bd sync: 2025-12-25 11:45:01
This commit is contained in:
Steve Yegge
62
.beads/formulas/mol-gastown-boot.formula.json
Normal file
62
.beads/formulas/mol-gastown-boot.formula.json
Normal file
@@ -0,0 +1,62 @@
|
||||
{
|
||||
"formula": "mol-gastown-boot",
|
||||
"description": "Mayor bootstraps Gas Town via a verification-gated lifecycle molecule.\n\n## Purpose\nWhen Mayor executes \"boot up gas town\", this proto provides the workflow.\nEach step has action + verification - steps stay open until outcome is confirmed.\n\n## Key Principles\n1. **Verification-gated steps** - Not \"command ran\" but \"outcome confirmed\"\n2. **gt peek for verification** - Capture session output to detect stalls\n3. **gt nudge for recovery** - Reliable message delivery to unstick agents\n4. **Parallel where possible** - Witnesses and refineries can start in parallel\n5. **Ephemeral execution** - Boot is a wisp, squashed to digest after completion\n\n## Execution\n```bash\nbd wisp mol-gastown-boot # Create wisp\n```",
|
||||
"version": 1,
|
||||
"steps": [
|
||||
{
|
||||
"id": "ensure-daemon",
|
||||
"title": "Ensure daemon",
|
||||
"description": "Verify the Gas Town daemon is running.\n\n## Action\n```bash\ngt daemon status || gt daemon start\n```\n\n## Verify\n1. Daemon PID file exists: `~/.gt/daemon.pid`\n2. Process is alive: `kill -0 $(cat ~/.gt/daemon.pid)`\n3. Daemon responds: `gt daemon status` returns success\n\n## OnFail\nCannot start daemon. Log error and continue - some commands work without daemon."
|
||||
},
|
||||
{
|
||||
"id": "ensure-deacon",
|
||||
"title": "Ensure deacon",
|
||||
"needs": ["ensure-daemon"],
|
||||
"description": "Start the Deacon and verify patrol mode is active.\n\n## Action\n```bash\ngt deacon start\n```\n\n## Verify\n1. Session exists: `tmux has-session -t gt-deacon 2>/dev/null`\n2. Not stalled: `gt peek deacon/` does NOT show \"> Try\" prompt\n3. Heartbeat fresh: `deacon/heartbeat.json` modified < 2 min ago\n\n## OnStall\n```bash\ngt nudge deacon/ \"Start patrol.\"\nsleep 30\n# Re-verify\n```"
|
||||
},
|
||||
{
|
||||
"id": "ensure-witnesses",
|
||||
"title": "Ensure witnesses",
|
||||
"needs": ["ensure-deacon"],
|
||||
"type": "parallel",
|
||||
"description": "Parallel container: Start all rig witnesses.\n\nChildren execute in parallel. Container completes when all children complete.",
|
||||
"children": [
|
||||
{
|
||||
"id": "ensure-gastown-witness",
|
||||
"title": "Ensure gastown witness",
|
||||
"description": "Start the gastown rig Witness.\n\n## Action\n```bash\ngt witness start gastown\n```\n\n## Verify\n1. Session exists: `tmux has-session -t gastown-witness 2>/dev/null`\n2. Not stalled: `gt peek gastown/witness` does NOT show \"> Try\" prompt\n3. Heartbeat fresh: Last patrol cycle < 5 min ago"
|
||||
},
|
||||
{
|
||||
"id": "ensure-beads-witness",
|
||||
"title": "Ensure beads witness",
|
||||
"description": "Start the beads rig Witness.\n\n## Action\n```bash\ngt witness start beads\n```\n\n## Verify\n1. Session exists: `tmux has-session -t beads-witness 2>/dev/null`\n2. Not stalled: `gt peek beads/witness` does NOT show \"> Try\" prompt\n3. Heartbeat fresh: Last patrol cycle < 5 min ago"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "ensure-refineries",
|
||||
"title": "Ensure refineries",
|
||||
"needs": ["ensure-deacon"],
|
||||
"type": "parallel",
|
||||
"description": "Parallel container: Start all rig refineries.\n\nChildren execute in parallel. Container completes when all children complete.",
|
||||
"children": [
|
||||
{
|
||||
"id": "ensure-gastown-refinery",
|
||||
"title": "Ensure gastown refinery",
|
||||
"description": "Start the gastown rig Refinery.\n\n## Action\n```bash\ngt refinery start gastown\n```\n\n## Verify\n1. Session exists: `tmux has-session -t gastown-refinery 2>/dev/null`\n2. Not stalled: `gt peek gastown/refinery` does NOT show \"> Try\" prompt\n3. Queue processing: Refinery can receive merge requests"
|
||||
},
|
||||
{
|
||||
"id": "ensure-beads-refinery",
|
||||
"title": "Ensure beads refinery",
|
||||
"description": "Start the beads rig Refinery.\n\n## Action\n```bash\ngt refinery start beads\n```\n\n## Verify\n1. Session exists: `tmux has-session -t beads-refinery 2>/dev/null`\n2. Not stalled: `gt peek beads/refinery` does NOT show \"> Try\" prompt\n3. Queue processing: Refinery can receive merge requests"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "verify-town-health",
|
||||
"title": "Verify town health",
|
||||
"needs": ["ensure-witnesses", "ensure-refineries"],
|
||||
"description": "Final verification that Gas Town is healthy.\n\n## Action\n```bash\ngt status\n```\n\n## Verify\n1. Daemon running: Shows daemon status OK\n2. Deacon active: Shows deacon in patrol mode\n3. All witnesses: Each rig witness shows active\n4. All refineries: Each rig refinery shows active\n\n## OnFail\nLog degraded state but consider boot complete. Some agents may need manual recovery.\nRun `gt doctor` for detailed diagnostics."
