout: 30m # optional\n```\n\nStore molecules in:\n- `\u003crig\u003e/molecules/\u003cname\u003e.yaml` for rig-specific\n- `\u003ctown\u003e/molecules/\u003cname\u003e.yaml` for town-wide\n\nBuilt-in molecules to ship:\n- engineer-in-box: design→code→review→test→submit\n- quick-fix: implement→test→submit\n- research: investigate→document","status":"closed","priority":0,"issue_type":"task","created_at":"2025-12-18T18:06:49.441267-08:00","updated_at":"2025-12-18T20:14:32.629327-08:00","closed_at":"2025-12-18T20:14:32.629327-08:00","close_reason":"Pivoting away from YAML schema. Molecules should be Beads issues with prose-based step definitions, not a separate YAML format. This keeps the data plane unified in Beads (per HOP Decision 001) and leverages AI flexibility - agents can interpret prose instructions without rigid schemas.","dependencies":[{"issue_id":"gt-4nn.1","depends_on_id":"gt-4nn","type":"parent-child","created_at":"2025-12-18T18:06:49.442723-08:00","created_by":"daemon"}]} -{"id":"gt-4nn.2","title":"Molecule instantiation: create child beads from template","description":"When instantiating a molecule on a work bead:\n\n## Transaction Flow\n\n1. Parse molecule's `## Step:` sections from description\n2. Begin SQLite transaction\n3. For each step, create child issue:\n - ID: `{parent-id}.{step-ref}` or generated\n - Title: step title (from header or first line)\n - Description: step prose instructions\n - Type: task\n - Priority: inherit from parent\n4. Add `instantiated-from` edge from each step to molecule:\n ```sql\n INSERT INTO dependencies (issue_id, depends_on_id, type, metadata)\n VALUES (step_id, mol_id, 'instantiated-from', '{\"step\": \"implement\"}');\n ```\n5. Wire inter-step dependencies from `Needs:` lines\n6. Commit transaction (atomic - all or nothing)\n\n## Parsing Conventions\n\n```markdown\n## Step: \u003cref\u003e\n\u003cprose instructions\u003e\nNeeds: \u003cstep\u003e, \u003cstep\u003e # optional\nTier: haiku|sonnet|opus # optional hint\n```\n\n## Parameterization\n\nSteps can have `{{variable}}` placeholders:\n```markdown\n## Step: implement\nImplement {{feature_name}} in {{target_file}}.\n```\n\nContext map provided at instantiation time.\n\n## API\n\n```go\nfunc (s *Store) InstantiateMolecule(mol *Issue, parent *Issue, ctx map[string]string) ([]*Issue, error)\nfunc ParseMoleculeSteps(description string) ([]MoleculeStep, error)\n```\n\nImplementation lives in `internal/beads/molecule.go`.","status":"open","priority":0,"issue_type":"task","created_at":"2025-12-18T18:06:52.071066-08:00","updated_at":"2025-12-18T20:15:15.502672-08:00","dependencies":[{"issue_id":"gt-4nn.2","depends_on_id":"gt-4nn","type":"parent-child","created_at":"2025-12-18T18:06:52.072554-08:00","created_by":"daemon"},{"issue_id":"gt-4nn.2","depends_on_id":"gt-4nn.1","type":"blocks","created_at":"2025-12-18T18:07:02.949242-08:00","created_by":"daemon"}]} +{"id":"gt-4nn.2","title":"Molecule instantiation: create child beads from template","description":"When instantiating a molecule on a work bead:\n\n## Transaction Flow\n\n1. Parse molecule's `## Step:` sections from description\n2. Begin SQLite transaction\n3. For each step, create child issue:\n - ID: `{parent-id}.{step-ref}` or generated\n - Title: step title (from header or first line)\n - Description: step prose instructions\n - Type: task\n - Priority: inherit from parent\n4. Add `instantiated-from` edge from each step to molecule:\n ```sql\n INSERT INTO dependencies (issue_id, depends_on_id, type, metadata)\n VALUES (step_id, mol_id, 'instantiated-from', '{\"step\": \"implement\"}');\n ```\n5. Wire inter-step dependencies from `Needs:` lines\n6. Commit transaction (atomic - all or nothing)\n\n## Parsing Conventions\n\n```markdown\n## Step: \u003cref\u003e\n\u003cprose instructions\u003e\nNeeds: \u003cstep\u003e, \u003cstep\u003e # optional\nTier: haiku|sonnet|opus # optional hint\n```\n\n## Parameterization\n\nSteps can have `{{variable}}` placeholders:\n```markdown\n## Step: implement\nImplement {{feature_name}} in {{target_file}}.\n```\n\nContext map provided at instantiation time.\n\n## API\n\n```go\nfunc (s *Store) InstantiateMolecule(mol *Issue, parent *Issue, ctx map[string]string) ([]*Issue, error)\nfunc ParseMoleculeSteps(description string) ([]MoleculeStep, error)\n```\n\nImplementation lives in `internal/beads/molecule.go`.","status":"closed","priority":0,"issue_type":"task","created_at":"2025-12-18T18:06:52.071066-08:00","updated_at":"2025-12-19T01:45:14.948112-08:00","closed_at":"2025-12-19T01:45:14.948112-08:00","close_reason":"Implemented ParseMoleculeSteps and InstantiateMolecule with template var expansion, dependency wiring, and validation","dependencies":[{"issue_id":"gt-4nn.2","depends_on_id":"gt-4nn","type":"parent-child","created_at":"2025-12-18T18:06:52.072554-08:00","created_by":"daemon"},{"issue_id":"gt-4nn.2","depends_on_id":"gt-4nn.1","type":"blocks","created_at":"2025-12-18T18:07:02.949242-08:00","created_by":"daemon"}]} {"id":"gt-4nn.3","title":"Molecule CLI: bd molecule commands","description":"Add molecule commands to bd:\n\n## Commands\n\n```bash\nbd molecule list # List molecules (type: molecule)\nbd molecule show \u003cid\u003e # Show molecule with parsed steps\nbd molecule parse \u003cid\u003e # Validate and show parsed structure \nbd molecule instantiate \u003cmol-id\u003e --parent=\u003cissue-id\u003e # Create steps\nbd molecule instances \u003cmol-id\u003e # Show all instantiations\n```\n\n## gt spawn integration\n\n```bash\ngt spawn --issue \u003cid\u003e --molecule \u003cmol-id\u003e\n```\n\nThis should:\n1. Call `bd molecule instantiate` (creates child beads atomically)\n2. Spawn polecat on first ready step\n3. Polecat grinds through via `bd ready`\n\n## Output Examples\n\n```\n$ bd molecule show mol-abc\n\nmol-abc: Engineer in a Box\nType: molecule\n\nSteps (5):\n design → (ready first)\n implement → Needs: design\n review → Needs: implement\n test → Needs: implement \n submit → Needs: review, test\n \nInstances: 3\n```\n\n```\n$ bd molecule instances mol-abc\n\nParent Status Created\ngt-xyz done 2025-12-15\ngt-abc active 2025-12-17 (3/5 complete)\ngt-def pending 2025-12-18\n```","status":"open","priority":0,"issue_type":"task","created_at":"2025-12-18T18:06:53.919884-08:00","updated_at":"2025-12-18T20:15:38.500265-08:00","dependencies":[{"issue_id":"gt-4nn.3","depends_on_id":"gt-4nn","type":"parent-child","created_at":"2025-12-18T18:06:53.921621-08:00","created_by":"daemon"},{"issue_id":"gt-4nn.3","depends_on_id":"gt-4nn.2","type":"blocks","created_at":"2025-12-18T18:07:03.048941-08:00","created_by":"daemon"}]} {"id":"gt-4nn.4","title":"Built-in molecules: engineer-in-box, quick-fix, research","description":"Create built-in molecules as Beads issues:\n\n## engineer-in-box\n\n```markdown\nid: mol-engineer-in-box\ntype: molecule\ntitle: Engineer in a Box\n\nFull workflow from design to merge.\n\n## Step: design\nThink carefully about architecture. Consider:\n- Existing patterns in the codebase\n- Trade-offs between approaches \n- Testability and maintainability\n\nWrite a brief design summary before proceeding.\n\n## Step: implement\nWrite the code. Follow codebase conventions.\nNeeds: design\n\n## Step: review\nSelf-review the changes. Look for:\n- Bugs and edge cases\n- Style issues\n- Missing error handling\nNeeds: implement\n\n## Step: test\nWrite and run tests. Cover happy path and edge cases.\nFix any failures before proceeding.\nNeeds: implement\n\n## Step: submit\nSubmit for merge via refinery.\nNeeds: review, test\n```\n\n## quick-fix\n\n```markdown\nid: mol-quick-fix\ntype: molecule \ntitle: Quick Fix\n\nFast path for small changes.\n\n## Step: implement\nMake the fix. Keep it focused.\n\n## Step: test\nRun relevant tests. Fix any regressions.\nNeeds: implement\n\n## Step: submit\nSubmit for merge.\nNeeds: test\n```\n\n## research\n\n```markdown\nid: mol-research\ntype: molecule\ntitle: Research\n\nInvestigation workflow.\n\n## Step: investigate\nExplore the question. Search code, read docs, \nunderstand context. Take notes.\n\n## Step: document\nWrite up findings. Include:\n- What you learned\n- Recommendations\n- Open questions\nNeeds: investigate\n```\n\n## Storage\n\nBuilt-in molecules live in `\u003ctown\u003e/.beads/` as regular issues.\nCreated during `gt install` or `bd init`.","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-18T18:07:04.574565-08:00","updated_at":"2025-12-18T20:15:38.8612-08:00","dependencies":[{"issue_id":"gt-4nn.4","depends_on_id":"gt-4nn","type":"parent-child","created_at":"2025-12-18T18:07:04.576587-08:00","created_by":"daemon"}]} {"id":"gt-51x","title":"Fix golangci-lint errcheck warnings (~160 issues)","description":"Running golangci-lint shows ~160 errcheck warnings for unchecked error returns.\n\nCommon patterns:\n- t.SetEnvironment() return values\n- os.WriteFile(), os.RemoveAll() \n- MarkFlagRequired() on cobra commands\n- Various manager methods\n\nRun: golangci-lint run ./...\n\nCould batch fix with:\n1. Add explicit _ = for intentionally ignored errors\n2. Handle errors properly where they matter\n3. Consider adding //nolint:errcheck for cobra flag setup","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-17T15:02:39.807659-08:00","updated_at":"2025-12-17T15:02:39.807659-08:00"} @@ -63,7 +63,7 @@ {"id":"gt-6z2.2","title":"Test Task 2: Add comment to version.go","description":"","status":"closed","priority":0,"issue_type":"task","created_at":"2025-12-16T21:57:43.693217-08:00","updated_at":"2025-12-16T22:06:41.127126-08:00","closed_at":"2025-12-16T22:06:41.127126-08:00","close_reason":"Test issues for MVP validation","dependencies":[{"issue_id":"gt-6z2.2","depends_on_id":"gt-6z2","type":"parent-child","created_at":"2025-12-16T21:57:43.69361-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-70b3","title":"detectSender() doesn't recognize crew workers","description":"## Problem\n\n`detectSender()` in mail.go only detects polecats, not crew workers.\n\n## Current Code (line 445)\n\n```go\n// If in a rig's polecats directory, extract address\nif strings.Contains(cwd, \"/polecats/\") {\n // extract rig/polecat\n}\n\n// Default to mayor\nreturn \"mayor/\"\n```\n\n## Symptom\n\nEmma (crew worker at `/Users/stevey/gt/beads/crew/emma`) runs:\n- `gt mail inbox` → checks `mayor/` inbox (wrong!)\n- Should check `beads/emma` or `beads/crew/emma`\n\n## Fix\n\nAdd crew detection:\n```go\n// If in a rig's crew directory, extract address \nif strings.Contains(cwd, \"/crew/\") {\n parts := strings.Split(cwd, \"/crew/\")\n if len(parts) \u003e= 2 {\n rigPath := parts[0]\n crewName := strings.Split(parts[1], \"/\")[0]\n rigName := filepath.Base(rigPath)\n return fmt.Sprintf(\"%s/%s\", rigName, crewName)\n }\n}\n```\n\n## Also Check\n\n- `gt prime` correctly detects role, so there may be another detection function that works\n- Should unify detection logic","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-12-18T21:40:26.520559-08:00","updated_at":"2025-12-18T21:55:54.679969-08:00","closed_at":"2025-12-18T21:55:54.679969-08:00","close_reason":"Added crew detection to detectSender() in mail.go","dependencies":[{"issue_id":"gt-70b3","depends_on_id":"gt-l4gm","type":"blocks","created_at":"2025-12-18T21:50:04.812663-08:00","created_by":"daemon"}]} {"id":"gt-71i","title":"Update architecture.md: Engineer role and Beads merge queue","description":"Update docs/architecture.md with recent design decisions:\n\n1. Agent table: Change \"Refinery\" role to \"Engineer\"\n - Refinery = place/module/directory\n - Engineer = role (agent that works in the Refinery)\n\n2. Merge Queue section: Document Beads-native model\n - MRs are beads issues with --type=merge-request\n - gt mq commands (submit, list, next, process, reorder)\n - Ordering via depends-on links\n\n3. CLI section: Add gt mq commands\n\n4. Key Design Decisions: Add decisions for:\n - #15: Merge Queue in Beads\n - #16: Engineer role (distinct from Refinery place)\n - #17: Session restart protocol for Engineer","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-16T23:12:03.616159-08:00","updated_at":"2025-12-16T23:12:03.616159-08:00","dependencies":[{"issue_id":"gt-71i","depends_on_id":"gt-h5n","type":"blocks","created_at":"2025-12-16T23:12:14.92163-08:00","created_by":"daemon","metadata":"{}"}]} -{"id":"gt-7ik","title":"Ephemeral polecats: spawn fresh, delete on completion","description":"## Design Decision\n\nSwitch from pooled/idle polecats to ephemeral model:\n- Spawn creates fresh worktree from main\n- Polecat requests shutdown when done (bottom-up)\n- Witness verifies handoff, kills session, deletes worktree\n- No 'idle' state - polecats exist only while working\n\n## Rationale\n\n1. **Git worktrees are fast** - pooling optimization is obsolete\n2. **Pooling creates maintenance burden:**\n - Git stashes accumulate\n - Untracked artifacts pile up\n - Branches drift from main\n - Beads DB gets stale\n3. **PGT sync problems** came from persistent branches\n4. **Support infrastructure exists** - Witness, Refinery, Mayor handle continuity\n5. **Simpler mental model** - polecat exists = work in progress\n\n## Lifecycle\n\n```\nSpawn:\n gt spawn --issue \u003cid\u003e\n → Creates fresh worktree: git worktree add polecats/\u003cname\u003e -b polecat/\u003cname\u003e\n → Initializes beads in worktree\n → Starts session, assigns work\n\nWorking:\n Polecat does task\n → Pushes to polecat/\u003cname\u003e branch\n → Submits to merge queue when ready\n\nCompletion (POLECAT-INITIATED):\n Polecat runs: gt handoff\n → Verifies git state clean\n → Sends mail to Witness: \"Ready for shutdown\"\n → Marks itself done, waits for termination\n\nCleanup (WITNESS-OWNED):\n Witness receives shutdown request\n → Verifies PR merged or in queue\n → Verifies no uncommitted changes\n → Kills session: gt session stop \u003crig\u003e/\u003cpolecat\u003e\n → Deletes worktree: git worktree remove polecats/\u003cname\u003e\n → Deletes branch: git branch -d polecat/\u003cname\u003e\n → Optionally: Notifies Mayor of completion\n```\n\n## Key Insight: Bottom-Up Shutdown\n\n**Old model (wrong)**: Top-down batch shutdown - \"cancel the swarm\"\n**New model (right)**: Bottom-up individual shutdown - polecat requests, Witness executes\n\nThis enables streaming:\n- Workers come and go continuously\n- No \"swarm end\" to trigger cleanup\n- Each worker manages its own lifecycle\n- Witness is the lifecycle authority\n\n## Implementation\n\n1. Add `gt handoff` command for polecats to request shutdown\n2. Modify gt spawn to always create fresh worktree\n3. Run bd init in new worktree (beads needs initialization)\n4. Add shutdown request handler to Witness\n5. Witness verifies handoff, then cleans up:\n - Kill session\n - Remove worktree\n - Delete branch\n6. Remove 'idle' state from polecat state machine\n7. Simplify gt polecat list (only shows active)\n\n## Impact on Other Tasks\n\n- gt-17r (Zombie cleanup): Becomes trivial - orphan worktrees\n- gt-4my (Worker health): Simpler - no idle/stuck ambiguity\n- gt-f9x.5/f9x.6 (Doctor): Fewer states to validate\n- gt-eu9 (Witness handoff): Witness receives polecat shutdown requests","status":"open","priority":1,"issue_type":"feature","created_at":"2025-12-17T15:44:31.139964-08:00","updated_at":"2025-12-18T11:39:23.202854-08:00"} +{"id":"gt-7ik","title":"Ephemeral