Adds the missing github-gate-check step that runs `bd gate discover` and
`bd gate check --type=gh` to evaluate GitHub CI gates. Updates
dispatch-gated-molecules to depend on both gate-evaluation and
github-gate-check.
Fixes: gt-sfxpr
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Enterprise teams can now customize integration branch names to match
their conventions (e.g., username/TICKET-123/feature-name).
- Add integration_branch_template to MergeQueueConfig
- Add --branch CLI override for gt mq integration create
- Support {epic}, {prefix}, {user} template variables
- Validate branch names for git-safe characters
- Store actual branch name in epic metadata at create time
- Read stored branch name in land/status (fallback for old epics)
Also fixes unrelated build error in polecat/manager.go (polecatPath
variable was undefined).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add --verbose/-v flag to gt costs command that outputs debug information
when silent failures occur during cost tracking operations:
- wisp list failures in querySessionCostWisps and deleteSessionCostWisps
- bd show failures when querying wisp details
- JSON unmarshal failures when parsing wisp/event data
- payload unmarshal failures when parsing session payloads
This makes debugging cost tracking issues much easier as these error
paths previously continued silently without any indication of failure.
Closes: bd-qv8f9
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Sort map keys before iteration in createCostDigestBead for deterministic
output ordering in By Role and By Rig sections (bd-66z6a)
- Batch wisp IDs into single bd show call to fix N+1 query pattern in
querySessionCostWisps (bd-3hqvs)
- Batch wisp deletion into single subprocess call in deleteSessionCostWisps
(bd-i8zab)
Part of: bd-1wmwp
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Agent sessions would fail on startup because send-keys arrived before the
shell was ready, causing 'bad pattern' and 'command not found' errors.
Fix: Create sessions with the command directly using tmux new-session's
command argument. This runs the agent as the pane's initial process,
avoiding shell readiness timing issues entirely.
Updated all agent managers: mayor, deacon, witness, refinery, polecat, crew.
Also fixes pre-existing build error in polecat/manager.go (polecatPath →
clonePath/newClonePath).
Closes#280
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Bare clones don't have remote.origin.fetch set by default, which breaks
worktrees that need to fetch and see origin/* refs. This caused refinery
to fail because origin/main never appeared after fetch.
- Add configureRefspec() to set standard refspec on bare repos
- Call from CloneBare() and CloneBareWithReference()
- Add BareRepoRefspecCheck to doctor for existing rigs
Closes#286
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Changes polecat worktree structure from:
polecats/<name>/
to:
polecats/<name>/<rigname>/
This gives Claude Code agents a recognizable directory name (e.g., tidepool/)
in their cwd instead of just the polecat name, preventing confusion about
which repo they are working in.
Key changes:
- Add clonePath() method to manager.go and session_manager.go for the actual
git worktree path, keeping polecatDir() for existence checks
- Update Add(), RepairWorktree(), Remove() to use new structure
- Update daemon lifecycle and restart code for new paths
- Update witness handlers to detect both structures
- Update doctor checks (rig_check, branch_check, config_check,
claude_settings_check) for backward compatibility
- All code includes fallback to old structure for existing polecats
Fixes#283
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds EnableMouseMode() and calls it from ConfigureGasTownSession so all
new GT sessions get mouse support. Users can now click panes, scroll with
mouse wheel, and resize by dragging. Hold Shift for terminal text selection.
Closes#33
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds support for alternative AI runtime backends (Codex, OpenCode) alongside
the default Claude backend through a runtime abstraction layer.
- internal/runtime/runtime.go - Runtime-agnostic helper functions
- Extended RuntimeConfig with provider-specific settings
- internal/opencode/ for OpenCode plugin support
- Updated session managers to use runtime abstraction
- Removed unused ensureXxxSession functions
- Fixed daemon.go indentation, updated terminology to runtime
Backward compatible: Claude remains default runtime.
Co-Authored-By: Ben Kraus <ben@cinematicsoftware.com>
Co-Authored-By: Cameron Palmer <cameronmpalmer@users.noreply.github.com>
* feat(costs): redesign session cost tracking with wisps and daily digests
Implement the wisp-based cost tracking architecture per gt-cm900:
- gt costs record now creates ephemeral wisps (not exported to JSONL)
to avoid log-in-database pollution with O(sessions/day) events
- gt costs digest aggregates yesterday's session wisps into a single
permanent "Cost Report YYYY-MM-DD" bead for audit purposes
- gt costs query updated: --today queries wisps, --week queries
digest beads + today's wisps
- gt costs migrate closes legacy open session.ended beads
- Deacon patrol formula updated with costs-digest step
The new architecture:
Session ends -> Wisp (fast, N/day) -> Patrol digest -> Bead (1/day)
This preserves audit trail while keeping issues.jsonl clean.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore: sync canonical formula with embedded copy
Update .beads/formulas/ with the costs-digest step added to
mol-deacon-patrol.formula.toml. The go:generate copies from
.beads/formulas/ to internal/formula/formulas/.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
- Remove unused ensureRefinerySession function from start.go
- Remove unused ensureSession and ensureWitness functions from up.go
- Remove unused ensureWitnessSession function from witness.go
- Remove orphaned imports (runtime, session, constants, config, rig, filepath, time)
- Fix indentation error in daemon.go triggerPendingSpawns comment
These functions were added as part of the Codex/OpenCode runtime support
but were never wired up. The existing managers (refinery.Manager.Start,
witness.Manager.Start) already handle session creation.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Polecats were creating GitHub PRs instead of using gt done to submit
to the Refinery. Added clear conditional language:
- If repo is steveyegge/beads or steveyegge/gastown: NEVER create PRs
- Polecats use gt done → Refinery merges
- Crew workers push directly to main
- PRs are for external contributors only
This fixes a prompting gap that led to PR #292 being created incorrectly.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When upgrading gt on an existing installation without .installed.json,
formulas that exist but don't match embedded were incorrectly marked as
"modified" (implying user customization). Now they're marked "untracked"
and are safe to update since there's no record of user modification.
This improves the upgrade experience:
- "modified" = tracked file user changed (skip update)
- "untracked" = file exists but not tracked (safe to update)
Adds 3 new tests for untracked scenarios.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds infrastructure to automatically update embedded formulas when
the binary is upgraded, while preserving user customizations.
Changes:
- Add CheckFormulaHealth() to detect outdated/modified/missing formulas
- Add UpdateFormulas() to safely update formulas via gt doctor --fix
- Track installed formula checksums in .beads/formulas/.installed.json
- Add FormulaCheck to gt doctor with auto-fix capability
- Compute checksums at runtime from embedded files (no build-time manifest)
Update scenarios:
- Outdated (embedded changed, user unchanged): Update automatically
- Modified (user customized): Skip with warning
- Missing (user deleted): Reinstall with message
- New (never installed): Install
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Two improvements:
1. gt crew start now infers rig from cwd when first arg is not a valid
rig name (gt-czltv). Previously, running `gt crew start bob` from
within a rig directory would fail because "bob" was treated as the
rig name. Now it checks if the arg is a valid rig first.
2. Refactored copyOverlay to shared rig.CopyOverlay utility:
- Eliminates code duplication between crew and polecat managers
- Preserves source file permissions instead of hardcoding 0644
- Follows PR #278 improvements
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a visible "CRITICAL" warning and pre-submission checklist to the
polecat template. Explicitly notes that polecats should NOT manually
close the root issue - the Refinery handles that after merge.
This addresses the intent of PR #287 while avoiding the conflicting
`bd close` instruction that would break the Refinery workflow.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add new step to mol-deacon-patrol.formula.toml that discovers molecules
blocked on gates that have now closed, and dispatches them to the
appropriate rig's polecat pool.
This completes the async resume cycle without explicit waiter tracking.
The molecule state IS the waiter - patrol discovers reality each cycle.
- Uses bd mol ready --gated to find gate-ready molecules
- Dispatches via gt sling <mol-id> <rig>/polecats
- Runs after gate-evaluation, before health-scan
- Bumps formula version to 6
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When rig/.beads doesn't exist, fall back to mayor/rig/.beads (tracked
beads architecture) with a warning suggesting 'bd doctor' to fix.
This restores behavior that was inadvertently removed in #290, which
simplified SetupRedirect but removed the fallback path.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace the hand-rolled contains() function with the standard library
strings.Contains(). Also removes the redundant len(data) > 0 check
since strings.Contains handles empty strings correctly.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The t.Skipf call had a raw newline inside a double-quoted string,
which is invalid Go syntax. Use \n escape sequence instead.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The SessionHookCheck was incorrectly flagging 'gt prime --hook' as invalid,
only accepting 'session-start.sh' wrapper. The --hook flag properly handles
session_id passthrough via stdin JSON, making it a valid alternative.
Changes:
- Update usesSessionStartScript to accept --hook flag
- Add containsFlag helper to prevent false positives (e.g., --hookup)
- Update error messages and fix hints to suggest both options
- Add comprehensive tests including edge cases
Tests cover:
- Bare gt prime (fails)
- gt prime --hook (passes)
- gt prime --hookup (fails - not a valid flag)
- gt prime --verbose --hook (passes - flag order doesn't matter)
- session-start.sh (passes)
- Mixed valid/invalid hooks in same file
- Town-level and rig-level settings
- Add custom types config after bd init in daemon tests
- Replace fixed sleeps with poll-based waiting in tmux tests
- Skip beads integration test for JSONL-only repos
Fixes flaky test failures in parallel execution.
Adds RigBeadsCheck to gt doctor to verify rig identity beads exist.
These beads track rig metadata (git URL, prefix, state) and are created
by gt rig add. The check scans routes.jsonl and verifies each rig
has an identity bead, with --fix to create missing ones.
Recovered from furiosa's uncommitted work after worker interruption.
Co-Authored-By: furiosa <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add overlay directory support to automatically copy gitignored files
(like .env, config files) from <rig>/.runtime/overlay/ to polecat
and crew worktree roots when they are spawned.
This allows services started by polecats/crew to have their required
configuration files at the root without committing them to git.
Changes:
- Add copyOverlay() function to polecat and crew managers
- Call copyOverlay() after setupSharedBeads() in AddWithOptions/RepairWorktreeWithOptions
- Non-fatal: overlay copy failures only log warnings, don't block spawn
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Claude Code can report its pane command as "node", "claude", or a version
number like "2.0.76". Previously only "node" was detected, causing healthy
sessions to be incorrectly identified as zombies and killed during daemon
heartbeat recovery.
This fix detects all three patterns to prevent witness sessions from being
killed every 3 minutes.
Based on michaellady's work in PR #174.
Co-Authored-By: michaellady <michaellady@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The orphan-processes check previously killed any Claude process without
a tmux ancestor, which incorrectly targeted user's personal Claude
sessions running in regular terminals.
Now the check is informational only:
- Changed from FixableCheck to BaseCheck (no auto-fix)
- Returns StatusOK with details listing processes outside tmux
- Message advises user to verify processes are expected
- Removed Fix method and related helpers
The orphan-sessions check remains fixable since it only targets gt-*
sessions that don't match valid Gas Town patterns.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The heartbeat now explicitly calls ensureDeaconRunning() for basic
"is Deacon alive" checks, while Boot handles intelligent triage
(stuck/nudge/interrupt decisions).
Changed ensureDeaconRunning to use deacon.Manager.Start() instead of
duplicating startup logic. This gives daemon the same benefits:
- WaitForShellReady (fixes race condition)
- Claude settings setup
- Theming
- StartupNudge and PropulsionNudge (GUPP)
Heartbeat order:
1. ensureDeaconRunning - restart if dead (via Manager)
2. ensureBootRunning - intelligent triage for stuck states
3. checkDeaconHeartbeat - belt-and-suspenders fallback
4-11. Other checks (witnesses, refineries, polecats, etc.)
This was inadvertently removed when Boot was introduced, which
delegated all Deacon checks to Boot. But Boot's mol doesn't actually
restart Deacon - it just reports. Now responsibilities are clear:
daemon ensures alive, Boot ensures responsive.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The deacon tmux session is named hq-deacon, not gt-deacon. Fix the
incorrect references in mol-boot-triage and mol-gastown-boot formulas.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The formula parser only supports TOML (uses toml.Decode). The JSON
version of mol-gastown-boot was never used - it was likely created
by mistake or for an abandoned experiment.
Changes:
- Remove .beads/formulas/mol-gastown-boot.formula.json
- Remove internal/formula/formulas/mol-gastown-boot.formula.json
- Simplify go:generate to only copy .formula.toml files
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously GT_ROOT was documented as a formula search path but never
actually set, making $GT_ROOT/.beads/formulas/ unreachable for agents.
Now BuildStartupCommand automatically sets GT_ROOT to the town root,
enabling all agents (witness, refinery, polecat, crew, etc.) to find
town-level formulas without relying on cwd-relative paths.
Also adds a doctor check (gt-root-env) that warns when existing sessions
are missing GT_ROOT, with instructions to restart sessions.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The SetupRedirect function was failing for rigs that use the tracked
beads architecture where the canonical beads location is mayor/rig/.beads
and there is no rig-level .beads directory.
This fix now checks for both locations:
1. rig/.beads (with optional redirect to mayor/rig/.beads)
2. mayor/rig/.beads directly (if no rig/.beads exists)
This ensures crew and polecat workspaces get the correct redirect file
pointing to the shared beads database in all configurations.
Closes: gt-jy77g
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds the ability to switch between Claude Code accounts with a single command:
gt account switch <handle>
The command:
1. Detects current account by checking ~/.claude symlink target
2. If ~/.claude is a real directory, moves it to the current account config_dir
3. Removes existing ~/.claude symlink (if any)
4. Creates symlink from ~/.claude to target account config_dir
5. Updates default account in accounts.json
6. Prints confirmation with restart reminder
Handles edge cases:
- Already on target account (no-op with message)
- Target account does not exist (error with list of valid accounts)
- ~/.claude is real directory (first-time setup scenario)
Closes gt-jd8m1
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add explicit handoff/cycling heuristics for the Witness role:
- Hand off after 15 patrol loops (vs Deacon's 20)
- Immediate handoff after extraordinary actions
- Define extraordinary actions specific to Witness role
- Add Handoff (Wisp-Based) section explaining idempotent patrols
This brings Witness documentation in line with Deacon's level of
detail for context cycling.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The manager refactors (ea8bef2, 72544cc0) conflicted with the agent
override feature, causing regressions:
Deacon (ea8bef2):
- Lost agentOverride parameter
- Re-added respawn loop (removed in 5f2e16f)
- Lost GUPP (startup + propulsion nudges)
Crew (72544cc0):
- Lost agentOverride wiring to StartOptions
- --agent flag had no effect on crew refresh/restart
This fix restores agent override support and GUPP while keeping
improvements from the manager refactors (zombie detection, etc).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: Add rig-level custom agent support
Implement rig-level custom agent configuration support to enable per-rig
agent definitions in <rig>/settings/config.json, following the same pattern as
town-level agents in settings/config.json.
Changes:
- Added RigSettings.Agents field to internal/config/types.go
- Added DefaultRigAgentRegistryPath() and LoadRigAgentRegistry() functions to internal/config/agents.go
- Updated ResolveAgentConfigWithOverride() to accept and pass rigSettings parameter
- Updated GetRuntimeCommandWithAgentOverride() to use rigSettings when available
- Updated GetRuntimeCommandWithPromptAndAgentOverride() to use rigSettings
- Updated all Build*WithOverride functions to pass rigSettings
This fixes the issue where rig-level agent settings were loaded but
ignored by lookupAgentConfig, enabling per-rig custom agents for
polecats and crew members.
* test: Add rig-level custom agent tests
Added comprehensive unit tests for rig agent registry functions:
- TestDefaultRigAgentRegistryPath: verifies path construction
- TestLoadRigAgentRegistry: verifies file loading and JSON parsing
- TestLookupAgentConfigWithRigSettings: verifies agent lookup priority (rig > town > builtin)
Added placeholder integration test for future CI/CD setup.
* initial commit
* fix: resolve compilation errors in rig-level custom agent support
- Add missing RigAgentRegistryPath function (alias for DefaultRigAgentRegistryPath)
- Restore ResolveAgentConfigWithOverride function that was incorrectly removed
- Fix ResolveAgentConfig to return single value (not triple)
- Add initRegistryLocked() call to LoadRigAgentRegistry to prevent nil panic
- Fix DefaultRigAgentRegistryPath to use rigPath directly (not parent dir)
- Fix test file syntax errors (remove EOF artifacts)
- Fix test parameter order for lookupAgentConfig calls
- Fix test expectations to match correct custom agent override behavior
* test: implement rig-level custom agent integration test
- Add stub agent script that simulates AI agent with Q&A capability
- Test ResolveAgentConfig correctly picks up rig-level agents
- Test BuildPolecatStartupCommand includes custom agent command
- Test ResolveAgentConfigWithOverride respects rig agents
- Test rig agents override town agents with same name
- Add tmux integration test that spawns session and verifies output
- Stub agent echoes 'STUB_AGENT_STARTED' and handles ping/pong Q&A
- All tests pass including real tmux session verification
* docs: add OpenCode custom agent example to reference
- Show settings/agents.json format for advanced configs
- Include OpenCode example with session resume flags
- Document OPENCODE_PERMISSION env var for autonomous mode
* fix: improve rig-level agent support with docs and test fixes
- Add rig-level agent documentation to reference.md
- Document agent resolution order (rig → town → built-in)
- Deduplicate LoadAgentRegistry/LoadRigAgentRegistry into shared helper
- Fix test isolation in TestLoadRigAgentRegistry
- Fix nil pointer dereference in test assertions (use t.Fatal not t.Error)
Replaces inline ensureRefinerySession function with refinery.NewManager(r).Start(false) in gt start --all. Gains zombie detection, proper state tracking, and WaitForShellReady fix.
