Replace .runtime/swarms.json with beads-backed swarm tracking:
- gt swarm create: calls bd create --type=epic --mol-type=swarm
- gt swarm status: calls bd swarm status
- gt swarm list: calls bd list --mol-type=swarm --type=epic
- gt swarm start: uses bd swarm status to find ready tasks
- gt swarm land: checks completion via bd, closes epic
- gt swarm cancel: closes epic with cancelled reason
Removed:
- SwarmStore type and LoadSwarmStore/Save functions
- Old spawnSwarmWorkers (replaced with spawnSwarmWorkersFromBeads)
- Unused helper functions (stateStyle, taskStateIcon, matchesStatus)
This implements "discovery over tracking" principle from swarm-architecture.md:
swarm state is now derived from beads epic/issue statuses rather than
maintaining separate state in .runtime/swarms.json.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Show unread mail count and first message subject for each agent
- Display format: "mail: 📬 N unread → Subject..."
- Only shows mail line when agent has unread messages
- Fix agent bead ID generation for global agents (mayor/, deacon/)
Example output:
🏭 Refinery
gt-refinery-gastown running
hook: refinery Handoff
mail: 📬 8 unread → MERGE_READY morsov
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Show full agent bead ID for each agent (e.g., gt-crew-gastown-joe)
- Display hook/pinned work with bead ID and title
- Use role icons and section separators for clarity
- Fall back to hooks array when agent bead lacks hook_bead field
Example output:
🎩 Mayor
gt-mayor running
hook: (none)
─── gastown/ ───────────────────────
🏭 Refinery
gt-refinery-gastown running
hook: refinery Handoff
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Use tree characters (├── └── │) for hierarchical display
- Group agents by role type (Witness, Refinery, Crew, Polecats)
- Add role icons (🎩 Mayor, 🔔 Deacon, 👁 Witness, 🏭 Refinery, 👷 Crew, 😺 Polecats)
- Show pinned work inline with truncation
- Fix unused import in polecat/manager.go
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Inverse of 'gt rig shutdown'. Starts rig patrol agents:
- Checks tmux sessions to avoid duplicates
- Starts witness if not running
- Starts refinery if not running
- Reports what was started vs skipped
Also adds ProcessExists util function needed by witness/refinery managers.
- polecat.go: Remove unreachable first loop in splitLines (was using filepath.SplitList incorrectly)
- townlog/logger.go: Remove unused Event.JSON() method and json import
- lock/lock.go: Remove unused ErrStaleLock error variable
- refinery/manager.go: Remove unused getTestCommand() method
Note: witness.StatePaused is actually used by cmd/witness.go, not dead code.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Polecats were going off-task during swarms. Added explicit guidance:
- ONE job: work your pinned bead until done
- DO NOT list for common distractions (mail checking, monitoring others, etc.)
- Reminder to file discovered work as beads, not fix it
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added constants.SupportedShells for consistent shell list
- Updated 7 usages across start.go, crew_lifecycle.go, crew_helpers.go, tmux.go
- All tests pass
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Enhanced the package-level documentation to explain why all write
operations in the keepalive package silently ignore errors.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add PrintWarning helper in internal/style/style.go
- Update 35 warning message outputs across 16 files to use consistent format
- All warnings now display as "⚠ Warning: <message>" in yellow/bold
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Instead of Go code checking git state to decide if polecat removal is safe,
the polecat now self-reports its cleanup_status via its agent bead.
