diff --git a/.beads/issues.jsonl b/.beads/issues.jsonl index cfe9fec3..61e691ce 100644 --- a/.beads/issues.jsonl +++ b/.beads/issues.jsonl @@ -34,7 +34,7 @@ {"id":"gt-0skyg","title":"Nudge newly spawned polecats","description":"Nudge newly spawned polecats that are ready for input.\n\nWhen polecats are spawned, their Claude session takes 10-20 seconds to initialize.\nThe spawn command returns immediately without waiting. This step finds spawned\npolecats that are now ready and sends them a trigger to start working.\n\n```bash\n# For each rig with polecats\nfor rig in gastown beads; do\n gt polecats $rig\n # For each working polecat, check if Claude is ready\n # Use tmux capture-pane to look for \"\u003e \" prompt\ndone\n```\n\nFor each ready polecat that hasn't been triggered yet:\n1. Send \"Begin.\" to trigger UserPromptSubmit hook\n2. The hook injects mail, polecat sees its assignment\n3. Mark polecat as triggered in state\n\nUse WaitForClaudeReady from tmux package (polls for \"\u003e \" prompt).\nTimeout: 60 seconds per polecat. If not ready, try again next cycle.\n","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-25T02:11:33.777565-08:00","updated_at":"2025-12-25T11:27:47.578347-08:00","closed_at":"2025-12-25T11:27:47.578347-08:00","close_reason":"No polecats to nudge","dependencies":[{"issue_id":"gt-0skyg","depends_on_id":"gt-uru8z","type":"blocks","created_at":"2025-12-25T02:11:33.977731-08:00","created_by":"stevey"}]} {"id":"gt-0xhh0","title":"Digest: mol-deacon-patrol","description":"Patrol 18: All healthy","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-25T00:36:17.883152-08:00","updated_at":"2025-12-25T00:36:17.883152-08:00","closed_at":"2025-12-25T00:36:17.883115-08:00"} {"id":"gt-0yn0","title":"test pin fix 2","notes":"Released: displaced by new sling","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-23T12:15:48.827437-08:00","updated_at":"2025-12-25T01:33:01.094267-08:00","closed_at":"2025-12-25T01:33:01.094267-08:00","close_reason":"Test pollution cleanup"} -{"id":"gt-0yqqw","title":"Messaging infrastructure: lists, queues, and channels","description":"## Problem\n\nCurrent messaging is point-to-point only:\n- Mail: A → B (durable, polling)\n- Nudge: A → B (ephemeral, real-time)\n\nNo support for broadcast, work queues, or pub/sub patterns.\n\n## Design\n\n### Addressing Syntax\n\n| Prefix | System | Resolution | Storage | Claim? |\n|--------|--------|------------|---------|--------|\n| `agent/` | Mail | Direct | Recipient inbox | N/A |\n| `@group` | Mail | Dynamic (filesystem) | Fan-out (N copies) | No |\n| `list:name` | Mail | Static config | Fan-out (N copies) | No |\n| `queue:name` | Mail | Static config | Shared (1 copy) | Yes |\n| `announce:name` | Mail | Static config | Shared (1 copy) | No |\n| `#channel` | Nudge | Dynamic (tmux) | None (ephemeral) | No |\n\n### Dynamic Aliases\n\n- `@rig/gastown` → scan ~/gt/gastown/ for agent dirs (witness, refinery, crew/*, polecats/*)\n- `@town` → scan ~/gt/ for all agent dirs\n- `@witnesses` → for each rig, include \u003crig\u003e/witness\n- `@crew/gastown` → scan ~/gt/gastown/crew/*\n- `#rig/gastown` → scan tmux for gastown/* sessions\n- `#town` → scan tmux for all Gas Town sessions\n\n**Mail** resolves against filesystem (agents that exist)\n**Channels** resolve against tmux (agents that are running)\n\n### Static Config\n\nLocation: `~/gt/config/` (JSON format, machine-edited)\n\n```json\n// lists.json\n{\n \"oncall\": [\"mayor/\", \"gastown/witness\", \"beads/witness\"],\n \"cleanup/gastown\": [\"gastown/witness\", \"deacon/\"]\n}\n```\n\n### Work Queue Semantics\n\n- `gt mail send queue:cleanup/gastown -s \"Task\" -m \"...