polecats: spawn fresh, delete on completion","description":"## Design Decision\n\nSwitch from pooled/idle polecats to ephemeral model:\n- Spawn creates fresh worktree from main\n- Polecat requests shutdown when done (bottom-up)\n- Witness verifies handoff, kills session, deletes worktree\n- No 'idle' state - polecats exist only while working\n\n## Rationale\n\n1. **Git worktrees are fast** - pooling optimization is obsolete\n2. **Pooling creates maintenance burden:**\n - Git stashes accumulate\n - Untracked artifacts pile up\n - Branches drift from main\n - Beads DB gets stale\n3. **PGT sync problems** came from persistent branches\n4. **Support infrastructure exists** - Witness, Refinery, Mayor handle continuity\n5. **Simpler mental model** - polecat exists = work in progress\n\n## Lifecycle\n\n```\nSpawn:\n gt spawn --issue \u003cid\u003e\n → Creates fresh worktree: git worktree add polecats/\u003cname\u003e -b polecat/\u003cname\u003e\n → Initializes beads in worktree\n → Starts session, assigns work\n\nWorking:\n Polecat does task\n → Pushes to polecat/\u003cname\u003e branch\n → Submits to merge queue when ready\n\nCompletion (POLECAT-INITIATED):\n Polecat runs: gt handoff\n → Verifies git state clean\n → Sends mail to Witness: \"Ready for shutdown\"\n → Marks itself done, waits for termination\n\nCleanup (WITNESS-OWNED):\n Witness receives shutdown request\n → Verifies PR merged or in queue\n → Verifies no uncommitted changes\n → Kills session: gt session stop \u003crig\u003e/\u003cpolecat\u003e\n → Deletes worktree: git worktree remove polecats/\u003cname\u003e\n → Deletes branch: git branch -d polecat/\u003cname\u003e\n → Optionally: Notifies Mayor of completion\n```\n\n## Key Insight: Bottom-Up Shutdown\n\n**Old model (wrong)**: Top-down batch shutdown - \"cancel the swarm\"\n**New model (right)**: Bottom-up individual shutdown - polecat requests, Witness executes\n\nThis enables streaming:\n- Workers come and go continuously\n- No \"swarm end\" to trigger cleanup\n- Each worker manages its own lifecycle\n- Witness is the lifecycle authority\n\n## Implementation\n\n1. Add `gt handoff` command for polecats to request shutdown\n2. Modify gt spawn to always create fresh worktree\n3. Run bd init in new worktree (beads needs initialization)\n4. Add shutdown request handler to Witness\n5. Witness verifies handoff, then cleans up:\n - Kill session\n - Remove worktree\n - Delete branch\n6. Remove 'idle' state from polecat state machine\n7. Simplify gt polecat list (only shows active)\n\n## Impact on Other Tasks\n\n- gt-17r (Zombie cleanup): Becomes trivial - orphan worktrees\n- gt-4my (Worker health): Simpler - no idle/stuck ambiguity\n- gt-f9x.5/f9x.6 (Doctor): Fewer states to validate\n- gt-eu9 (Witness handoff): Witness receives polecat shutdown requests","status":"closed","priority":1,"issue_type":"feature","created_at":"2025-12-17T15:44:31.139964-08:00","updated_at":"2025-12-19T01:49:11.730856-08:00","closed_at":"2025-12-19T01:49:11.730856-08:00","close_reason":"Implemented ephemeral polecat model"} {"id":"gt-7lt","title":"gt mail send should tmux-notify recipient","description":"## Problem\n\nWhen mail is sent via gt mail send, the recipient session does not get a tmux notification. In Python Gas Town (PGT), mail delivery triggers a tmux display-message or similar notification so the agent knows mail arrived.\n\n## Expected Behavior\n\nWhen gt mail send \u003caddr\u003e is called:\n1. Mail is delivered to recipient inbox\n2. If recipient has an active tmux session, send notification\n3. Notification should be visible (display-message or bell)\n\n## Current Behavior\n\nMail is delivered but no notification. Agent has to poll inbox to discover new mail.\n\n## Impact\n\n- Agents miss time-sensitive messages\n- Heartbeat pokes from daemon will not wake agents\n- Coordination is slower (polling vs push)\n\n## Implementation Notes\n\nAfter successful mail delivery, check if recipient has active session:\n- gt session list can identify active sessions\n- tmux display-message or send-keys can notify\n- Could inject a visible prompt like \"[MAIL] New message from \u003csender\u003e\"\n\n## Reference\n\nCheck PGT implementation for how it handles this.","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-12-18T12:28:50.142075-08:00","updated_at":"2025-12-18T20:09:53.112902-08:00","closed_at":"2025-12-18T20:09:53.112902-08:00","close_reason":"Implemented tmux notification via display-message for all mail recipients"} {"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-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"} @@ -112,8 +112,8 @@ {"id":"gt-b3p","title":"Resource Beads: Leases, locks, and quotas","description":"Resource beads represent reserved resources. Types: vm, lock, slot, quota. Fields: holder, expires, renewable. Daemon monitors for expiry and manages contention.","status":"open","priority":2,"issue_type":"epic","created_at":"2025-12-18T18:08:12.745602-08:00","updated_at":"2025-12-18T18:08:12.745602-08:00"} {"id":"gt-bfd","title":"Keepalive signal from bd/gt commands","description":"Every bd and gt command should touch a keepalive file to signal 'agent is alive/working'.\n\n## Implementation\n\nTouch `\u003cworkspace\u003e/.gastown/keepalive.json`:\n```json\n{\"last_command\": \"bd show gt-99m\", \"timestamp\": \"2025-12-18T13:45:00Z\"}\n```\n\n## Usage by Daemon\n\n- Fresh (\u003c 2 min) → agent is working, skip heartbeat\n- Stale (2-5 min) → might be thinking, gentle poke\n- Very stale (\u003e 5 min) → likely idle, safe to interrupt\n\n## Benefits\n\n- Zero cost (just file I/O)\n- Works during long tool calls\n- Doesn't require agent cooperation\n- Foundation for smarter backoff strategies","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-18T14:19:26.241957-08:00","updated_at":"2025-12-18T20:03:43.816952-08:00","closed_at":"2025-12-18T20:03:43.816952-08:00","close_reason":"Implemented keepalive.Touch() in internal/keepalive package, integrated via PersistentPreRun in root command","dependencies":[{"issue_id":"gt-bfd","depends_on_id":"gt-99m","type":"blocks","created_at":"2025-12-18T14:19:46.407664-08:00","created_by":"daemon"}]} {"id":"gt-bmjw","title":"gt polecat add: should handle existing branch gracefully","description":"## Problem\n\n`gt polecat add gastown Nux` fails if the branch `polecat/Nux` already exists.\n\n## Current Behavior\n\n```\nfatal: a branch named 'polecat/Nux' already exists\n```\n\n## Expected Behavior\n\nShould either:\n1. Reuse the existing branch\n2. Or prompt to delete/recreate\n3. Or auto-suffix: polecat/Nux-2\n\n## Context\n\nBranch may exist from previous polecat that was removed but branch wasn't cleaned up.","status":"open","priority":2,"issue_type":"bug","created_at":"2025-12-18T21:52:09.361672-08:00","updated_at":"2025-12-18T21:52:09.361672-08:00"} -{"id":"gt-bqbw","title":"detectSender() doesn't recognize crew workers","description":"## Problem\n\ndetectSender() in internal/cmd/mail.go only checks for /polecats/ directories. Crew workers in /crew/\u003cname\u003e/ fall through to the default 'mayor/', so:\n- gt mail inbox shows mayor's inbox instead of the crew worker's\n- gt mail send sets the wrong From address\n\n## Fix\n\nAdd crew worker detection before the /polecats/ check:\n\nif strings.Contains(cwd, \"/crew/\") {\n parts := strings.Split(cwd, \"/crew/\")\n ...\n return fmt.Sprintf(\"%s/crew/%s\", rigName, crewMember)\n}\n\n## Affected\n- Any crew worker running gt mail inbox without explicit address\n- Crew worker handoffs (wrong sender)","status":"open","priority":1,"issue_type":"bug","created_at":"2025-12-18T20:09:42.556373-08:00","updated_at":"2025-12-18T20:09:42.556373-08:00"} -{"id":"gt-bzd","title":"beads: Stop searching upward when .beads found","description":"## Problem\n\nWhen running bd commands in a nested directory structure with multiple .beads directories, bd shows a confusing warning:\n\n```\n╔══════════════════════════════════════════════════════════════════════════╗\n║ WARNING: 2 beads databases detected in directory hierarchy ║\n╠══════════════════════════════════════════════════════════════════════════╣\n║ Multiple databases can cause confusion and database pollution. ║\n║ ║\n║ /Users/stevey/gt/gastown/.beads (261 issues) ║\n║ /Users/stevey/gt/.beads (21 issues) ║\n║ ║\n║ WARNING: Not using the closest database! Check your BEADS_DB setting. ║\n║ ║\n║ RECOMMENDED: Consolidate or remove unused databases to avoid confusion. ║\n╚══════════════════════════════════════════════════════════════════════════╝\n```\n\n## Why This Is Wrong\n\nIn Gas Town, nested .beads directories are **intentional and necessary**:\n- Town level: /Users/stevey/gt/.beads (mail, town-level issues)\n- Rig level: /Users/stevey/gt/gastown/.beads (gastown project issues)\n- Worker level: polecats have their own beads in worktrees\n\nThese are **unrelated** beads instances for different scopes. They should never be consolidated.\n\n## Expected Behavior\n\nWhen bd finds a .beads directory, it should:\n1. Use that directory (closest ancestor wins)\n2. **Stop searching upward** - do not look for parent .beads directories\n3. **No warning** about multiple databases\n\n## Current Behavior\n\nbd searches all the way up to root, finds all .beads directories, and warns about \"multiple databases\" even though they are separate, intentional instances.\n\n## Fix\n\nIn the database discovery code, stop the upward search as soon as a .beads directory is found. The first .beads found is the one to use, and parent directories are out of scope.\n\n## Note\n\nThis is a beads issue, filed here for tracking. Should be implemented in the beads codebase.","status":"open","priority":1,"issue_type":"bug","created_at":"2025-12-18T19:09:44.295743-08:00","updated_at":"2025-12-18T19:09:44.295743-08:00"} +{"id":"gt-bqbw","title":"detectSender() doesn't recognize crew workers","description":"## Problem\n\ndetectSender() in internal/cmd/mail.go only checks for /polecats/ directories. Crew workers in /crew/\u003cname\u003e/ fall through to the default 'mayor/', so:\n- gt mail inbox shows mayor's inbox instead of the crew worker's\n- gt mail send sets the wrong From address\n\n## Fix\n\nAdd crew worker detection before the /polecats/ check:\n\nif strings.Contains(cwd, \"/crew/\") {\n parts := strings.Split(cwd, \"/crew/\")\n ...\n return fmt.Sprintf(\"%s/crew/%s\", rigName, crewMember)\n}\n\n## Affected\n- Any crew worker running gt mail inbox without explicit address\n- Crew worker handoffs (wrong sender)","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-12-18T20:09:42.556373-08:00","updated_at":"2025-12-19T01:33:49.861756-08:00","closed_at":"2025-12-19T01:33:49.861756-08:00","close_reason":"Merged to main in swarm session"} +{"id":"gt-bzd","title":"beads: Stop searching upward when .beads found","description":"## Problem\n\nWhen running bd commands in a nested directory structure with multiple .beads directories, bd shows a confusing warning:\n\n```\n╔══════════════════════════════════════════════════════════════════════════╗\n║ WARNING: 2 beads databases detected in directory hierarchy ║\n╠══════════════════════════════════════════════════════════════════════════╣\n║ Multiple databases can cause confusion and database pollution. ║\n║ ║\n║ /Users/stevey/gt/gastown/.beads (261 issues) ║\n║ /Users/stevey/gt/.beads (21 issues) ║\n║ ║\n║ WARNING: Not using the closest database! Check your BEADS_DB setting. ║\n║ ║\n║ RECOMMENDED: Consolidate or remove unused databases to avoid confusion. ║\n╚══════════════════════════════════════════════════════════════════════════╝\n```\n\n## Why This Is Wrong\n\nIn Gas Town, nested .beads directories are **intentional and necessary**:\n- Town level: /Users/stevey/gt/.beads (mail, town-level issues)\n- Rig level: /Users/stevey/gt/gastown/.beads (gastown project issues)\n- Worker level: polecats have their own beads in worktrees\n\nThese are **unrelated** beads instances for different scopes. They should never be consolidated.\n\n## Expected Behavior\n\nWhen bd finds a .beads directory, it should:\n1. Use that directory (closest ancestor wins)\n2. **Stop searching upward** - do not look for parent .beads directories\n3. **No warning** about multiple databases\n\n## Current Behavior\n\nbd searches all the way up to root, finds all .beads directories, and warns about \"multiple databases\" even though they are separate, intentional instances.\n\n## Fix\n\nIn the database discovery code, stop the upward search as soon as a .beads directory is found. The first .beads found is the one to use, and parent directories are out of scope.\n\n## Note\n\nThis is a beads issue, filed here for tracking. Should be implemented in the beads codebase.","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-12-18T19:09:44.295743-08:00","updated_at":"2025-12-19T00:44:28.741548-08:00","closed_at":"2025-12-19T00:44:28.741548-08:00","close_reason":"Fixed in beads repo commit 42ac923e: FindAllDatabases now stops searching upward when .beads is found"} {"id":"gt-c92","title":"CLI: all command for batch polecat operations","description":"Batch operations across multiple polecats.\n\n## Commands\n\n### gt all start\n```\ngt all start [--awake-only] [\u003cspecs\u003e...]\n```\nStart sessions for multiple polecats.\n- --awake-only: Only start awake polecats\n- specs: Polecat names, rig/polecat patterns\n\n### gt all stop\n```\ngt all stop [\u003cspecs\u003e...] [--force]\n```\nStop sessions for multiple polecats.\n\n### gt all status\n```\ngt all status [\u003cspecs\u003e...] [--json]\n```\nShow status of multiple polecats.\n\n### gt all attach\n```\ngt all attach [\u003cspecs\u003e...]\n```\nAttach to multiple sessions in tmux panes/windows.\n\n### gt all run\n```\ngt all run \u003ccommand\u003e [\u003cspecs\u003e...]\n```\nRun command in multiple polecat sessions.\n\n## Spec Patterns\n- `Toast`: Specific polecat (in default/current rig)\n- `gastown/Toast`: Specific rig/polecat\n- `gastown/*`: All polecats in rig\n- `*`: All polecats everywhere\n\n## Implementation\n```go\nfunc expandSpecs(specs []string, awakeOnly bool) ([]*polecat.Polecat, error) {\n // Expand patterns to list of polecats\n}\n\nfunc runForAll(polecats []*polecat.Polecat, action func(*polecat.Polecat) error) error {\n // Run action for each, collect errors\n}\n```\n\n## New File\ninternal/cmd/all.go\n\n## PGT Reference\ngastown-py/src/gastown/cli/all_cmd.py\n\n## Acceptance Criteria\n- [ ] Pattern expansion works\n- [ ] Parallel execution where safe\n- [ ] Aggregate error reporting\n- [ ] --awake-only filter works","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-16T14:48:12.411789-08:00","updated_at":"2025-12-16T16:05:47.255503-08:00"} {"id":"gt-caz","title":"Timed Beads: Scheduled recurring work","description":"## Summary\n\nTimed beads wake up periodically and get injected into the ready queue by the daemon.