|
||||
}
|
||||
]
|
||||
}
|
||||
36
.beads/formulas/mol-polecat-lease.formula.json
Normal file
36
.beads/formulas/mol-polecat-lease.formula.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"formula": "mol-polecat-lease",
|
||||
"description": "Semaphore tracking a single polecat's lifecycle.\n\nUsed by Witness to track polecat lifecycle during patrol. The Witness bonds this proto for each active polecat, creating a lease that tracks the polecat from spawn through work to cleanup.\n\n## Variables\n\n| Variable | Required | Description |\n|----------|----------|-------------|\n| polecat | Yes | Name of the polecat |\n| issue | Yes | The issue assigned to the polecat |",
|
||||
"version": 1,
|
||||
"variables": [
|
||||
{
|
||||
"name": "polecat",
|
||||
"required": true,
|
||||
"description": "Name of the polecat"
|
||||
},
|
||||
{
|
||||
"name": "issue",
|
||||
"required": true,
|
||||
"description": "The issue assigned to the polecat"
|
||||
}
|
||||
],
|
||||
"steps": [
|
||||
{
|
||||
"id": "boot",
|
||||
"title": "Boot",
|
||||
"description": "Spawned. Verify it starts working.\n\nCheck if the polecat is alive and working:\n```bash\ngt peek {{polecat}}\n```\n\nIf idle for too long, nudge:\n```bash\ngt nudge {{polecat}} \"Please start working on your assigned issue.\"\n```\n\nTimeout: 60s before escalation to Mayor."
|
||||
},
|
||||
{
|
||||
"id": "working",
|
||||
"title": "Working",
|
||||
"needs": ["boot"],
|
||||
"description": "Actively working. Monitor for stuck.\n\nThe polecat is processing its assigned issue ({{issue}}).\nMonitor via peek. Watch for:\n- Progress on commits\n- Status updates in beads\n- SHUTDOWN mail when done\n\nWait for SHUTDOWN signal from the polecat."
|
||||
},
|
||||
{
|
||||
"id": "done",
|
||||
"title": "Done",
|
||||
"needs": ["working"],
|
||||
"description": "Exit received. Ready for cleanup.\n\nThe polecat has completed its work and sent SHUTDOWN.\nPerform cleanup:\n```bash\ngt session kill {{polecat}}\ngt worktree prune {{polecat}}\n```\n\nUpdate beads state and close the lease."
|
||||
}
|
||||
]
|
||||
}
|
||||
37
.beads/formulas/mol-polecat-work.formula.json
Normal file
37
.beads/formulas/mol-polecat-work.formula.json
Normal file
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"formula": "mol-polecat-work",
|
||||
"description": "Full polecat lifecycle from assignment to decommission.\n\nThis proto enables nondeterministic idempotence for polecat work. A polecat that crashes after any step can restart, read its molecule state, and continue from the last completed step. No work is lost.\n\n## Variables\n\n| Variable | Required | Description |\n|----------|----------|-------------|\n| issue | Yes | The source issue ID being worked on |",
|
||||
"version": 1,
|
||||
"variables": [
|
||||
{
|
||||
"name": "issue",
|
||||
"required": true,
|
||||
"description": "The source issue ID being worked on"
|
||||
}
|
||||
],
|
||||
"steps": [
|
||||
{
|
||||
"id": "load-context",
|
||||
"title": "Load context",
|
||||
"description": "Run gt prime and bd prime. Verify issue assignment.\nCheck inbox for any relevant messages.\n\nRead the assigned issue ({{issue}}) and understand the requirements.\nIdentify any blockers or missing information."
|
||||
},
|
||||
{
|
||||
"id": "implement",
|
||||
"title": "Implement",
|
||||
"needs": ["load-context"],
|
||||
"description": "Implement the solution for {{issue}}. Follow codebase conventions.\nFile discovered work as new issues with bd create.\n\nMake regular commits with clear messages.\nKeep changes focused on the assigned issue."
|
||||
},
|
||||
{
|
||||
"id": "self-review",
|
||||
"title": "Self-review",
|
||||
"needs": ["implement"],
|
||||
"description": "Review your own changes. Look for:\n- Bugs and edge cases\n- Style issues\n- Missing error handling\n- Security concerns\n\nFix any issues found before proceeding."
|
||||
},
|
||||
{
|
||||
"id": "request-shutdown",
|
||||
"title": "Request shutdown",
|
||||
"needs": ["self-review"],
|
||||
"description": "Send shutdown request to Witness.\nWait for termination.\n\nThe polecat is now ready to be cleaned up.\nDo not exit directly - wait for Witness to kill the session."