CI failures (lint in beads.go, integration tests) are pre-existing issues unrelated to this PR's changes.
Co-Authored-By: julianknutsen <julianknutsen@users.noreply.github.com>
Key decisions:
- Fixed pool of 5 goroutines (not Claude sessions)
- State file persistence for crash recovery
- Warrant queuing when pool exhausted
- Dogs are lightweight state machine executors
- New internal/shutdown/ package (separate from existing dog package)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The Deacon patrol formula's zombie-scan step now:
- Only detects zombies via --dry-run, never kills directly
- Files death warrants for Boot to handle interrogation/execution
- Includes psychological weight language about termination gravity
This prevents accidental destruction of worker context, mid-task
progress, and unsaved state. Kill authority belongs to Boot.
Bumped version to 5.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add WaitForShellReady call before SendKeys in all agent managers
(deacon, mayor, witness, refinery). This prevents intermittent
"can't find pane" errors that occur when the tmux session is
created but the shell isn't ready to receive input yet.
The issue manifests under load (e.g., during `gt up` when multiple
agents start in sequence) where the 200ms delay in SendKeysDelayed
isn't sufficient for the pane to be fully initialized.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* bd sync: 2026-01-05 06:22:43
* bd sync: 2026-01-05 07:08:42
* bd sync: 2026-01-05 07:24:58
* feat: Add code coverage PR comment to GitHub Actions
Adds a step to the CI workflow that:
- Collects code coverage during test runs
- Parses per-package coverage percentages
- Posts a markdown table comment on PRs with:
- Overall coverage percentage
- Per-package breakdown table
- Updates existing comment on subsequent pushes
Closes: ga-tl5
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(ci): handle fork PR permissions for coverage comment
Fork PRs cannot write comments via GITHUB_TOKEN due to security
restrictions. Add condition to skip comment step for external PRs
and upload coverage report as artifact instead.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor(ci): separate coverage into dedicated job
- Test job now uploads coverage.out and test-output.txt as artifacts
- New Coverage Report job runs after tests complete
- Downloads coverage data, generates report, uploads as artifact
- Always uploads coverage-report artifact (for both fork and internal PRs)
- Comments on PR only for internal PRs (fork PRs get notice message)
- Cleaner separation of concerns
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(ci): coverage job waits for both test and integration
Coverage Report job now depends on [test, integration] to ensure
it only runs after all test stages complete successfully.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(ci): restore Coverage Report job after Test and Integration
Coverage Report job now properly:
- Depends on [test, integration] - waits for both to complete
- Downloads coverage data from Test job
- Generates and uploads coverage-report artifact
- Comments on internal PRs only
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: add debugging output to TestInstallTownRoleSlots
Add logging for gt install output and bd list to help diagnose
CI failures where agent beads may not be created.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(ci): update beads to @main and fix lint errors
- Change CI to install beads from @main instead of @latest
(latest release doesn't support role/agent issue types)
- Remove error return from cleanBeadsRuntimeFiles since all
errors are intentionally ignored (best-effort cleanup)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(ci): pin beads to v0.44.0 for agent/role types
Beads main recently extracted Gas Town-specific types (agent, role, etc.)
from core. Pin CI to v0.44.0 which still has these types.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix(ci): unpin beads version back to @latest
Beads v0.46.0 now supports agent/role types again.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore: remove stale gastown/.beads files from PR
These beads files are local runtime state that shouldn't be committed.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Defines the state machine that Dogs execute for death warrants:
- 3-attempt interrogation with escalating timeouts (60s, 120s, 240s)
- PARDON path when session responds with ALIVE
- EXECUTE path after all attempts exhausted
- EPITAPH step for audit logging
Key design decisions documented:
- Dogs are goroutines, not Claude sessions
- Timeout gates close on timer OR early response detection
- State persisted to ~/gt/deacon/dogs/active/ for crash recovery
Implements specification for gt-cd404.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When gt doctor --fix detects stale Claude settings at town root, it was
automatically killing ALL Gas Town sessions (gt-* and hq-*). This is too
disruptive because:
1. Deacon runs gt doctor automatically, creating a restart loop
2. Active crew/polecat work could be lost mid-task
3. Settings are only read at startup, so running agents already have
the config loaded in memory
Instead, warn the user and tell them to restart agents manually:
"Town-root settings were moved. Restart agents to pick up new config:
gt up --restart"
Addresses PR #239 feedback.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
TestGetReturnsWorkingWithoutBeads assumes bd is not available and
expects state to default to StateWorking. When bd is installed, it
actually queries beads and returns the real state, causing the test
to fail.
Skip the test when bd is detected to avoid environment-dependent
failures.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add Cursor Agent as compatible agent for Gas Town
Add AgentCursor preset with ProcessNames field for multi-agent detection:
- AgentCursor preset: cursor-agent -p -f (headless + force mode)
- ProcessNames field on AgentPresetInfo for agent detection
- IsAgentRunning(session, processNames) in tmux package
- GetProcessNames(agentName) helper function
Closes: ga-vwr
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: centralize agent preset list in config.go
Replace hardcoded ["claude", "gemini", "codex"] arrays with calls to
config.ListAgentPresets() to dynamically include all registered agents.
This fixes cursor agent not appearing in `gt config agent list` and
ensures new agent presets are automatically included everywhere.
Also updated doc comments to include "cursor" in example lists.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* test: add comprehensive agent client tests
Add tests for agent detection and command generation:
- TestIsAgentRunning: validates process name detection for all agents
(claude/node, gemini, codex, cursor-agent)
- TestIsAgentRunning_NonexistentSession: edge case handling
- TestIsClaudeRunning: backwards compatibility wrapper
- TestListAgentPresetsMatchesConstants: ensures ListAgentPresets()
returns all AgentPreset constants
- TestAgentCommandGeneration: validates full command line generation
for all supported agents
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add Auggie agent, fix Cursor interactive mode
Add Auggie CLI as supported agent:
- Command: auggie
- Args: --allow-indexing
- Supports session resume via --resume flag
Fix Cursor agent configuration:
- Remove -p flag (requires prompt, breaks interactive mode)
- Clear SessionIDEnv (cursor uses --resume with chatId directly)
- Keep -f flag for force/YOLO mode
Updated all test cases for both agents.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat(agents): add Sourcegraph AMP as agent preset
Add AgentAmp constant and builtinPresets entry for Sourcegraph AMP CLI.
Configuration:
- Command: amp
- Args: --dangerously-allow-all --no-ide
- ResumeStyle: subcommand (amp threads continue <threadId>)
- ProcessNames: amp
Closes: ga-guq
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: lint error in cleanBeadsRuntimeFiles
Change function to not return error (was always nil).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: beads v0.46.0 compatibility and test fixes
- Add custom types config (agent,role,rig,convoy,event) after bd init calls
- Fix tmux_test.go to use variadic IsAgentRunning signature
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* docs: update agent documentation for new presets
- README.md: Update agent examples to show cursor/auggie, add built-in presets list
- docs/reference.md: Add cursor, auggie, amp to built-in agents list
- CHANGELOG.md: Add entry for new agent presets under [Unreleased]
Addresses PR #247 review feedback.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
During `gt install`, the beads database is initialized but Gas Town's
custom issue types (agent, role, rig, convoy, slot) were not being
registered. This caused subsequent agent bead creation to fail with
"invalid issue type: agent" errors.
The fix adds `bd config set types.custom "agent,role,rig,convoy,slot"`
after `bd init` completes. This is idempotent and safe to run multiple
times.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Error: Ran 1 stop hook
⎿ Stop hook error: Failed with non-blocking status code: Error: --session flag required (or set GT_SESSION env var, or GT_RIG/GT_ROLE)
Usage:
gt costs record [flags]
deriveSessionName() now falls back to gt-{role} when GT_ROLE is mayor
or deacon but GT_TOWN is not set. Previously this case returned empty
string, causing the Stop hook to fail.
- Show clearer error explaining user needs to specify crew name or cd into crew dir
- When --rig is specified, list available crew members in that rig
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The TMUX environment variable is not inherited when Claude Code runs
bash commands, even though we are inside a tmux session. This caused
the Stop hook's 'gt costs record' to fail with:
Error: --session flag required
Fix: Remove the early return that checked TMUX env var. The
tmux display-message command will naturally fail if we're not
in tmux, so the check was unnecessary and harmful.
Fixes: hq-to0lr
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Rig operational state management, unified agent startup, and extensive
stability fixes. See CHANGELOG.md for full release notes.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Logs a warning when checking rig operational state if the wisp
config file doesn't exist. This helps diagnose cases where a
parked rig unexpectedly restarts because its parked state was lost.
- Remove references to non-existent .repo.git bare repo
- Clarify that polecats/refinery are worktrees from mayor/rig
- Clarify that crew/* are full clones for human developers
- Update routes.jsonl examples to match actual format
- Add explanation of why routes point to mayor/rig
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously, SetupRedirect used os.RemoveAll() which deleted all files
in .beads/ including tracked files like formulas/, README.md, config.yaml.
Now cleanBeadsRuntimeFiles() selectively removes only gitignored runtime
files (*.db, daemon.*, issues.jsonl, etc.) while preserving tracked content.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously `gt doctor --fix` would automatically kill and restart patrol
sessions when fixing stale settings.json files. This was disruptive as it
interrupted work without explicit consent.
Now session cycling only happens when `--restart-sessions` is explicitly
passed along with `--fix`. Without the flag, settings files are updated
but running sessions are left alone.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The isTownLevelSession() function was checking workspace.FindFromCwd()
which fails when gt cycle is invoked via tmux run-shell, since run-shell
executes from whatever directory the tmux server started in (often / or
home), not from within the Gas Town workspace.
Town-level sessions (hq-mayor, hq-deacon) can be identified by their
fixed names alone - no workspace context needed. This fix removes the
unnecessary workspace dependency, allowing C-b n/p to cycle between
Mayor and Deacon sessions as intended.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
gt doctor --fix was killing all sessions with stale settings, including
crew and polecats that cannot auto-recover. Now only kills patrol roles
(witness, refinery, deacon, mayor) which the daemon will restart.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When checking if a polecat can be nuked, verify that any hooked bead is
still active (not closed). If the hooked bead was closed externally, the
hook is stale and should not block the nuke.
Also shows 'stale' in dry-run output when hook points to a closed bead.
stale_hooks.go was using hardcoded 'gt-deacon' and 'gt-mayor' instead of
session.DeaconSessionName() and session.MayorSessionName() which return
'hq-deacon' and 'hq-mayor'. This caused incorrect session lookups.
Also fixes duplicate WorktreeAddFromRef method from merge conflict.
Merge artifact - two versions of the method existed. Keep the one
with sparse checkout support.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Deacon is a town-level role, so its beads should be at ctx.TownRoot
(~/gt/.beads/) not ctx.WorkDir (~/gt/deacon/). This fixes the issue
where outputDeaconPatrolContext couldn't find patrol molecules because
it was looking in the wrong location.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
verifyBeadExists was setting BEADS_DIR to town root, which overrides
bd's native prefix-based routing via routes.jsonl. This broke resolution
of rig-level beads (e.g., gt-* beads routed via gt- -> gastown/mayor/rig).
Fix:
- Remove BEADS_DIR override in verifyBeadExists
- Set cmd.Dir to town root so bd can find routes.jsonl
- Apply same fix to getBeadInfo for consistency
Now gt sling gt-xxx correctly finds beads using the same routing as
bd show gt-xxx.
(gt-l5qwb)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Regenerate formulas to sync with source templates
- Fix unparam lint warnings in status.go (unused townRoot parameters)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add version check that enforces beads >= 0.44.0 at CLI startup,
required for custom type support (bd-i54l). Commands like version,
help, and completion bypass the check.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Verify that rig add creates settings.json in correct locations:
- witness/.claude/settings.json (outside git repo)
- refinery/.claude/settings.json (outside git repo)
- crew/.claude/settings.json (shared, outside git repos)
- polecats/.claude/settings.json (shared, outside git repos)
Also verify settings are NOT created inside source repos
(witness/rig/.claude, refinery/rig/.claude) which would
pollute the source repos.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
CLAUDE.md moved from town root to mayor/ to prevent inheritance
pollution to child workspaces.
Also verify mayor/.claude/settings.json and deacon/.claude/settings.json
exist at their correct locations (outside source repos).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Daemon's restartPolecatSession was calling BuildPolecatStartupCommand
with empty rigPath, causing polecats to fall back to town-level defaults
instead of honoring rig-specific agent settings.
Now passes rigPath so rig agent settings are honored.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Witness was calling BuildAgentStartupCommand with empty rigPath,
causing it to fall back to town-level defaults instead of honoring
rig-specific agent settings (like RigSettings.Agent).
Now passes m.rig.Path so rig agent settings are honored, consistent
with how refinery already passes the rig path.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Tests were creating mayor settings at townRoot/.claude/ but the check
now correctly identifies that location as wrong (should be mayor/.claude/).
Updated tests to use mayor/.claude/settings.json which is the correct
location that doesn't pollute child workspaces via directory traversal.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create mayor.Manager for mayor lifecycle (Start/Stop/IsRunning/Status)
- Create deacon.Manager for deacon lifecycle with respawn loop
- Move session.Manager to polecat.SessionManager (clearer naming)
- Add zombie session detection for mayor/deacon (kills tmux if Claude dead)
- Remove duplicate session startup code from up.go, start.go, mayor.go
- Rename sessMgr -> polecatMgr for consistency
- Make witness/refinery SessionName() public for status display
All agent types now follow the same Manager pattern:
mgr := agent.NewManager(...)
mgr.Start(...)
mgr.Stop()
mgr.IsRunning()
mgr.Status()
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Creates settings.json automatically during initial setup, so Claude
settings are available immediately on launch.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Prevents mayor-specific files (CLAUDE.md, hooks) from polluting child
agent workspaces. Child agents inherit the parent's working directory,
so keeping mayor files in a dedicated subdirectory ensures they don't
interfere with agent operations.
Includes:
- MayorDir constant in templates for consistent path handling
- Updated hooks.go, prime.go, role.go to use mayor/ paths
- Documentation updates
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Refactors all agent startup paths (witness, refinery, crew, polecat) to use
a consistent Manager interface with Start(), Stop(), IsRunning(), and
SessionName() methods.
Includes:
- Witness manager with GUPP propulsion nudge for startup
- Refinery manager for engineer sessions
- Crew manager for worker agents
- Session/polecat manager updates
- claude_settings_check doctor check for settings validation
- Settings management consolidated from rig/manager.go
- Settings location moved outside source repos to prevent conflicts
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Excludes all Claude Code context files to prevent source repo instructions
from interfering with Gas Town agent configuration:
- .claude/ : settings, rules, agents, commands
- CLAUDE.md : primary context file
- CLAUDE.local.md: personal context file
- .mcp.json : MCP server configuration
Legacy configurations (only excluding .claude/) are detected and upgraded
by gt doctor --fix.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Complete the "discover, don't track" refactoring:
- checkGUPPViolations: use tmux.IsClaudeRunning() instead of agent_state
- checkOrphanedWork: derive dead agents from tmux, not agent_state=dead
- assessStaleness: rely on HasActiveSession (tmux), not agent_state
Non-observable states (stuck, awaiting-gate) are still respected.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add Status line showing operational state (OPERATIONAL/PARKED/DOCKED)
with source indication (local/global - synced/default).
The state is looked up using the property layer system:
1. Wisp layer (local/ephemeral): .beads-wisp/config/<rig>.json
2. Rig bead labels (global/synced): status:parked or status:docked
3. Default: OPERATIONAL
Example output:
gastown
Status: PARKED (local)
Path: /Users/stevey/gt/gastown
...
Closes: gt-5l7h4
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement gt rig dock <rig> and gt rig undock <rig> commands for
global/persistent rig control:
- dock: stops witness/refinery, sets status:docked label on rig bead
- undock: removes docked label, allows daemon to restart agents
This is Level 2 (global/persistent) control:
- Uses rig identity bead labels (synced via git)
- Affects all clones of the rig
- Persists until explicitly undocked
Also includes cherry-picked rig identity bead infrastructure:
- RigFields struct for rig metadata
- CreateRigBead and RigBeadID helpers
- Auto-create rig bead for legacy rigs on first dock
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update daemon to check rig config before auto-starting agents:
- Check wisp config "status" - skip if parked or docked
- Check "auto_restart" config - skip if blocked or false
- Log skip reason for visibility
Affects ensureWitnessRunning, ensureRefineryRunning,
restartPolecatSession, and lifecycle restartSession.
(gt-68c46)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Additional cleanup from the agent_state refactoring:
- Remove dead code: checkStaleAgents(), markAgentDead() in lifecycle.go
- Remove dead code: reportAgentState(), getAgentFields() in prime.go
- Update getAgentBeadState() comment to clarify non-observable states only
- Update mol-witness-patrol.formula.toml to use tmux discovery
- Update mol-polecat-lease.formula.toml to use POLECAT_DONE mail
- Update docs/watchdog-chain.md to reflect new architecture
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement gt rig park <rig> and gt rig unpark <rig> commands:
- park: stops witness/refinery, sets status=parked in wisp layer
- unpark: clears parked status, allows daemon to restart agents
This is Level 1 (local/ephemeral) control - affects only this town
and disappears on wisp cleanup. Exports IsRigParked() for daemon use.
(gt-vxv0u)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements config viewing and manipulation commands for rig configuration
across property layers.