\n\n## Schema Extension\n\n```yaml\nid: gt-weekly-sync\ntype: task # or sentinel\nschedule: \"0 9 * * 1\" # cron: Monday 9am\n# OR\ninterval: 24h # every 24 hours\ntier: haiku # cheap model for routine checks\nnext_run: 2025-12-20T09:00:00Z\n```\n\n## Daemon Integration\n\nDaemon heartbeat loop:\n1. Check timed beads where `next_run \u003c= now`\n2. For each due bead:\n - Inject into ready queue (set status to open if needed)\n - Update `next_run` based on schedule/interval\n3. Witnesses pick up work via `bd ready`\n\n## Use Cases\n\n- Weekly team sync reminders\n- Daily health checks\n- Periodic cleanup tasks\n- Scheduled reports\n\n## Interaction with Pinned Beads\n\nA pinned bead can be timed - it wakes up periodically but never closes.\nThis is how you model \"background services\" in Gas Town.","status":"open","priority":2,"issue_type":"epic","created_at":"2025-12-18T18:07:39.665294-08:00","updated_at":"2025-12-18T18:07:39.665294-08:00"} {"id":"gt-cik","title":"Overseer Crew: User-managed persistent workspaces","description":"## Overview\n\nCrew workers are the overseer's (human's) personal workspaces within a rig. Unlike polecats which are witness-managed and ephemeral, crew workers are:\n\n- **Persistent**: Not auto-garbage-collected\n- **User-managed**: Overseer controls lifecycle\n- **Long-lived identities**: dave, emma, fred - recognizable names\n- **Gas Town integrated**: Mail, handoff mechanics work\n- **Tmux optional**: Can work in terminal directly\n\n## Directory Structure\n\n```\n\u003crig\u003e/\n polecats/ # Managed workers (witness controls)\n refinery/ # Merge queue processor\n witness/ # Pit boss\n crew/ # Overseer's personal workspaces\n dave/ # Full clone, persistent\n emma/ # Full clone, persistent\n fred/ # Full clone, persistent\n```\n\n## Key Differences from Polecats\n\n- Location: crew/ instead of polecats/\n- Lifecycle: User-managed, not witness-managed\n- Auto-cleanup: Never (polecats auto-cleanup on swarm land)\n- Issue assignment: Optional (polecats require it)\n- Tmux: Optional (polecats require it)\n- Mail \u0026 Handoff: Yes for both\n- Identity: Persistent (polecats are ephemeral)\n\n## CLI Commands\n\n- gt crew add \u003cname\u003e [--rig \u003crig\u003e] - Create crew workspace\n- gt crew list [--rig \u003crig\u003e] - List crew workspaces\n- gt crew at \u003crig\u003e/\u003cname\u003e - Attach to workspace (start session)\n- gt crew attach \u003cname\u003e - Attach (infer rig from cwd)\n- gt crew refresh \u003cname\u003e - Handoff + restart (context cycling)\n- gt crew remove \u003cname\u003e [--force] - Remove workspace\n- gt crew status [\u003cname\u003e] - Show workspace status\n\n## Design Notes\n\n- Crew workers use full git clones (not worktrees)\n- Optional beads integration via BEADS_DIR\n- Mail-to-self handoff works for context cycling\n- No witness monitoring or nudging\n- No automatic issue assignment required\n\n## Background\n\nUsers often maintain separate repo clones for serial agent work. This is tedious to set up manually. Crew workspaces bring these into Gas Town's infrastructure while keeping user control.","status":"closed","priority":1,"issue_type":"epic","created_at":"2025-12-16T16:47:37.529887-08:00","updated_at":"2025-12-16T20:59:46.13518-08:00","closed_at":"2025-12-16T20:59:46.13518-08:00","close_reason":"All crew commands implemented and merged"} @@ -131,12 +131,12 @@ {"id":"gt-cr0","title":"Consolidate design docs into beads descriptions","description":"The markdown design docs (swarm-shutdown-design.md, polecat-beads-access-design.md, mayor-handoff-design.md) will decay. Extract key decisions and prompting templates into the beads descriptions themselves, then archive or remove the markdown files. Beads are the source of truth.","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-15T20:24:05.45131-08:00","updated_at":"2025-12-15T20:51:52.083465-08:00","closed_at":"2025-12-15T20:51:52.083465-08:00","close_reason":"Consolidated: created docs/architecture.md, moved design content into bead descriptions, deleted 4 individual design docs"} {"id":"gt-cr9","title":"Harness Design \u0026 Documentation","description":"The harness (Gas Town installation directory) needs design cleanup, documentation, and tooling.\n\n## Current Problems\n\n1. **Shared harness confusion**: ~/ai is shared by PGT and GGT with overlapping structures\n - PGT uses ~/ai/mayor/ as town-level Mayor home\n - GGT Mayor works in ~/ai/mayor/rigs/gastown/\n - ~/ai/gastown/ has both .gastown/ (PGT) and mayor/ (git clone)\n\n2. **Beads redirect**: ~/ai/.beads/redirect → mayor/rigs/gastown/.beads\n - This is specific to GGT's decentralized structure\n - Should be documented as an example\n\n3. **architecture.md**: Verify rig-level mayor/rig/ is shown correctly\n\n4. **No harness creation tooling**: Users must manually set up\n\n## Proposed Work\n\n- Document what a harness IS (installation directory)\n- Create harness creation command or template repo\n- Update architecture.md if needed \n- Create example harness configuration for docs\n- Resolve PGT/GGT sharing issue","status":"open","priority":1,"issue_type":"epic","created_at":"2025-12-17T17:15:08.769961-08:00","updated_at":"2025-12-17T17:15:17.610323-08:00"} {"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":"open","priority":1,"issue_type":"task","created_at":"2025-12-18T21:28:05.738035-08:00","updated_at":"2025-12-18T21:28:05.738035-08:00"} +{"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":"2025-12-19T01:51:28.999675-08:00","closed_at":"2025-12-19T01:51:28.999675-08:00","close_reason":"Implemented pinned beads for handoffs"} {"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","close_reason":"Addressed by architecture.md Key Decision #12 (Agent Session Lifecycle). Daemon monitors agent health and restarts sessions after handoff. Witness self-cycling protocol documented in prompts.md."} {"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"}]} {"id":"gt-d3d","title":"Design: Additional design issues (placeholder)","description":"Placeholder for additional design issues the user wants to raise and work through. Convert to specific subtasks as issues are identified.","status":"open","priority":4,"issue_type":"epic","created_at":"2025-12-15T20:24:12.601585-08:00","updated_at":"2025-12-15T23:17:32.467687-08:00"} {"id":"gt-d46","title":"Mail CLI: archive, purge, search, mark","description":"GGT mail CLI needs more commands for mail management.\n\n## Commands to Add\n\n### gt mail check\nCheck for new mail without full inbox display.\n```\ngt mail check [--quiet] [--inject]\n```\n- --quiet: Only output if new mail (for scripts)\n- --inject: Send notification to running session\n\n### gt mail mark\nChange read status.\n```\ngt mail mark \u003cid\u003e --read\ngt mail mark \u003cid\u003e --unread\n```\n\n### gt mail delete\nRemove message from inbox.\n```\ngt mail delete \u003cid\u003e [--force]\n```\n- Confirm unless --force\n\n### gt mail archive\nMove old/read messages to archive.\n```\ngt mail archive [--older-than DAYS] [--all-read] [--dry-run]\n```\n- Creates inbox.jsonl.archive or separate archive.jsonl\n\n### gt mail purge\nPermanently delete archived messages.\n```\ngt mail purge [--older-than DAYS] [--dry-run] [--force]\n```\n\n### gt mail search\nFind messages by content.\n```\ngt mail search \u003cquery\u003e [--from SENDER] [--subject] [--body]\n```\n\n### gt mail reply\nReply to a message.\n```\ngt mail reply \u003cid\u003e -m BODY\n```\n- Auto-sets reply_to and thread_id\n- Auto-addresses to original sender\n\n## Files to Modify\n- internal/cmd/mail.go: Add commands\n- internal/mail/mailbox.go: Add Archive(), Search(), Delete()\n\n## Acceptance Criteria\n- [ ] All commands implemented\n- [ ] Archive stores in separate file\n- [ ] Search supports regex patterns\n- [ ] Delete confirms by default","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-16T14:46:57.158136-08:00","updated_at":"2025-12-16T16:04:32.922813-08:00"} -{"id":"gt-d7i","title":"gt session capture: Support positional line count argument","description":"Make 'gt session capture gastown/Toast 50' work.\n\nCurrently requires: gt session capture gastown/Toast -n 50\nShould also accept: gt session capture gastown/Toast 50\n\nAgent UX principle: commands should work the way agents guess they work.","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-17T22:28:44.291285-08:00","updated_at":"2025-12-17T22:28:44.291285-08:00"} +{"id":"gt-d7i","title":"gt session capture: Support positional line count argument","description":"Make 'gt session capture gastown/Toast 50' work.\n\nCurrently requires: gt session capture gastown/Toast -n 50\nShould also accept: gt session capture gastown/Toast 50\n\nAgent UX principle: commands should work the way agents guess they work.","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-17T22:28:44.291285-08:00","updated_at":"2025-12-19T01:33:49.860862-08:00","closed_at":"2025-12-19T01:33:49.860862-08:00","close_reason":"Merged to main in swarm session"} {"id":"gt-dck","title":"Update config location: .gastown/ → config/","description":"Move rig configuration from hidden .gastown/ to visible config/:\n- config/rig.json: Rig configuration\n- config/engineer.json: Engineer settings (test command, etc.)\n- config/witness.json: Witness settings (heartbeat interval, etc.)\n\nHidden directories are poorly discovered by AI agents.","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-16T23:02:20.400818-08:00","updated_at":"2025-12-16T23:02:20.400818-08:00","dependencies":[{"issue_id":"gt-dck","depends_on_id":"gt-h5n","type":"blocks","created_at":"2025-12-16T23:02:55.69517-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-dkc","title":"Add harness overview to Mayor priming","description":"Update gt prime Mayor context to explain the harness concept: umbrella repo for GT installation, rigs underneath, Mayor sits above all rigs","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-17T16:42:44.864606-08:00","updated_at":"2025-12-17T16:44:12.568963-08:00","closed_at":"2025-12-17T16:44:12.568963-08:00","close_reason":"Added harness overview, architecture section, and updated directory structure in prime.go","dependencies":[{"issue_id":"gt-dkc","depends_on_id":"gt-l1o","type":"blocks","created_at":"2025-12-17T16:42:54.736437-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-dq3","title":"Split PGT/GGT harness or migrate to GGT-only","description":"Current ~/ai harness is shared by PGT and GGT with confusing overlap. Options:\n1. Keep separate (document the coexistence)\n2. Migrate fully to GGT structure\n3. Create separate harnesses\n\nThis affects the beads redirect, Mayor home location, and rig structure.","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-17T17:15:32.308192-08:00","updated_at":"2025-12-17T17:15:32.308192-08:00","dependencies":[{"issue_id":"gt-dq3","depends_on_id":"gt-cr9","type":"blocks","created_at":"2025-12-17T17:15:51.717903-08:00","created_by":"daemon","metadata":"{}"}]} @@ -177,11 +177,11 @@ {"id":"gt-h5n.15","title":"Rollback support: gt mq revert for problematic merges","description":"Implement 'gt mq revert \u003cmr-id\u003e' for rolling back merges.\n\nActions:\n1. Find merge commit from closed MR\n2. Create revert commit: git revert \u003cmerge-commit\u003e\n3. Push revert to target branch\n4. Create 'reverted' MR tracking the revert\n5. Optionally reopen source issue\n\nOptions:\n- --reason REASON: required explanation\n- --reopen-issue: reopen the source work item\n\nTrack revert in MR metadata for audit trail.\n\nReference: docs/merge-queue-design.md#open-questions","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-17T13:52:51.440782-08:00","updated_at":"2025-12-17T13:52:51.440782-08:00","dependencies":[{"issue_id":"gt-h5n.15","depends_on_id":"gt-h5n","type":"parent-child","created_at":"2025-12-17T13:52:51.442642-08:00","created_by":"daemon","metadata":"{}"},{"issue_id":"gt-h5n.15","depends_on_id":"gt-3x1.5","type":"blocks","created_at":"2025-12-17T13:53:23.862389-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-h5n.2","title":"MR ID generation: prefix-mr-hash convention","description":"Generate merge-request IDs following the convention: \u003cprefix\u003e-mr-\u003chash\u003e\n\nExample: gt-mr-abc123 for a gastown merge request.\n\nThis distinguishes MRs from regular issues while keeping them in the same namespace.\nThe hash should be derived from branch name + timestamp for uniqueness.\n\nImplement: GenerateMRID(prefix, branch string) string\n\nReference: docs/merge-queue-design.md#id-convention","status":"closed","priority":0,"issue_type":"task","created_at":"2025-12-17T13:47:59.023788-08:00","updated_at":"2025-12-18T20:00:33.789237-08:00","closed_at":"2025-12-18T20:00:33.789237-08:00","close_reason":"Already implemented in commit 0c73162","dependencies":[{"issue_id":"gt-h5n.2","depends_on_id":"gt-h5n","type":"parent-child","created_at":"2025-12-17T13:47:59.027042-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-h5n.3","title":"MR state transitions: validate open→in_progress→closed","description":"Enforce valid state transitions for merge-requests:\n\nValid transitions:\n- open → in_progress (Engineer claims MR)\n- in_progress → closed (merge success or rejection)\n- in_progress → open (failure, reassign to worker)\n- open → closed (manual rejection)\n\nInvalid:\n- closed → anything (immutable once closed)\n\nImplement validation in MR update operations.\n\nReference: docs/merge-queue-design.md#state-machine","status":"closed","priority":0,"issue_type":"task","created_at":"2025-12-17T13:50:00.417825-08:00","updated_at":"2025-12-18T20:00:58.572216-08:00","closed_at":"2025-12-18T20:00:58.572216-08:00","close_reason":"State transition validation implemented in internal/refinery/types.go with comprehensive tests","dependencies":[{"issue_id":"gt-h5n.3","depends_on_id":"gt-h5n","type":"parent-child","created_at":"2025-12-17T13:50:00.419924-08:00","created_by":"daemon","metadata":"{}"}]} -{"id":"gt-h5n.4","title":"gt mq integration create: create integration branch for epic","description":"Implement 'gt mq integration create \u003cepic\u003e' command.\n\nActions:\n1. Verify epic exists\n2. Create branch: integration/\u003cepic-id\u003e from main\n3. Push to origin\n4. Store integration branch info in epic metadata\n\nUsage:\n gt mq integration create gt-auth-epic\n # Creates integration/gt-auth-epic from main\n\nFuture MRs for this epic's children will auto-target this branch.\n\nReference: docs/merge-queue-design.md#integration-branches","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-17T13:51:35.679837-08:00","updated_at":"2025-12-17T13:51:35.679837-08:00","dependencies":[{"issue_id":"gt-h5n.4","depends_on_id":"gt-h5n","type":"parent-child","created_at":"2025-12-17T13:51:35.681828-08:00","created_by":"daemon","metadata":"{}"},{"issue_id":"gt-h5n.4","depends_on_id":"gt-svi.1","type":"blocks","created_at":"2025-12-17T13:53:16.28634-08:00","created_by":"daemon","metadata":"{}"}]} +{"id":"gt-h5n.4","title":"gt mq integration create: create integration branch for epic","description":"Implement 'gt mq integration create \u003cepic\u003e' command.\n\nActions:\n1. Verify epic exists\n2. Create branch: integration/\u003cepic-id\u003e from main\n3. Push to origin\n4. Store integration branch info in epic metadata\n\nUsage:\n gt mq integration create gt-auth-epic\n # Creates integration/gt-auth-epic from main\n\nFuture MRs for this epic's children will auto-target this branch.