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -356,7 +356,7 @@
|
||||
{"id":"gt-8tmz.27","title":"Computed range expansion (for-each over expressions)","description":"Support for-each expansion over computed ranges, not just static lists:\n\nfor-each:\n var: move_num\n range: \"1..2^{disks}\" # Computed at cook time\n\nThis enables formulas like Towers of Hanoi where the step count is a function of input variables. The range expression is evaluated during cooking.\n\nRelated: towers-of-hanoi.formula.yaml demonstrates the need.\nDepends on: gt-8tmz.8 (Runtime dynamic expansion)","status":"open","priority":2,"issue_type":"feature","created_at":"2025-12-23T19:27:02.71296-08:00","updated_at":"2025-12-23T19:27:02.71296-08:00","dependencies":[{"issue_id":"gt-8tmz.27","depends_on_id":"gt-8tmz","type":"parent-child","created_at":"2025-12-23T19:27:02.713399-08:00","created_by":"daemon"},{"issue_id":"gt-8tmz.27","depends_on_id":"gt-8tmz.8","type":"blocks","created_at":"2025-12-23T19:27:08.191351-08:00","created_by":"daemon"}]}
|
||||
{"id":"gt-8tmz.28","title":"Formula error handling and recovery","description":"Specify how cooking errors are reported and recovered:\n- What happens when extends chain is broken (missing formula)?\n- What happens when aspect pointcut matches nothing?\n- What happens when expansion produces invalid structure?\n- Graceful degradation vs fail-fast semantics\n- Error metadata in cooked protos\n\nDeferred: post-launch polish","status":"open","priority":4,"issue_type":"task","created_at":"2025-12-23T20:06:28.452872-08:00","updated_at":"2025-12-23T20:06:28.452872-08:00","dependencies":[{"issue_id":"gt-8tmz.28","depends_on_id":"gt-8tmz","type":"parent-child","created_at":"2025-12-23T20:06:28.453346-08:00","created_by":"daemon"}]}
|
||||
{"id":"gt-8tmz.29","title":"Formula versioning and migration strategy","description":"Define how formula versions are managed:\n- What does the version field mean? Semver? Integer?\n- When a formula changes, what happens to existing protos?\n- Do protos track their source formula version?\n- Migration path: old proto + new formula = ?\n- Backwards compatibility guarantees (if any)\n\nDeferred: post-launch polish","status":"open","priority":4,"issue_type":"task","created_at":"2025-12-23T20:06:45.764277-08:00","updated_at":"2025-12-23T20:06:45.764277-08:00","dependencies":[{"issue_id":"gt-8tmz.29","depends_on_id":"gt-8tmz","type":"parent-child","created_at":"2025-12-23T20:06:45.764686-08:00","created_by":"daemon"}]}
|
||||
{"id":"gt-8tmz.3","title":"Expansion operators: expand and map (macros)","description":"Implement macro-style expansion operators:\n- expand(target, template) - apply template to single step\n- map(molecule, template) - apply template to all matching steps\n\nTemplates use {target} substitution for step references.\nRule of Five is the canonical example.","status":"in_progress","priority":1,"issue_type":"task","created_at":"2025-12-23T18:04:31.472199-08:00","updated_at":"2025-12-25T11:33:56.821674-08:00","dependencies":[{"issue_id":"gt-8tmz.3","depends_on_id":"gt-8tmz","type":"parent-child","created_at":"2025-12-23T18:04:31.472662-08:00","created_by":"daemon"},{"issue_id":"gt-8tmz.3","depends_on_id":"gt-8tmz.1","type":"blocks","created_at":"2025-12-23T18:04:49.809887-08:00","created_by":"daemon"},{"issue_id":"gt-8tmz.3","depends_on_id":"gt-8tmz.13","type":"blocks","created_at":"2025-12-23T18:48:18.717567-08:00","created_by":"daemon"}]}
|
||||
{"id":"gt-8tmz.3","title":"Expansion operators: expand and map (macros)","description":"Implement macro-style expansion operators:\n- expand(target, template) - apply template to single step\n- map(molecule, template) - apply template to all matching steps\n\nTemplates use {target} substitution for step references.\nRule of Five is the canonical example.","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-23T18:04:31.472199-08:00","updated_at":"2025-12-25T11:45:01.290769-08:00","closed_at":"2025-12-25T11:45:01.290769-08:00","close_reason":"Expansion operators working - fixed dependency updates after expansion, fixed formula files schema","dependencies":[{"issue_id":"gt-8tmz.3","depends_on_id":"gt-8tmz","type":"parent-child","created_at":"2025-12-23T18:04:31.472662-08:00","created_by":"daemon"},{"issue_id":"gt-8tmz.3","depends_on_id":"gt-8tmz.1","type":"blocks","created_at":"2025-12-23T18:04:49.809887-08:00","created_by":"daemon"},{"issue_id":"gt-8tmz.3","depends_on_id":"gt-8tmz.13","type":"blocks","created_at":"2025-12-23T18:48:18.717567-08:00","created_by":"daemon"}]}