Commands:
- gt rig config show <rig> # Show effective config
- gt rig config show <rig> --layers # Show source of each value
- gt rig config set <rig> <key> <value> # Set in wisp layer
- gt rig config set <rig> <key> <value> --global # Set in bead layer
- gt rig config set <rig> <key> --block # Block inheritance
- gt rig config unset <rig> <key> # Remove from wisp
Includes cherry-picked dependencies:
- Property layer lookup (cb927a73, gt-emh1c)
- Rig identity bead schema for bead layer
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The agent_state field was recording observable state like "running",
"dead", "idle" which violated the "Discover, Don't Track" principle.
This caused stale state bugs where agents were marked "dead" in beads
but actually running in tmux.
Changes:
- Remove daemon's checkStaleAgents() which marked agents "dead"
- Simplify ensureXxxRunning() to use tmux.IsClaudeRunning() directly
- Remove reportAgentState() calls from gt prime and gt handoff
- Add SetHookBead/ClearHookBead helpers that don't update agent_state
- Use ClearHookBead in gt done and gt unsling
- Simplify gt status to derive state from tmux, not bead
Non-observable states (stuck, awaiting-gate, muted, paused) are still
set because they represent intentional agent decisions that can't be
discovered from tmux state.
Fixes: gt-zecmc
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add --verbose/-v flag to show detailed multi-line output (old behavior)
- Compact mode shows: name + status indicator (●/○) + hook + mail count
- MQ info displayed inline with refinery
- Fix Makefile install target to use ~/.local/bin
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When the daemon detects that an agent bead state doesn't match tmux
(e.g., bead says stopped but Claude is running), it now:
1. Logs the divergence clearly with STATE DIVERGENCE prefix
2. Nudges the agent with an actionable command to fix its state
3. Still skips the restart (safety - don't kill healthy sessions)
This prevents silent state drift where bead state diverges from reality.
Applied to: Deacon, Witness, Refinery ensure functions.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add watch mode to gt status
- Add --watch/-w flag for continuous status refresh
- Add --interval/-n flag to set refresh interval (default 2s)
- Clears screen and shows timestamp on each refresh
- Graceful Ctrl+C handling to stop watch mode
- Works with existing --fast and --json flags
* fix(status): validate watch interval to prevent panic on zero/negative values
* fix(status): harden watch mode with signal cleanup, TTY detection, and tests
- Add defer signal.Stop() to prevent signal handler leak
- Reject --json + --watch combination (produces invalid output)
- Add TTY detection for ANSI escapes (safe when piped)
- Use style.Dim for header when in TTY mode
- Fix duplicate '(default 2)' in flag help
- Add tests for interval validation and flag conflicts
Resolved conflict in internal/witness/manager.go:
- Kept session import (used by PR code)
- Kept PR's more accurate comment for PID check
- Removed duplicate sessionName method introduced by merge
Implement wisp-based config storage at .beads-wisp/config/<rig>.json
for local-only settings that are never synced via git.
API:
- Get(key) - returns value or nil
- Set(key, value) - stores value
- Block(key) - marks key as blocked (NullValue equivalent)
- Unset(key) - removes from values and blocked
- IsBlocked(key) - checks if blocked
(gt-3w685)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The witness manager's Stop() method was only updating runtime JSON state
without killing the tmux session, causing 'gt rig shutdown' to leave
witness sessions running.
Added sessionName() method and tmux kill-session logic to match the
refinery's existing implementation.
Fixes: bd-gxaf
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The previous commit (a3bccc8) violated ZFC by implementing molecule step logic
in Go handlers. Per PRIMING.md: Agent decides. Go transports.
This commit:
1. Reverts the gt witness process command (Go code should not make decisions)
2. Updates mol-witness-patrol formula with explicit CLI commands
3. Fixes --wisp to --ephemeral (bd create flag correction)
4. Removes --wisp from bd list calls (invalid flag)
The Witness Claude agent now has explicit instructions:
- Parse POLECAT_DONE message for polecat name
- Check cleanup_status via bd show
- Run gt polecat nuke or bd create --ephemeral based on status
- Archive mail after handling
ZFC: Agent decides. Go transports.
Fixed two issues in `gt crew stop <name>`:
1. --dry-run flag now works for individual crew stops (previously only
worked with --all)
2. HasSession errors are now properly handled instead of being ignored,
which could cause "No session found" messages even when sessions exist
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The Witness handlers (HandlePolecatDone, HandleMerged, etc.) existed in Go
code but were never called - there was no CLI command to invoke them.
This caused polecats to remain in 'done' state after MR merge because
POLECAT_DONE messages were never processed.
Changes:
- Add `gt witness process <rig>` command to process Witness mail
- Fix --wisp flag to --ephemeral in cleanup wisp creation
- Command processes POLECAT_DONE, MERGED, HELP, SWARM_START messages
- Auto-nukes clean polecats, creates cleanup wisps for dirty ones
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add `gt deacon stale-hooks` command to find and unhook stale beads.
Problem: Beads can get stuck in 'hooked' status when agents die or
abandon work without properly unhooking.
Solution:
- New command scans for hooked beads older than threshold (default 1h)
- Checks if assignee agent is still alive (tmux session exists)
- Unhooks beads with dead agents (sets status back to 'open')
- Supports --dry-run to preview without making changes
Also adds "stale-hook-check" step to Deacon patrol formula.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Added steps from discovered cleanup operations:
- clear-hooks: Detach all hooked work from agents
- reset-in-progress: Reset in-progress beads to open status
- burn-wisps: Clean up wisp directories and ephemeral beads
- validate-clean: Verify all cleanup operations succeeded
Updated existing steps with more detailed procedures.
Key principles preserved:
- No forcing, no lost work
- Idempotent (safe to run multiple times)
- Crew workers NOT affected (user-managed)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase 2 of Heresy Correction: Local-Only Polecat Branches
Changes:
- Replace FetchBranch("origin", branch) with BranchExists() check
- Use local branch directly for CheckConflicts() and MergeNoFF()
- Remove "origin/" prefix from branch references
The Refinery worktree shares .repo.git with polecat worktrees, so
branches created by polecats are already visible locally without
needing to fetch from origin.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase 3 of heresy correction: polecat branches stay local, Refinery
accesses them via shared .repo.git.
Changes:
- templates/polecat-CLAUDE.md: Remove push from completion checklist
- mol-polecat-work.formula.toml: Remove push step from cleanup-workspace
- polecat.md.tmpl: Update landing rule for local branches
- refinery.md.tmpl: Change origin/polecat to local branch references
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase 4 of local-only polecat branches: Handle conflict resolution edge case.
Problem: If polecat worktree is nuked before MR merges, the local branch
is gone and conflict resolution can't access it.
Solution: Witness now defers cleanup for polecats with pending MRs:
- HandlePolecatDone creates a cleanup wisp with "merge-requested" state
- Polecat worktree preserved until MERGED signal arrives
- HandleMerged then nukes the polecat (existing behavior)
Also updated mol-polecat-conflict-resolve.formula.toml:
- Removed fetch from origin (branches are local-only now)
- Added instructions to fetch from source polecat's worktree
- Added rig and source_polecat variables
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When the Refinery detects a build error or test failure and refuses
to merge, the polecat was never notified. This fixes the notification
pipeline by:
1. Adding MERGE_FAILED protocol support to Witness:
- PatternMergeFailed regex pattern
- ProtoMergeFailed protocol type constant
- MergeFailedPayload struct with all failure details
- ParseMergeFailed parser function
- ClassifyMessage case for MERGE_FAILED
2. Adding HandleMergeFailed handler to Witness:
- Parses the failure notification
- Sends HIGH priority mail to polecat with fix instructions
- Includes branch, issue, failure type, and error details
3. Adding mail notification in Refinery's handleFailureFromQueue:
- Creates mail.Router for sending protocol messages
- Sends MERGE_FAILED to Witness when merge fails
- Includes failure type (build/tests/conflict) and error
4. Adding comprehensive unit tests:
- TestParseMergeFailed for full body parsing
- TestParseMergeFailed_MinimalBody for minimal body
- TestParseMergeFailed_InvalidSubject for error handling
- ClassifyMessage test cases for MERGE_FAILED
Fixes#114🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
gt sling failed when hooking rig-level beads from town root because
bd update doesn't support cross-database routing like bd show does.
The fix adds a ResolveHookDir helper that:
1. Extracts the prefix from bead ID (e.g., "ap-xxx" → "ap-")
2. Looks up the rig path from routes.jsonl
3. Falls back to townRoot if prefix not found
Also removes the BEADS_DIR environment override which was preventing
routing from working correctly.
Fixes#148
buildRestartCommand() now propagates Claude-related env vars when
respawning sessions via tmux. Fresh shells don't inherit parent env,
so CLAUDE_CODE_USE_BEDROCK, ANTHROPIC_API_KEY, AWS_*, etc. were lost.
This caused any tmux respawn to result in a non-functional claude.
Adds claudeEnvVars list and includes them in the export command when
building the restart command.
* 📝 (README.md): rewrite documentation with comprehensive guides, architecture diagrams, and detailed workflows
The README has been completely overhauled to provide a more structured and detailed explanation of the Gas Town system. It now includes architecture diagrams, in-depth descriptions of core concepts, step-by-step installation and usage guides, and troubleshooting tips to improve the developer onboarding experience.
* 📝 (README.md): improve formatting, alignment, and spacing
The tables are realigned to improve readability in the raw view, and missing newlines are added before code blocks and after section headers to ensure proper rendering and visual separation.
* fix: create mayor/daemon.json during gt start and gt doctor --fix (#5)
- Add DaemonPatrolConfig type with heartbeat and patrol settings
- Add Load/Save/Ensure functions for daemon patrol config
- Create daemon.json in gt start (non-fatal if fails)
- Make PatrolHooksWiredCheck fixable with Fix() method
- Add comprehensive tests for both config and doctor checks
This fixes the issue where gt doctor expects mayor/daemon.json to exist
but it was never created by gt start or any other command.
* refactor: use constants.DirMayor instead of hardcoded string
* feat: Beads redirect architecture for tracked and local beads
This change implements proper redirect handling so that all rig agents
(Witness, Refinery, Crew, Polecats) can work with both:
- Tracked beads: .beads/ checked into git at mayor/rig/.beads
- Local beads: .beads/ created at rig root during gt rig add
Key changes:
1. SetupRedirect now handles tracked beads by skipping redirect chains.
The bd CLI doesn't support chains (A→B→C), so worktrees redirect
directly to the final destination (mayor/rig/.beads for tracked).
2. ResolveBeadsDir is now used consistently in polecat and refinery
managers instead of hardcoded mayor/rig paths.
3. Rig-level agents (witness, refinery) now use rig beads with rig
prefix instead of town beads. This follows the architecture where
town beads are only for Mayor/Deacon.
4. prime.go simplified to always use ../../.beads for crew redirects,
letting rig-level redirect handle tracked vs local routing.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat(doctor): Add beads-redirect check for tracked beads
When a repo has .beads/ tracked in git (at mayor/rig/.beads), the rig root
needs a redirect file pointing to that location. This check:
- Detects missing rig-level redirect for tracked beads
- Verifies redirect points to correct location (mayor/rig/.beads)
- Auto-fixes with 'gt doctor --fix'
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: Handle fileLock.Unlock error in daemon
Wrap fileLock.Unlock() return value to satisfy errcheck linter.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
This prevents .repo.git/ directories from showing up as untracked files
in town git status.
Changes:
- manager.go: Add .repo.git/ to rig .gitignore during setup
When `gt sling` targets an existing polecat session, it now waits for
Claude to be ready before sending the nudge message. This fixes issue #115
where the "Work slung" message would arrive before Claude had fully started.
Changes:
- Add getSessionFromPane() to extract session name from pane target
- Add ensureClaudeReady() to wait for Claude startup using the same
pragmatic approach as session.Start() (poll for node, accept bypass
dialog, then 8-second delay)
- Call ensureClaudeReady() before injectStartPrompt() in runSling()
The fix uses IsClaudeRunning() for a fast path when Claude is already
running, avoiding unnecessary delays for sessions that have been
running for a while.
Fixes#115🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
- Handle empty repos in ConfigureSparseCheckout (skip read-tree when no HEAD)
- Fix errcheck: wrap fileLock.Unlock() error in defer
- Fix unparam: remove unused *rig.Rig return from getWitnessManager
- Fix unparam: mark unused agentType parameter with blank identifier
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
detectCurrentTmuxSession() was only accepting gt-* prefix sessions,
rejecting town-level sessions like hq-mayor. Now accepts both gt-*
and hq-* prefixes.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Witness and Refinery startup was duplicated across cmd/witness.go, cmd/up.go,
cmd/rig.go, and daemon.go. Worse, not all code paths sent the propulsion nudge
(GUPP - Gas Town Universal Propulsion Principle). Now unified in Manager.Start()
which handles everything including nudges.
Changes:
- witness/manager.go: Full rewrite with session creation, env vars, theming,
WaitForClaudeReady, startup nudge, and propulsion nudge (GUPP)
- refinery/manager.go: Add propulsion nudge sequence after Claude startup
- cmd/witness.go: Simplify to just call mgr.Start(), remove ensureWitnessSession
- cmd/rig.go: Use witness.Manager.Start() instead of inline session creation
- cmd/start.go: Use witness.Manager.Start()
- cmd/up.go: Use witness.Manager.Start(), remove ensureWitness(),
add EnsureSettingsForRole in ensureSession()
- daemon.go: Use witness.Manager.Start() and refinery.Manager.Start() for
unified startup with proper nudges
This ensures all agent startup paths (gt witness start, gt rig boot, gt up,
daemon restarts) consistently apply GUPP propulsion nudges.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Settings creation was scattered across multiple places (createPatrolHooks,
ensurePatrolHooks, inline code). Now unified via claude.EnsureSettingsForRole().
Changes:
- Add "deacon" to autonomous roles in claude/settings.go
- Remove ensurePatrolHooks() from cmd/deacon.go, use EnsureSettingsForRole
- Remove createPatrolHooks() from rig/manager.go (no longer needed at rig add)
- Add EnsureSettingsForRole call in crew_lifecycle.go
- Add doctor check for stale/missing Claude settings files
- Wire up claude-settings check in cmd/doctor.go
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When cloning or creating worktrees from repos that have their own .claude/
directory, those settings would override Gas Town's agent settings. This adds
sparse checkout configuration to automatically exclude .claude/ from all
clones and worktrees.
Changes:
- Add ConfigureSparseCheckout() to git.go, called from all Clone/WorktreeAdd methods
- Add IsSparseCheckoutConfigured() to detect if sparse checkout is properly set up
- Add doctor check to verify sparse checkout config (checks config, not symptoms)
- Doctor --fix will configure sparse checkout for repos missing it
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace panic calls in generateID() and generateThreadID() with
time-based fallback when crypto/rand.Read fails. This is an extremely
rare error case, but panicking is not the right behavior for ID
generation functions.
🤝 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Add a new 'prefix-mismatch' check to gt doctor that detects when the
prefix configured in rigs.json differs from what routes.jsonl actually
uses for a rig's beads.
This can happen when:
- deriveBeadsPrefix() generates a different prefix than what's in the DB
- Someone manually edited rigs.json with the wrong prefix
- Beads were initialized before auto-derive existed with a different prefix
The check is fixable: running 'gt doctor --fix' will update rigs.json
to match the actual prefixes from routes.jsonl.
Includes comprehensive tests for:
- No routes (nothing to check)
- No rigs.json (nothing to check)
- Matching prefixes (OK)
- Mismatched prefixes (Warning)
- Fix functionality
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add AppendRouteToDir helper and use it to add hq-* route during rig
initialization. This allows rig beads to resolve role beads and other
hq-* prefixed beads stored in town beads.
Uses safe append pattern (load, merge, write) instead of overwriting
to avoid clobbering future rig routes.
Supersedes PR #184 with proper implementation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Per docs/architecture.md, Witness and Refinery are rig-level agents that
should use the rig's configured prefix (e.g., pi- for pixelforge) instead
of hardcoded "gt-".
This extends PR #183's creation fix to also fix all lookup paths:
- internal/rig/manager.go: Create agent beads in rig beads with rig prefix
- internal/daemon/daemon.go: Use rig prefix when looking up agent state
- internal/daemon/lifecycle.go: Use rig prefix for identity-to-bead mapping
- internal/cmd/sling.go: Pass townRoot for prefix lookup
- internal/cmd/unsling.go: Pass townRoot for prefix lookup
- internal/cmd/molecule_status.go: Use rig prefix for agent bead lookups
- internal/cmd/molecule_attach.go: Use rig prefix for agent bead lookups
- internal/config/loader.go: Add GetRigPrefix helper
Without this fix, the daemon would:
- Create pi-gastown-witness but look for gt-gastown-witness
- Report agents as missing/dead when they are running
- Fail to manage agent lifecycle correctly
Based on work by Johann Taberlet in PR #183.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Johann Taberlet <johann.taberlet@gmail.com>
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace Unix-only syscall.Flock with gofrs/flock library for
cross-platform file locking. This enables the daemon to run on
Windows in addition to Unix-like systems.
- Add github.com/gofrs/flock v0.13.0 dependency
- Replace syscall.Flock calls with flock.TryLock/Unlock
- Maintain same non-blocking exclusive lock semantics
(gt-5354h)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
In startConfiguredCrew(), only HasSession() was checked, missing the case
where a tmux session exists but Claude has exited. Now checks IsClaudeRunning()
and restarts Claude with BuildCrewStartupCommand if dead, matching the behavior
in runStartCrew(). (gt-ms8s4)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add --purge flag to gt crew remove that:
- Deletes the agent bead (not just closes it)
- Unassigns any beads assigned to the crew member
- Properly handles git worktrees (not just regular clones)
- Add gt doctor crew-worktrees check to detect stale cross-rig worktrees
- Worktrees in crew/ with hyphenated names are now properly cleaned up
using git worktree remove instead of rm -rf
The --purge flag is for accidental/test crew that should leave no trace
in the capability ledger. Normal crew removal closes the agent bead to
preserve CV history per HOP architecture.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Session-ended event beads were accumulating without being processed.