\"`\n- `bd update \u003cmsg-id\u003e --claim` → atomic claim (sets assignee + in_progress)\n- If already claimed, returns error \"already claimed by X\"\n\n### Use Cases\n\n1. **Polecat spawn**: `gt mail send @rig/gastown` → Witness + Deacon both notified\n2. **Polecat cleanup**: `gt mail send queue:cleanup/gastown` → first to claim handles it\n3. **Town broadcast**: `gt mail send @town -s \"Handoff now\"` → everyone gets copy\n4. **Real-time alert**: `gt channel publish #witnesses \"Swarm incoming\"`\n\n## Implementation Tasks\n\n1. Create ~/gt/config/ directory structure\n2. Implement dynamic alias resolution (filesystem scan)\n3. Implement static list lookup (config/lists.json)\n4. Add fan-out at send time for @/list: addresses\n5. Implement queue: with shared storage\n6. Add `bd update --claim` for work queue semantics\n7. Implement channel resolution (tmux scan)\n8. Add `gt channel publish` command","status":"open","priority":2,"issue_type":"epic","created_at":"2025-12-25T13:39:38.624096-08:00","updated_at":"2025-12-25T13:39:38.624096-08:00"} +{"id":"gt-0yqqw","title":"Messaging infrastructure: lists, queues, and channels","description":"## Problem\n\nCurrent messaging is point-to-point only:\n- Mail: A → B (durable, polling)\n- Nudge: A → B (ephemeral, real-time)\n\nNo support for broadcast, work queues, or pub/sub patterns.\n\n## Design\n\n### Addressing Syntax\n\n| Prefix | System | Resolution | Storage | Claim? |\n|--------|--------|------------|---------|--------|\n| `agent/` | Mail | Direct | Recipient inbox | N/A |\n| `@group` | Mail | Dynamic (filesystem) | Fan-out (N copies) | No |\n| `list:name` | Mail | Static config | Fan-out (N copies) | No |\n| `queue:name` | Mail | Static config | Shared (1 copy) | Yes |\n| `announce:name` | Mail | Static config | Shared (1 copy) | No |\n| `#channel` | Nudge | Dynamic (tmux) | None (ephemeral) | No |\n\n### Dynamic Aliases\n\n- `@rig/gastown` → scan ~/gt/gastown/ for agent dirs (witness, refinery, crew/*, polecats/*)\n- `@town` → scan ~/gt/ for all agent dirs\n- `@witnesses` → for each rig, include \u003crig\u003e/witness\n- `@crew/gastown` → scan ~/gt/gastown/crew/*\n- `#rig/gastown` → scan tmux for gastown/* sessions\n- `#town` → scan tmux for all Gas Town sessions\n\n**Mail** resolves against filesystem (agents that exist)\n**Channels** resolve against tmux (agents that are running)\n\n### Static Config\n\nLocation: `~/gt/config/` (JSON format, machine-edited)\n\n```json\n// lists.json\n{\n \"oncall\": [\"mayor/\", \"gastown/witness\", \"beads/witness\"],\n \"cleanup/gastown\": [\"gastown/witness\", \"deacon/\"]\n}\n```\n\n### Work Queue Semantics\n\n- `gt mail send queue:cleanup/gastown -s \"Task\" -m \"...\"`\n- `bd update \u003cmsg-id\u003e --claim` → atomic claim (sets assignee + in_progress)\n- If already claimed, returns error \"already claimed by X\"\n\n### Use Cases\n\n1. **Polecat spawn**: `gt mail send @rig/gastown` → Witness + Deacon both notified\n2. **Polecat cleanup**: `gt mail send queue:cleanup/gastown` → first to claim handles it\n3. **Town broadcast**: `gt mail send @town -s \"Handoff now\"` → everyone gets copy\n4. **Real-time alert**: `gt channel publish #witnesses \"Swarm incoming\"`\n\n## Implementation Tasks\n\n1. Create ~/gt/config/ directory structure\n2. Implement dynamic alias resolution (filesystem scan)\n3. Implement static list lookup (config/lists.json)\n4. Add fan-out at send time for @/list: addresses\n5. Implement queue: with