|
||||
{"id":"gt-8tmz.30","title":"Proto debugging and inspection tools","description":"Tools for understanding cooked protos:\n- bd cook --dry-run (already planned)\n- Step-through cooking: see each compose rule applied\n- Diff between proto versions\n- Provenance tracing: which formula/rule produced this step?\n- Visualization of step graph (ASCII or graphviz)\n\nDeferred: post-launch polish","status":"open","priority":4,"issue_type":"task","created_at":"2025-12-23T20:06:46.58776-08:00","updated_at":"2025-12-23T20:06:46.58776-08:00","dependencies":[{"issue_id":"gt-8tmz.30","depends_on_id":"gt-8tmz","type":"parent-child","created_at":"2025-12-23T20:06:46.58989-08:00","created_by":"daemon"}]}
|
||||
{"id":"gt-8tmz.31","title":"Formula validation specification","description":"Complete validation rules for formulas:\n- Required vs optional fields\n- Valid step ID patterns\n- Valid pointcut glob syntax\n- Variable reference validation\n- Compose rule ordering constraints\n- Type-specific validation (workflow vs expansion vs aspect)\n\nDeferred: post-launch polish","status":"open","priority":4,"issue_type":"task","created_at":"2025-12-23T20:06:47.618799-08:00","updated_at":"2025-12-23T20:06:47.618799-08:00","dependencies":[{"issue_id":"gt-8tmz.31","depends_on_id":"gt-8tmz","type":"parent-child","created_at":"2025-12-23T20:06:47.620975-08:00","created_by":"daemon"}]}
|
||||
{"id":"gt-8tmz.32","title":"Consolidate molecular-chemistry.md with rig-cook-run.md","description":"Merge rig-cook-run.md into molecular-chemistry.md as the canonical chemical algebra spec:\n- Rig/Cook/Run as the lifecycle backbone\n- Full generation graph: Formula → Compound Formula → Proto → Mol/Wisp\n- Bond table at artifact level (symmetric)\n- Rig operator at source level\n- Unified vocabulary\n- Archive or redirect rig-cook-run.md","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-23T20:06:48.82201-08:00","updated_at":"2025-12-23T20:09:55.176385-08:00","closed_at":"2025-12-23T20:09:55.176385-08:00","close_reason":"Consolidated rig-cook-run.md into molecular-chemistry.md. Updated all references.","dependencies":[{"issue_id":"gt-8tmz.32","depends_on_id":"gt-8tmz","type":"parent-child","created_at":"2025-12-23T20:06:48.823692-08:00","created_by":"daemon"}]}
|
||||
@@ -770,9 +770,9 @@
|
||||
{"id":"gt-ie33.1","title":"Polecat Arm (arm-toast)","description":"Single polecat inspection and action cycle.\n\nThis molecule is bonded dynamically by mol-witness-patrol's survey-workers step.\nEach polecat being monitored gets one arm that runs in parallel with other arms.\n\n## Variables\n\n| Variable | Required | Description |\n|----------|----------|-------------|\n| polecat_name | Yes | Name of the polecat to inspect |\n| rig | Yes | Rig containing the polecat |\n\n## Step: capture\nCapture recent tmux output for toast.\n\n```bash\ntmux capture-pane -t gt-gastown-toast -p | tail -50\n```\n\nRecord:\n- Last activity timestamp (when was last tool call?)\n- Visible errors or stack traces\n- Completion indicators (\"Done\", \"Finished\", etc.)\n\n## Step: assess\nCategorize polecat state based on captured output.\n\nStates:\n- **working**: Recent tool calls, active processing\n- **idle**: At prompt, no recent activity\n- **error**: Showing errors or stack traces\n- **requesting_shutdown**: Sent LIFECYCLE/Shutdown mail\n- **done**: Showing completion indicators\n\nCalculate: minutes since last activity.\nNeeds: capture\n\n## Step: load-history\nRead nudge history for toast from patrol state.\n\n```\nnudge_count = state.nudges[toast].count\nlast_nudge_time = state.nudges[toast].timestamp\n```\n\nThis data was loaded by the parent patrol's load-state step and passed\nto the arm via the bonding context.\nNeeds: assess\n\n## Step: decide\nApply the nudge matrix to determine action for toast.\n\n| State | Idle Time | Nudge Count | Action |\n|-------|-----------|-------------|--------|\n| working | any | any | none |\n| idle | \u003c10min | any | none |\n| idle | 10-15min | 0 | nudge-1 (gentle) |\n| idle | 15-20min | 1 | nudge-2 (direct) |\n| idle | 20+min | 2 | nudge-3 (final) |\n| idle | any | 3 | escalate |\n| error | any | any | assess-severity |\n| requesting_shutdown | any | any | pre-kill-verify |\n| done | any | any | pre-kill-verify |\n\nNudge text:\n1. \"How's progress? Need any help?\"\n2. \"Please wrap up soon. What's blocking you?\"\n3. \"Final check. Will escalate in 5 min if no response.\"\n\nRecord decision and rationale.\nNeeds: load-history\n\n## Step: execute\nTake the decided action for toast.