Modified costs.go to auto-close these events immediately after creation
since they are informational audit events. The event data is preserved
in the closed bead and remains queryable.
Also bulk-closed 83 existing stale session-ended events.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When Deacon respawns refinery/witness sessions via LIFECYCLE requests,
the new sessions were starting at the Claude welcome screen without
the propulsion nudge that triggers autonomous execution.
Added StartupNudge and PropulsionNudgeForRole calls to restartSession()
in lifecycle.go, matching the pattern used in ensureRefinerySession()
in start.go. This ensures respawned agents receive the GUPP nudge and
begin autonomous work immediately.
Fixes: gt-01jpg
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
gt crew start beads and gt crew stop beads now default to --all
behavior when no crew names are specified, matching user expectations.
- crew start: accepts 0-1 args (rig only) and starts all crew
- crew stop: detects if single arg is a rig name vs crew name
- Updated help text with new examples
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Global agents like mayor and deacon are town-level agents that should use
the "hq-" prefix, not "gt-". Changed to use AgentBeadIDWithPrefix with
TownBeadsPrefix for consistency with the beads architecture.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add DefaultBranch field to RoleData struct
- Update refinery.md.tmpl to use {{ .DefaultBranch }} template variable
- Populate DefaultBranch from rig config in prime.go and rig/manager.go
- Default to 'main' if not configured
- Add test verifying DefaultBranch rendering in refinery template
Fixes issue where refinery agents merged to master instead of the
configured default branch (e.g., 'develop' or 'develop-cstar').
The test helper createTestGitRepo was using plain `git init` which
creates a branch based on the system's init.defaultBranch config.
When AddRig tries to detect and checkout the default branch, it
falls back to "main" if detection fails, causing "pathspec 'main'
did not match" errors in CI where the system default is "master".
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Town-level services (Mayor, Deacon) now use hq- prefix instead of gt-:
- hq-mayor (was gt-mayor)
- hq-deacon (was gt-deacon)
This distinguishes town-level sessions from rig-level sessions which
continue to use gt- prefix (gt-gastown-witness, gt-gastown-crew-max, etc).
Changes:
- session.MayorSessionName() returns "hq-mayor"
- session.DeaconSessionName() returns "hq-deacon"
- ParseSessionName() handles both hq- and gt- prefixes
- categorizeSession() handles both prefixes
- categorizeSessions() accepts both prefixes
- Updated all tests and documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Audit of test coverage identifying:
- 10 packages with 0 test coverage (2,452 lines)
- Priority list for new tests (internal/lock is P0)
- 1 flaky test candidate (feed/curator_test.go)
- Test quality analysis and recommendations
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fixes gt-v07fl: Polecat lifecycle cleanup for stale worktrees and git
tracking conflicts.
Changes:
1. Add .claude/ to .gitignore (prevents untracked file accumulation)
2. Add beads runtime state patterns to .gitignore (prevents future tracking)
3. Remove .beads/ runtime state from git tracking (mq/, issues.jsonl, etc.)
- Formulas and config remain tracked (needed for go install)
- Created follow-up gt-mpyuq for formulas refactor
4. Add DetectStalePolecats() to polecat manager for identifying cleanup candidates
5. Add CountCommitsBehind() to git package for staleness detection
6. Add `gt polecat stale <rig>` command for stale polecat detection/cleanup
- Shows polecats without active sessions
- Identifies polecats far behind main (configurable threshold)
- Optional --cleanup flag to auto-nuke stale polecats
The existing `gt polecat gc` command handles branch cleanup.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When slinging rig-level beads (gt-*, bd-*, etc.), the BEADS_DIR was
unconditionally set to town beads, which could bypass the redirect-based
routing needed for these beads. This caused assignee updates to potentially
fail silently or target the wrong database.
Changes:
- sling.go: Only set BEADS_DIR for town-level (hq-*) beads; rig-level
beads now use redirect from polecat worktree for proper routing
- convoy.go: Add --no-daemon to bd show calls to ensure fresh data
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create internal/agent package with shared State type and StateManager
- StateManager uses Go generics for type-safe load/save operations
- Update witness and refinery to use shared State type alias
- Replace loadState/saveState implementations with StateManager delegation
- Maintains backwards compatibility through re-exported constants
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Introduces a typed CleanupStatus with constants:
- CleanupClean, CleanupUncommitted, CleanupStash, CleanupUnpushed, CleanupUnknown
Adds helper methods:
- IsSafe(): true for clean status
- RequiresRecovery(): true for uncommitted/stash/unpushed
- CanForceRemove(): true if force flag can bypass
Updated files to use the new type:
- internal/polecat/types.go: Type definition and methods
- internal/polecat/manager.go: Validation logic
- internal/witness/handlers.go: Nuke safety checks
- internal/cmd/done.go: Status reporting
- internal/cmd/polecat.go: Recovery status checks
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Create util.ExecWithOutput and util.ExecRun to consolidate repeated
exec.Command patterns across witness/handlers.go and refinery/manager.go.
Changes:
- Add internal/util/exec.go with ExecWithOutput (returns stdout) and
ExecRun (runs command without output)
- Refactor witness/handlers.go to use utility functions (7 call sites)
- Refactor refinery/manager.go, removing unused gitRun/gitOutput methods
- Add comprehensive tests in exec_test.go
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Extracted duplicate bd command execution pattern from mailbox.go and
router.go into a new helper function in bd.go. This reduces code
duplication and provides consistent error handling via the bdError type.
Changes:
- Added internal/mail/bd.go with runBdCommand helper and bdError type
- Refactored 5 functions in mailbox.go to use runBdCommand
- Refactored 5 functions in router.go to use runBdCommand
- Net reduction of 55 lines of code
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- DiscoverRigs() now logs failed rig loads to stderr instead of silently
continuing
- AddRig warnings now output to stderr instead of stdout, matching the
codebase convention for non-fatal warnings
- Added clarifying comment for best-effort git ref update in worktree
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously, when gt done was called, it cleared the agent's hook_bead
slot but didn't update the status of the hooked bead itself. This left
handoff beads with status=hooked forever.
Now the hooked bead is closed (status changed from hooked to closed)
before clearing the agent's hook slot.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The TestIntegration test was flaky because it uses the real .beads directory
and the SQLite database could be out of sync with the JSONL file (e.g., after
git pull updates the JSONL but before the database is re-imported).
The fix runs `bd sync --import-only` at the start of the test to ensure
the database is synchronized before running the actual test operations.
Fixes gt-5ww96
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add debugSession helper that logs non-fatal errors when GT_DEBUG_SESSION=1.
Replaced all _ = error patterns with debugSession() calls for better
visibility when diagnosing session startup issues.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously, listFromDir silently ignored all query errors and returned an
empty list with no error if all queries failed. This could hide real problems
like a corrupted beads database or missing bd command.
Now the function tracks whether at least one query succeeded. If all queries
fail, it returns the last error wrapped with context. This enables graceful
degradation (partial results if some queries work) while surfacing complete
failures.
(gt-lm41t)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The --molecule flag was defined but never wired up - the slingMolecule
variable was set by the flag parser but never read by any code path.
Users should use --on instead, which is fully implemented:
gt sling <formula> --on <bead> <target>
The --on flag properly instantiates the formula (cook + wisp + bond)
and applies it to the target bead before slinging.
Keeping --on as the canonical way to apply formulas to beads since it's
actually wired up and working. The --molecule flag can be re-added later
if a different argument order is desired.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The --quality flag (basic|shiny|chrome) referenced mol-polecat-* formulas
that were removed in c47a746 ("Remove obsolete polecat formula files") but
the flag code was left behind, causing errors when used.
Rather than restore the formulas, remove the flag entirely since:
- The default `gt sling <bead> <rig>` is now the standard workflow
- Formula-on-bead via `--on` or `--molecule` covers custom workflows
- The quality-level formulas were intentionally deprecated
Removes:
- --quality/-q flag and help text
- qualityToFormula() function
- Quality Levels section from command documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add isValidBeadsPrefix() to validate prefix format before passing to
exec.Command. Prefixes from config files (detectBeadsPrefixFromConfig)
are now validated to contain only alphanumeric and hyphen characters,
start with a letter, and be max 20 chars.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Verifies all clones have core.hooksPath set to .githooks.
Auto-fixable with 'gt doctor --fix'.
This ensures the pre-push hook is active on all clones,
blocking pushes to invalid branches (no internal PRs).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Use regexp.QuoteMeta to treat Query and FromFilter as literal strings
instead of raw regex patterns. This prevents ReDoS attacks from malicious
patterns and provides more intuitive literal string matching for users.
Fixes gt-kwa09
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Audit of test coverage identifying:
- 10 packages with 0 test coverage (2,452 lines)
- Priority list for new tests (internal/lock is P0)
- 1 flaky test candidate (feed/curator_test.go)
- Test quality analysis and recommendations
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Avoid template literals with backticks that confuse YAML parsers.
Use array.join() instead.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add --no-daemon to all 17 bd exec calls to bypass daemon socket timing issues
- Set BEADS_DIR in verifyBeadExists() so bd can find beads from any directory
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Gas Town agents must push directly to main, not create PRs.
This adds defense-in-depth:
1. .githooks/pre-push - Blocks pushes to non-main branches locally
2. .github/workflows/block-internal-prs.yml - Auto-closes PRs from
the same repo (forks/contributors can still create PRs)
3. internal/git/git.go - Auto-configures core.hooksPath on clone
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add error suppression for enc.Encode() calls in info.go (errcheck lint)
- Add missing encoding/json import in install_integration_test.go
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fixes PR #39 to follow the pattern established in PR #54 - all beads
initialization in done.go should use ResolveBeadsDir to support
.beads/redirect files in worktrees.
* fix: Commit embedded formulas for go install @latest
The internal/formula/formulas/ directory was gitignored, causing
`go install github.com/steveyegge/gastown/cmd/gt@latest` to fail with:
pattern formulas/*.formula.json: no matching files found
The go:embed directive requires these files at build time, but
go install @latest doesn't run go:generate. By committing the
generated formulas, users can install directly without cloning.
Maintainers should run `go generate ./...` after modifying
.beads/formulas/ to keep the embedded copy in sync.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* ci: Add check for committed embedded formulas
Adds a new CI job that:
1. Builds without running go:generate (catches missing formulas)
2. Verifies committed formulas match .beads/formulas/ source
Also removes redundant go:generate steps from other jobs since
formulas are now committed.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore: exclude towers-of-hanoi test formulas from embed
These are durability stress test fixtures (pre-computed move sequences),
not production formulas users need. Excluding them reduces embedded
content by ~10K lines.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: gus <steve.yegge@gmail.com>
Sync with mayor/rig fix: Set hook slot in CreateAgentBead and pass
beadID to UpdateAgentState.
Fixes: mi-619
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Previously, BuildStartupCommand, GetRuntimeCommand, and
GetRuntimeCommandWithPrompt would fall back to DefaultRuntimeConfig()
(hardcoded "claude") when rigPath was empty, instead of reading
the town settings for the default_agent.
This meant that `gt config default-agent` had no effect on town-level
agents like the mayor.
Fix: Added findTownRootFromCwd() to detect town root from cwd,
then call ResolveAgentConfig() to read the town's default_agent
setting and custom agents.
Now `gt mayor attach` (and other town-level agents) correctly use
the agent configured in town settings.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
When no rig argument is provided, now uses GetRole() to detect the
rig from the current directory or GT_ROLE environment variable.
Shows a helpful error message if rig cannot be determined.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The issue: gt crew start --all was not priming crew sessions like
gt crew at does.
Root cause: gt crew at passes "gt prime" as the initial prompt to
BuildCrewStartupCommand(), while gt crew start (via startCrewMember
and runStartCrew) passed an empty string and tried to send gt prime
afterwards via NudgeSession. This created a race condition where the
SessionStart hook would fire and Claude would start responding before
the nudge arrived.
Fix: Pass "gt prime" directly in the startup command for all three
cases: startCrewMember, runStartCrew new session, and runStartCrew
session restart. This makes the behavior consistent with gt crew at.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Wisps now live in main .beads/ directory with type=wisp instead
of a separate .beads-wisp/ directory. Updated documentation to
reflect this architectural change.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updates README.md and docs/reference.md with the new gt config command usage, including:
- All subcommands (agent list, get, set, remove, default-agent)
- Example of setting up a custom agent (claude-glm)
- Note about overriding built-in agents
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
The crew start command now infers the rig name from the current
working directory when using --all without specifying a rig. This
matches the behavior of crew stop and other commands.
Before: gt crew start gastown --all (required)
After: gt crew start --all (infers from cwd)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements GitHub issue #127 - allow custom agent configuration
through a CLI interface instead of command-line aliases.
The gt config command provides:
- gt config agent list [--json] List all agents
- gt config agent get <name> Show agent configuration
- gt config agent set <name> <cmd> Set custom agent command
- gt config agent remove <name> Remove custom agent
- gt config default-agent [name] Get/set default agent
Users can now define custom agents (e.g., claude-glm) and
override built-in presets (claude, gemini, codex) through
town settings instead of shell aliases.
Changes:
- Add SaveTownSettings() to internal/config/loader.go
- Add internal/cmd/config.go with full config command implementation
- Add comprehensive unit tests for both SaveTownSettings and
all config subcommands (17 test cases covering success and
error scenarios)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Extract the cross-rig bead formatting logic into a testable helper
function and add comprehensive unit tests:
- TestFormatTrackBeadID: 8 test cases covering HQ beads, cross-rig
beads, and edge cases (single segment, empty string, many segments)
- TestFormatTrackBeadIDConsumerCompatibility: 3 test cases verifying
the external ref format can be correctly parsed by consumers in
convoy.go, model.go, feed/convoy.go, and web/fetcher.go
The helper function includes godoc with examples showing expected
behavior for different bead ID formats.
When creating auto-convoys for cross-rig beads (e.g., gt-xxx or gu-xxx),
the tracking relation was failing because bd couldn't resolve the bead ID
from HQ context. Now formats non-HQ beads as external:prefix:id for proper
resolution.
Fixes convoy tracking for cross-rig sling operations.
When patrol agents (witness, refinery, deacon) complete their patrol wisp,
they were left idle because the instructions only said "loop back" without
specifying the command to create a new wisp.
Updated:
- Work loop instructions in prime.go now explicitly tell agents:
* If context LOW: run `bd mol wisp mol-<role>-patrol` to create new wisp
* If context HIGH: use `gt handoff` and exit for daemon respawn
- mol-witness-patrol.formula.toml loop-or-exit step now has clear commands
This ensures patrol agents always either create a new wisp or exit cleanly,
preventing the "session alive but idle" state that caused mail to pile up.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The hook query now falls back to checking in_progress beads assigned to the
agent when no hooked beads are found. This ensures work is not lost when
a session is interrupted after claiming work.
Previously, gt hook only looked for status=hooked beads, so work that had
been claimed but not completed appeared lost. The fix extends the query to
also include in_progress beads assigned to the agent.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Sync with mayor/rig fix: Set hook slot in CreateAgentBead and pass
beadID to UpdateAgentState.
Fixes: mi-619
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update version.go to 0.2.0
- Add comprehensive CHANGELOG.md entry for v0.2.0 (178 commits)
- Add gt info command with --whats-new flag for agent-relevant changes
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The bd slot command doesn't route correctly from town root - it only
works when run from the rig directory. This fix changes done.go to
use the rig path (filepath.Join(townRoot, ctx.Rig)) instead of
townRoot when calling slot commands.
Bug: gt polecat nuke was blocked by stale hooks on closed beads
because gt done wasn't actually clearing the hook_bead field.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
gt peek now correctly handles crew worker paths by detecting the crew/
prefix and using the proper crew session name format (gt-{rig}-crew-{name}).
Changes:
- Add CaptureSession method to Manager for raw session ID capture
- Detect crew/ prefix in peek command and use CrewSessionName
- Update help text with crew path examples
Fixes: gt-yud21
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
In multi-remote setups, the code may live on a remote other than
"origin" (e.g., "gastown" for gastown.git). The verifyCommitOnMain
function now iterates through all configured remotes to find the
one containing the default branch with the merged commit.
Changes:
- Add git.Remotes() method to list all configured remote names
- Update verifyCommitOnMain to check all remotes/<defaultBranch>
instead of only origin/<defaultBranch>
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Optimize getWorkersForIssues() from O(N×R) to O(R) subprocess calls:
- Batch sqlite queries per rig using WHERE hook_bead IN (...)
- Parallelize rig lookups with goroutines
Expected improvement: 300-600ms → 50-100ms for moderate convoys
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When repairing a stale polecat worktree, start from origin/<default-branch>
instead of the bare repo's HEAD. This ensures repaired polecats have the
latest fetched commits rather than potentially stale code.
- Add WorktreeAddFromRef to git package for creating worktrees from a ref
- RepairWorktreeWithOptions now uses origin/<default-branch> as start point
- Respects rig's configured default branch (main, master, etc.)
Based on PR #112 by markov-kernel. Test changes from that PR can be
submitted separately.
Closes#101🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: markov-kernel <markov-kernel@users.noreply.github.com>
The transient polecat model says: "Polecats exist only while working."