shared storage\n6. Add `bd update --claim` for work queue semantics\n7. Implement channel resolution (tmux scan)\n8. Add `gt channel publish` command","status":"open","priority":2,"issue_type":"epic","created_at":"2025-12-25T13:39:38.624096-08:00","updated_at":"2025-12-25T13:39:38.624096-08:00","dependencies":[{"issue_id":"gt-0yqqw","depends_on_id":"gt-s89rg","type":"blocks","created_at":"2025-12-25T14:57:38.134092-08:00","created_by":"daemon"},{"issue_id":"gt-0yqqw","depends_on_id":"gt-flje1","type":"blocks","created_at":"2025-12-25T14:57:38.221076-08:00","created_by":"daemon"}]} {"id":"gt-110m","title":"Digest: mol-deacon-patrol","description":"Patrol 1: All healthy, no lifecycle requests, no orphans","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-24T23:05:14.439933-08:00","updated_at":"2025-12-24T23:05:14.439933-08:00","closed_at":"2025-12-24T23:05:14.439903-08:00","close_reason":"Squashed from 8 wisps"} {"id":"gt-14hd","title":"Work on ga-xxp: Define mol-polecat-work standard molecule...","description":"Work on ga-xxp: Define mol-polecat-work standard molecule. See bd show ga-xxp for full details.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-19T21:49:14.070072-08:00","updated_at":"2025-12-19T22:01:24.336471-08:00","closed_at":"2025-12-19T22:01:24.336471-08:00"} {"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":"2025-12-23T14:27:07.858717-08:00","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"},{"issue_id":"gt-17r","depends_on_id":"gt-7ik","type":"blocks","created_at":"2025-12-17T15:44:41.945064-08:00","created_by":"daemon"}]} @@ -319,6 +319,7 @@ {"id":"gt-7o7","title":"Session pre-shutdown checks","description":"Session stop should verify clean state before killing, like PGT.\n\n## Pre-Shutdown Checks\n\n### 1. Git Working Tree Clean\n```go\nfunc checkGitClean(clonePath string) error {\n // git status --porcelain\n // Fail if any output\n}\n```\n\n### 2. All Commits Pushed\n```go\nfunc checkCommitsPushed(clonePath string) error {\n // git log origin/HEAD..HEAD\n // Fail if any unpushed commits\n}\n```\n\n### 3. Assigned Issues Handled\n```go\nfunc checkIssuesHandled(polecat *Polecat) error {\n // If polecat.Issue != \"\", check if closed or reassigned\n}\n```\n\n### 4. Beads Synced\n```go\nfunc checkBeadsSynced(clonePath string) error {\n // bd sync --status in clone directory\n}\n```\n\n## Behavior on Failure\n1. First attempt: Nudge worker to fix\n2. Retry up to 3 times with delay\n3. After retries: Escalate to Witness/Mayor\n\n## Integration\nModify internal/session/manager.go Stop():\n```go\nfunc (m *Manager) Stop(polecat string, force bool) error {\n if !force {\n if err := m.runPreShutdownChecks(polecat); err != nil {\n return fmt.Errorf(\"pre-shutdown checks failed: %w\", err)\n }\n }\n // existing stop logic\n}\n```\n\n## Flags\n- --force: Skip checks\n- --grace-period N: Time to wait for fixes\n\n## Dependencies\n- Ties into gt-69l (hook system) - can be hook-based\n- Ties into gt-f8v (Witness pre-kill verification)\n\n## Acceptance Criteria\n- [ ] Stop fails if uncommitted changes (without --force)\n- [ ] Stop fails if unpushed commits\n- [ ] Clear error messages with fix instructions\n- [ ] --force bypasses all checks","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-16T14:47:55.968983-08:00","updated_at":"2025-12-16T16:05:02.795812-08:00"} {"id":"gt-7oow","title":"gt mail: Cross-level routing is broken","description":"**Problem:**\nWhen Mayor (at ~/gt) sends mail to a rig worker (gastown/crew/max), the message lands in town-level beads (~/.beads/) but the recipient checks rig-level beads (crew/max/.beads/).