\n\nReference: docs/merge-queue-design.md#integration-branches","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-17T13:51:35.679837-08:00","updated_at":"2025-12-19T01:46:18.06761-08:00","closed_at":"2025-12-19T01:46:18.06761-08:00","close_reason":"Implemented gt mq integration create command","dependencies":[{"issue_id":"gt-h5n.4","depends_on_id":"gt-h5n","type":"parent-child","created_at":"2025-12-17T13:51:35.681828-08:00","created_by":"daemon","metadata":"{}"},{"issue_id":"gt-h5n.4","depends_on_id":"gt-svi.1","type":"blocks","created_at":"2025-12-17T13:53:16.28634-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-h5n.5","title":"gt mq integration land: merge integration branch to main","description":"Implement 'gt mq integration land \u003cepic\u003e' command.\n\nActions:\n1. Verify all MRs targeting integration/\u003cepic\u003e are merged\n2. Verify integration branch exists\n3. Merge integration/\u003cepic\u003e to main (--no-ff)\n4. Run tests on main\n5. Push to origin\n6. Delete integration branch\n7. Update epic status\n\nOptions:\n- --force: land even if some MRs still open\n- --skip-tests: skip test run\n- --dry-run: preview only\n\nThis creates a single merge commit for the entire epic's work.\n\nReference: docs/merge-queue-design.md#integration-branches","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-17T13:51:37.465635-08:00","updated_at":"2025-12-17T13:51:37.465635-08:00","dependencies":[{"issue_id":"gt-h5n.5","depends_on_id":"gt-h5n","type":"parent-child","created_at":"2025-12-17T13:51:37.467603-08:00","created_by":"daemon","metadata":"{}"},{"issue_id":"gt-h5n.5","depends_on_id":"gt-h5n.4","type":"blocks","created_at":"2025-12-17T13:53:16.40717-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-h5n.6","title":"gt mq integration status: show integration branch status","description":"Implement 'gt mq integration status \u003cepic\u003e' command.\n\nDisplay:\n- Integration branch name and creation date\n- Commits ahead of main\n- MRs merged to integration (closed)\n- MRs pending (open, targeting integration)\n- Comparison: main..integration/\u003cepic\u003e\n\nOutput example:\n Integration: integration/gt-auth-epic\n Created: 2025-12-17\n Ahead of main: 5 commits\n \n Merged MRs (3):\n gt-mr-001 Fix login timeout\n gt-mr-002 Fix session expiry \n gt-mr-003 Update auth config\n \n Pending MRs (1):\n gt-mr-004 Update auth tests (in_progress)\n\nReference: docs/merge-queue-design.md#integration-branches","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-17T13:51:39.554771-08:00","updated_at":"2025-12-17T13:51:39.554771-08:00","dependencies":[{"issue_id":"gt-h5n.6","depends_on_id":"gt-h5n","type":"parent-child","created_at":"2025-12-17T13:51:39.556726-08:00","created_by":"daemon","metadata":"{}"},{"issue_id":"gt-h5n.6","depends_on_id":"gt-h5n.4","type":"blocks","created_at":"2025-12-17T13:53:16.528122-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-h5n.7","title":"Auto-target: MRs for epic children target integration branch","description":"Automatically target integration branches for epic children.\n\nWhen 'gt mq submit' is called:\n1. Parse source issue from branch\n2. Check if issue has a parent epic\n3. Check if integration/\u003cepic\u003e branch exists\n4. If yes: set target=integration/\u003cepic\u003e\n5. If no: set target=main\n\nThis ensures batch work automatically flows to integration branches.\n\nAlso update 'gt mq submit --epic' to explicitly target an epic's integration branch.\n\nReference: docs/merge-queue-design.md#integration-branches","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-17T13:51:56.992465-08:00","updated_at":"2025-12-17T13:51:56.992465-08:00","dependencies":[{"issue_id":"gt-h5n.7","depends_on_id":"gt-h5n","type":"parent-child","created_at":"2025-12-17T13:51:56.994579-08:00","created_by":"daemon","metadata":"{}"},{"issue_id":"gt-h5n.7","depends_on_id":"gt-h5n.4","type":"blocks","created_at":"2025-12-17T13:53:16.648727-08:00","created_by":"daemon","metadata":"{}"}]} -{"id":"gt-h5n.8","title":"MQ config schema: merge_queue section in rig config.json","description":"Define and implement merge_queue configuration in rig config.\n\nSchema:\n{\n \"merge_queue\": {\n \"enabled\": true,\n \"target_branch\": \"main\",\n \"integration_branches\": true,\n \"on_conflict\": \"assign_back\", // or \"auto_rebase\"\n \"run_tests\": true,\n \"test_command\": \"go test ./...\",\n \"delete_merged_branches\": true,\n \"retry_flaky_tests\": 1,\n \"poll_interval\": \"30s\",\n \"max_concurrent\": 1\n }\n}\n\nImplement:\n- Config loading in rig package\n- Default values\n- Validation\n\nReference: docs/merge-queue-design.md#configuration","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-17T13:52:00.322779-08:00","updated_at":"2025-12-17T13:52:00.322779-08:00","dependencies":[{"issue_id":"gt-h5n.8","depends_on_id":"gt-h5n","type":"parent-child","created_at":"2025-12-17T13:52:00.324781-08:00","created_by":"daemon","metadata":"{}"}]} +{"id":"gt-h5n.8","title":"MQ config schema: merge_queue section in rig config.json","description":"Define and implement merge_queue configuration in rig config.\n\nSchema:\n{\n \"merge_queue\": {\n \"enabled\": true,\n \"target_branch\": \"main\",\n \"integration_branches\": true,\n \"on_conflict\": \"assign_back\", // or \"auto_rebase\"\n \"run_tests\": true,\n \"test_command\": \"go test ./...\",\n \"delete_merged_branches\": true,\n \"retry_flaky_tests\": 1,\n \"poll_interval\": \"30s\",\n \"max_concurrent\": 1\n }\n}\n\nImplement:\n- Config loading in rig package\n- Default values\n- Validation\n\nReference: docs/merge-queue-design.md#configuration","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-17T13:52:00.322779-08:00","updated_at":"2025-12-19T01:33:49.864359-08:00","closed_at":"2025-12-19T01:33:49.864359-08:00","close_reason":"Merged to main in swarm session","dependencies":[{"issue_id":"gt-h5n.8","depends_on_id":"gt-h5n","type":"parent-child","created_at":"2025-12-17T13:52:00.324781-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-h5n.9","title":"Per-epic config overrides: custom merge settings","description":"Allow per-epic merge configuration overrides.\n\nEpic can specify merge_config in its description:\n merge_config:\n run_tests: true\n test_command: 'go test -race ./...'\n on_conflict: assign_back\n\nWhen processing MRs for an epic:\n1. Load rig-level merge_queue config\n2. Check if epic has merge_config\n3. Merge epic config over rig config\n4. Use merged config for processing\n\nUse cases:\n- Risky refactors: more thorough testing\n- Urgent fixes: skip some checks\n- Experimental work: different test suite\n\nReference: docs/merge-queue-design.md#per-epic-overrides","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-17T13:52:02.32832-08:00","updated_at":"2025-12-17T13:52:02.32832-08:00","dependencies":[{"issue_id":"gt-h5n.9","depends_on_id":"gt-h5n","type":"parent-child","created_at":"2025-12-17T13:52:02.32997-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-hgk","title":"Mail system: message types and threading","description":"GGT mail system needs message types and threading like PGT.\n\n## 1. Message Types\nAdd to internal/mail/types.go:\n```go\ntype MessageType string\nconst (\n TypeTask MessageType = \"task\" // Required processing\n TypeScavenge MessageType = \"scavenge\" // Optional first-come work\n TypeNotification MessageType = \"notification\" // Informational\n TypeReply MessageType = \"reply\" // Response to message\n)\n\n// Update Message struct\ntype Message struct {\n // existing fields...\n Type MessageType `json:\"type\"`\n ThreadID string `json:\"thread_id,omitempty\"`\n ReplyTo string `json:\"reply_to,omitempty\"`\n}\n```\n\n## 2. Priority Levels\nExpand from 2 to 4:\n```go\ntype Priority string\nconst (\n PriorityLow Priority = \"low\"\n PriorityNormal Priority = \"normal\"\n PriorityHigh Priority = \"high\"\n PriorityUrgent Priority = \"urgent\"\n)\n```\n\n## 3. CLI Updates\ninternal/cmd/mail.go:\n- Add --type flag to send: `gt mail send ... --type task`\n- Add --reply-to flag: `gt mail send ... --reply-to \u003cmsg-id\u003e`\n- Add thread command: `gt mail thread \u003cthread-id\u003e`\n\n## 4. Threading Logic\nNewMessage() should auto-generate thread_id if not a reply.\nReply messages inherit thread_id from original.\n\n## Files to Modify\n- internal/mail/types.go: Add types, expand Priority\n- internal/mail/mailbox.go: Thread filtering\n- internal/cmd/mail.go: CLI flags and thread command\n\n## PGT Reference\ngastown-py/src/gastown/mail/message.py\n\n## Acceptance Criteria\n- [ ] Messages have type field (default: notification)\n- [ ] 4 priority levels supported\n- [ ] Reply creates thread with shared thread_id\n- [ ] gt mail thread \u003cid\u003e shows conversation","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-16T14:46:55.29463-08:00","updated_at":"2025-12-18T20:14:28.308997-08:00","closed_at":"2025-12-18T20:14:28.308997-08:00","close_reason":"Implemented message types and threading"} {"id":"gt-hw6","title":"GGT Command Parity: Complete gt command coverage","description":"Complete gt command set to match/exceed PGT town commands.\n\nCovers: uninstall, rig info, refinery attach, witness, session mgmt, mail UX, daemon.","status":"open","priority":1,"issue_type":"epic","created_at":"2025-12-17T22:22:21.720078-08:00","updated_at":"2025-12-17T22:22:21.720078-08:00"} @@ -189,8 +189,8 @@ {"id":"gt-ic0j","title":"🤝 HANDOFF: Timing fixes applied","description":"Fixed mayor attach timing bug. Completed: timing fix, gt-tulx, Emma beads-6v2. Remaining P1: gt-17zr, gt-kcee, gt-szsq. Run gt prime on startup.","status":"closed","priority":2,"issue_type":"message","assignee":"mayor/","created_at":"2025-12-18T22:19:57.731032-08:00","updated_at":"2025-12-18T23:28:33.950423-08:00","closed_at":"2025-12-18T23:28:33.950423-08:00","close_reason":"Migrated to town-level beads","sender":"Steve Yegge","ephemeral":true} {"id":"gt-iib","title":"Architecture: Decentralized rig structure with per-rig agents","description":"## Decision\n\nAdopt decentralized architecture where each rig contains all its agents (mayor/, witness/, refinery/, polecats/) rather than centralizing mayor clones at town level.\n\n## Town Level Structure\n\n```\n~/ai/ # Town root\n├── config/ # Town config (VISIBLE, not hidden)\n│ ├── town.json # {\"type\": \"town\"}\n│ ├── rigs.json # Registry of managed rigs\n│ └── federation.json # Wasteland config (future)\n│\n├── mayor/ # Mayor's HOME at town level\n│ ├── CLAUDE.md\n│ ├── mail/inbox.jsonl\n│ └── state.json\n│\n└── \u003crigs\u003e/ # Managed projects\n```\n\n## Rig Level Structure (e.g., wyvern)\n\n```\nwyvern/ # Rig = clone of project repo\n├── .git/info/exclude # Gas Town adds: polecats/ refinery/ witness/ mayor/\n├── .beads/ # Beads (if project uses it)\n├── [project files] # Clean project code on main\n│\n├── polecats/ # Worker clones\n│ └── \u003cname\u003e/ # Each is a git clone\n│\n├── refinery/\n│ ├── rig/ # Refinery's clone\n│ ├── state.json\n│ └── mail/inbox.jsonl\n│\n├── witness/ # NEW: Per-rig pit boss\n│ ├── rig/ # Witness's clone\n│ ├── state.json\n│ └── mail/inbox.jsonl\n│\n└── mayor/\n ├── rig/ # Mayor's clone for this rig\n └── state.json\n```\n\n## Key Decisions\n\n1. **Visible config dir**: `config/` not `.gastown/` (models don't find hidden dirs)\n2. **Witness per-rig**: Each rig has its own Witness (pit boss) with its own clone\n3. **Mayor decentralized**: Mayor's clones live IN each rig at `\u003crig\u003e/mayor/rig/`\n4. **Minimal invasiveness**: Only `.git/info/exclude` modified, no commits to project\n5. **Clone subdir name**: Keep `rig/` for consistency (refinery/rig/, witness/rig/, mayor/rig/)\n\n## Role Detection\n\n- Town root or mayor/ → Mayor (town level)\n- Rig root → Mayor (canonical main)\n- \u003crig\u003e/mayor/rig/ → Mayor (rig-specific)\n- \u003crig\u003e/refinery/rig/ → Refinery\n- \u003crig\u003e/witness/rig/ → Witness\n- \u003crig\u003e/polecats/\u003cname\u003e/ → Polecat\n\n## Migration from PGT\n\n- `mayor/rigs/\u003crig\u003e/` → `\u003crig\u003e/mayor/rig/`\n- `\u003crig\u003e/town/` → eliminated (rig root IS the clone)\n- Add `witness/` to each rig","status":"closed","priority":0,"issue_type":"task","created_at":"2025-12-15T19:21:19.913928-08:00","updated_at":"2025-12-15T19:21:40.461186-08:00","closed_at":"2025-12-15T19:21:40.461186-08:00","close_reason":"Design decision recorded","dependencies":[{"issue_id":"gt-iib","depends_on_id":"gt-u1j","type":"blocks","created_at":"2025-12-15T19:21:40.374551-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-j87","title":"Design: Work flow simulation and validation","description":"Validate GGT designs through simulation before implementation.\n\n## Validation Approaches\n\n### 1. Dry-Run Simulation (Recommended First)\nMayor walks through scenarios mentally/on paper:\n- \"If polecat Toast signals done with dirty git state, what happens?\"\n- \"If Witness context fills mid-verification, what state is lost?\"\n- \"If two polecats try to close same issue, what happens?\"\n\nCreate beads for any gaps discovered.\n\n### 2. Real Work in gastown-py\nUse Python Gas Town to stress-test assumptions:\n- Run actual batch work on test repos\n- Observe edge cases in practice\n- Document issues found\n\n### 3. Edge Case Analysis\nSystematic review of failure modes:\n- Agent crashes mid-operation\n- Network failures during sync\n- Concurrent access to shared state\n- Context limits hit at bad times\n\n## Key Scenarios to Validate\n\n- [ ] Witness session cycling (state preservation)\n- [ ] Polecat decommission with dirty state\n- [ ] Merge conflicts in queue\n- [ ] Beads sync conflicts between workers\n- [ ] Escalation path (stuck worker -\u003e Mayor)\n- [ ] Cross-rig communication\n- [ ] Federation mail routing (future)\n\n## Success Criteria\n\n- No data loss scenarios identified\n- Clear recovery paths for all failure modes\n- Edge cases either handled or documented as limitations\n- Design improves as model cognition improves\n\n## Output\n\nFor each scenario validated:\n1. Document in relevant bead if issue found\n2. Create new beads for missing functionality\n3. Update architecture.md if design changes","status":"open","priority":1,"issue_type":"epic","created_at":"2025-12-15T20:24:11.251841-08:00","updated_at":"2025-12-16T17:25:49.858717-08:00"} -{"id":"gt-jpt","title":"Town-level beads: Real DB for coordination mail","description":"Implement Option A from mail redesign: Town gets real beads DB for coordination.