\n\n**nudge-N**:\n```bash\ntmux send-keys -t gt-gastown-toast \"{{nudge_text}}\" Enter\n```\n\n**pre-kill-verify**:\n```bash\ncd polecats/toast\ngit status # Must be clean\ngit log origin/main..HEAD # Check for unpushed\nbd show \u003cassigned-issue\u003e # Verify closed/deferred\n```\nIf clean: kill session, remove worktree, delete branch\nIf dirty: record failure, retry next cycle\n\n**escalate**:\n```bash\ngt mail send mayor/ -s \"Escalation: toast stuck\" -m \"...\"\n```\n\n**none**: No action needed.\n\nRecord: action taken, result, updated nudge count.\nNeeds: decide\n\n## Output\n\nThe arm completes with:\n- action_taken: none | nudge-1 | nudge-2 | nudge-3 | killed | escalated\n- result: success | failed | pending\n- updated_state: New nudge count and timestamp for toast\n\nThis data feeds back to the parent patrol's aggregate step.\n---\nbonded_from: mol-polecat-arm\nbonded_to: gt-ie33\nbonded_ref: arm-toast\nbonded_at: 2025-12-23T10:00:00Z\n","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-24T00:10:09.989188-08:00","updated_at":"2025-12-24T00:10:10.192864-08:00","closed_at":"2025-12-24T00:10:10.192864-08:00"}
|
||||
{"id":"gt-ieem","title":"Test Patrol Parent","description":"Test parent for Christmas Ornament pattern","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-24T21:04:09.817241-08:00","updated_at":"2025-12-25T01:33:00.484839-08:00","closed_at":"2025-12-25T01:33:00.484839-08:00","close_reason":"Test pollution cleanup"}
|
||||
{"id":"gt-ieem.1","title":"Test Polecat Arm","description":"Test child for bonding pattern","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-24T21:04:09.907713-08:00","updated_at":"2025-12-25T01:33:00.467952-08:00","closed_at":"2025-12-25T01:33:00.467952-08:00","close_reason":"Test pollution cleanup","dependencies":[{"issue_id":"gt-ieem.1","depends_on_id":"gt-ieem","type":"parent-child","created_at":"2025-12-24T21:04:09.908178-08:00","created_by":"daemon"}]}
|
||||
{"id":"gt-iep9","title":"mol-deacon-patrol","description":"[RESURRECTED] This issue was deleted but recreated as a tombstone to preserve hierarchical structure.\n\nOriginal description:\nDeacon patrol molecule template. Label: template","status":"closed","priority":4,"issue_type":"epic","created_at":"2025-12-21T17:50:22.545763-08:00","updated_at":"2025-12-22T13:08:47.571042-08:00","closed_at":"2025-12-22T13:08:47.571042-08:00","labels":["template"]}
|
||||
{"id":"gt-iep9.1","title":"inbox-check","description":"Handle callbacks from agents. Check gt mail inbox, process lifecycle requests.","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-21T17:50:57.090986-08:00","updated_at":"2025-12-21T17:50:57.090986-08:00","dependencies":[{"issue_id":"gt-iep9.1","depends_on_id":"gt-iep9","type":"parent-child","created_at":"2025-12-21T17:50:57.092836-08:00","created_by":"daemon"}]}
|
||||
{"id":"gt-iep9.7","title":"loop-or-exit","description":"Decision: burn and loop if context low, exit for respawn if context high.","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-21T17:51:04.755716-08:00","updated_at":"2025-12-21T17:51:04.755716-08:00","dependencies":[{"issue_id":"gt-iep9.7","depends_on_id":"gt-iep9","type":"parent-child","created_at":"2025-12-21T17:51:04.75713-08:00","created_by":"daemon"}]}
|
||||
{"id":"gt-iep9","title":"mol-deacon-patrol","description":"[RESURRECTED] This issue was deleted but recreated as a tombstone to preserve hierarchical structure.\n\nOriginal description:\nDeacon patrol molecule template. Label: template","status":"tombstone","priority":4,"issue_type":"epic","created_at":"2025-12-21T17:50:22.545763-08:00","updated_at":"2025-12-25T11:44:16.881599-08:00","labels":["template"],"deleted_at":"2025-12-25T11:44:16.881599-08:00","deleted_by":"batch delete","delete_reason":"batch delete","original_type":"epic"}
|
||||
{"id":"gt-iep9.1","title":"inbox-check","description":"Handle callbacks from agents. Check gt mail inbox, process lifecycle requests.","status":"tombstone","priority":2,"issue_type":"task","created_at":"2025-12-21T17:50:57.090986-08:00","updated_at":"2025-12-25T11:44:16.881599-08:00","deleted_at":"2025-12-25T11:44:16.881599-08:00","deleted_by":"batch delete","delete_reason":"batch delete","original_type":"task"}
|
||||
{"id":"gt-iep9.7","title":"loop-or-exit","description":"Decision: burn and loop if context low, exit for respawn if context high.","status":"tombstone","priority":2,"issue_type":"task","created_at":"2025-12-21T17:51:04.755716-08:00","updated_at":"2025-12-25T11:44:16.881599-08:00","deleted_at":"2025-12-25T11:44:16.881599-08:00","deleted_by":"batch delete","delete_reason":"batch delete","original_type":"task"}