\n\n**Reproduction:**\n```bash\ncd ~/gt\ngt mail send gastown/crew/max -s 'Test' -m 'body'\n# Message goes to ~/gt/.beads/ with prefix hq-*\n\ncd ~/gt/gastown/crew/max \ngt mail inbox\n# Does NOT see the message - it's looking in crew/max/.beads/\n```\n\n**Root cause:**\n`findBeadsWorkDir()` walks up from CWD to find .beads. `Router.Send()` runs `bd create` in that directory. This means messages always go to the sender's beads, not the recipient's.\n\n**Fix options:**\n1. Route based on recipient address - if sending to rig/*, use that rig's .beads\n2. Use a single shared beads database for all mail (simpler but less isolated)\n3. Teach agents to check both levels (workaround, not fix)\n\n**Related:**\n- gt-ngu1: Pinned beads sorting (done but pointless if mail doesn't route)\n- This blocks all cross-level mail functionality","status":"closed","priority":1,"issue_type":"bug","created_at":"2025-12-20T17:57:30.258991-08:00","updated_at":"2025-12-20T18:35:54.390121-08:00","closed_at":"2025-12-20T18:35:54.390121-08:00"} {"id":"gt-7q4","title":"HOP: Skill vectors on work items","description":"Add skill embeddings to work items for capability-based matching. See ~/ai/stevey-gastown/hop/CONTEXT.md. Post-v0.1 work.","status":"open","priority":3,"issue_type":"feature","created_at":"2025-12-17T01:00:43.251085-08:00","updated_at":"2025-12-17T01:00:43.251085-08:00"} +{"id":"gt-7qgm0","title":"Digest: mol-deacon-patrol","description":"Patrol 14: All healthy, read Mayor handoff (info)","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-25T14:54:20.388504-08:00","updated_at":"2025-12-25T14:54:20.388504-08:00","closed_at":"2025-12-25T14:54:20.388478-08:00","close_reason":"Squashed from 8 wisps","dependencies":[{"issue_id":"gt-7qgm0","depends_on_id":"gt-71b8c","type":"parent-child","created_at":"2025-12-25T14:54:20.389223-08:00","created_by":"deacon"}]} {"id":"gt-7sqi","title":"Refactor: Extract common manager creation boilerplate","description":"Five nearly identical functions exist for creating managers:\n- getPolecatManager (polecat.go:241)\n- getSessionManager (session.go:183)\n- getCrewManager (crew_helpers.go:44)\n- getRefineryManager (refinery.go:116)\n- getWitnessManager (witness.go:102)\n\nAll follow the same pattern: find workspace, load config, get rig, create manager. Should extract to a common helper that takes a factory function.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-21T21:34:30.495275-08:00","updated_at":"2025-12-21T21:45:39.65029-08:00","closed_at":"2025-12-21T21:45:39.65029-08:00","close_reason":"Extracted common getRig() helper in internal/cmd/rig_helpers.go, updated all 5 manager creation functions to use it"} {"id":"gt-7tt8","title":"Default crew name should be something better than 'main'","description":"When creating a new rig, the default crew worker name is 'main'. This is confusing since:\n\n1. 'main' is also the git branch name\n2. It doesn't convey that this is the user's personal workspace\n3. Crew names should feel more personal/distinct\n\nConsider alternatives like:\n- 'home' - the user's home base\n- 'desk' - their personal desk\n- 'joe/max/etc' - actual name-based defaults\n- Let user pick during rig init","status":"open","priority":3,"issue_type":"task","created_at":"2025-12-21T16:46:51.049367-08:00","updated_at":"2025-12-21T16:46:59.133599-08:00"} {"id":"gt-7wcf","title":"README: Update Install section for homebrew/npm","description":"README currently shows:\n go install github.com/steveyegge/gastown/cmd/gt@latest\n\nBut users