This removes the deprecated StateIdle and updates the codebase:
- Remove StateIdle from polecat/types.go (keep StateActive for legacy data)
- Update manager.go: Get() returns StateDone (not StateIdle) when no work
- Update manager.go: Add/Recreate return StateWorking (not StateIdle)
- Remove zombie scan logic from deacon.go (no idle polecats to scan for)
- Update tests to reflect new behavior
The correct lifecycle is now:
- Spawn: polecat created with work (StateWorking)
- Work: sessions cycle, sandbox persists
- Done: polecat signals completion (StateDone)
- Nuke: Witness destroys sandbox
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Clarify that this operation is for stale state recovery, not normal recycling:
- Recreate → RepairWorktree
- RecreateWithOptions → RepairWorktreeWithOptions
- Updated comments to explain this handles reconciliation when AllocateName
returns a name that already exists (stale state needing repair)
- Updated polecat_spawn.go output: Recreating → Repairing stale
- Updated gc command help text for consistency
The function is useful for atomic hook_bead setting during repair, so kept
rather than replacing with Remove + Add.
Fixes gt-l0lok
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
These commands transitioned polecats to idle state, violating the transient
model. From PRIMING.md: "Polecats exist only while working. One task, then nuked."
Removed:
- gt polecat done - marked polecat as done and returned to idle
- gt polecat reset - force reset polecat to idle state
- gt polecat finish - alias for done
- gt polecat sleep - deprecated transition to done state
- gt polecat wake - deprecated transition to working state
- Manager.Finish() method
- Manager.Reset() method
- Manager.Wake() method
- Manager.Sleep() method
The correct model is: polecats use 'gt done' which signals Witness for nuke.
There is no "return to idle" - only death.
(gt-32d4a)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Clarifies the three distinct lifecycle layers to prevent confusion:
- Session (Claude context): ephemeral, cycles per step
- Sandbox (worktree): persistent until nuke
- Slot (name from pool): persistent until nuke
Addresses anti-patterns like "idle polecats" and misunderstanding
what recycling means. (gt-bc6gm)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add --branch flag to `gt rig add` to specify a custom default branch
instead of auto-detecting from remote. This supports repositories that
use non-standard default branches like `develop` or `release`.
Changes:
- Add --branch flag to `gt rig add` command
- Store default_branch in rig config.json
- Propagate default branch to refinery, witness, daemon, and all commands
- Rename ensureMainBranch to ensureDefaultBranch for clarity
- Add Rig.DefaultBranch() method for consistent access
- Update crew/manager.go and swarm/manager.go to use rig config
Based on PR #49 by @kustrun - rebased and extended with additional fixes.
Co-authored-by: kustrun <kustrun@users.noreply.github.com>
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Migrate all role bead references from gt-*-role to hq-*-role using
beads.RoleBeadIDTown() function. Role beads are stored in town beads
(~/gt/.beads/) with the hq- prefix.
Changes:
- internal/cmd/prime.go: Use RoleBeadIDTown() for all roles
- internal/doctor/agent_beads_check.go: Use RoleBeadIDTown() for rig agents
- internal/polecat/manager.go: Use RoleBeadIDTown("polecat")
- internal/cmd/crew_add.go: Use RoleBeadIDTown("crew")
- internal/beads/beads.go: Update comments to document hq- convention
- Templates: Update bd show gt-deacon to bd show hq-deacon
Note: Tmux session names remain as gt-* (runtime identifiers).
Bead IDs use hq-* for town-level agents (persistent storage).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When a polecat worker is recycled via RecreateWithOptions, it now starts
from the latest fetched origin/<default-branch> instead of the stale HEAD.
Previously, `WorktreeAdd` created branches from the current HEAD, but after
fetching, HEAD still pointed to old commits. The new `WorktreeAddFromRef`
method allows specifying a start point (e.g., "origin/main").
Fixes#101
- Add mutex protection for global registry state
- Cache loaded config paths to avoid redundant file reads
- Add ResetRegistryForTesting() for test isolation
- Add BuildResumeCommand() for agent-specific session resume
- Add SupportsSessionResume() and GetSessionIDEnvVar() helpers
Fixes: gt-sn610, gt-otgn3, gt-r2eg1
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The Witness lifecycle was not reliably killing polecat tmux sessions after
POLECAT_DONE. Sessions were piling up because gt polecat nuke may fail to
kill the session due to rig loading issues or race conditions with
IsRunning checks.
Fix: Kill the tmux session FIRST and unconditionally in NukePolecat,
before calling gt polecat nuke. This ensures the session is always killed
regardless of what happens in the downstream nuke command.
The session name pattern is deterministic (gt-<rig>-<polecat>), so we can
construct it directly from the rigName and polecatName parameters.
Fixes: gt-g9ft5
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When creating agent beads for polecats or crew workers, the code was
using the rig root path (e.g., ~/gt/infra-dashboard/) instead of the
mayor/rig path where the actual beads database lives.
The rig root .beads/ directory only contains config.yaml with no
database. When bd runs from there, it walks up the directory tree
and finds the town-level beads database (with 'gm' prefix) instead
of the rig's database (with the rig's prefix like 'id'). This causes
prefix mismatch errors:
Error: prefix mismatch: database uses 'gm' but you specified 'id'
The routes.jsonl file maps rig prefixes to <rig>/mayor/rig, so the
code should always use that path for beads operations.
Changes:
- polecat/manager.go: Always use mayor/rig path, remove fallback logic
- cmd/crew_add.go: Use mayor/rig path instead of rig root
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
- Use underscores instead of stripping invalid characters
- Convert suggestion to lowercase for consistency
- Explicitly state that underscores are allowed
Before: "MyProject.jl" → "MyProjectjl"
After: "MyProject.jl" → "myproject_jl"
Closes#97
Co-Authored-By: Olivier Debeuf De Rijcker <markov-kernel@users.noreply.github.com>
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
gt costs record now auto-detects the current tmux session when
running inside tmux, so the Stop hook no longer requires --session
flag or GT_SESSION env var.
Detection order:
1. --session flag
2. GT_SESSION env var
3. GT_RIG/GT_ROLE derivation
4. Current tmux session (new)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add syscall.Flock() exclusive lock in daemon.Run() to prevent TOCTOU
race condition where concurrent 'gt daemon start' commands could spawn
multiple daemons. Only the first to acquire the lock succeeds; others
exit cleanly. Lock is per-town (in townRoot/daemon/daemon.lock) so
multiple GT instances from different directories work independently.
Also detect race losers in runDaemonStart() by comparing spawned PID
with PID file, reporting 'already running' instead of false success.
Implements agent abstraction layer to support multiple AI coding agents.
Built-in presets (E2E tested):
- Claude Code (default)
- Gemini CLI
- OpenAI Codex
Key changes:
- Add AgentRegistry with built-in presets and custom agent support
- Add TownSettings with default_agent and custom agents map
- Add Agent field to RigSettings for per-rig agent selection
- Update ResolveAgentConfig for hierarchical config resolution
- Update spawn paths to use configured agent instead of hardcoded claude
Configuration hierarchy (first match wins):
1. Rig's Runtime config (backwards compat)
2. Rig's Agent -> custom agents -> built-in presets
3. Town's default_agent setting
4. Fallback to Claude
Additional agents (aider, opencode, etc.) can be added via config file:
settings/agents.json
Addresses Issue #10: Agent Agnostic Engine with Multi-provider support
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add TownBeadsPrefix constant to agent_ids.go to centralize the "hq"
prefix string used for town-level agent beads. This makes prefix
changes easier and reduces string duplication.
Also update agent_beads_check.go to use the helper functions instead
of hardcoded strings for consistency.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Introduces a const TownBeadsPrefix = "hq" to centralize the town-level
beads prefix. Updates all hq- string literals in agent_ids.go to use
the constant, making prefix changes easier and reducing duplication.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Explain why agent bead creation failures are hard errors while role bead
creation failures are soft errors (log and continue).
Agent beads are identity beads that form the CV/reputation ledger foundation.
Role beads are documentation templates not required for agent operation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The isFirstRig parameter was no longer used - it was being assigned
to a blank identifier. Since initAgentBeads is an internal function
with only 2 callers in this repo, remove the parameter entirely.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add Dog role bead creation to the roleDefs slice, ensuring Dog
agents have their role definition created during gt install.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Agent directories (witness/, refinery/, mayor/) contained state.json files
with last_active timestamps that were never updated, making them stale and
misleading. This change removes:
- initAgentStates function that created vestigial state.json files
- AgentState type and related Load/Save functions from config package
- MayorStateValidCheck from doctor checks
- requesting_* lifecycle verification (dead code - flags were never set)
- FileStateJSON constant and MayorStatePath function
Kept intact:
- daemon/state.json (actively used for daemon runtime state)
- crew/<name>/state.json (operational CrewWorker metadata)
- Agent state tracking via beads (the ZFC-compliant approach)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Install now detects existing town-level agents via bd list to avoid relying on
bd show prefix matching, and the role slot test reads JSON from stdout only to
ignore stderr warnings.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Install now creates town role beads before agents and only skips agent creation
when the exact agent bead exists, so role slots get set reliably. Add an
integration test that asserts role slots are populated after install.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The gt doctor patrol-hooks-wired check was recommending 'gt daemon init'
which doesn't exist. The daemon is auto-initialized when running
'gt daemon start', so that's the correct command to recommend.
Fixes#94🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The integration.yml was running ./... which includes beads tests that
require database initialization. Changed to match ci.yml's scope of
./internal/cmd/... which contains the actual integration tests.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The integration.yml workflow was missing the beads CLI installation
that the main ci.yml has. This caused integration tests to fail with
"beads dependency check failed".
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds CI fix to run go generate before build steps.
- Adds claude.EnsureSettingsForRole() call in gt install after CLAUDE.md
- Adds go generate ./internal/formula/... to ci.yml (test, lint, integration jobs)
- Adds go generate ./internal/formula/... to integration.yml
The go generate step creates the embedded formula JSON files that are
gitignored but required for the go:embed directive in embed.go.
Fixes#84🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When users run `claude` directly at the town root instead of
`gt mayor start`, Claude wasn't receiving the Mayor delegation
protocol because `gt prime` never ran.
Root cause: `gt install` created CLAUDE.md but not the
.claude/settings.json with SessionStart hooks that run `gt prime`.
This adds `claude.EnsureSettingsForRole(absPath, "mayor")` to
`gt install` to ensure the Mayor always gets proper Claude settings
with hooks that enforce the delegation protocol.
Fixes#84🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously, town-level session stopping (Mayor, Boot, Deacon) was
implemented inline in gt down with separate code blocks for each
session. The shutdown order (Boot must stop before Deacon to prevent
the watchdog from restarting Deacon) was implicit in the code ordering.
Add session.TownSessions() and session.StopTownSession() to centralize
town-level session management. This provides a single source of truth
for the session list, shutdown order, and graceful/force logic.
Refactor gt down to use these helpers instead of inline logic.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update all callers of deprecated MayorBeadID()/DeaconBeadID() to use
MayorBeadIDTown()/DeaconBeadIDTown() which return hq- prefix IDs for
town-level beads storage.
Changes:
- internal/daemon/lifecycle.go: identityToAgentBeadID and checkStaleAgents
- internal/cmd/prime.go: getAgentBeadID
- internal/cmd/molecule_status.go: buildAgentBeadID
- internal/cmd/prime_test.go: update expected values to hq-*
- Comments updated to reflect hq- prefix for town-level agents
The deprecated functions remain for backward compatibility and are used
by the migration tool (migrate_agents.go).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase 5 of epic gt-4r1ph (align agent/role beads with two-level architecture):
- Create docs/architecture.md with agent bead storage table documenting
the correct two-level architecture:
- Town beads (~/gt/.beads/): hq-mayor, hq-deacon, hq-*-role
- Rig beads (<rig>/.beads/): <prefix>-<rig>-witness, <prefix>-<rig>-refinery
- Update internal/rig/manager.go initAgentBeads() comments with MIGRATION
NOTEs explaining current state vs target architecture (gt-4r1ph)
- Close PR #50 with explanation that the fix direction was wrong
CLAUDE.md templates already correctly document hq-* for town beads and
project prefix for rig beads.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase 1: Create agent_ids.go with town-level bead ID helpers
- MayorBeadIDTown(), DeaconBeadIDTown(), DogBeadIDTown()
- RoleBeadIDTown() and role-specific helpers (hq-*-role)
- Add deprecation notices to old gt-* prefix functions
Phase 2: Create town-level agent beads during gt install
- initTownAgentBeads() creates hq-mayor, hq-deacon agent beads
- Creates role beads: hq-mayor-role, hq-deacon-role, etc.
- Update rig/manager.go to use rig beads for Witness/Refinery
This aligns with the two-level beads architecture:
- Town beads (~/gt/.beads/): hq-* prefix for Mayor, Deacon, roles
- Rig beads (<rig>/.beads/): <prefix>-* for Witness, Refinery, Polecats
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement two-level beads architecture for agent lookups:
- Town-level agents (Mayor, Deacon) now use hq- prefix and are
looked up in town beads (~/.beads/)
- Rig-level agents continue using rig prefix (e.g., gt-) and are
looked up in rig beads
Changes:
- Add MayorBeadIDTown(), DeaconBeadIDTown(), DogBeadIDTown() helpers
- Add GetTownBeadsPath() for town beads path resolution
- Update gt status to pre-fetch town-level agent beads
- Update agentIDToBeadID() to use town-level IDs
- Update agent_beads_check.go to check/fix in correct tier
- Update agentAddressToIDs() in deacon.go
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add new helper functions for town-level agent bead IDs:
- MayorBeadIDTown() → "hq-mayor"
- DeaconBeadIDTown() → "hq-deacon"
- DogBeadIDTown(name) → "hq-dog-<name>"
- RoleBeadIDTown(role) → "hq-<role>-role"
These use the hq- prefix for town-level beads storage, distinct from
the gt- prefix used for rig-level beads.
Mark MayorBeadID() and DeaconBeadID() as deprecated in favor of the
new *Town() variants.
(gt-y24km)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements Phase 4 of the two-level beads architecture migration:
- Add hq- prefix helper functions for town-level agent beads
- Add CreateWithID method for deterministic bead creation
- Create gt migrate-agents command with dry-run/execute modes
- Migrate gt-mayor/gt-deacon to hq-mayor/hq-deacon in town beads
- Migrate role beads (gt-*-role) to town beads (hq-*-role)
- Add migration labels to old beads for tracking
- Idempotent: skips already-migrated beads
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When using gt sling with --quality=shiny, the mol bond command was
failing with "mol bond requires direct database access" error. This
was because bd daemon can be slow to start or unavailable, and mol
bond requires direct database access.
Fix: Added --no-daemon flag to the bd mol bond invocation in sling.go
at line 407. This bypasses the daemon and uses direct database access
for molecule bonding operations.
Fixes gt--4hz
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
When `gt install` creates a new HQ, formulas were not being provisioned
to `.beads/formulas/`. This embeds the formula library into the gt binary
and copies them during installation.
- Add go:generate directive to copy formulas from .beads/formulas/
- Add internal/formula/embed.go with ProvisionFormulas() function
- Call ProvisionFormulas() from runInstall() after beads init
- Add generate target to Makefile (build depends on it)
- Add TestInstallFormulasProvisioned integration test
- Log warning if formula stat fails with unexpected error
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Comprehensive end-to-end tests for convoy dashboard:
- TestE2E_Server_FullDashboard: Full dashboard with all sections
- TestE2E_Server_ActivityColors: Activity color rendering (green/yellow/red)
- TestE2E_Server_MergeQueueEmpty: Always-visible section with empty state
- TestE2E_Server_MergeQueueStatuses: All PR status combinations
- TestE2E_Server_HTMLStructure: HTML document structure validation
- TestE2E_Server_RefineryInPolecats: Refinery appears in workers section
Tests use httptest.NewServer for real HTTP server testing.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Added 11 new integration tests covering:
- Error handling: FetchConvoys error returns 500
- Merge queue rendering: PR numbers, repos, CI status badges
- Empty merge queue state
- Polecat workers rendering: names, rigs, activity colors, status hints
- Work status rendering: complete/active/stale/stuck/waiting states
- Progress bar rendering with percentage calculation
- HTMX auto-refresh attributes (hx-get, hx-trigger, every 10s)
- Full dashboard integration with all sections
- Non-fatal errors: merge queue/polecat failures don't break convoys
Tests use MockConvoyFetcher interface to simulate various data scenarios.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The Refinery Merge Queue section now displays always, even when idle:
- Shows 'No PRs in queue' message when merge queue is empty
- Displays PR table with number, title, CI status, and mergeable when PRs exist
- Added empty-state-inline CSS for consistent styling
Previously the section was hidden entirely when no PRs existed.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Document the web dashboard for monitoring Gas Town:
- Run command: gt dashboard --port 8080
- Features: convoy tracking, polecat workers, refinery status
- Auto-refresh every 10 seconds
- Work status indicator reference table
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
session_activity only updates on session-level events. window_activity
tracks actual window activity (keypresses, output) for more accurate
last activity times in the Polecat Workers section.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The status column now shows computed work status based on progress and activity:
- "complete" (green) - all tracked items are done
- "active" (green) - recent polecat activity (within 1 min)
- "stale" (yellow) - older activity (1-5 min)
- "stuck" (red) - stale activity (5+ min)
- "waiting" (gray) - no assignee/activity
Previously the status column always showed "open" since we only fetch
open convoys, making it static and uninformative.
Changes:
- templates.go: Add WorkStatus field to ConvoyRow, add workStatusClass func
- fetcher.go: Add calculateWorkStatus() to compute status from progress/activity
- convoy.html: Add work status badge styling, use WorkStatus in table
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The misspell linter flags "cancelled" but this is the actual value
returned by GitHub's Check Runs API (British spelling). Added nolint
directive with explanation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Merges PR #85 (fix/convoy-last-activity) into PR #71 (feature/convoy-dashboard).