\n\n## Background\n\nMail is now Beads. But currently:\n- Town .beads/redirect points to rig beads\n- mayor/mail/ has legacy JSONL files\n- Cross-rig coordination has no clear home\n\n## Design\n\nTown beads = coordination, cross-rig mail, mayor inbox, handoffs\nRig beads = project issues, work items\n\nMatches HOP hierarchy: platform \u003e project \u003e worker\n\n## Structure\n\n~/gt/\n .beads/ # REAL beads DB (prefix: gm-)\n mayor/\n town.json\n state.json # NO mail/ directory\n gastown/\n .beads/ # Rig beads (prefix: ga-)\n\n## Tasks\n\n1. Delete ~/gt/.beads/redirect\n2. Run bd init --prefix gm at ~/gt/ (town beads)\n3. Delete ~/gt/mayor/mail/ directory\n4. Update gt mail to use beads not JSONL\n5. Add mail fields (thread_id, reply_to, msg_type)\n6. Update gt prime for two-tier model\n7. Update docs/architecture.md\n\n## Addressing\n\n- mayor/ -\u003e town beads\n- rig/agent -\u003e rig beads\n- Cross-rig -\u003e town beads","status":"open","priority":1,"issue_type":"epic","created_at":"2025-12-17T19:09:55.855955-08:00","updated_at":"2025-12-17T19:10:06.399802-08:00"} -{"id":"gt-kcee","title":"Witness commands: gt witness start/stop/status needed","description":"## Summary\n\nNo `gt witness` command exists. The witness should:\n- Monitor polecats for stuck/idle state\n- Nudge polecats that seem blocked\n- Report status to mayor\n- Handle polecat lifecycle\n\n## Expected Commands\n\n```bash\ngt witness start gastown # Start witness for rig\ngt witness stop gastown # Stop witness\ngt witness status # Show witness status\n```\n\n## Current State\n\n- Witness directory exists: /Users/stevey/gt/gastown/witness/\n- Has state.json but no active process\n- gt status shows 'Witnesses: 0'\n\n## Context\n\nFull polecat flow needs witness monitoring for production use.","status":"open","priority":1,"issue_type":"feature","created_at":"2025-12-18T21:55:24.079671-08:00","updated_at":"2025-12-18T21:55:24.079671-08:00"} +{"id":"gt-jpt","title":"Town-level beads: Real DB for coordination mail","description":"Implement Option A from mail redesign: Town gets real beads DB for coordination.\n\n## Background\n\nMail is now Beads. But currently:\n- Town .beads/redirect points to rig beads\n- mayor/mail/ has legacy JSONL files\n- Cross-rig coordination has no clear home\n\n## Design\n\nTown beads = coordination, cross-rig mail, mayor inbox, handoffs\nRig beads = project issues, work items\n\nMatches HOP hierarchy: platform \u003e project \u003e worker\n\n## Structure\n\n~/gt/\n .beads/ # REAL beads DB (prefix: gm-)\n mayor/\n town.json\n state.json # NO mail/ directory\n gastown/\n .beads/ # Rig beads (prefix: ga-)\n\n## Tasks\n\n1. Delete ~/gt/.beads/redirect\n2. Run bd init --prefix gm at ~/gt/ (town beads)\n3. Delete ~/gt/mayor/mail/ directory\n4. Update gt mail to use beads not JSONL\n5. Add mail fields (thread_id, reply_to, msg_type)\n6. Update gt prime for two-tier model\n7. Update docs/architecture.md\n\n## Addressing\n\n- mayor/ -\u003e town beads\n- rig/agent -\u003e rig beads\n- Cross-rig -\u003e town beads","status":"closed","priority":1,"issue_type":"epic","created_at":"2025-12-17T19:09:55.855955-08:00","updated_at":"2025-12-19T01:47:54.759787-08:00","closed_at":"2025-12-19T01:47:54.759787-08:00","close_reason":"Implemented: gt install now initializes real town beads DB (gm- prefix) instead of redirect file. Mayor mail uses beads, not JSONL."} +{"id":"gt-kcee","title":"Witness commands: gt witness start/stop/status needed","description":"## Summary\n\nNo `gt witness` command exists. The witness should:\n- Monitor polecats for stuck/idle state\n- Nudge polecats that seem blocked\n- Report status to mayor\n- Handle polecat lifecycle\n\n## Expected Commands\n\n```bash\ngt witness start gastown # Start witness for rig\ngt witness stop gastown # Stop witness\ngt witness status # Show witness status\n```\n\n## Current State\n\n- Witness directory exists: /Users/stevey/gt/gastown/witness/\n- Has state.json but no active process\n- gt status shows 'Witnesses: 0'\n\n## Context\n\nFull polecat flow needs witness monitoring for production use.","status":"closed","priority":1,"issue_type":"feature","created_at":"2025-12-18T21:55:24.079671-08:00","updated_at":"2025-12-19T01:33:49.856942-08:00","closed_at":"2025-12-19T01:33:49.856942-08:00","close_reason":"Merged to main in swarm session"} {"id":"gt-kmn","title":"Batch Work System: Integration branch, merge queue, landing","description":"## Overview\n\nThis epic tracks batch work coordination in GGT. Key insight: **work is a stream, not discrete swarms**.\n\nThere are no \"swarm IDs\" - the epic IS the grouping, the merge queue IS the coordination. \"Swarming an epic\" is colloquial for spawning multiple workers on its children.\n\n## Architecture\n\n- **Epics** group related work\n- **Issues** are individual tasks \n- **Dependencies** encode ordering (multi-wave emerges automatically)\n- **Merge queue** coordinates completed work\n- **Workers** process issues independently\n\nSee Key Decision #11 in docs/architecture.md: \"Work is a Stream (No Swarm IDs)\"\n\n## What This Epic Covers\n\n1. Integration branch management for batch merges\n2. Refinery semantic merge processing\n3. Witness landing protocol (cleanup)\n4. Report generation (epic-based, not swarm-ID-based)\n5. Git safety auditing\n6. Work reconciliation\n\n## What Was Removed\n\n- Swarm IDs (sw-1, sw-2, etc.)\n- Per-swarm directories (.gastown/swarms/\u003cid\u003e/)\n- Swarm manifest/state/events files\n- swarm-started/swarm-landed beads\n\nThese were redundant - beads already provides hierarchy, status, dependencies, and history.\n\n## References\n\n- Architecture: docs/architecture.md (Key Decision #11, Multi-Wave Work Processing)\n- PGT: swarm/manager.py, swarm/landing.py (behavioral reference, but ignore swarm ID patterns)","status":"open","priority":0,"issue_type":"epic","created_at":"2025-12-16T00:08:15.339127-08:00","updated_at":"2025-12-16T17:25:33.208338-08:00"} {"id":"gt-kmn.1","title":"Swarm package: Swarm, SwarmTask, SwarmState types","description":"Define core swarm types.\n\n## Types (in `internal/swarm/`)\n\n```go\n// SwarmState represents swarm lifecycle\ntype SwarmState string\nconst (\n SwarmCreated SwarmState = \"created\"\n SwarmActive SwarmState = \"active\"\n SwarmMerging SwarmState = \"merging\"\n SwarmLanded SwarmState = \"landed\"\n SwarmFailed SwarmState = \"failed\"\n SwarmCancelled SwarmState = \"cancelled\"\n)\n\n// Swarm references a beads epic that tracks swarm work\ntype Swarm struct {\n ID string // matches beads epic ID\n RigName string\n EpicID string // beads epic tracking this swarm\n BaseCommit string // git SHA all workers branch from\n Integration string // integration branch name\n State SwarmState\n CreatedAt time.Time\n Workers []string // polecat names assigned\n}\n\n// SwarmTask represents a single task in the swarm (maps to beads issue)\ntype SwarmTask struct {\n IssueID string // beads issue ID\n Assignee string // polecat name\n Branch string // worker branch name\n State string // mirrors beads status\n}\n```\n\n## Note\n\nSwarm state is primarily stored IN beads. These types are in-memory representations for the SwarmManager to work with. No separate manifest.json files.","status":"closed","priority":0,"issue_type":"task","created_at":"2025-12-16T00:08:30.364047-08:00","updated_at":"2025-12-16T13:31:56.20815-08:00","closed_at":"2025-12-16T13:31:56.20815-08:00","close_reason":"Closed","dependencies":[{"issue_id":"gt-kmn.1","depends_on_id":"gt-kmn","type":"parent-child","created_at":"2025-12-16T00:08:30.364431-08:00","created_by":"daemon","metadata":"{}"},{"issue_id":"gt-kmn.1","depends_on_id":"gt-u1j.1","type":"blocks","created_at":"2025-12-16T00:11:20.646487-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-kmn.10","title":"Batch work landing report generation","description":"Generate reports on batch work completion.\n\n## Trigger\n\nWhen all children of an epic are closed, generate a completion report.\n\n## Report Contents\n\n- Epic metadata (ID, title, created by, duration)\n- Task summary (completed counts, timing)\n- Per-task details (issue, assignee, time taken)\n- Git stats (commits merged, lines changed)\n- Cleanup stats (branches deleted)\n\n## Output Locations\n\n1. Mail to Mayor - summary report\n2. Optional: save to file with --save flag\n\n## Command\n\n```bash\ngt report --epic \u003cepic-id\u003e [--save report.md]\n```\n\n## Format\n\nMarkdown with sections:\n- Summary\n- Tasks\n- Workers\n- Timeline\n\n## Note\n\nThis replaces the swarm-based reporting (gt-662). Reports are generated from epic/issue data, not from separate swarm state files.\n\n## Reference\n\nPGT: swarm/report.py (for format ideas, ignore swarm ID patterns)","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-16T00:10:23.242931-08:00","updated_at":"2025-12-16T17:26:27.99208-08:00","dependencies":[{"issue_id":"gt-kmn.10","depends_on_id":"gt-kmn","type":"parent-child","created_at":"2025-12-16T00:10:23.243287-08:00","created_by":"daemon","metadata":"{}"}]} @@ -226,7 +226,9 @@ {"id":"gt-rm3","title":"CLI: gt refinery commands (start, stop, status, queue)","description":"CLI commands for managing the Refinery agent.\n\n## Commands\n\n```bash\ngt refinery start \u003crig\u003e # Start refinery for a rig\ngt refinery stop \u003crig\u003e # Stop refinery\ngt refinery status \u003crig\u003e # Show refinery status\ngt refinery queue \u003crig\u003e # Show merge queue\n```\n\n## gt refinery start\n\nStarts the Refinery daemon for the specified rig.\n\nOptions:\n- --foreground: Run in foreground (default: background)\n- --auto-merge: Enable auto-merge (default: from config)\n\n## gt refinery stop\n\nStops a running Refinery. Gracefully finishes current MR if processing.\n\n## gt refinery status\n\nShows:\n- Running state (running/stopped)\n- Current MR being processed (if any)\n- Queue length\n- Last merge time\n- Recent activity\n\n## gt refinery queue\n\nShows the merge queue:\n```\nMerge queue for 'wyvern':\n 1. [pending] Toast/polecat-auth-fix (15m ago)\n 2. [pending] Capable/polecat-new-feature (5m ago)\n \n1 merged today, 0 rejected\n```\n\n## Implementation\n\nUses gt-ov2 (Refinery agent) for daemon functionality.","status":"closed","priority":0,"issue_type":"task","created_at":"2025-12-15T23:22:24.754361-08:00","updated_at":"2025-12-16T14:16:34.593637-08:00","closed_at":"2025-12-16T14:16:34.593637-08:00","close_reason":"Closed","dependencies":[{"issue_id":"gt-rm3","depends_on_id":"gt-ov2","type":"blocks","created_at":"2025-12-15T23:22:30.679909-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-ruw","title":"Fix TestHasPolecat test failure in internal/session","description":"TestHasPolecat in internal/session/manager_test.go fails because it expects\nspecific polecats (Toast, Cheedo) to exist in the test environment.\n\nError:\n```\nmanager_test.go:46: expected hasPolecat(Toast) = true\nmanager_test.go:49: expected hasPolecat(Cheedo) = true\n```\n\nFix: Either create test fixtures or mock the filesystem check.","status":"open","priority":2,"issue_type":"bug","created_at":"2025-12-17T15:02:30.030032-08:00","updated_at":"2025-12-17T15:02:30.030032-08:00"} {"id":"gt-ry8","title":"HOP: Entity chain tracking for agents","description":"Track work history per-entity (CV chains). See ~/ai/stevey-gastown/hop/decisions/002-entity-chains.md for design. Post-v0.1 work.","status":"open","priority":3,"issue_type":"feature","created_at":"2025-12-17T01:00:41.347764-08:00","updated_at":"2025-12-17T01:00:41.347764-08:00"} +{"id":"gt-s3m0","title":"gt polecat: add 'done' or 'finish' command to transition from working to idle","description":"When a polecat finishes work but session wasn't properly cleaned up, there's no way to reset it from 'working' state back to 'idle'.\n\nTried:\n```\ngt polecat sleep gastown/Angharad\nError: sleeping polecat: polecat is not active (state: working)\n```\n\nThe sleep command only works on 'active' polecats, not 'working' ones.\n\nHad to manually edit state.json to reset:\n```\njq '.state = \"idle\" | .issue = \"\"' state.json\n```\n\nNeed a command like:\n```\ngt polecat done gastown/Angharad # working -\u003e idle\ngt polecat finish gastown/Angharad # working -\u003e idle \ngt polecat reset gastown/Angharad # any state -\u003e idle (force)\n```","status":"closed","priority":2,"issue_type":"bug","created_at":"2025-12-19T01:41:39.851037-08:00","updated_at":"2025-12-19T01:51:00.479006-08:00","closed_at":"2025-12-19T01:51:00.479006-08:00","close_reason":"Implemented done/finish and reset commands"} {"id":"gt-sd6","title":"Enhanced polecat decommission prompting","description":"Add decommission checklist to polecat AGENTS.md.template. Make crystal clear: verify ALL before signaling done.\n\n## Checklist for AGENTS.md.template\n\n```markdown\n## Decommission Checklist\n\n**CRITICAL**: Before signaling done, you MUST complete this checklist.\nThe Witness will verify each item and bounce you back if dirty.\n\n### Pre-Done Verification\n\n```bash\n# 1. Git status - must be clean\ngit status\n# Expected: \"nothing to commit, working tree clean\"\n\n# 2. Stash list - must be empty\ngit stash list\n# Expected: (empty output)\n\n# 3. Beads sync - must be up to date\nbd sync --status\n# Expected: \"Up to date\" or \"Nothing to sync\"\n\n# 4. Branch merged - your work must be on main\ngit log main --oneline -1\ngit log HEAD --oneline -1\n# Expected: Same commit\n```\n\n### If Any Check Fails\n\n- **Uncommitted changes**: Commit them or discard if unnecessary\n- **Stashes**: Pop and commit, or drop if obsolete\n- **Beads out of sync**: Run `bd sync`\n- **Branch not merged**: Complete the merge workflow\n\n### Signaling Done\n\nOnly after ALL checks pass:\n\n```bash\nbd close \u003cissue-id\u003e\nbd sync\ntown mail send \u003crig\u003e/witness -s \"Work Complete\" -m \"Issue \u003cid\u003e done.\"\n```\n```\n\n## Implementation\n\nAdd to AGENTS.md.template in the polecat prompting section.","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-15T19:48:57.911311-08:00","updated_at":"2025-12-15T20:47:30.062333-08:00","dependencies":[{"issue_id":"gt-sd6","depends_on_id":"gt-82y","type":"blocks","created_at":"2025-12-15T19:49:06.008061-08:00","created_by":"daemon","metadata":"{}"}]} +{"id":"gt-selw","title":"gt spawn: add --polecat flag for explicit worker selection","description":"Currently gt spawn requires positional arg format:\n```\ngt spawn gastown/Angharad --issue gt-xyz\n```\n\nBut I tried the more intuitive flag form:\n```\ngt spawn --issue gt-xyz --polecat Angharad\n```\n\nThis failed with 'unknown flag: --polecat'.\n\nThe flag form is more discoverable and consistent with other commands. Add --polecat flag as alternative to positional arg.","status":"closed","priority":2,"issue_type":"bug","created_at":"2025-12-19T01:41:38.540563-08:00","updated_at":"2025-12-19T01:46:33.500625-08:00","closed_at":"2025-12-19T01:46:33.500625-08:00","close_reason":"Implemented --polecat and --rig flags as alternatives to positional argument"} {"id":"gt-slo","title":"Fix TestHasPolecat test failure","description":"","status":"closed","priority":0,"issue_type":"bug","created_at":"2025-12-17T17:30:19.474356-08:00","updated_at":"2025-12-17T21:12:07.625984-08:00","closed_at":"2025-12-17T21:12:07.625984-08:00","close_reason":"Fixed: Remove() signature (added bool arg), hasPolecat() test (create temp dirs)"} {"id":"gt-sqi","title":"gt session restart/status: Complete session management","description":"Add missing session subcommands:\n\n- gt session restart \u003crig\u003e \u003cpolecat\u003e - Restart a session (stop + start)\n- gt session status \u003crig\u003e \u003cpolecat\u003e - Show session status details\n\nstatus should show:\n- Running state\n- Uptime\n- Current activity\n- Last output timestamp","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-17T21:47:34.700494-08:00","updated_at":"2025-12-17T21:47:34.700494-08:00","dependencies":[{"issue_id":"gt-sqi","depends_on_id":"gt-hw6","type":"blocks","created_at":"2025-12-17T22:23:43.034222-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-sr8","title":"Test merge request","description":"branch: polecat/Test/gt-test\ntarget: main\nsource_issue: gt-test\nworker: TestWorker\nrig: gastown","status":"closed","priority":2,"issue_type":"merge-request","created_at":"2025-12-18T20:08:22.678439-08:00","updated_at":"2025-12-18T20:08:36.133169-08:00","closed_at":"2025-12-18T20:08:36.133169-08:00","close_reason":"Test issue, cleaning up"} @@ -237,7 +239,7 @@ {"id":"gt-svi.4","title":"gt mq retry: retry a failed MR","description":"Implement 'gt mq retry \u003cid\u003e' to retry a failed merge request.