will install via homebrew or npm. Update to show:\n brew install gastown\n # or\n npm install -g @anthropic/gastown\n\nAlso add prerequisites section (tmux, Claude Code CLI).","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-24T13:04:51.751097-08:00","updated_at":"2025-12-24T23:27:52.2809-08:00","closed_at":"2025-12-24T23:27:52.2809-08:00","close_reason":"Updated Install section with prerequisites and future package manager options","dependencies":[{"issue_id":"gt-7wcf","depends_on_id":"gt-jo9n","type":"blocks","created_at":"2025-12-24T13:05:00.100253-08:00","created_by":"daemon"}]} @@ -670,6 +671,7 @@ {"id":"gt-fjvo","title":"mol-code-review: Self-improving code review molecule","description":"Create a code review molecule that enables Gas Town to self-improve through automated PR review. Flywheel: review generates quality checks, discovered issues, pattern learning.","status":"open","priority":1,"issue_type":"feature","created_at":"2025-12-20T21:03:10.117272-08:00","updated_at":"2025-12-20T21:03:10.117272-08:00"} {"id":"gt-fk8ys","title":"Digest: mol-deacon-patrol","description":"Patrol 6: All agents healthy","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-25T01:26:31.406007-08:00","updated_at":"2025-12-25T01:26:31.406007-08:00","closed_at":"2025-12-25T01:26:31.405973-08:00","close_reason":"Squashed from 8 wisps"} {"id":"gt-fko","title":"Add Gas Town theory of operation to all role primings","description":"All roles (Mayor, Witness, Refinery, Polecat) should get basic GT architecture context: harness, rigs, agents, mail, beads workflow","status":"tombstone","priority":2,"issue_type":"task","created_at":"2025-12-17T16:42:46.445526-08:00","updated_at":"2025-12-25T01:30:41.67682-08:00","dependencies":[{"issue_id":"gt-fko","depends_on_id":"gt-l1o","type":"blocks","created_at":"2025-12-17T16:42:54.87032-08:00","created_by":"daemon"},{"issue_id":"gt-fko","depends_on_id":"gt-dkc","type":"blocks","created_at":"2025-12-17T16:42:56.409618-08:00","created_by":"daemon"}],"deleted_at":"2025-12-25T01:30:41.67682-08:00","deleted_by":"batch delete","delete_reason":"batch delete","original_type":"task"} +{"id":"gt-flje1","title":"Phase 2: Awareness and real-time channels (announce:, #channel)","description":"## Scope\n\nExtensions for awareness broadcasting and ephemeral real-time communication.\n\n### Deliverables\n\n1. **announce:name** - Shared single-copy bulletin board\n - Informational, not work-creating\n - Recipients check when convenient, missing is OK\n - Use case: 'Bob is refactoring logging, be aware'\n2. **#channel resolution** - Dynamic tmux scan for running agents\n - #rig/gastown → tmux sessions matching gastown/*\n - #town → all Gas Town sessions\n3. **gt channel publish** - Ephemeral nudge broadcast to channel\n\n### Key semantics\n- announce: shared copy (1 message, N readers) vs list: (N copies, N obligations)\n- #channel ephemeral - no storage, real-time only\n- Channels resolve against running sessions, not filesystem","status":"open","priority":3,"issue_type":"epic","created_at":"2025-12-25T14:56:45.075014-08:00","updated_at":"2025-12-25T14:56:45.075014-08:00","dependencies":[{"issue_id":"gt-flje1","depends_on_id":"gt-s89rg","type":"blocks","created_at":"2025-12-25T14:56:52.344399-08:00","created_by":"daemon"}]} {"id":"gt-fly0","title":"bd close --continue: auto-advance to next molecule step","description":"Add --continue flag to bd close for seamless molecule step transitions.