Resolved conflict in fetcher.go by taking the simplified tmux-based activity tracking.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add FetchPolecats() to fetch tmux session data for active polecats
- Display polecat name, rig, activity status (green/yellow/red)
- Show status hint from last line of pane output
- Add FetchMergeQueue stub for interface compliance
- Update handler to pass polecats data to template
- Add Polecat Workers table section to convoy.html
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The template was updated to refresh every 10s (2bb1f1e) but the test
still expected 30s. Update test to match the new intended behavior.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Improvements to convoy dashboard last_activity column:
1. When issues have no assignee:
- Fall back to issue's updated_at timestamp
- Show age with "(unassigned)" suffix, e.g., "2m (unassigned)"
2. When issues have assignee but no active tmux session:
- Show "idle" instead of "no activity"
3. Added UpdatedAt field to track issue timestamps
This provides better context for convoys that haven't been assigned yet.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The convoy dashboard last_activity column was showing "no activity" because
the old code looked for agent records in beads databases at wrong paths.
Changed approach:
- Use the issue's assignee field (e.g., "roxas/polecats/dag")
- Parse assignee to get rig and polecat name
- Query tmux for session activity directly (#{session_activity})
This is more reliable since it uses actual tmux session state instead of
trying to find agent records in beads databases.
Fixes hq-kdhf
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The tmux send-keys Enter key was unreliable because SendKeys used only
100ms debounce while NudgeSession (known to work) uses 500ms.
Root cause: When agents start other agents or inject startup commands,
they use SendKeys() which had only 100ms debounce. This is insufficient
for Claude Code to process the paste before Enter arrives.
The fix increases DefaultDebounceMs from 100ms to 500ms, making all
SendKeys calls as reliable as NudgeSession calls.
Fixes: hq-y9id
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Complete convoy dashboard feature with real-time status tracking:
- Activity package: LastActivity calculation with color thresholds
(green <2min, yellow 2-5min, red >5min)
- Web package: Template, handler, fetcher for convoy list
- CLI: `gt dashboard [--port=8080] [--open]` command
- Browser E2E tests with rod (headless Chrome)
Features:
- Real-time convoy status with htmx auto-refresh (30s)
- Progress tracking for each convoy
- Last activity indicator with color coding
- Empty state handling
Supersedes: PRs #55, #57, #58, #65, #66🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The rigs/ directory was created by gt install but never used by
gt rig add, which puts rigs at the town root. Rather than restructure
the entire codebase to use rigs/, we remove the unused directory.
Flat structure is fine - similar to Android top-level layout with
100+ subprojects. Rigs at root works well and avoids a breaking change.
Closes#74🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fixes nested workspace detection and symlink path issues in workspace.Find()
- Remove filepath.EvalSymlinks() for consistency with os.Getwd()
- Add isInWorktreePath() to detect polecats/crew directories
- Continue walking up to outermost workspace when in worktree paths
- Add integration tests for symlink and nested workspace scenarios
- gt install now creates ~/gt/.claude/commands/ with all commands
- Removed per-workspace provisioning from crew/polecat managers
- Updated bd doctor to check town-level instead of per-workspace
- All agents inherit via Claude directory traversal
This eliminates duplicate /handoff skills in the picker.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update the archive command to accept variadic arguments like bd close,
allowing users to archive multiple messages in a single command.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Updates HandlePolecatDone to auto-nuke polecats immediately after MR submission
when cleanup_status=clean. This separates polecat lifecycle from MR lifecycle:
- Polecat lifecycle: spawning → working → mr_submitted → nuked
- MR lifecycle: created → queued → processed → merged (handled by Refinery)
Key changes:
- Try auto-nuke for ALL POLECAT_DONE messages regardless of MR status
- If cleanup_status=clean (branch pushed), nuke immediately
- If dirty state, create cleanup wisp for manual intervention
- Cleanup wisps are now exception handling, not the normal flow
Conflict resolution is handled by the Refinery, which creates NEW tasks
for NEW polecats when merge conflicts are detected.
(gt-si8rq.9)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Reverts the session naming changes from PR #70. Multi-town support
on a single machine is not a real use case - rigs provide project
isolation, and true isolation should use containers/VMs.
Changes:
- MayorSessionName() and DeaconSessionName() no longer take townName parameter
- ParseSessionName() handles simple gt-mayor and gt-deacon formats
- Removed Town field from AgentIdentity and AgentSession structs
- Updated all callers and tests
Generated with Claude Code
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add progress feedback during slow clone operations (30+ seconds)
- Fix README Quick Start to match actual workflow (--git flag, crew add)
- Update install output to use 'gt mayor attach' consistently
- Clarify "Next steps" wording in rig add output
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Refinery monitoring to daemon heartbeat (ensureRefineriesRunning)
- Add circuit breaker: agents marked dead by checkStaleAgents() are
now force-killed and restarted, even if Claude process is alive
- Fixes zombie Claude sessions that werent updating their bead state
The circuit breaker flow:
1. Agent gets stuck (stops updating bead state)
2. After 15 minutes: checkStaleAgents() marks bead as dead
3. On next heartbeat: ensure*Running() sees state=dead
4. Force-kill session and restart fresh
Generated with Claude Code
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updates mol-witness-patrol.formula.toml to document the new ephemeral model:
- Added Ephemeral Polecat Model section explaining lifecycle separation
- Updated POLECAT_DONE handling to describe immediate auto-nuke
- Updated process-cleanups to focus on exception handling (dirty polecats)
- Updated survey-workers Step 4a for ephemeral done polecat handling
- Updated patrol-cleanup for ephemeral model expectations
Key principle: Polecat lifecycle is separate from MR lifecycle.
Polecats are recyclable immediately after MR submission.
(gt-si8rq.9)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Runs integration tests on PRs that touch install, rig, config, or routing code.
Uses -tags=integration build tag with 5-minute timeout and Go module caching.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updates HandlePolecatDone to auto-nuke polecats immediately after MR submission
when cleanup_status=clean. This separates polecat lifecycle from MR lifecycle:
- Polecat lifecycle: spawning → working → mr_submitted → nuked
- MR lifecycle: created → queued → processed → merged (handled by Refinery)
Key changes:
- Try auto-nuke for ALL POLECAT_DONE messages regardless of MR status
- If cleanup_status=clean (branch pushed), nuke immediately
- If dirty state, create cleanup wisp for manual intervention
- Cleanup wisps are now exception handling, not the normal flow
Conflict resolution is handled by the Refinery, which creates NEW tasks
for NEW polecats when merge conflicts are detected.
(gt-si8rq.9)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
CI: Add integration test job that runs go test -tags=integration for
install, rig, and beads routing tests.
Crew lifecycle: Pass startup beacon as Claude's initial prompt instead
of nudging after startup. Removes timing-dependent sleep/nudge sequence.
Also removes redundant SetEnvironment calls (env vars already exported
in BuildCrewStartupCommand).
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Session names `gt-mayor` and `gt-deacon` were hardcoded, causing tmux
session name collisions when running multiple towns simultaneously.
Changed to `gt-{town}-mayor` and `gt-{town}-deacon` format (e.g.,
`gt-ai-mayor`) to allow concurrent multi-town operation.
Key changes:
- session.MayorSessionName() and DeaconSessionName() now take townName param
- Added workspace.GetTownName() helper to load town name from config
- Updated all callers in cmd/, daemon/, doctor/, mail/, rig/, templates/
- Updated tests with new session name format
- Bead IDs remain unchanged (already scoped by .beads/ directory)
Fixes#60🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The handleSuccessFromQueue function was missing critical steps that
exist in the legacy handleSuccess function:
1. Fetch and update the MR bead with merge_commit SHA and close_reason
2. Close the MR bead with CloseWithReason("merged", mr.ID)
Without these steps, the MR bead stayed "open" in beads even after the
queue file was deleted. This caused Mayor (which queries beads for open
merge-requests) to think there were pending MRs while Refinery (which
uses the queue) reported completion.
Fixes#46
When sending messages to Claude sessions via tmux, the Enter key send
could fail silently. This caused polecats to receive their initial
prompt but never submit it - the message appeared in Claude's input
area but Enter was never pressed.
Add retry logic (up to 3 attempts with 200ms delays) for the Enter
send step in both NudgeSession() and NudgePane(). This ensures message
submission is more reliable even if tmux has transient issues.
Fixes#41
Adds RemoteDefaultBranch() to git.go that detects the repo's actual
default branch by checking origin/HEAD, then falling back to checking
for origin/master or origin/main.
Updates done.go to use this detection instead of hardcoded "main":
- Line 168: CommitsAhead now uses detected default branch
- Line 173: Error message uses detected branch name
- Line 187: Target branch defaults to detected branch
Fixes repos using 'master' as default branch (pre-2020 repos).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Steve Yegge <steve.yegge@gmail.com>
PropulsionNudgeForRole now accepts a workDir parameter and reads
session ID from .runtime/session_id to append [session:xxx] to the
nudge message. This enables Claude Code's /resume picker to discover
Gas Town sessions.
(gt-u49zh)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add LastActivity calculation for convoy dashboard (hq-x2xy)
Adds internal/activity package with color-coded activity tracking:
- Green: <2 minutes (active)
- Yellow: 2-5 minutes (stale)
- Red: >5 minutes (stuck)
Features:
- Calculate() function returns Info with formatted age and color class
- Helper methods: IsActive(), IsStale(), IsStuck()
- Handles edge cases: zero time, future time (clock skew)
Tests: 8 test functions with 25 sub-tests covering all thresholds.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add convoy dashboard HTML template with Last Activity (hq-fq1g)
Adds internal/web package with convoy dashboard template:
- convoy.html with Last Activity column and color coding
- Green (<2min), Yellow (2-5min), Red (>5min) activity indicators
- htmx auto-refresh every 30 seconds
- Progress bars for convoy completion
- Status indicators for open/closed convoys
- Empty state when no convoys
Also includes internal/activity package (dependency from hq-x2xy):
- Calculate() returns Info with formatted age and color class
- Helper methods: IsActive(), IsStale(), IsStuck()
Tests: 6 template tests + 8 activity tests, all passing.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add convoy list handler with activity data (hq-3edt)
Adds HTTP handler that wires convoy dashboard template to real data:
- ConvoyHandler: HTTP handler for GET / rendering convoy dashboard
- LiveConvoyFetcher: Fetches convoys from beads with activity data
- ConvoyFetcher interface: Enables mocking for tests
Features:
- Fetches open convoys from town beads
- Calculates progress (completed/total) from tracked issues
- Gets Last Activity from worker agent beads
- Color codes activity: Green (<2min), Yellow (2-5min), Red (>5min)
Includes dependencies (not yet merged):
- internal/activity: Activity calculation (hq-x2xy)
- internal/web/templates: HTML template (hq-fq1g)
Tests: 5 handler tests + 6 template tests + 8 activity tests = 19 total
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add 'gt dashboard' CLI command (hq-s1bg)
Add dashboard command to start the convoy tracking web server.
Usage: gt dashboard [--port=8080] [--open]
Features:
- --port: Configurable HTTP port (default 8080)
- --open: Auto-open browser on start
- Cross-platform browser launch (darwin/linux/windows)
- Graceful workspace detection
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
tmux has-session -t does prefix matching by default, so "gt-deacon-boot"
would match when checking for "gt-deacon". This caused gt start to think
the Deacon was running when only a stale gt-deacon-boot session existed.
Using "=" prefix forces exact matching in tmux.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Enables gt prime to receive session metadata from LLM runtime hooks.
When called with --hook, reads JSON from stdin containing session_id
and persists it to .runtime/session_id for use by PropulsionNudge.
- Add --hook flag for hook mode
- Parse Claude Code session JSON from stdin
- Support GT_SESSION_ID environment variable fallback
- Persist session ID to .runtime/session_id
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Address review comment: the test now explicitly asserts that ResolveBeadsDir
follows exactly one level of redirect, returning intermediate (not canonical).
The implementation intentionally does NOT follow chains transitively - it stops
at the first resolved path and prints a warning about the detected chain.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Use git --reference-if-able when a local repo is provided so rigs and crew share objects without changing remotes.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When the daemon checks if Deacon/Witness is running, it first checks the
agent bead state. If this check fails (bead not found, JSON parse error,
or stale state), it would previously attempt to restart the session -
even if the tmux session was perfectly healthy.
This caused "session already exists" errors when:
1. Agent bead state couldn't be read (prefix mismatch, missing bead)
2. But the tmux session was actually running with Claude active
Fix: Add a tmux session health check as fallback before attempting restart.
If the session exists AND Claude is running in it, skip the restart and
log that we're preserving the healthy session despite stale bead state.
This maintains ZFC compliance (still trusts agent bead as primary source)
while adding a defensive check to prevent unnecessary session kills.
Fixes#63🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Add tests verifying that done.go correctly uses beads.ResolveBeadsDir()
to follow .beads/redirect files. This is critical for polecat/crew
worktrees that redirect to a shared mayor/rig/.beads directory.
Tests cover:
- Redirect followed from polecat directory
- Both ExitCompleted (line 181) and ExitPhaseComplete (line 277) paths
- Fallback behavior when no redirect exists
- Empty redirect file handling
- Circular redirect protection
- Redirect chain handling
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
gt done was not following .beads/redirect files, causing it to fail
in worktrees where beads are redirected to a shared location.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The Quick Start section incorrectly showed `cd ~/gt && gt prime` as the
way to enter the Mayor's office. However, `gt prime` only outputs role
context to stdout (for use in Claude Code prompt hooks) - it doesn't
start or attach to any session.
Changed to `gt mayor attach` which properly attaches to the Mayor tmux
session (and auto-starts it if not running).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When a crew or other agent dispatches work to a polecat using `gt sling`,
the polecat now tracks who dispatched the work and sends them a completion
notification when running `gt done`.
Changes:
- Add DispatchedBy field to AttachmentFields in beads/fields.go
- Store dispatcher agent ID in bead when slinging (both direct and formula)
- Check for dispatcher in done.go and send WORK_DONE notification to them
This fixes the orchestration issue where crews were left waiting because
polecats only notified the Witness on completion, not the dispatcher.
Fixes: id-c17
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
New molecule formula mol-polecat-conflict-resolve defines the workflow for
polecats handling merge conflict resolution tasks:
1. Load task and extract metadata from conflict-resolution bead
2. Acquire merge slot (prevents racing via "Monkey Knife Fight" prevention)
3. Checkout the conflicting branch
4. Rebase onto main and resolve conflicts
5. Run tests to verify resolution
6. Push resolved changes directly to main (bypasses queue)
7. Close original MR bead and source issue
8. Release merge slot for next waiter
9. Clean up and close the conflict-resolution task
This completes the polecat side of the ephemeral merge workflow architecture.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Validates:
- bd show routes to correct rig based on issue ID prefix
- bd show hq-* routes to town beads
- Redirect chains (.beads/redirect) resolve correctly
- bd list works from polecat/crew directories with redirects
- Prefix conflicts are detected in routes.jsonl
- Routes loading, appending, and removal work correctly
- GetPrefixForRig returns correct prefix for rig name
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The tmux session name "gt-deacon-boot" was causing HasSession("gt-deacon")
to return true due to tmux prefix matching behavior. This made the daemon
think the Deacon was running when only Boot was active, and caused commands
targeting "gt-deacon" to be sent to Boot session instead.
The fix renames Boot session from "gt-deacon-boot" to "gt-boot", which
has no prefix overlap with "gt-deacon".
Fixes: gt-sgzsb
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The gt status command now properly reconciles the tmux session
existence with the agent bead state to surface mismatches:
- If session exists AND bead says running/idle → "running"
- If session exists BUT bead says stopped/dead → "running [bead: <state>]"
- If session gone BUT bead says running/idle → "running [dead]"
- If session gone AND bead says stopped → "stopped"
This surfaces the key mismatch case where a tmux session is actually
running but the bead state incorrectly says "stopped" or "dead".
Fixes: gt-doih4
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The daemon was failing to restart agents when zombie tmux sessions existed
(session alive but Claude dead). Added EnsureSessionFresh() helper to
tmux package that:
- Checks if session exists
- If exists but Claude not running (zombie), kills the session
- Creates fresh session
Updated all daemon session creation points to use EnsureSessionFresh:
- ensureDeaconRunning()
- ensureWitnessRunning()
- restartPolecatSession()
- restartSession() in lifecycle.go
Added tests for the new helper function. (gt-j1i0r)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
gt witness start and gt refinery start now detect zombie sessions
(tmux alive but Claude dead) and automatically kill and recreate them.
This makes the start commands idempotent:
- If no session exists → create new session
- If session exists and healthy → do nothing (already running)
- If session exists but zombie → kill and recreate
Previously users had to manually run stop then start, or use restart.
Closes: gt-ekc5u
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Shows binary modification time in gt daemon status and warns when
the binary is newer than the running process, suggesting a restart.
This helps detect when bug fixes or new features aren't active because
the daemon is running old code.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Merged with conflict resolution after PR #34. Key fixes:
- Remove invalid --no-agents flag from bd init
- Agent beads now created in town beads (gt-* prefix) using NewWithBeadsDir
- Use canonical WitnessBeadID/RefineryBeadID functions
- Update test to verify town beads usage
Original PR by @PepijnSenders, conflict resolution applied.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add Claude Code Stop hook that automatically records session costs when
sessions end. The hook calls `gt costs record` which now can derive the
session name from GT_* environment variables (GT_RIG, GT_POLECAT, GT_CREW,
GT_ROLE).
Changes:
- Add deriveSessionName() to infer tmux session name from environment
- Add Stop hook to settings-autonomous.json and settings-interactive.json
- Add unit tests for deriveSessionName function
When a Gas Town session ends, the Stop hook fires and records the session
cost as a bead event. Costs then appear in `gt costs --today` output.