|
||||
{"id":"gt-ih0s","title":"Fix blocking bugs (gt-dsfi, gt-n7z7, gm-c6b)","description":"Fix bugs blocking Witness functionality:\n\n1. gt-dsfi: handoff deadlock\n - Polecats hang when trying to exit\n - Blocks shutdown request handler\n\n2. gt-n7z7: refinery foreground race condition \n - Sometimes detects parent as already running\n - Blocks reliable Refinery startup\n\n3. gm-c6b: mail coordination\n - Cross-rig mail should use town-level database\n - Affects Witness \u003c-\u003e Mayor communication\n\nThese should be fixed early as they'll block integration testing.","notes":"Fixed gt-dsfi and gt-n7z7. Issue gm-c6b not found in database.","status":"closed","priority":1,"issue_type":"task","created_at":"2025-12-20T03:14:25.803822-08:00","updated_at":"2025-12-20T07:47:50.444171-08:00","closed_at":"2025-12-20T07:47:50.444171-08:00","dependencies":[{"issue_id":"gt-ih0s","depends_on_id":"gt-53w6","type":"parent-child","created_at":"2025-12-20T03:14:37.430142-08:00","created_by":"daemon"}]}
|
||||
{"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":"tombstone","priority":0,"issue_type":"task","created_at":"2025-12-15T19:21:19.913928-08:00","updated_at":"2025-12-25T01:30:41.67682-08:00","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"}],"deleted_at":"2025-12-25T01:30:41.67682-08:00","deleted_by":"batch delete","delete_reason":"batch delete","original_type":"task"}
|
||||
{"id":"gt-ijmgg","title":"Digest: mol-deacon-patrol","description":"Patrol 2: All agents healthy, routine check","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-25T00:45:14.673074-08:00","updated_at":"2025-12-25T00:45:14.673074-08:00","closed_at":"2025-12-25T00:45:14.673033-08:00","close_reason":"Squashed from 8 wisps"}
|
||||
@@ -1047,7 +1047,7 @@
|
||||
{"id":"gt-qbdb","title":"Work on ga-lzh: Add gt witness attach command. Allow atta...","description":"Work on ga-lzh: Add gt witness attach command. Allow attaching to witness session for a rig, similar to gt mayor attach. When done, submit MR (not PR) to integration branch for Refinery.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-19T22:58:44.945425-08:00","updated_at":"2025-12-19T23:19:24.42686-08:00","closed_at":"2025-12-19T23:19:24.42686-08:00"}
|
||||
{"id":"gt-qcr6","title":"Polecat template: fix 'git clone' to 'git worktree'","description":"Template says 'You're in a project git clone' but polecats use worktrees, not clones. Fix terminology.","status":"closed","priority":2,"issue_type":"bug","created_at":"2025-12-23T16:56:44.091888-08:00","updated_at":"2025-12-23T17:09:02.10909-08:00","closed_at":"2025-12-23T17:09:02.10909-08:00","close_reason":"Completed in commit 1931ec7","dependencies":[{"issue_id":"gt-qcr6","depends_on_id":"gt-t9u7","type":"parent-child","created_at":"2025-12-23T16:57:16.207186-08:00","created_by":"daemon"}]}
|
||||
{"id":"gt-qe9w","title":"Simplify and reorganize molecular chemistry docs","description":"The Gas Town molecular chemistry docs (molecules.md, molecular-chemistry.md, molecule-algebra.md) are too dramatic and verbose. They need a simplification pass to be more reference-manual style.\n\n**Current problems:**\n1. Too much metaphor and philosophy, not enough practical reference\n2. Start with the chemistry abstraction instead of what users care about (patrols, workflows)\n3. Layer cake is presented top-down (formulas → protos → molecules) instead of bottom-up (issues → dependencies → execution)\n\n**Proposed structure (inverted pyramid):**\n\n1. **Start with execution semantics:**\n - Work = issues with dependencies\n - Dependencies control execution (blocks = sequential, no dep = parallel)\n - Agents traverse dependency graphs until blocked\n - Multi-day workflows via compound bonding\n\n2. **Move to molecules:**\n - Molecules are just epics with workflow intent\n - Bonding = creating dependencies between work graphs\n - No protos required for ad-hoc workflows\n\n3. **Then templates (protos/wisps):**\n - Phase metaphor for storage locations\n - pour/wisp/squash/burn operations\n - When to use each phase\n\n4. **Finally formulas (for advanced users):**\n - YAML compile-time composition\n - extends, compose, aspects\n - Only needed for complex reusable patterns\n\n**Style guidelines:**\n- Reference manual with quick examples\n- Written like agent priming (context they need to execute)\n- Less dramatic, more straightforward\n- TL;DR at top of each doc\n\n**See also:**\n- beads/docs/MOLECULES.md has a simplified version to use as template\n- The execution model section explains multi-day traversal clearly","status":"open","priority":2,"issue_type":"task","created_at":"2025-12-24T19:51:42.43826-08:00","updated_at":"2025-12-24T19:51:42.43826-08:00"}