\n\n## Usage\n\nbd close \u003cstep-id\u003e --continue [--no-auto]\n\n## Behavior\n\n1. Closes the specified step\n2. Finds next ready step in same molecule (sibling/child)\n3. By default, marks it in_progress (--no-auto to skip)\n4. Outputs the transition\n\n## Output\n\n[checkmark] Closed gt-abc.3: Implement feature\n\nNext ready in molecule:\n gt-abc.4: Write tests\n\n[arrow] Marked in_progress (use --no-auto to skip)\n\n## If no next step\n\n[checkmark] Closed gt-abc.6: Exit decision\n\nMolecule gt-abc complete! All steps closed.\nConsider: bd mol squash gt-abc --summary '...'\n\n## Key behaviors\n- Detects parent molecule from closed step\n- Finds next unblocked sibling\n- Auto-claims by default (propulsion principle)\n- Graceful handling when molecule is complete\n\n## Beads feature\nThis is a bd command - needs implementation in beads repo.","status":"closed","priority":1,"issue_type":"feature","created_at":"2025-12-22T17:01:00.437929-08:00","updated_at":"2025-12-22T17:04:13.464939-08:00","closed_at":"2025-12-22T17:04:13.464939-08:00","close_reason":"Moved to beads: bd-ieyy"} {"id":"gt-fm75","title":"os.Exit() calls in library code prevent proper error handling","description":"internal/cmd/mail.go and other files have os.Exit() calls.\n\nIssues:\n- Hard to test\n- Prevents graceful shutdown\n- Can lose unsaved state\n- Doesn't compose well in library code\n\nShould return errors instead of calling os.Exit() directly.\nLet main() decide how to exit.","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-24T12:51:19.086806-08:00","updated_at":"2025-12-24T12:51:19.086806-08:00","dependencies":[{"issue_id":"gt-fm75","depends_on_id":"gt-jo9n","type":"blocks","created_at":"2025-12-24T12:52:07.642098-08:00","created_by":"daemon"}]} {"id":"gt-fmkr","title":"Merge: gt-pyqv","description":"branch: polecat/dementus\ntarget: main\nsource_issue: gt-pyqv\nrig: gastown","status":"closed","priority":2,"issue_type":"merge-request","created_at":"2025-12-20T01:11:33.237777-08:00","updated_at":"2025-12-21T17:20:27.508367-08:00","closed_at":"2025-12-21T17:20:27.508367-08:00","close_reason":"ORPHANED: Branch never pushed, worktree deleted"} @@ -1158,6 +1160,7 @@ {"id":"gt-s18k","title":"Witness patrol: stale MR queue detection needs state tracking","description":"The mol-witness-patrol check-refinery step says 'if queue is non-empty for \u003e30 min, send nudge' but doesn't explain how to track when the queue first became non-empty.\n\n## Problem\nThe Witness needs to persist:\n- When MR queue first became non-empty\n- Previous queue state for comparison\n\nWithout this, the Witness can't detect stale queues.\n\n## Solution\nAdd to witness handoff bead:\n- mr_queue_nonempty_since: timestamp\n- Update in save-state step\n- Check in check-refinery step","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-23T01:02:38.497753-08:00","updated_at":"2025-12-23T01:02:38.497753-08:00","dependencies":[{"issue_id":"gt-s18k","depends_on_id":"gt-bjft","type":"blocks","created_at":"2025-12-23T01:03:12.026206-08:00","created_by":"daemon"}]} {"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":"2025-12-19T01:57:17.031611-08:00","closed_at":"2025-12-19T01:57:17.031611-08:00"} {"id":"gt-s6dw","title":"Batch wisp squashing in Deacon maintenance","description":"Add wisp squashing to Deacon's maintenance duties:\n- Patrol plugin to find orphaned/completed wisps across all rigs\n- Squash completed patrol wisps to digests\n- Burn abandoned wisps that have no audit value\n- Part of the hygiene/cleanup system\n\nAlso: Witness polecat shutdown should spawn its own short wisp for the cleanup protocol.","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-22T21:52:49.403649-08:00","updated_at":"2025-12-22T21:52:49.403649-08:00"} +{"id":"gt-s89rg","title":"Phase 1: Core messaging primitives (@group, list:, queue:)","description":"## Scope\n\nCore messaging infrastructure that enables multi-recipient and work-queue patterns.