Closes: gt-ntzhc
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Claude Code v2.0+ deprecated .claude/commands/ in favor of .claude/skills/.
This migrates the handoff skill to the new format with proper YAML frontmatter.
Changes:
- Create .claude/skills/handoff/SKILL.md with frontmatter
- Remove deprecated .claude/commands/handoff.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds merge-slot integration to the Refinery's Engineer for serializing
conflict resolution. When a conflict is detected:
- Acquire the merge slot before creating a conflict resolution task
- If slot is held, defer task creation (MR stays in queue)
- Release slot after successful merge
This prevents cascading conflicts from multiple polecats racing to
resolve conflicts simultaneously.
Adds MergeSlot wrapper functions to beads package for slot operations.
(gt-4u49x)
🤖 Generated with Claude Code
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When merge conflicts occur, the Refinery now creates a conflict resolution
task and blocks the MR on that task, allowing the queue to continue to the
next MR without waiting.
Changes:
- Add BlockedBy field to mrqueue.MR for tracking blocking tasks
- Update handleFailureFromQueue to set BlockedBy after creating conflict task
- Add ListReady method to mrqueue that filters out blocked MRs
- Add ListBlocked method for monitoring blocked MRs
- Add IsBeadOpen, ListReadyMRs, ListBlockedMRs helpers to Engineer
- Add 'gt refinery ready' command (unclaimed AND unblocked MRs)
- Add 'gt refinery blocked' command (shows blocked MRs)
When the conflict resolution task closes, the MR unblocks and re-enters
the ready queue for processing.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The agent-beads-exist check was hardcoding '/mayor/rig' suffix when
constructing the beads path, but routes.jsonl can contain paths like
'my-saas' without this suffix.
This caused the check to look for beads in the wrong location:
- Expected: <town>/<route-path>/.beads (e.g., ~/gt/my-saas/.beads)
- Actual: <town>/<rig>/mayor/rig/.beads (e.g., ~/gt/my-saas/mayor/rig/.beads)
The fix stores the full route path and uses it directly when creating
the beads client, instead of reconstructing an assumed path structure.
Fixes agent beads not being found when routes use simple rig names.
- startCrewMember: now uses BuildCrewStartupCommand (was GetRuntimeCommand)
- refinery/manager.go: now uses BuildAgentStartupCommand (was GetRuntimeCommand)
Both now properly inject BD_ACTOR and GT_ROLE so seance can identify
sessions correctly. This completes the seance metadata fix started in
the previous commit.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
gt crew start was using GetRuntimeCommand which doesn't set BD_ACTOR,
GT_RIG, GT_CREW, etc. This caused seance to misidentify crew sessions
(showing as "mayor" instead of their actual identity).
Now uses BuildCrewStartupCommand like gt crew restart does, ensuring
proper env var injection for session identification. (gt-jwxgb)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Added 'spawn' as an alias for 'start' in the following commands:
- gt witness start → also gt witness spawn
- gt refinery start → also gt refinery spawn
- gt deacon start → also gt deacon spawn
- gt crew start → also gt crew spawn
This improves discoverability since agents are guessing 'spawn'
when trying to start roles.
Note: gt polecat does not have a 'start' command - polecat spawning
is handled via 'gt sling'.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Allows slinging multiple beads in a single command:
gt sling gt-abc gt-def gt-ghi gastown
Each bead gets its own freshly spawned polecat. This parallelizes
work dispatch without running gt sling N times manually.
Changes:
- Updated Args from RangeArgs(1,2) to MinimumNArgs(1)
- Added batch mode detection when len(args)>2 and last arg is a rig
- Added runBatchSling() to handle multiple beads with progress tracking
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds 'gt rig restart <rig>...' command that stops then starts witness
and refinery for one or more rigs. Supports --force and --nuclear flags
like the existing start/stop commands. (gt-s7t1h)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When adding a crew member with 'gt crew add' or spawning a polecat,
provision the .claude/commands/ directory with standard slash commands
like /handoff. This ensures all agents have Gas Town utilities even if
the source repo does not have them tracked.
Changes:
- Add embedded commands templates (internal/templates/commands/)
- Add ProvisionCommands() to templates package
- Call ProvisionCommands from crew and polecat managers
- Add gt doctor commands-provisioned check with --fix support
Add `gt convoy stranded` command to detect convoys with ready work but
no workers processing them. A convoy is stranded when it has open,
unblocked issues with no live assignee.
- New command outputs stranded convoy IDs with ready issue counts
- Supports --json for automation by Deacon patrol
- Checks blocked status via bd blocked
- Verifies assignee session liveness via tmux
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
PROBLEM: Agents were reading formula files directly and manually creating beads
for each step, rather than using the cook→pour→molecule pipeline.
FIXES:
- polecat-CLAUDE.md: Changed "following the formula" to "work through your
pinned molecule" and added explicit anti-pattern warning
- mol-polecat-work.formula.toml: Added note that formula defines template,
use bd ready to find step beads
- docs/molecules.md: Added "Common Mistake" section with WRONG/RIGHT examples
- mol-*.formula.toml (5 files): Changed "execute this formula" to "work
through molecules (poured from this formula)"
The key insight: Formulas are source templates (like source code). You never
read them directly. The cook → pour pipeline creates step beads for you.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Shows convoys with their tracked issues in a tree format:
🚚 hq-cv-abc: Convoy Name (3/5)
├── ✓ gt-123: Closed issue
├── ▶ gt-456: In progress issue
└── ○ gt-789: Pending issue
Makes convoy progress visible at a glance without running 'gt convoy status' on each one.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements priority scoring for merge queue ordering:
## Changes to gt mq list
- Add SCORE column showing priority score (higher = process first)
- Sort MRs by score descending instead of simple priority
- Add CONVOY column showing convoy ID if tracked
## New gt mq next command
- Returns highest-score MR ready for processing
- Supports --strategy=fifo for FIFO ordering fallback
- Supports --quiet for just printing MR ID
- Supports --json for programmatic access
## Changes to Refinery
- Queue() now sorts by priority score instead of simple priority
- Uses ScoreMR from mrqueue package for consistent scoring
## MR Fields Extended
- Added retry_count, last_conflict_sha, conflict_task_id
- Added convoy_id, convoy_created_at for convoy tracking
- These fields feed into priority scoring function
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Document bash/zsh/fish completion setup in README.
Cobra provides `gt completion <shell>` out of the box.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
After squash merge, polecat branches have different commit SHAs than main
even though the content is identical. This was causing false "unpushed
commits" warnings during nuke safety checks.
Now uses `git diff` to verify if content differs from main, rather than
just counting commits ahead. If diff is empty, content is on main
(via squash merge) and nuke is safe. (gt-fo9iz)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add retry_count, last_conflict_sha, and conflict_task_id fields to MR bead
descriptions when created via `gt done`. These are initialized at creation
time and will be updated by the Refinery when handling merge conflicts.
- retry_count: 0 (number of conflict-resolution cycles)
- last_conflict_sha: null (SHA of main when conflict occurred)
- conflict_task_id: null (link to conflict-resolution task if any)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add support for signaling phase completion when a polecat needs to wait
on a gate before continuing. The --phase-complete flag with --gate ID
allows polecats to hand off control while awaiting external conditions.
Changes:
- done.go: Add --phase-complete and --gate flags, PHASE_COMPLETE exit type
- protocol.go: Add Gate field to PolecatDonePayload
- handlers.go: Handle PHASE_COMPLETE by recycling session (keep worktree)
- beads.go: Add AddGateWaiter method for gate registration
This enables multi-phase molecule workflows with async coordination (bd-gxb4)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Town-level agents (mayor/, deacon/) need trailing slash to match
addressToIdentity() normalization.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Three issues were causing errors when running `gt rig add`:
1. **bd init flag**: Removed non-existent `--no-agents` flag from bd init
command that was causing silent failures.
2. **BEADS_DIR for init**: Added explicit BEADS_DIR to bd init and migrate
commands to prevent bd from finding parent directory databases.
3. **Agent beads location**: Agent beads now go in town beads (gt-* prefix)
instead of rig beads. This is necessary because:
- Agent IDs use canonical gt-* prefix (e.g., gt-tribal-witness)
- Rig beads use rig-specific prefixes (e.g., tr-*)
- bd strictly validates ID prefix against database prefix
- Town beads must be initialized with `gt` prefix
4. **beads.run() BEADS_DIR**: Modified to explicitly pass BEADS_DIR in child
process environment to ensure bd uses the correct database.
5. **Agent ID prefix**: Use WitnessBeadID/RefineryBeadID (canonical gt-*)
instead of WithPrefix variants.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Convoys in town beads track issues in rig beads via external:rig:id
references. When bd close runs in a rig, the convoy auto-close logic
only checks the local database, missing convoys in town beads.
This adds `gt convoy check` to bridge that gap:
- Finds all open convoys in town beads
- Checks if all tracked issues (across rigs) are closed
- Auto-closes completed convoys
- Sends notification if convoy has notify address
Can be called manually or by deacon patrol.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When running bd update commands for hq-* beads from a polecat worktree,
the redirect mechanism only exposes gt-* beads. This fix sets BEADS_DIR
to the town-level .beads directory so hq-* beads are accessible.
Also adds NewWithBeadsDir() constructor to beads package for explicit
cross-database access when needed.
Previously, when running `gt polecat nuke <name> <rig>`, the parseAddress
function would infer the rig from cwd for each argument, causing a plain
rig name to be misinterpreted as a polecat name. For example, running from
a gastown directory:
gt polecat nuke angharad gastown --force
Would try to nuke both gastown/angharad AND gastown/gastown.
Now both runPolecatNuke and runPolecatRemove validate that each address
argument contains "/" before parsing, enforcing the documented
`<rig>/<polecat>` format and preventing this misinterpretation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When first arg to `gt convoy create` looks like a beads issue ID
(e.g., gt-abc, bd-xyz), treat all args as issues and auto-generate
the convoy name from the first issue title.
This prevents the bug where `gt convoy create gt-abc` would use
"gt-abc" as the convoy name instead of recognizing it as an issue
to track.
(gt-7qyfh)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update polecat template to reflect the new --exit flag behavior:
- Completion checklist now uses `gt done --exit` instead of waiting
- Remove "Wait for Witness" step - polecats now self-terminate
- Update Polecat Contract to reflect new exit flow
- Remove outdated "Don't exit yourself" guidance
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The command already clears all messages by default, but agents naturally
try --all when they want to clear everything. Adding it as a no-op flag
improves discoverability and natural usage patterns.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When slinging to an existing polecat, the bd update command was running
from town root which doesn't support prefix-based routing for writes.
Fix: Capture the target agent's working directory from resolveTargetAgent
and use it as hookWorkDir. This ensures bd update runs from the polecat's
worktree where the .beads/redirect file enables routing to the correct
database.
Also fixed the self-sling case to capture and use selfWorkDir.
When cloning a repo that has .beads/ tracked in git, the beads.db file
is missing (gitignored) but issues.jsonl exists. The bd commands fail
with "prefix mismatch" because:
1. No beads.db means no prefix config stored
2. bd falls back to walking up to find a database
3. Finds town-level database with 'hq-' prefix
Fix: After detecting the source repo's prefix from config.yaml or issues,
run 'bd init --prefix <prefix>' to create the database and auto-import
from issues.jsonl. Also updated initAgentBeads to use the correct beads
location (mayor/rig/.beads for repos with tracked beads).
When Claude starts with --dangerously-skip-permissions, it shows a warning
dialog requiring Down+Enter to accept. This blocked automated polecat and
agent startup.
Added AcceptBypassPermissionsWarning() to tmux package that:
- Checks if the warning dialog is present by capturing pane content
- Only sends Down+Enter if "Bypass Permissions mode" text is found
- Avoids interfering with sessions that don't show the warning
Updated all Claude startup locations:
- session/manager.go (polecat sessions)
- cmd/up.go (mayor, witness, crew, polecat cold starts)
- daemon/daemon.go (crashed polecat restarts)
- daemon/lifecycle.go (role session starts)
Polecats need access to town-level beads (hq- prefix) for hooks and
convoys. Update session manager to set BEADS_DIR to town root .beads/
instead of rig-level .beads/.
Also update mail.go's findLocalBeadsDir() to respect the BEADS_DIR
environment variable, which is necessary for polecats using
redirect-based beads access.
When slinging work to a polecat, run bd commands from the polecat's
worktree directory instead of town root. This enables redirect-based
routing to work correctly since the polecat's .beads/redirect file
points to the canonical database location.
Adds hookWorkDir variable to track the polecat's clone path and passes
it to updateAgentHookBead for proper beads access.
Route to the correct beads location based on whether the source repo
has .beads/ tracked in git:
- If source has .beads/ tracked: route to mayor/rig/.beads
- Otherwise: route to rig root .beads/ (created by initBeads)
Updates both route registration in rig.go and polecat manager's
NewManager/setupSharedBeads to use consistent conditional logic.
When adding a rig from a source repo that has .beads/ tracked in git,
detect and use the project's existing prefix instead of generating a
new one. This prevents prefix mismatch errors when accessing existing
issues via bd commands.
Adds detectBeadsPrefixFromConfig() which reads the prefix from either
config.yaml or by parsing the first issue ID from issues.jsonl.
Add --exit flag to `gt done` that terminates the Claude session
immediately after submitting the MR to the merge queue. This prevents
polecats from sitting idle (and wasting money) while waiting for the
Witness to kill them.
Changes:
- Rename existing --exit flag to --status (for exit type)
- Add new --exit boolean flag for session self-termination
- Update docs and help text to reflect new flag names
Usage: gt done --exit
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Updated `gt costs record` to create session.ended events in beads
- Updated `gt costs --today/--week` queries to use bd instead of JSONL
- Removed JSONL ledger support (getLedgerPath, readLedger, WriteLedgerEntry)
- Session costs now stored with event_kind, actor, target, and payload fields
- Filed bd-xwvo for beads bug where --rig flag loses event fields
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Changed command signature from `gt crew start [name...]` to
`gt crew start <rig> [name]` with --all flag support:
- Takes rig as first required positional argument
- Optional crew member name(s) as subsequent arguments
- --all flag to start all crew members in the rig
- Validates that either name or --all must be provided
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a new doctor check that verifies all settings.json files in the
town use session-start.sh wrapper for SessionStart and PreCompact hooks.
Without this wrapper, session_id passthrough fails, which breaks
gt seance discovery of sessions.
The check:
- Scans all settings.json files across town, rigs, crew, and polecats
- Warns if any file uses bare 'gt prime' without session-start.sh
- Provides fix hint pointing to the correct wrapper configuration
(gt-77fhi)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add new `gt rig stop <rig>...` command that supports stopping multiple rigs
with the same shutdown semantics as `gt rig shutdown`:
- Stops all polecat sessions
- Stops the refinery (if running)
- Stops the witness (if running)
- Checks for uncommitted work before shutdown (unless --nuclear)
Includes --force flag for immediate shutdown and --nuclear flag to bypass
safety checks. (gt-lhitf)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add new 'gt rig start <rig>...' command that starts witness and refinery
on patrol for one or more rigs. Similar to 'gt rig boot' but supports
multiple rigs in a single invocation.
- Iterates over all provided rig names
- Skips already-running agents with clear output
- Reports success/failure per-rig with summary
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Shows detailed status for a specific rig including all workers:
- Rig info (name, path, beads prefix)
- Witness status (running/stopped, uptime)
- Refinery status (running/stopped, uptime, queue size)
- Polecats (name, state, assigned issue, session status)
- Crew members (name, branch, session status, git status)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The status line was counting rigs based on tmux session names without
validating they were actually registered in mayor/rigs.json. This could
cause incorrect rig counts when session names matched the pattern but
were not real rigs.
Now loads registered rigs from rigs.json and only counts:
- Rigs that are actually registered
- Polecats belonging to registered rigs
Fixes#17🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add repo-fingerprint check to gt doctor that verifies beads databases have
valid repository fingerprints. Missing or empty fingerprints can cause daemon
startup failures and sync issues.
The check:
- Uses bd doctor --json to check fingerprint status
- Runs on town-level and rig-level beads directories
- Can fix by running bd migrate --update-repo-id
- Restarts daemon after migration if it was running
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add validation in Manager.AddRig() to reject rig names containing
characters that break agent ID parsing. Agent IDs use format
<prefix>-<rig>-<role>[-<name>] with hyphens as delimiters, so
hyphenated rig names like op-baby cause parsing failures.
The validation rejects hyphens, dots, and spaces, and suggests a
sanitized alternative in the error message.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add a new doctor check that verifies the bd (beads) daemon is running
and healthy. When the daemon fails to start, the check:
- Surfaces specific error messages (legacy database, repo mismatch)
- Provides one-liner fix commands
- Auto-fixes by running bd migrate --update-repo-id when appropriate
This addresses GH #25: gt status slow when bd daemon not running.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Change polecat contract from wait-for-termination to ephemeral
- Rename close-issue → prepare-for-review (Refinery closes after merge)
- Rename signal-complete → submit-and-exit (polecat recyclable after gt done)
- Bump formula version to 4
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add bd daemon health check at the start of gt status:
- Check daemon health via bd daemon health --json
- Attempt restart if daemons are unhealthy (version mismatch, stale, unresponsive)
- Show warning at end of status output if daemons could not be started
- Non-blocking: status display continues regardless of daemon state
This prevents the 39+ second slowdown when bd daemons are not running
properly, as each bd command falls back to slow direct mode.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements cost tracking v1 for Gas Town agents:
- `gt costs` shows live costs scraped from running tmux sessions
- `gt costs --today/--week` shows historical costs from ledger
- `gt costs --by-role/--by-rig` shows cost breakdowns
- `gt costs record` for Stop hook integration to record final costs
Cost ledger stored at ~/.gt/costs.jsonl with JSONL entries per session.