Changes:
- Add CleanupStatus field to AgentFields struct
- Update FormatAgentDescription and ParseAgentFields for cleanup_status
- Add UpdateAgentCleanupStatus function to beads package
- Update gt done to compute and report git cleanup status
- Update RemoveWithOptions to read cleanup_status from agent bead first,
falling back to git check for backward compatibility
Valid cleanup_status values:
- clean: no uncommitted work
- has_uncommitted: has uncommitted changes
- has_stash: has stashed changes
- has_unpushed: has unpushed commits
- unknown: git check failed
This follows ZFC (Zero Figuring in Code) principles - the polecat is the
authority on its own state, not Go code inferring it from external signals.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Extended the unified cycle system to include rig infrastructure sessions:
- Witness ↔ Refinery (per rig) now cycle with C-b n/p
Also moved SetCycleBindings into ConfigureGasTownSession so ALL Gas Town
sessions automatically get the unified cycle bindings. Removed redundant
individual calls from crew, mayor, and deacon startup code.
Cycle groups are now:
- Town: Mayor ↔ Deacon
- Crew (per rig): All crew members in same rig
- Infra (per rig): Witness ↔ Refinery
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fail fast with clear error when run outside ~/gt instead of
hanging while bd tries to start.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Reduced runStart from 126 lines to 48 lines by extracting:
- startCoreAgents: Mayor and Deacon session startup (28 lines)
- startRigAgents: Witness/Refinery startup for --all flag (37 lines)
- startConfiguredCrew: Auto-start configured crew members (29 lines)
No behavior change - all existing tests pass.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Return *Model from NewModel() so SetEventChannel works
- Use sync.Once for safe channel close on quit
- Use pointer receivers consistently throughout
- Capture channels in closure to prevent race
- Fix indent panic in renderAgent when indent < 2
- Remove unused filterActive and err fields
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Notifications now come immediately after push, before cleanup
- Added STOP HERE warning after push
- Made verification gate more emphatic
- Cleanup happens only after notifications confirmed
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updated mol-refinery-patrol.formula.toml:
- Added MR bead ID tracking to inbox-check MERGE_READY parsing
- Restructured merge-push into 3 clear steps with REQUIRED callouts
- Added Step 2: MERGED notification (DO NOT SKIP)
- Added Step 3: Close MR bead (DO NOT SKIP)
- Added verification checklist before proceeding
- Added generate-summary verification to catch missed notifications
This ensures refinery agents complete the full lifecycle and trigger
witness cleanup (gt polecat nuke) after merge.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add bubbletea and bubbles dependencies
- Create internal/tui/feed package with:
- model.go: Main bubbletea model with agent tree and event stream
- view.go: Rendering logic with lipgloss styling
- keys.go: Vim-style key bindings (j/k, tab, /, q)
- styles.go: Color palette and component styles
- events.go: Event source from bd activity
- Update gt feed to use TUI by default (--plain for text mode)
- TUI features: agent tree by role, event stream, keyboard nav
Closes gt-be0as, gt-lexye, gt-1uhmj
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Create AgentIdentity type to parse and construct session names, replacing
duplicated logic in sling.go and handoff.go.
- Add internal/session/identity.go with AgentIdentity type
- ParseSessionName handles: mayor, deacon, witness, refinery, crew, polecat
- SessionName() reconstructs valid tmux session name
- Address() returns mail-style address (e.g., "gastown/crew/max")
- GTRole() returns GT_ROLE env var format
- Update sling.go:sessionToAgentID to use ParseSessionName
- Update handoff.go:sessionToGTRole to use ParseSessionName
- Add comprehensive unit tests with round-trip verification
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The sessionToAgentID function was missing handling for polecat sessions,
causing gt sling to fail to update the agent bead's hook_bead field.
Before: gt-gastown-nux -> gt-gastown-nux (unchanged, no match)
After: gt-gastown-nux -> gastown/polecats/nux (correct format)
This enables updateAgentHookBead to properly convert to the agent bead ID
(gt-polecat-gastown-nux) and update the hook_bead field, which is
required for agents to know they have work on their hook.
Found via E2E test (gt-j0gx2) - nux wasn't picking up slung work because
hook_bead was null despite the task being pinned.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Claude needs ~2 seconds to initialize before it can process nudges.
Without this delay, the initial "Work slung" message would arrive
before Claude was ready, causing the SessionStart hook not to fire.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