\n\nActions:\n1. Verify MR exists and is in failed state (open with failure labels)\n2. Remove failure labels (needs-rebase, needs-fix)\n3. Reset to ready state\n4. Optionally re-run immediately (--now flag)\n\nOptions:\n- --now: immediately process (instead of waiting for Engineer loop)\n\nReference: docs/merge-queue-design.md#cli-commands","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-17T13:50:36.336017-08:00","updated_at":"2025-12-18T20:11:15.063571-08:00","closed_at":"2025-12-18T20:11:15.063571-08:00","close_reason":"Implemented in commit 81c5f6a","dependencies":[{"issue_id":"gt-svi.4","depends_on_id":"gt-svi","type":"parent-child","created_at":"2025-12-17T13:50:36.3382-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-svi.5","title":"gt mq reject: manual MR rejection","description":"Implement 'gt mq reject \u003cid\u003e --reason \"...\"' for manual rejection.\n\nActions:\n1. Verify MR exists and is open\n2. Close MR with close_reason=rejected\n3. Notify worker via mail (optional)\n4. Do NOT close source issue (work not done)\n\nOptions:\n- --reason REASON: required explanation\n- --notify: send mail to worker\n\nReference: docs/merge-queue-design.md#cli-commands","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-17T13:50:38.691775-08:00","updated_at":"2025-12-18T20:10:46.524526-08:00","closed_at":"2025-12-18T20:10:46.524526-08:00","close_reason":"Implemented gt mq reject command with FindMR, RejectMR, and worker notification","dependencies":[{"issue_id":"gt-svi.5","depends_on_id":"gt-svi","type":"parent-child","created_at":"2025-12-17T13:50:38.693749-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-sye","title":"Mayor startup protocol prompting","description":"Add startup protocol to Mayor CLAUDE.md template.\n\n## On Session Start\n\n1. Check for handoff:\n town inbox | grep \"Session Handoff\"\n\n2. If handoff found:\n - Read it: town read \u003cmsg-id\u003e\n - Process pending escalations (highest priority)\n - Check status of noted swarms\n - Verify rig health matches notes\n - Continue with documented next steps\n\n3. If no handoff:\n town status # Overall health\n town rigs # Each rig\n bd ready # Work items\n town inbox # Any messages\n Build your own picture of current state.\n\n4. After processing handoff:\n - Archive or delete the handoff message\n - You now own the current state\n\n## Handoff Best Practices\n\n- Be specific: 'Toast has merge conflict in auth/middleware.go' not 'Toast is stuck'\n- Include context: Why decisions are pending, what you were thinking\n- Prioritize next steps: What is most urgent\n- Note time-sensitive items: Anything that might have changed since handoff","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-15T20:15:27.915484-08:00","updated_at":"2025-12-15T20:48:57.555724-08:00","dependencies":[{"issue_id":"gt-sye","depends_on_id":"gt-u82","type":"blocks","created_at":"2025-12-15T20:15:39.459108-08:00","created_by":"daemon","metadata":"{}"}]} -{"id":"gt-szsq","title":"gt spawn --create should auto-add polecat if missing","description":"## Problem\n\n`gt spawn gastown --issue gt-xxx --create` fails if no polecats exist.\n\n## Current Behavior\n\n```\nError: auto-select polecat: no available polecats in rig 'gastown'\n```\n\n## Expected Behavior\n\n`--create` should:\n1. Create a new polecat if none exist\n2. Or create the specified polecat if `gt spawn gastown/NewName --create`\n\n## Workaround\n\nMust manually run `gt polecat add gastown Name` first.\n\n## Principle\n\nAgent UX should be forgiving - if I say spawn with --create, make it work.","status":"open","priority":1,"issue_type":"bug","created_at":"2025-12-18T21:52:07.75062-08:00","updated_at":"2025-12-18T21:52:07.75062-08:00"} +{"id":"gt-szsq","title":"gt spawn --create should auto-add polecat if missing","description":"## Problem\n\n`gt spawn gastown --issue gt-xxx --create` fails if no polecats exist.\n\n## Current Behavior\n\n```\nError: auto-select polecat: no available polecats in rig 'gastown'\n```\n\n## Expected Behavior\n\n`--create` should:\n1. Create a new polecat if none exist\n2. Or create the specified polecat if `gt spawn gastown/NewName --create`\n\n## Workaround\n\nMust manually run `gt polecat add gastown Name` first.\n\n## Principle\n\nAgent UX should be forgiving - if I say spawn with --create, make it work.","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-12-18T21:52:07.75062-08:00","updated_at":"2025-12-19T01:33:49.859926-08:00","closed_at":"2025-12-19T01:33:49.859926-08:00","close_reason":"Merged to main in swarm session"} {"id":"gt-tl54","title":"MR: gt-test (main)","description":"branch: main\ntarget: main\nsource_issue: gt-test","status":"closed","priority":3,"issue_type":"merge-request","created_at":"2025-12-18T20:16:41.125975-08:00","updated_at":"2025-12-18T20:21:54.162843-08:00","closed_at":"2025-12-18T20:21:54.162843-08:00","close_reason":"Test MRs, cleaning up"} {"id":"gt-tulx","title":"gt mq submit: creates task type instead of merge-request type","description":"## Problem\n\n`gt mq submit` creates an issue with `type: task` but should be `type: merge-request`.\n\n## Evidence\n\n```\n$ bd show gt-n508\ngt-n508: Merge: gt-70b3\nStatus: open\nPriority: P1\nType: task \u003c-- WRONG, should be merge-request\n...\nDescription:\ntype: merge-request \u003c-- Correct type is in description, not in actual type field\n```\n\n## Impact\n\n`gt mq list` shows empty queue because it queries for `type: merge-request`\n\n## Fix\n\n`gt mq submit` should set `--type merge-request` when creating the bead.","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-12-18T21:57:37.905848-08:00","updated_at":"2025-12-18T22:16:31.393114-08:00","closed_at":"2025-12-18T22:16:31.393114-08:00","close_reason":"Fixed in mq.go - now uses Type: merge-request. Existing gt-n508 needs resubmit."} {"id":"gt-u1j","title":"Port Gas Town to Go","description":"Complete rewrite of Gas Town in Go for improved performance and single-binary distribution.\n\n## Goals\n- Single installable binary (gt)\n- All Python functionality ported\n- Federation support built-in\n- Improved performance\n\n## Phases\n1. Core infrastructure (config, workspace, git wrapper)\n2. Rig \u0026 polecat management\n3. Session \u0026 tmux operations\n4. Mail system\n5. CLI commands\n6. TUI (optional)","status":"open","priority":0,"issue_type":"epic","created_at":"2025-12-15T16:36:28.769343-08:00","updated_at":"2025-12-15T16:36:28.769343-08:00"} @@ -268,7 +270,7 @@ {"id":"gt-v5k","title":"Design: Failure modes and recovery","description":"Document failure modes and recovery strategies for Gas Town operations.\n\n## Critical Failure Modes\n\n### 1. Agent Crash Mid-Operation\n\n**Scenario**: Polecat crashes while committing, Witness crashes while verifying\n\n**Detection**:\n- Session suddenly gone (tmux check fails)\n- State shows 'working' but no session\n- Heartbeat stops (for Witness)\n\n**Recovery**:\n- Doctor detects via ZombieSessionCheck\n- Capture any recoverable state\n- Reset agent state to 'idle'\n- For Witness: auto-restart via supervisor or manual gt witness start\n\n### 2. Git State Corruption\n\n**Scenario**: Merge conflict, failed rebase, detached HEAD\n\n**Detection**:\n- Git commands fail\n- Dirty state that won't commit\n- Branch diverged from origin\n\n**Recovery**:\n- gt doctor reports git health issues\n- Manual intervention recommended\n- Severe cases: remove clone, re-clone\n\n### 3. Beads Sync Conflict\n\n**Scenario**: Two polecats modify same issue\n\n**Detection**:\n- bd sync fails with conflict\n- Beads tombstone mechanism handles most cases\n\n**Recovery**:\n- Beads has last-write-wins semantics\n- bd sync --force in extreme cases\n- Issues may need manual dedup\n\n### 4. Tmux Failure\n\n**Scenario**: Tmux server crashes, socket issues\n\n**Detection**:\n- All sessions inaccessible\n- \"no server running\" errors\n\n**Recovery**:\n- Kill any orphan processes\n- tmux kill-server \u0026\u0026 tmux start-server\n- All agent states reset to idle\n- Re-spawn active work\n\n### 5. Claude API Issues\n\n**Scenario**: Rate limits, outages, context limits\n\n**Detection**:\n- Sessions hang or produce errors\n- Repeated failure patterns\n\n**Recovery**:\n- Exponential backoff (handled by Claude Code)\n- For context limits: session cycling (mail-to-self)\n- For outages: wait and retry\n\n### 6. Disk Full\n\n**Scenario**: Clones, logs, or beads fill disk\n\n**Detection**:\n- Write operations fail\n- git/bd commands error\n\n**Recovery**:\n- Clean up logs: rm ~/.gastown/logs/*\n- Remove old polecat clones\n- gt doctor --fix can clean some cruft\n\n### 7. Network Failure\n\n**Scenario**: Can't reach GitHub, API servers\n\n**Detection**:\n- git fetch/push fails\n- Claude sessions hang\n\n**Recovery**:\n- Work continues locally\n- Queue pushes for later\n- Sync when connectivity restored\n\n## Recovery Principles\n\n1. **Fail safe**: Prefer stopping over corrupting\n2. **State is recoverable**: Git and beads have recovery mechanisms\n3. **Doctor heals**: gt doctor --fix handles common issues\n4. **Emergency stop**: gt stop --all as last resort\n5. **Human escalation**: Some failures need Overseer intervention\n\n## Implementation\n\n- Document each failure mode in architecture.md\n- Ensure doctor checks cover detection\n- Add recovery hints to error messages\n- Log all failures for debugging","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-15T23:19:07.198289-08:00","updated_at":"2025-12-15T23:19:28.171942-08:00"} {"id":"gt-vc1n","title":"Tmux status line: rig color themes and worker identity display","description":"## Summary\n\nCustomize tmux status line for Gas Town workers with:\n1. Per-rig configurable color themes\n2. Clear worker name and role visibility\n\n## Current Problem\n\n- Only mayor shows in status line (and truncated)\n- Can't tell which rig/worker you're looking at\n- All sessions look the same\n\n## Proposed Design\n\n### Per-rig colors\n```yaml\n# In rig config or beads\ntheme:\n primary: '#ff6600' # Orange for gastown\n secondary: '#333333'\n accent: '#ffcc00'\n```\n\n### Status line format\n```\n[gastown/Rictus] polecat | gt-70b3 | branch: polecat/Rictus\n[beads/emma] crew | working | branch: main \n[mayor] coordinator | idle\n```\n\n### Components\n- Rig name with rig color\n- Worker name\n- Role (polecat/crew/mayor/witness/refinery)\n- Current issue or status\n- Branch name\n\n## Configuration\n\nCould use pinned beads for this (see gm-w13, beads-6v2):\n- `bd show \u003crig\u003e-theme` returns theme config\n- Stored as pinned bead, always available\n- Part of 'config in beads data plane' initiative","status":"open","priority":2,"issue_type":"feature","created_at":"2025-12-18T21:58:58.547188-08:00","updated_at":"2025-12-18T21:58:58.547188-08:00"} {"id":"gt-vci","title":"Mayor handoff mail template","description":"Add MAYOR_HANDOFF mail template to templates.py.\n\n## Template Function\n\ndef mayor_handoff(\n active_swarms: List[SwarmStatus],\n rig_status: Dict[str, RigStatus],\n pending_escalations: List[Escalation],\n in_flight_decisions: List[Decision],\n recent_actions: List[str],\n delegated_work: List[DelegatedItem],\n user_requests: List[str],\n next_steps: List[str],\n warnings: Optional[str] = None,\n session_duration: Optional[str] = None,\n) -\u003e Message:\n metadata = {\n 'template': 'MAYOR_HANDOFF',\n 'timestamp': datetime.utcnow().isoformat(),\n 'session_duration': session_duration,\n 'active_swarm_count': len(active_swarms),\n 'pending_escalation_count': len(pending_escalations),\n }\n # ... format sections ...\n return Message.create(\n sender='mayor/',\n recipient='mayor/',\n subject='Session Handoff',\n body=body,\n priority='high',\n )\n\n## Metadata Fields\n\n- template: MAYOR_HANDOFF\n- timestamp: ISO format\n- session_duration: Human readable\n- active_swarm_count: Number of active swarms\n- pending_escalation_count: Number of escalations\n\n## Mail Priority\n\nUse priority='high' to ensure handoff is seen on startup.","status":"open","priority":1,"issue_type":"task","created_at":"2025-12-15T20:15:30.26323-08:00","updated_at":"2025-12-15T20:48:59.550689-08:00","dependencies":[{"issue_id":"gt-vci","depends_on_id":"gt-u82","type":"blocks","created_at":"2025-12-15T20:15:39.554108-08:00","created_by":"daemon","metadata":"{}"}]} -{"id":"gt-vdp0","title":"Crew workers getting wrong CLAUDE.md (shows Refinery)","description":"## Problem\n\nCrew workers (emma, dave) have CLAUDE.md that says they're the Refinery.\n\n## Evidence\n\n```\n$ head -5 /Users/stevey/gt/beads/crew/emma/CLAUDE.md\n# Claude: Beads Refinery\nYou are the **Refinery** for the **beads** rig...\n```\n\n## Expected\n\nShould use crew.md.tmpl which correctly says:\n```\n# Crew Worker Context\nYou are a **crew worker** - the overseer's (human's) personal workspace...\n```\n\n## Impact\n\n- Crew workers have wrong identity in static context\n- `gt prime` correctly outputs crew context, but CLAUDE.md conflicts\n- Confusing role information\n\n## Fix\n\nCheck `gt crew create` or whatever populates CLAUDE.md for crew workers.","status":"open","priority":1,"issue_type":"bug","created_at":"2025-12-18T21:40:56.518032-08:00","updated_at":"2025-12-18T21:40:56.518032-08:00","dependencies":[{"issue_id":"gt-vdp0","depends_on_id":"gt-l4gm","type":"blocks","created_at":"2025-12-18T21:50:04.955247-08:00","created_by":"daemon"}]} +{"id":"gt-vdp0","title":"Crew workers getting wrong CLAUDE.md (shows Refinery)","description":"## Problem\n\nCrew workers (emma, dave) have CLAUDE.md that says they're the Refinery.\n\n## Evidence\n\n```\n$ head -5 /Users/stevey/gt/beads/crew/emma/CLAUDE.md\n# Claude: Beads Refinery\nYou are the **Refinery** for the **beads** rig...\n```\n\n## Expected\n\nShould use crew.md.tmpl which correctly says:\n```\n# Crew Worker Context\nYou are a **crew worker** - the overseer's (human's) personal workspace...\n```\n\n## Impact\n\n- Crew workers have wrong identity in static context\n- `gt prime` correctly outputs crew context, but CLAUDE.md conflicts\n- Confusing role information\n\n## Fix\n\nCheck `gt crew create` or whatever populates CLAUDE.md for crew workers.","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-12-18T21:40:56.518032-08:00","updated_at":"2025-12-19T01:33:49.863259-08:00","closed_at":"2025-12-19T01:33:49.863259-08:00","close_reason":"Merged to main in swarm session","dependencies":[{"issue_id":"gt-vdp0","depends_on_id":"gt-l4gm","type":"blocks","created_at":"2025-12-18T21:50:04.955247-08:00","created_by":"daemon"}]} {"id":"gt-vjv","title":"Add bulk session stop command (gt session stop --all)","description":"When decommissioning a rig, need to stop multiple sessions one at a time. A --all or --rig flag would allow: gt session stop --rig gastown","status":"closed","priority":3,"issue_type":"feature","created_at":"2025-12-18T11:33:33.394649-08:00","updated_at":"2025-12-18T11:38:51.399298-08:00","closed_at":"2025-12-18T11:38:51.399298-08:00","close_reason":"Wrong model: streaming doesn't need bulk shutdown commands - polecats request their own shutdown"} {"id":"gt-vjw","title":"Swarm learning: Session cleanup missing from swarm workflow","description":"## Problem\n\nAfter Enders Game swarm completed (18 issues merged), 16 polecat sessions were left running but idle. No automated cleanup occurred.