|
||||
{"id":"gt-qflq","title":"mol-witness-patrol","description":"Per-rig worker monitor patrol loop using the Christmas Ornament pattern.\n\nThe Witness is the Pit Boss for your rig. You watch polecats, nudge them toward\ncompletion, verify clean git state before kills, and escalate stuck workers.\n\n**You do NOT do implementation work.** Your job is oversight, not coding.\n\n## The Christmas Ornament Shape\n\nThis molecule uses dynamic bonding to create inspection arms per-polecat:\n\n```\n ★ mol-witness-patrol (trunk)\n /|\\\n ┌─────┘ │ └─────┐\n PREFLIGHT DISCOVERY CLEANUP\n │ │ │\n ┌───┴───┐ ┌─┴─┐ ┌───┴───┐\n │inbox │ │sur│ │aggreg │\n │refnry │ │vey│ │save │\n │load │ └─┬─┘ │summary│\n └───────┘ │ │contxt │\n │ │loop │\n ┌─────────┼─────────┐ └───────┘\n │ │ │\n ● ● ● mol-polecat-arm (dynamic)\n ace nux toast\n │ │ │\n ┌──┴──┐ ┌──┴──┐ ┌──┴──┐\n │cap │ │cap │ │cap │\n │ass │ │ass │ │ass │\n │dec │ │dec │ │dec │\n │exec │ │exec │ │exec │\n └──┬──┘ └──┬──┘ └──┬──┘\n │ │ │\n └─────────┴─────────┘\n │\n ⬣ base (cleanup)\n```\n\n## Phases\n\n### PREFLIGHT (fixed steps)\n1. inbox-check - Process lifecycle requests, help messages\n2. check-refinery - Ensure MQ is alive and processing\n3. load-state - Read persistent state (nudge counts, etc.)\n\n### DISCOVERY (spawns dynamic arms)\n4. survey-workers - List polecats, bond mol-polecat-arm per polecat\n5. run-plugins - Bond mol-plugin-runner for each witness plugin\n\n### CLEANUP (gate + fixed steps)\n6. aggregate - GATE: WaitsFor all arms + plugins to complete\n7. save-state - Persist nudge counts, action log\n8. generate-summary - Create digest content\n9. context-check - Check if context is high\n10. burn-or-loop - Squash/burn wisp, then loop or exit\n\n## Dynamic Arms\n\nEach polecat gets mol-polecat-arm bonded as a wisp child:\n- capture - Capture tmux output\n- assess - Categorize state (working/idle/error/done)\n- load-history - Get nudge counts for this polecat\n- decide - Apply nudge matrix\n- execute - Take action (nudge/kill/escalate/none)\n\nArms run in PARALLEL. The aggregate step waits for all to complete.\n\n## Activity Feed\n\nThis design enables real-time visibility:\n\n```\n[14:32:08] + patrol-x7k.arm-ace bonded (5 steps)\n[14:32:09] → patrol-x7k.arm-ace.capture in_progress\n[14:32:10] ✓ patrol-x7k.arm-ace.capture completed\n[14:32:14] ✓ patrol-x7k.arm-ace.decide completed (action: nudge-1)\n[14:32:17] ✓ patrol-x7k.arm-ace COMPLETE\n```\n\n## Storage\n\n- Wisp storage: .beads-wisp/ (ephemeral, gitignored)\n- Persistent state: witness handoff bead (nudge counts, etc.)\n- Digests: Squashed summaries in permanent beads\n\n## Dependencies\n\n- bd-xo1o: Dynamic Molecule Bonding epic (in beads rig)\n - bd mol bond with variable substitution\n - WaitsFor directive for fanout gates\n - Activity feed query\n\nLabels: [template, christmas-ornament]","status":"closed","priority":1,"issue_type":"epic","created_at":"2025-12-23T01:39:31.895817-08:00","updated_at":"2025-12-24T14:05:05.645834-08:00","closed_at":"2025-12-24T14:05:05.645834-08:00","close_reason":"Superseded by mol-witness-patrol proto","labels":["template"]}
|
||||
{"id":"gt-qflq","title":"mol-witness-patrol","description":"Per-rig worker monitor patrol loop using the Christmas Ornament pattern.\n\nThe Witness is the Pit Boss for your rig. You watch polecats, nudge them toward\ncompletion, verify clean git state before kills, and escalate stuck workers.\n\n**You do NOT do implementation work.** Your job is oversight, not coding.\n\n## The Christmas Ornament Shape\n\nThis molecule uses dynamic bonding to create inspection arms per-polecat:\n\n```\n ★ mol-witness-patrol (trunk)\n /|\\\n ┌─────┘ │ └─────┐\n PREFLIGHT DISCOVERY CLEANUP\n │ │ │\n ┌───┴───┐ ┌─┴─┐ ┌───┴───┐\n │inbox │ │sur│ │aggreg │\n │refnry │ │vey│ │save │\n │load │ └─┬─┘ │summary│\n └───────┘ │ │contxt │\n │ │loop │\n ┌─────────┼─────────┐ └───────┘\n │ │ │\n ● ● ● mol-polecat-arm (dynamic)\n ace nux toast\n │ │ │\n ┌──┴──┐ ┌──┴──┐ ┌──┴──┐\n │cap │ │cap │ │cap │\n │ass │ │ass │ │ass │\n │dec │ │dec │ │dec │\n │exec │ │exec │ │exec │\n └──┬──┘ └──┬──┘ └──┬──┘\n │ │ │\n └─────────┴─────────┘\n │\n ⬣ base (cleanup)\n```\n\n## Phases\n\n### PREFLIGHT (fixed steps)\n1. inbox-check - Process lifecycle requests, help messages\n2. check-refinery - Ensure MQ is alive and processing\n3. load-state - Read persistent state (nudge counts, etc.)