\n\n### Deliverables\n\n1. **Config directory structure** - ~/gt/config/ with lists.json, queues.json\n2. **@group dynamic resolution** - Filesystem scan for agent directories\n - @rig/gastown → scan gastown/ for agents\n - @town → scan all rigs\n - @witnesses, @crew/gastown, etc.\n3. **list:name static lookup** - Fan-out to N copies (each recipient gets work item)\n4. **queue:name with claim** - Shared storage, atomic claim via bd update --claim\n5. **Fan-out at send time** - gt mail send handles expansion\n\n### Key semantics\n- @group and list: both fan out (N copies, N obligations)\n- queue: shared copy, first-to-claim wins\n- All resolve at send time, not receive time","status":"open","priority":2,"issue_type":"epic","created_at":"2025-12-25T14:56:33.896754-08:00","updated_at":"2025-12-25T14:56:33.896754-08:00"} {"id":"gt-s8iu","title":"Digest: mol-deacon-patrol","description":"Test patrol cycle - verifying wisp flow","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-22T02:10:19.639919-08:00","updated_at":"2025-12-22T02:10:19.639919-08:00","closed_at":"2025-12-22T02:10:19.639888-08:00","close_reason":"Squashed from 5 wisps","dependencies":[{"issue_id":"gt-s8iu","depends_on_id":"gt-1klr","type":"parent-child","created_at":"2025-12-22T02:10:19.640388-08:00","created_by":"stevey"}]} {"id":"gt-s9im","title":"Remove gt context --usage estimation","description":"The external context estimation approach doesn't work:\n- tmux scrollback trick breaks with --cycle\n- Can't see actual context usage from outside\n- Only the agent knows its internal state\n\nRemove or deprecate:\n- gt context --usage flag\n- Any external context monitoring logic\n\nDocument why in comments: 'Context management is agent-initiated, not externally monitored.\nSee self-check guidance in role templates.'\n\nThis is P3 because it's cleanup - the feature just doesn't work, not actively harmful.","status":"open","priority":3,"issue_type":"task","created_at":"2025-12-23T01:46:42.887818-08:00","updated_at":"2025-12-23T01:46:42.887818-08:00"} {"id":"gt-sadkq","title":"Execute registered plugins","description":"Execute registered plugins.\n\nScan ~/gt/plugins/ for plugin directories. Each plugin has a plugin.md with\nYAML frontmatter defining its gate (when to run) and instructions (what to do).\n\nSee docs/deacon-plugins.md for full documentation.\n\nGate types:\n- cooldown: Time since last run (e.g., 24h)\n- cron: Schedule-based (e.g., \"0 9 * * *\")\n- condition: Metric threshold (e.g., wisp count \u003e 50)\n- event: Trigger-based (e.g., startup, heartbeat)\n\nFor each plugin:\n1. Read plugin.md frontmatter to check gate\n2. Compare against state.json (last run, etc.)\n3. If gate is open, execute the plugin\n\nPlugins marked parallel: true can run concurrently using Task tool subagents.\nSequential plugins run one at a time in directory order.\n\nSkip this step if ~/gt/plugins/ does not exist or is empty.\n","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-25T02:11:33.776878-08:00","updated_at":"2025-12-25T11:27:29.564239-08:00","closed_at":"2025-12-25T11:27:29.564239-08:00","close_reason":"No plugins registered","dependencies":[{"issue_id":"gt-sadkq","depends_on_id":"gt-v7wq4","type":"blocks","created_at":"2025-12-25T02:11:33.919459-08:00","created_by":"stevey"}]}