\n\n## What Should Happen\n\n1. Witness detects polecat completed work (idle at prompt)\n2. Witness verifies git state is clean\n3. Witness shuts down session\n4. Witness reports completion to Mayor\n\n## GGT Components\n\n- gt-cxx: Witness context cycling (covers self-cycling)\n- gt-u1j.9: Witness daemon heartbeat loop\n- gt-kmn.6: Witness swarm landing protocol\n\n## Recommendation\n\nAdd to Witness responsibilities:\n- Monitor for 'work complete' signals (DONE keyword, idle detection)\n- Automated session shutdown after verification\n- Swarm completion reporting to Mayor\n\nSee also: architecture.md 'Worker Cleanup (Witness-Owned)' section which describes this but it wasn't implemented in PGT.","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-16T01:27:52.796587-08:00","updated_at":"2025-12-16T01:51:37.409965-08:00","closed_at":"2025-12-16T01:51:37.409965-08:00","close_reason":"Addressed by gt-u1j.9 (daemon heartbeat) which now includes session lifecycle management and worker shutdown. See architecture.md Key Decision #12."} {"id":"gt-vnp9","title":"tmux notifications: display-message too subtle, use send-keys instead","description":"## Problem\n\n`tmux display-message` notifications are not visible enough - they appear briefly in the status bar and are easy to miss.\n\n## Current Behavior\n\nrouter.go uses:\n```go\nr.tmux.DisplayMessageDefault(sessionID, notification)\n```\n\n## What Works\n\nSending echo commands directly to the terminal:\n```bash\ntmux send-keys -t \u003csession\u003e \"echo '📬 NEW MAIL from mayor'\" Enter\n```\n\n## Proposed Fix\n\nChange notification method to send visible output to the terminal, perhaps with a box/banner:\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n📬 NEW MAIL from mayor\nSubject: \u003csubject\u003e\nRun: bd mail inbox\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n```\n\n## Considerations\n\n- This interrupts the terminal output (acceptable for important mail)\n- Could check if Claude is mid-response and queue notification\n- Or use tmux popup if available","notes":"Additional issues:\n1. Enter key not sent properly when chained with send-keys\n2. Need to debounce and send Enter separately\n3. Correct pattern: send text, sleep briefly, then send Enter","status":"open","priority":2,"issue_type":"bug","created_at":"2025-12-18T21:35:28.542985-08:00","updated_at":"2025-12-18T21:35:43.867634-08:00"} @@ -280,7 +282,7 @@ {"id":"gt-y0t","title":"session stop: --force flag is defined but not used","description":"","status":"closed","priority":2,"issue_type":"bug","created_at":"2025-12-16T13:55:12.848848-08:00","updated_at":"2025-12-16T13:56:39.09003-08:00","closed_at":"2025-12-16T13:56:39.09003-08:00","close_reason":"Closed"} {"id":"gt-y5o","title":"Daemon: verify requesting_cycle before kill","description":"Per gt-gby spec, daemon should verify agent state shows requesting_cycle=true before killing session. Currently kills on any lifecycle request without verification.\n\nRequires state.json in agent workspace with requesting_cycle field.","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-18T13:38:13.049988-08:00","updated_at":"2025-12-18T13:38:13.049988-08:00","dependencies":[{"issue_id":"gt-y5o","depends_on_id":"gt-99m","type":"blocks","created_at":"2025-12-18T13:38:26.590883-08:00","created_by":"daemon"}]} {"id":"gt-yls","title":"Document merge queue architecture","description":"Update docs/architecture.md with:\n\n- Merge Queue section explaining Beads-native approach\n- Engineer role (renamed from Refinery)\n- Session restart protocol\n- gt mq command reference\n- Federation considerations for queue\n\nAlso update any references to .gastown/ → config/.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-16T23:02:41.533065-08:00","updated_at":"2025-12-17T13:43:41.657433-08:00","closed_at":"2025-12-17T13:43:41.657433-08:00","close_reason":"Created docs/merge-queue-design.md","dependencies":[{"issue_id":"gt-yls","depends_on_id":"gt-h5n","type":"blocks","created_at":"2025-12-16T23:02:56.043373-08:00","created_by":"daemon","metadata":"{}"}]} -{"id":"gt-yx4","title":"Town root .beads has schema mismatch with bd","description":"The .beads directory at town root (/Users/stevey/gt/.beads) has an incompatible schema:\n\n```\nError: failed to open database: failed to initialize schema: sqlite3: SQL logic error: no such column: thread_id\n```\n\nMeanwhile, gastown/.beads (symlinked to mayor/rig/.beads) works fine.\n\n## Impact\n\n- gt mail inbox fails at town root\n- gt handoff sends mail to broken db\n- Daemon can't check its inbox\n\n## Options\n\n1. Delete town root .beads/beads.db and let it recreate\n2. Symlink town root .beads to gastown/.beads\n3. Run schema migration on existing db\n\n## Root Cause\n\nLikely a beads version upgrade that added thread_id column, but the town root db was created before that.","status":"open","priority":1,"issue_type":"bug","created_at":"2025-12-18T14:31:35.559042-08:00","updated_at":"2025-12-18T14:31:35.559042-08:00"} +{"id":"gt-yx4","title":"Town root .beads has schema mismatch with bd","description":"The .beads directory at town root (/Users/stevey/gt/.beads) has an incompatible schema:\n\n```\nError: failed to open database: failed to initialize schema: sqlite3: SQL logic error: no such column: thread_id\n```\n\nMeanwhile, gastown/.beads (symlinked to mayor/rig/.beads) works fine.\n\n## Impact\n\n- gt mail inbox fails at town root\n- gt handoff sends mail to broken db\n- Daemon can't check its inbox\n\n## Options\n\n1. Delete town root .beads/beads.db and let it recreate\n2. Symlink town root .beads to gastown/.beads\n3. Run schema migration on existing db\n\n## Root Cause\n\nLikely a beads version upgrade that added thread_id column, but the town root db was created before that.","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-12-18T14:31:35.559042-08:00","updated_at":"2025-12-19T00:39:32.211083-08:00","closed_at":"2025-12-19T00:39:32.211083-08:00","close_reason":"Schema already fixed. Town root .beads now has thread_id column in dependencies table. bd doctor passes (v0.30.6), gt mail inbox works."} {"id":"gt-z4g","title":"Plugin: Plan-to-Epic converter","description":"## Purpose\n\nHelp users create beads epics from various planning inputs.\n\n## Inputs\n- Markdown task lists\n- GitHub issues\n- Linear/Jira exports\n- Free-form descriptions\n- Existing beads epics\n\n## Output\n- Beads epic with properly structured children\n- Dependencies set for wave ordering\n- Priorities assigned\n- Ready for `gt spawn --epic \u003cid\u003e`\n\n## Implementation Options\n\n### Option A: CLI Tool\n```bash\ngt plan import --from github --repo owner/repo --label batch-candidate\ngt plan import --from markdown tasks.md\ngt plan structure \u003cepic-id\u003e # analyze and add dependencies\n```\n\n### Option B: Plugin Agent\nA plugin at `\u003crig\u003e/plugins/plan-oracle/` that:\n- Receives planning requests via mail\n- Analyzes scope and requirements\n- Creates structured beads epic\n- Sets dependencies based on analysis\n\n### Option C: Interactive Mode\n```bash\ngt plan create\n# Walks through questions, creates epic interactively\n```\n\n## Axiom\n\nAs stated: 'The Planning phase should end in the creation of a workable Beads plan.'\n\nThis plugin bridges the gap between human planning and machine-executable work.\n\n## Priority\n\nP2 - Nice to have for MVP. Manual epic creation works for now.\n\n## Note\n\nNo \"swarm IDs\" - output is just a beads epic with children. Workers process it independently.","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-16T02:10:20.663549-08:00","updated_at":"2025-12-16T17:26:41.087304-08:00"} {"id":"gt-zko","title":"gt rig info: Show detailed rig information","description":"Add 'gt rig info \u003crig\u003e' command to show detailed rig status.\n\nShould show:\n- Rig path and git URL\n- Active polecats with status\n- Refinery status\n- Witness status\n- Recent activity\n- Beads summary (open issues count)","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-17T21:47:17.879255-08:00","updated_at":"2025-12-17T22:29:46.970197-08:00","closed_at":"2025-12-17T22:29:46.970197-08:00","close_reason":"Implemented gt rig info command with detailed rig status display","dependencies":[{"issue_id":"gt-zko","depends_on_id":"gt-hw6","type":"blocks","created_at":"2025-12-17T22:22:47.502099-08:00","created_by":"daemon","metadata":"{}"}]} {"id":"gt-zly","title":"Swarm learning: Beads database locality gap","description":"## PGT Bug (GGT Design Already Correct)\n\nMayor created issues in `~/ai/mayor/rigs/beads/.beads/` but polecats use `~/ai/beads/.beads/`. Different databases = polecats can't see Mayor's beads.\n\n**GGT Fix**: architecture.md already specifies:\n- All agents use BEADS_DIR pointing to rig-level `.beads/`\n- Lines 116-143: Beads Configuration for Multi-Agent\n- Lines 573-586: Rig-Level Beads via BEADS_DIR\n\nThis is a PGT implementation gap, not a design issue. GGT spawn must set BEADS_DIR correctly.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-16T01:21:45.37072-08:00","updated_at":"2025-12-16T01:28:40.74469-08:00","closed_at":"2025-12-16T01:28:40.74469-08:00","close_reason":"PGT implementation gap documented. GGT design already correct - architecture.md specifies BEADS_DIR for all agents pointing to rig-level .beads/"} diff --git a/internal/cmd/handoff.go b/internal/cmd/handoff.go index c103f2d1..0419763a 100644 --- a/internal/cmd/handoff.go +++ b/internal/cmd/handoff.go @@ -226,9 +226,12 @@ func getManager(role Role) string { case RoleMayor, RoleWitness: return "daemon/" case RolePolecat, RoleRefinery: - // Would need rig context to determine witness address - // For now, use a placeholder pattern - return "/witness" + // Detect rig from environment or working directory + rigName := detectRigName() + if rigName != "" { + return rigName + "/witness" + } + return "witness/" // fallback case RoleCrew: return "human" // Crew is human-managed default: @@ -236,6 +239,41 @@ func getManager(role Role) string { } } +// detectRigName detects the rig name from environment or directory context. +func detectRigName() string { + // Check environment variable first + if rig := os.Getenv("GT_RIG"); rig != "" { + return rig + } + + // Try to detect from tmux session name (format: gt--) + out, err := exec.Command("tmux", "display-message", "-p", "#{session_name}").Output() + if err == nil { + sessionName := strings.TrimSpace(string(out)) + if strings.HasPrefix(sessionName, "gt-") { + parts := strings.SplitN(sessionName, "-", 3) + if len(parts) >= 2 { + return parts[1] + } + } + } + + // Try to detect from working directory + cwd, err := os.Getwd() + if err != nil { + return "" + } + + // Look for "polecats" in path: .../rig/polecats/polecat/... + if idx := strings.Index(cwd, "/polecats/"); idx != -1 { + // Extract rig name from path before /polecats/ + rigPath := cwd[:idx] + return filepath.Base(rigPath) + } + + return "" +} + // sendHandoffMail sends a handoff message to ourselves for the successor to read. func sendHandoffMail(role Role, townRoot string) error { // Determine our address @@ -286,19 +324,26 @@ func sendLifecycleRequest(manager string, role Role, action HandoffAction, townR return nil } + // Get polecat name for identification + polecatName := detectPolecatName() + rigName := detectRigName() + subject := fmt.Sprintf("LIFECYCLE: %s requesting %s", role, action) body := fmt.Sprintf(`Lifecycle request from %s. Action: %s +Rig: %s +Polecat: %s Time: %s Please verify state and execute lifecycle action. -`, role, action, time.Now().Format(time.RFC3339)) +`, role, action, rigName, polecatName, time.Now().Format(time.RFC3339)) // Send via bd mail (syntax: bd mail send -s -m ) cmd := exec.Command("bd", "mail", "send", manager, "-s", subject, "-m", body, + "--type", "task", // Mark as task requiring action ) cmd.Dir = townRoot @@ -309,6 +354,45 @@ Please verify state and execute lifecycle action. return nil } +// detectPolecatName detects the polecat name from environment or directory context. +func detectPolecatName() string { + // Check environment variable first + if polecat := os.Getenv("GT_POLECAT"); polecat != "" { + return polecat + } + + // Try to detect from tmux session name (format: gt--) + out, err := exec.Command("tmux", "display-message", "-p", "#{session_name}").Output() + if err == nil { + sessionName := strings.TrimSpace(string(out)) + if strings.HasPrefix(sessionName, "gt-") { + parts := strings.SplitN(sessionName, "-", 3) + if len(parts) >= 3 { + return parts[2] + } + } + } + + // Try to detect from working directory + cwd, err := os.Getwd() + if err != nil { + return "" + } + + // Look for "polecats" in path: .../rig/polecats/polecat/... + if idx := strings.Index(cwd, "/polecats/"); idx != -1 { + // Extract polecat name from path after /polecats/ + remainder := cwd[idx+len("/polecats/"):] + // Take first component + if slashIdx := strings.Index(remainder, "/"); slashIdx != -1 { + return remainder[:slashIdx] + } + return remainder + } + + return "" +} + // setRequestingState updates state.json to indicate we're requesting lifecycle action. func setRequestingState(role Role, action HandoffAction, townRoot string) error { // Determine state file location based on role diff --git a/internal/cmd/polecat.go b/internal/cmd/polecat.go index 39ca75ca..0e79be88 100644 --- a/internal/cmd/polecat.go +++ b/internal/cmd/polecat.go @@ -40,11 +40,11 @@ var polecatListCmd = &cobra.Command{ Short: "List polecats in a rig", Long: `List polecats in a rig or all rigs. -Output: - - Name - - State (idle/active/working/done/stuck) - - Current issue (if any) - - Session status (running/stopped) +In the ephemeral model, polecats exist only while working. The list shows +all currently active polecats with their states: + - working: Actively working on an issue + - done: Completed work, waiting for cleanup + - stuck: Needs assistance Examples: gt polecat list gastown @@ -85,10 +85,13 @@ Example: var polecatWakeCmd = &cobra.Command{ Use: "wake /", - Short: "Mark polecat as active (ready for work)", - Long: `Mark polecat as active (ready for work). + Short: "(Deprecated) Resume a polecat to working state", + Long: `Resume a polecat to working state. -Transitions: idle → active +DEPRECATED: In the ephemeral model, polecats are created fresh for each task +via 'gt spawn'. This command is kept for backward compatibility. + +Transitions: done → working Example: gt polecat wake gastown/Toast`, @@ -98,11 +101,14 @@ Example: var polecatSleepCmd = &cobra.Command{ Use: "sleep /", - Short: "Mark polecat as idle (not available)", - Long: `Mark polecat as idle (not available). + Short: "(Deprecated) Mark polecat as done", + Long: `Mark polecat as done. -Transitions: active → idle -Fails if session is running (stop first). +DEPRECATED: In the ephemeral model, polecats use 'gt handoff' when complete, +which triggers automatic cleanup by the Witness. This command is kept for +backward compatibility. + +Transitions: working → done Example: gt polecat sleep gastown/Toast`, @@ -259,11 +265,11 @@ func runPolecatList(cmd *cobra.Command, args []string) error { } if len(allPolecats) == 0 { - fmt.Println("No polecats found.") + fmt.Println("No active polecats found.") return nil } - fmt.Printf("%s\n\n", style.Bold.Render("Polecats")) + fmt.Printf("%s\n\n", style.Bold.Render("Active Polecats")) for _, p := range allPolecats { // Session indicator sessionStatus := style.Dim.Render("○") @@ -271,9 +277,15 @@ func runPolecatList(cmd *cobra.Command, args []string) error { sessionStatus = style.Success.Render("●") } + // Normalize state for display (legacy idle/active → working) + displayState := p.State + if p.State == polecat.StateIdle || p.State == polecat.StateActive { + displayState = polecat.StateWorking + } + // State color - stateStr := string(p.State) - switch p.State { + stateStr := string(displayState) + switch displayState { case polecat.StateWorking: stateStr = style.Info.Render(stateStr) case polecat.StateStuck: @@ -351,6 +363,9 @@ func runPolecatRemove(cmd *cobra.Command, args []string) error { } func runPolecatWake(cmd *cobra.Command, args []string) error { + fmt.Println(style.Warning.Render("DEPRECATED: Use 'gt spawn' to create fresh polecats instead")) + fmt.Println() + rigName, polecatName, err := parseAddress(args[0]) if err != nil { return err @@ -365,11 +380,14 @@ func runPolecatWake(cmd *cobra.Command, args []string) error { return fmt.Errorf("waking polecat: %w", err) } - fmt.Printf("%s Polecat %s is now active.