\n\n### DISCOVERY (spawns dynamic arms)\n4. survey-workers - List polecats, bond mol-polecat-arm per polecat\n5. run-plugins - Bond mol-plugin-runner for each witness plugin\n\n### CLEANUP (gate + fixed steps)\n6. aggregate - GATE: WaitsFor all arms + plugins to complete\n7. save-state - Persist nudge counts, action log\n8. generate-summary - Create digest content\n9. context-check - Check if context is high\n10. burn-or-loop - Squash/burn wisp, then loop or exit\n\n## Dynamic Arms\n\nEach polecat gets mol-polecat-arm bonded as a wisp child:\n- capture - Capture tmux output\n- assess - Categorize state (working/idle/error/done)\n- load-history - Get nudge counts for this polecat\n- decide - Apply nudge matrix\n- execute - Take action (nudge/kill/escalate/none)\n\nArms run in PARALLEL. The aggregate step waits for all to complete.\n\n## Activity Feed\n\nThis design enables real-time visibility:\n\n```\n[14:32:08] + patrol-x7k.arm-ace bonded (5 steps)\n[14:32:09] → patrol-x7k.arm-ace.capture in_progress\n[14:32:10] ✓ patrol-x7k.arm-ace.capture completed\n[14:32:14] ✓ patrol-x7k.arm-ace.decide completed (action: nudge-1)\n[14:32:17] ✓ patrol-x7k.arm-ace COMPLETE\n```\n\n## Storage\n\n- Wisp storage: .beads-wisp/ (ephemeral, gitignored)\n- Persistent state: witness handoff bead (nudge counts, etc.)\n- Digests: Squashed summaries in permanent beads\n\n## Dependencies\n\n- bd-xo1o: Dynamic Molecule Bonding epic (in beads rig)\n - bd mol bond with variable substitution\n - WaitsFor directive for fanout gates\n - Activity feed query\n\nLabels: [template, christmas-ornament]","status":"tombstone","priority":1,"issue_type":"epic","created_at":"2025-12-23T01:39:31.895817-08:00","updated_at":"2025-12-25T11:44:16.881599-08:00","close_reason":"Superseded by mol-witness-patrol proto","labels":["template"],"deleted_at":"2025-12-25T11:44:16.881599-08:00","deleted_by":"batch delete","delete_reason":"batch delete","original_type":"epic"}
|
||||
{"id":"gt-qgbe","title":"Digest: mol-deacon-patrol","description":"Patrol 3: OK","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-24T20:55:49.186887-08:00","updated_at":"2025-12-24T20:55:49.186887-08:00","closed_at":"2025-12-24T20:55:49.186851-08:00","close_reason":"Squashed from 8 wisps"}
|
||||
{"id":"gt-qh2","title":"Session cycling UX: smooth transitions via TUI wrapper","description":"## Problem\n\nCurrent CLI agent session cycling is painful:\n- Shell → CC starts → priming → context loads → ready → work → exit/crash → repeat\n- Each cycle is 30-60 seconds of cold boot\n- No continuity between shell and agent's inner state\n- Raw \"session not running, starting...\" loop is the baseline\n\n## GGT Advantages (already have)\n\n- Beads: Work state survives session death completely\n- Mail: Handoff notes from past-self to future-self \n- Prime commands: Structured context reload\n\n## Gap: Transition Mechanics\n\nIdeas to explore when actively using CLI:\n\n1. **In-band cycling** - `/restart` or `/cycle` command, agent handles own restart without dropping to shell\n\n2. **Hot standby** - TUI maintains pre-warmed session in background, switch to already-primed agent\n\n3. **Persistent wrapper** - Bubbletea TUI stays running across session cycles, CC sessions come/go inside it\n\n4. **Session pooling** - Keep 2-3 primed sessions ready, never wait for cold start\n\n## Deferred\n\nDeliberately P4 until we're actively using the simpler CLI and feel the pain firsthand.","status":"open","priority":4,"issue_type":"task","created_at":"2025-12-15T20:38:12.660716-08:00","updated_at":"2025-12-15T23:17:34.27061-08:00"}
|
||||
{"id":"gt-qivm","title":"gt crew at: auto-prime when exec'ing Claude in-session","description":"When running 'gt crew at \u003cname\u003e' from inside the target session, we exec Claude directly. But this means we can't send 'gt prime' afterward since we ARE the process.\n\nPossible solutions:\n1. Claude startup hook that runs gt prime\n2. Pass prompt as argument to claude CLI\n3. Wrapper script approach\n\nRelated: crew resume prompt also can't be sent in this path.","status":"closed","priority":2,"issue_type":"task","created_at":"2025-12-19T15:13:38.035775-08:00","updated_at":"2025-12-21T11:50:55.924767-08:00","closed_at":"2025-12-21T11:50:55.924767-08:00","close_reason":"Implemented: execClaude now passes 'gt prime' as initial prompt to Claude CLI"}
|
||||
|
||||
Reference in New Issue
Block a user