\n", style.SuccessPrefix, polecatName) + fmt.Printf("%s Polecat %s is now working.\n", style.SuccessPrefix, polecatName) return nil } func runPolecatSleep(cmd *cobra.Command, args []string) error { + fmt.Println(style.Warning.Render("DEPRECATED: Use 'gt handoff' from within a polecat session instead")) + fmt.Println() + rigName, polecatName, err := parseAddress(args[0]) if err != nil { return err @@ -385,14 +403,14 @@ func runPolecatSleep(cmd *cobra.Command, args []string) error { sessMgr := session.NewManager(t, r) running, _ := sessMgr.IsRunning(polecatName) if running { - return fmt.Errorf("session is running. Stop it first with: gt session stop %s/%s", rigName, polecatName) + return fmt.Errorf("session is running. Use 'gt handoff' from the polecat session, or stop it with: gt session stop %s/%s", rigName, polecatName) } if err := mgr.Sleep(polecatName); err != nil { - return fmt.Errorf("sleeping polecat: %w", err) + return fmt.Errorf("marking polecat as done: %w", err) } - fmt.Printf("%s Polecat %s is now idle.\n", style.SuccessPrefix, polecatName) + fmt.Printf("%s Polecat %s is now done.\n", style.SuccessPrefix, polecatName) return nil } diff --git a/internal/polecat/manager.go b/internal/polecat/manager.go index 45cc4be3..bfad5578 100644 --- a/internal/polecat/manager.go +++ b/internal/polecat/manager.go @@ -80,12 +80,12 @@ func (m *Manager) Add(name string) (*Polecat, error) { return nil, fmt.Errorf("creating worktree: %w", err) } - // Create polecat state + // Create polecat state - ephemeral polecats start in working state now := time.Now() polecat := &Polecat{ Name: name, Rig: m.rig.Name, - State: StateIdle, + State: StateWorking, ClonePath: polecatPath, Branch: branchName, CreatedAt: now, @@ -204,6 +204,7 @@ func (m *Manager) AssignIssue(name, issue string) error { } // ClearIssue removes the issue assignment from a polecat. +// In the ephemeral model, this transitions to Done state for cleanup. func (m *Manager) ClearIssue(name string) error { polecat, err := m.Get(name) if err != nil { @@ -211,38 +212,44 @@ func (m *Manager) ClearIssue(name string) error { } polecat.Issue = "" - polecat.State = StateIdle + polecat.State = StateDone polecat.UpdatedAt = time.Now() return m.saveState(polecat) } // Wake transitions a polecat from idle to active. +// Deprecated: In the ephemeral model, polecats start in working state. +// This method is kept for backward compatibility with existing polecats. func (m *Manager) Wake(name string) error { polecat, err := m.Get(name) if err != nil { return err } - if polecat.State != StateIdle { + // Accept both idle and done states for legacy compatibility + if polecat.State != StateIdle && polecat.State != StateDone { return fmt.Errorf("polecat is not idle (state: %s)", polecat.State) } - return m.SetState(name, StateActive) + return m.SetState(name, StateWorking) } // Sleep transitions a polecat from active to idle. +// Deprecated: In the ephemeral model, polecats are deleted when done. +// This method is kept for backward compatibility. func (m *Manager) Sleep(name string) error { polecat, err := m.Get(name) if err != nil { return err } - if polecat.State != StateActive { + // Accept working state as well for legacy compatibility + if polecat.State != StateActive && polecat.State != StateWorking { return fmt.Errorf("polecat is not active (state: %s)", polecat.State) } - return m.SetState(name, StateIdle) + return m.SetState(name, StateDone) } // Finish transitions a polecat from working/done/stuck to idle and clears the issue. @@ -304,10 +311,11 @@ func (m *Manager) loadState(name string) (*Polecat, error) { if err != nil { if os.IsNotExist(err) { // Return minimal polecat if state file missing + // Use StateWorking since ephemeral polecats are always working return &Polecat{ Name: name, Rig: m.rig.Name, - State: StateIdle, + State: StateWorking, ClonePath: m.polecatDir(name), }, nil } diff --git a/internal/polecat/manager_test.go b/internal/polecat/manager_test.go index 59b979cb..73500628 100644 --- a/internal/polecat/manager_test.go +++ b/internal/polecat/manager_test.go @@ -9,21 +9,22 @@ import ( "github.com/steveyegge/gastown/internal/rig" ) -func TestStateIsAvailable(t *testing.T) { +func TestStateIsActive(t *testing.T) { tests := []struct { - state State - available bool + state State + active bool }{ - {StateIdle, true}, - {StateActive, true}, - {StateWorking, false}, + {StateWorking, true}, {StateDone, false}, {StateStuck, false}, + // Legacy states are treated as active + {StateIdle, true}, + {StateActive, true}, } for _, tt := range tests { - if got := tt.state.IsAvailable(); got != tt.available { - t.Errorf("%s.IsAvailable() = %v, want %v", tt.state, got, tt.available) + if got := tt.state.IsActive(); got != tt.active { + t.Errorf("%s.IsActive() = %v, want %v", tt.state, got, tt.active) } } } @@ -299,7 +300,7 @@ func TestClearIssue(t *testing.T) { t.Fatalf("ClearIssue: %v", err) } - // Verify + // Verify - in ephemeral model, ClearIssue transitions to Done polecat, err := m.Get("Test") if err != nil { t.Fatalf("Get: %v", err) @@ -307,7 +308,7 @@ func TestClearIssue(t *testing.T) { if polecat.Issue != "" { t.Errorf("Issue = %q, want empty", polecat.Issue) } - if polecat.State != StateIdle { - t.Errorf("State = %v, want StateIdle", polecat.State) + if polecat.State != StateDone { + t.Errorf("State = %v, want StateDone", polecat.State) } } diff --git a/internal/polecat/types.go b/internal/polecat/types.go index 1d31a964..03687e9a 100644 --- a/internal/polecat/types.go +++ b/internal/polecat/types.go @@ -4,35 +4,39 @@ package polecat import "time" // State represents the current state of a polecat. +// In the ephemeral model, polecats exist only while working. type State string const ( - // StateIdle means the polecat is not actively working. - StateIdle State = "idle" - - // StateActive means the polecat session is running but not assigned work. - StateActive State = "active" - // StateWorking means the polecat is actively working on an issue. + // This is the initial and primary state for ephemeral polecats. StateWorking State = "working" - // StateDone means the polecat has completed its assigned work. + // StateDone means the polecat has completed its assigned work + // and is ready for cleanup by the Witness. StateDone State = "done" // StateStuck means the polecat needs assistance. StateStuck State = "stuck" -) -// IsAvailable returns true if the polecat can be assigned new work. -func (s State) IsAvailable() bool { - return s == StateIdle || s == StateActive -} + // Legacy states for backward compatibility during transition. + // New code should not use these. + StateIdle State = "idle" // Deprecated: use StateWorking + StateActive State = "active" // Deprecated: use StateWorking +) // IsWorking returns true if the polecat is currently working. func (s State) IsWorking() bool { return s == StateWorking } +// IsActive returns true if the polecat session is actively working. +// For ephemeral polecats, this is true for working state and +// legacy idle/active states (treated as working). +func (s State) IsActive() bool { + return s == StateWorking || s == StateIdle || s == StateActive +} + // Polecat represents a worker agent in a rig. type Polecat struct { // Name is the polecat identifier. diff --git a/internal/witness/manager.go b/internal/witness/manager.go index 4f61a80d..c4c9bc61 100644 --- a/internal/witness/manager.go +++ b/internal/witness/manager.go @@ -1,14 +1,22 @@ package witness import ( + "bytes" "encoding/json" "errors" "fmt" "os" + "os/exec" "path/filepath" + "regexp" + "strings" "time" + "github.com/steveyegge/gastown/internal/git" + "github.com/steveyegge/gastown/internal/polecat" "github.com/steveyegge/gastown/internal/rig" + "github.com/steveyegge/gastown/internal/session" + "github.com/steveyegge/gastown/internal/tmux" ) // Common errors @@ -157,20 +165,33 @@ func (m *Manager) run(w *Witness) error { fmt.Println("Witness running...") fmt.Println("Press Ctrl+C to stop") + // Initial check immediately + m.checkAndProcess(w) + ticker := time.NewTicker(30 * time.Second) defer ticker.Stop() for { select { case <-ticker.C: - // Perform health check - if err := m.healthCheck(w); err != nil { - fmt.Printf("Health check error: %v\n", err) - } + m.checkAndProcess(w) } } } +// checkAndProcess performs health check and processes shutdown requests. +func (m *Manager) checkAndProcess(w *Witness) { + // Perform health check + if err := m.healthCheck(w); err != nil { + fmt.Printf("Health check error: %v\n", err) + } + + // Check for shutdown requests + if err := m.processShutdownRequests(w); err != nil { + fmt.Printf("Shutdown request error: %v\n", err) + } +} + // healthCheck performs a health check on all monitored polecats. func (m *Manager) healthCheck(w *Witness) error { now := time.Now() @@ -178,12 +199,155 @@ func (m *Manager) healthCheck(w *Witness) error { w.Stats.TotalChecks++ w.Stats.TodayChecks++ - // For MVP, just update state - // Future: check keepalive files, nudge idle polecats, escalate stuck ones - return m.saveState(w) } +// processShutdownRequests checks mail for lifecycle requests and handles them. +func (m *Manager) processShutdownRequests(w *Witness) error { + // Get witness mailbox via bd mail inbox + messages, err := m.getWitnessMessages() + if err != nil { + return fmt.Errorf("getting messages: %w", err) + } + + for _, msg := range messages { + // Look for LIFECYCLE requests + if strings.Contains(msg.Subject, "LIFECYCLE:") && strings.Contains(msg.Subject, "shutdown") { + fmt.Printf("Processing shutdown request: %s\n", msg.Subject) + + // Extract polecat name from message body + polecatName := extractPolecatName(msg.Body) + if polecatName == "" { + fmt.Printf(" Warning: could not extract polecat name from message\n") + m.ackMessage(msg.ID) + continue + } + + fmt.Printf(" Polecat: %s\n", polecatName) + + // Perform cleanup + if err := m.cleanupPolecat(polecatName); err != nil { + fmt.Printf(" Cleanup error: %v\n", err) + // Don't ack message on error - will retry + continue + } + + fmt.Printf(" Cleanup complete\n") + + // Acknowledge the message + m.ackMessage(msg.ID) + } + } + + return nil +} + +// WitnessMessage represents a mail message for the witness. +type WitnessMessage struct { + ID string `json:"id"` + Subject string `json:"subject"` + Body string `json:"body"` + From string `json:"from"` +} + +// getWitnessMessages retrieves unread messages for the witness. +func (m *Manager) getWitnessMessages() ([]WitnessMessage, error) { + // Use bd mail inbox --json + cmd := exec.Command("bd", "mail", "inbox", "--json") + cmd.Dir = m.workDir + cmd.Env = append(os.Environ(), "BEADS_AGENT_NAME="+m.rig.Name+"-witness") + + var stdout, stderr bytes.Buffer + cmd.Stdout = &stdout + cmd.Stderr = &stderr + + if err := cmd.Run(); err != nil { + // No messages is not an error + if strings.Contains(stderr.String(), "no messages") { + return nil, nil + } + return nil, fmt.Errorf("%s", stderr.String()) + } + + if stdout.Len() == 0 { + return nil, nil + } + + var messages []WitnessMessage + if err := json.Unmarshal(stdout.Bytes(), &messages); err != nil { + // Try parsing as empty array + if strings.TrimSpace(stdout.String()) == "[]" { + return nil, nil + } + return nil, fmt.Errorf("parsing messages: %w", err) + } + + return messages, nil +} + +// ackMessage acknowledges a message (marks it as read/handled). +func (m *Manager) ackMessage(id string) { + cmd := exec.Command("bd", "mail", "ack", id) + cmd.Dir = m.workDir + cmd.Run() // Ignore errors +} + +// extractPolecatName extracts the polecat name from a lifecycle request body. +func extractPolecatName(body string) string { + // Look for "Polecat: " pattern + re := regexp.MustCompile(`Polecat:\s*(\S+)`) + matches := re.FindStringSubmatch(body) + if len(matches) >= 2 { + return matches[1] + } + return "" +} + +// cleanupPolecat performs the full cleanup sequence for an ephemeral polecat. +// 1. Kill session +// 2. Remove worktree +// 3. Delete branch +func (m *Manager) cleanupPolecat(polecatName string) error { + fmt.Printf(" Cleaning up polecat %s...\n", polecatName) + + // Get managers + t := tmux.NewTmux() + sessMgr := session.NewManager(t, m.rig) + polecatGit := git.NewGit(m.rig.Path) + polecatMgr := polecat.NewManager(m.rig, polecatGit) + + // 1. Kill session + running, err := sessMgr.IsRunning(polecatName) + if err == nil && running { + fmt.Printf(" Killing session...\n") + if err := sessMgr.Stop(polecatName, true); err != nil { + fmt.Printf(" Warning: failed to stop session: %v\n", err) + } + } + + // 2. Remove worktree (this also removes the directory) + fmt.Printf(" Removing worktree...\n") + if err := polecatMgr.Remove(polecatName, true); err != nil { + // Only error if polecat actually exists + if !errors.Is(err, polecat.ErrPolecatNotFound) { + return fmt.Errorf("removing worktree: %w", err) + } + } + + // 3. Delete branch from mayor's clone + branchName := fmt.Sprintf("polecat/%s", polecatName) + mayorPath := filepath.Join(m.rig.Path, "mayor", "rig") + mayorGit := git.NewGit(mayorPath) + + fmt.Printf(" Deleting branch %s...\n", branchName) + if err := mayorGit.DeleteBranch(branchName, true); err != nil { + // Branch might already be deleted or merged, not a critical error + fmt.Printf(" Warning: failed to delete branch: %v\n", err) + } + + return nil +} + // processExists checks if a process with the given PID exists. func processExists(pid int) bool { proc, err := os.FindProcess(pid)