Ref: gt-nrpiq
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Town beads should use 'hq-' prefix to match documented architecture:
- Town beads (~/gt/.beads/): hq-* prefix for mayor mail, coordination
- Rig beads: project-specific prefix
The 'gm' prefix was causing convoy creation failures due to prefix
mismatch.
Fixes#19🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add internal/deps package for dependency management
- Check for bd before gt install and gt rig add
- Auto-install bd via go install if missing
- Version check warns if bd is too old (min: 0.43.0)
Closes#22🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Change tmux from "optional" to "recommended for the full experience"
- Add "Enter the Mayor's office" step after gt rig add
- Explain Mayor role upfront in Core Concepts
- Reorder workflows to put Full Stack (Recommended) first
- Add example of conversational interaction with Mayor
- Document gt agents for session navigation
Closes#21🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add GetAllRoleTemplates tests (basic and content validity)
- Add FixMultipleRigs test for multi-rig fix scenario
- Add DetailsFormat test verifying rig:template prefix format
- Add MalformedRigsJSON test for error handling
- Add EmptyRigsConfig test for edge case
- PatrolRolesHavePromptsCheck now verifies templates exist in each rig's
mayor clone at <rig>/mayor/rig/internal/templates/roles/
- Track missing templates by rig using missingByRig map
- Fix copies embedded templates to each rig's location
- Add GetAllRoleTemplates helper to templates package
- Add tests for no-rigs case and multiple-rigs scenarios
"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 mol 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."
description="Per-rig worker monitor patrol loop.\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## Design Philosophy\n\nThis patrol follows Gas Town principles:\n- **Discovery over tracking**: Observe reality each cycle, don't maintain state\n- **Events over state**: POLECAT_DONE mail triggers cleanup wisps\n- **Cleanup wisps as finalizers**: Pending cleanups are wisps, not queue entries\n- **Task tool for parallelism**: Subagents inspect polecats, not molecule arms\n\n## Patrol Shape (Linear, Deacon-style)\n\n```\ninbox-check ─► process-cleanups ─► check-refinery ─► survey-workers\n │\n ┌──────────────────────────────────────────────────┘\n ▼\n check-swarm ─► ping-deacon ─► patrol-cleanup ─► context-check ─► loop-or-exit\n```\n\nNo dynamic arms. No fanout gates. No persistent nudge counters.\nState is discovered each cycle from reality (tmux, beads, mail)."
description="Per-rig worker monitor patrol loop.\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## Ephemeral Polecat Model\n\nPolecats are truly ephemeral - done at MR submission, recyclable immediately:\n\n```\nPolecat lifecycle: spawning → working → mr_submitted → nuked\nMR lifecycle: created → queued → processed → merged (Refinery handles)\n```\n\nOnce a polecat's branch is pushed (cleanup_status=clean), the polecat can be\nnuked immediately. The MR continues independently in the Refinery. If conflicts\narise, Refinery creates a NEW conflict-resolution task for a NEW polecat.\n\n**Key principle**: Polecat lifecycle is separate from MR lifecycle.\n\n## Design Philosophy\n\nThis patrol follows Gas Town principles:\n- **Discovery over tracking**: Observe reality each cycle, don't maintain state\n- **Events over state**: POLECAT_DONE mail triggers immediate cleanup\n- **Ephemeral by default**: Clean polecats are nuked immediately, no waiting\n- **Cleanup wisps for exceptions**: Only created when intervention needed\n- **Task tool for parallelism**: Subagents inspect polecats, not molecule arms\n\n## Patrol Shape (Linear, Deacon-style)\n\n```\ninbox-check ─► process-cleanups ─► check-refinery ─► survey-workers\n │\n ┌──────────────────────────────────────────────────┘\n ▼\n check-timer-gates ─► check-swarm ─► ping-deacon ─► patrol-cleanup ─► context-check ─► loop-or-exit\n```\n\nNo dynamic arms. No fanout gates. No persistent nudge counters.\nState is discovered each cycle from reality (tmux, beads, mail)."
formula='mol-witness-patrol'
version=2
[[steps]]
description="Check inbox and handle messages.\n\n```bash\ngt mail inbox\n```\n\nFor each message:\n\n**POLECAT_STARTED**:\nA new polecat has started working. Acknowledge and archive.\n```bash\n# Acknowledge startup (optional: log for activity tracking)\ngt mail archive <message-id>\n```\nNo action needed beyond acknowledgment - archive immediately.\n\n**POLECAT_DONE / LIFECYCLE:Shutdown**:\nCreate a cleanup wisp for this polecat:\n```bash\nbd create --wisp --title \"cleanup:<polecat>\" --description \"Verify and cleanup polecat <name>\" --labels cleanup,polecat:<name>,state:pending\n```\nThe wisp's existence IS the pending cleanup. Process in next step.\n**Do NOT archive yet** - archive after cleanup completes (in MERGED handling).\n\n**MERGED**:\nA branch was merged successfully. Complete the cleanup.\n```bash\n# Find the cleanup wisp for this polecat\nbd list --wisp --labels=polecat:<name>,state:merge-requested --status=open\n\n# If found, proceed with full polecat nuke:\n# - Kill Claude session\n# - Delete worktree\n# - Delete branch\n# - Remove agent bead\ngt polecat nuke <name>\n\n# Burn the cleanup wisp\nbd close <wisp-id>\n\n# NOW archive both the MERGED mail and the original POLECAT_DONE mail\n# (The POLECAT_DONE message ID should be tracked in the cleanup wisp or MR bead)\ngt mail archive <merged-message-id>\ngt mail archive <polecat-done-message-id> # If tracked\n```\nArchive after cleanup is complete.\n\n**HELP / Blocked**:\nAssess the request. Can you help? If not, escalate to Mayor:\n```bash\ngt mail send mayor/ -s \"Escalation: <polecat> needs help\" -m \"<details>\"\n```\nArchive after handling (escalated or resolved):\n```bash\ngt mail archive <message-id>\n```\n\n**HANDOFF**:\nRead predecessor context. Continue from where they left off.\nArchive after absorbing context:\n```bash\ngt mail archive <message-id>\n```\n\n**SWARM_START**:\nMayor initiating batch polecat work. Initialize swarm tracking.\n```bash\n# Parse swarm info from mail body: {\"swarm_id\": \"batch-123\", \"beads\": [\"bd-a\", \"bd-b\"]}\nbd create --wisp --title \"swarm:<swarm_id>\" --description \"Tracking batch: <swarm_id>\" --labels swarm,swarm_id:<swarm_id>,total:<N>,completed:0,start:<timestamp>\n```\nArchive after creating swarm tracking wisp:\n```bash\ngt mail archive <message-id>\n```\n\n**Hygiene principle**: Archive messages after they're fully processed.\nKeep only: active work, unprocessed requests. Inbox should be near-empty."
description="Check inbox and handle messages.\n\n```bash\ngt mail inbox\n```\n\nFor each message:\n\n**POLECAT_STARTED**:\nA new polecat has started working. Acknowledge and archive.\n```bash\n# Acknowledge startup (optional: log for activity tracking)\ngt mail archive <message-id>\n```\nNo action needed beyond acknowledgment - archive immediately.\n\n**POLECAT_DONE / LIFECYCLE:Shutdown**:\n\n*EPHEMERAL MODEL*: Polecats are truly ephemeral - done at MR submission,\nrecyclable immediately. Once the branch is pushed (cleanup_status=clean),\nthe polecat can be nuked. The MR lifecycle continues independently in the\nRefinery. If conflicts arise, Refinery creates a NEW conflict-resolution\ntask for a NEW polecat.\n\nPolecat lifecycle: spawning → working → mr_submitted → nuked\nMR lifecycle: created → queued → processed → merged (handled by Refinery)\n\nThe handler (HandlePolecatDone) will:\n1. Check cleanup_status from agent bead\n2. If \"clean\" (branch pushed): AUTO-NUKE immediately, archive mail\n3. If dirty: Create cleanup wisp for manual intervention\n\n```bash\n# The handler does this automatically:\n# - For clean state: gt polecat nuke <name> → archive mail\n# - For dirty state: create wisp → process in next step\n```\n\nCleanup wisps are only created when something is wrong (uncommitted changes,\nunpushed commits). Most POLECAT_DONE messages result in immediate nuke.\n\n**MERGED**:\nA branch was merged successfully. This is informational in the ephemeral model\nsince the polecat was already nuked after MR submission.\n\nIf a cleanup wisp exists (dirty state), complete the cleanup:\n```bash\n# Find the cleanup wisp for this polecat\nbd list --wisp --labels=polecat:<name>,state:merge-requested --status=open\n\n# If found, proceed with full polecat nuke:\ngt polecat nuke <name>\n\n# Burn the cleanup wisp\nbd close <wisp-id>\n```\nArchive after cleanup is complete.\n\n**HELP / Blocked**:\nAssess the request. Can you help? If not, escalate to Mayor:\n```bash\ngt mail send mayor/ -s \"Escalation: <polecat> needs help\" -m \"<details>\"\n```\nArchive after handling (escalated or resolved):\n```bash\ngt mail archive <message-id>\n```\n\n**HANDOFF**:\nRead predecessor context. Continue from where they left off.\nArchive after absorbing context:\n```bash\ngt mail archive <message-id>\n```\n\n**SWARM_START**:\nMayor initiating batch polecat work. Initialize swarm tracking.\n```bash\n# Parse swarm info from mail body: {\"swarm_id\": \"batch-123\", \"beads\": [\"bd-a\", \"bd-b\"]}\nbd create --wisp --title \"swarm:<swarm_id>\" --description \"Tracking batch: <swarm_id>\" --labels swarm,swarm_id:<swarm_id>,total:<N>,completed:0,start:<timestamp>\n```\nArchive after creating swarm tracking wisp:\n```bash\ngt mail archive <message-id>\n```\n\n**Hygiene principle**: Archive messages after they're fully processed.\nKeep only: active work, unprocessed requests. Inbox should be near-empty."
id='inbox-check'
title='Process witness mail'
[[steps]]
description="Find and process cleanup wisps (the finalizer pattern).\n\n```bash\n# Find all cleanup wisps\nbd list --wisp --labels=cleanup --status=open\n```\n\nFor each cleanup wisp, check its state label:\n\n## State: pending (needs verification → MERGE_READY)\n\n1. **Extract polecat name** from wisp title/labels\n\n2. **Pre-kill verification**:\n```bash\ncd polecats/<name>\ngit status # Must be clean\ngit log origin/main..HEAD # Commits should be pushed\nbd show <assigned-issue> # Issue closed or deferred\n```\n\n3. **Get branch and issue info**:\n```bash\n# Get current branch\ngit rev-parse --abbrev-ref HEAD\n\n# Get the hook_bead from agent bead\nbd show <agent-bead> # Look for hook_bead field\n```\n\n4. **Verify productive work** (ZFC - you make the call):\n - Check git log for commits mentioning the issue\n - Legitimate exceptions: already fixed, duplicate, deferred\n - If closing as 'done' with no commits, flag for review\n\n5. **If clean**: Send MERGE_READY to refinery\n```bash\ngt mail send <rig>/refinery -s \"MERGE_READY <polecat>\" -m \"Branch: <branch>\nIssue: <issue-id>\nPolecat: <polecat>\nVerified: clean git state, issue closed\"\n```\nThen update the wisp to merge-requested state:\n```bash\nbd update <wisp-id> --labels cleanup,polecat:<name>,state:merge-requested\n```\n**Do NOT kill the polecat yet** - wait for MERGED confirmation from refinery.\n\n6. **If dirty**: Leave wisp open, log the issue, retry next cycle.\n\n## State: merge-requested (waiting for refinery)\n\nSkip - waiting for MERGED mail from refinery. The inbox-check step handles\nMERGED messages and completes these cleanup wisps.\n\n**Parallelism**: Use Task tool subagents to process multiple cleanups concurrently.\nEach cleanup is independent - perfect for parallel execution."
description="Process cleanup wisps (exception handling for dirty polecats).\n\nIn the ephemeral model, cleanup wisps are only created when a polecat has\ndirty state (uncommitted changes, unpushed commits) that prevented immediate\nnuke. Most polecats are nuked immediately on POLECAT_DONE and never create wisps.\n\n```bash\n# Find all cleanup wisps\nbd list --wisp --labels=cleanup --status=open\n```\n\nIf no wisps, skip this step (most common case in ephemeral model).\n\nFor each cleanup wisp, investigate and resolve the dirty state:\n\n## State: pending (needs investigation)\n\n1. **Extract polecat name** from wisp title/labels\n\n2. **Diagnose the problem**:\n```bash\ncd polecats/<name>\ngit status # What's uncommitted?\ngit stash list # Any stashed work?\ngit log origin/main..HEAD # Any unpushed commits?\n```\n\n3. **Resolution options**:\n - **Uncommitted changes**: Commit and push, then nuke\n - **Stashed work**: Pop and commit, or discard if not valuable\n - **Unpushed commits**: Push to origin, then nuke\n - **All valuable work lost**: Escalate to Mayor for recovery\n\n4. **If resolvable locally**: Fix and nuke\n```bash\n# Example: push unpushed commits\ngit push origin HEAD\n\n# Then nuke\ngt polecat nuke <name>\n\n# Close the wisp\nbd close <wisp-id> --reason \"Resolved: pushed commits, nuked\"\n```\n\n5. **If needs escalation**: Send RECOVERY_NEEDED to Mayor\n```bash\ngt mail send mayor/ -s \"RECOVERY_NEEDED <rig>/<polecat>\" \\\n -m \"Cleanup Status: <status>\nBranch: <branch>\nIssue: <issue-id>\n\nCannot auto-resolve. Please advise.\"\n```\nLeave wisp open until Mayor resolves.\n\n## State:merge-requested (legacy, rare)\n\nThis state was used before the ephemeral model. If found, the polecat is\nwaiting for a MERGED signal. The inbox-check step handles these.\n\n**Parallelism**: Use Task tool subagents to process multiple cleanups concurrently.\nEach cleanup is independent - perfect for parallel execution."
id='process-cleanups'
needs=['inbox-check']
title='Process pending cleanup wisps'
@@ -20,15 +20,21 @@ needs = ['process-cleanups']
title='Ensure refinery is alive'
[[steps]]
description="Survey all polecats using agent beads (ZFC: trust what agents report).\n\n**Step 1: List polecat agent beads**\n\n```bash\nbd list --type=agent --json\n```\n\nFilter the JSON output for entries where description contains `role_type: polecat`.\nEach polecat agent bead has fields in its description:\n- `role_type: polecat`\n- `rig: <rig-name>`\n- `agent_state: running|idle|stuck|done`\n- `hook_bead: <current-work-id>`\n\n**Step 2: For each polecat, check agent_state**\n\n| agent_state | Meaning | Action |\n|-------------|---------|--------|\n| running | Actively working | Check progress (Step 3) |\n| idle | No work assigned | Auto-nuke if clean (Step 3a) |\n| stuck | Self-reported stuck | Handle stuck protocol |\n| done | Work complete | Verify cleanup triggered (see Step 4a) |\n\n**Step 3: For running polecats, assess progress**\n\nCheck the hook_bead field to see what they're working on:\n```bash\nbd show <hook_bead> # See current step/issue\n```\n\nYou can also verify they're responsive:\n```bash\ntmux capture-pane -t gt-<rig>-<name> -p | tail -20\n```\n\nLook for:\n- Recent tool activity → making progress\n- Idle at prompt → may need nudge\n- Error messages → may need help\n\n**Step 3a: For idle polecats, auto-nuke if clean**\n\nWhen agent_state=idle, the polecat has no work assigned. Check if it's safe to nuke:\n\n```bash\n# Check git status in the polecat's worktree\ncd polecats/<name>\ngit status --porcelain # Should be empty (clean)\ngit log origin/main..HEAD # Should have no unpushed commits\n```\n\n**If clean** (no uncommitted changes, no unpushed commits):\n```bash\n# Safe to nuke - no work to lose\ngt polecat nuke <name>\n```\nLog the auto-nuke for audit purposes. No escalation needed.\n\n**If dirty** (uncommitted or unpushed work):\n```bash\n# Escalate to Mayor - polecat has work that might be valuable\ngt mail send mayor/ -s \\\"IDLE_DIRTY: <polecat> has uncommitted work\\\" \\\n -m \\\"Polecat: <name>\nState: idle (no hook_bead)\nGit status: <uncommitted-files>\nUnpushed commits: <count>\n\nPlease advise: recover work or discard?\\\"\n```\n\n**Rationale**: Idle polecats with clean git state are pure overhead. They have\nno work and no state worth preserving. Nuking them immediately frees resources\nand reduces noise. Only escalate when there's actual work at risk.\n\n**Step 4: Decide action**\n\n| Observation | Action |\n|-------------|--------|\n| agent_state=running, recent activity | None |\n| agent_state=running, idle 5-15 min | Gentle nudge |\n| agent_state=running, idle 15+ min | Direct nudge with deadline |\n| agent_state=stuck | Assess and help or escalate |\n| agent_state=done | Verify cleanup triggered (see Step 4a) |\n\n**Step 4a: Handle agent_state=done**\n\nCheck if a cleanup wisp exists for this polecat:\n```bash\nbd list --wisp --labels=polecat:<name> --status=open\n```\n\nIf cleanup wisp exists:\n- state:pending → Will be processed in process-cleanups\n- state:merge-requested → Waiting for refinery MERGED response\n\nIf NO cleanup wisp exists (POLECAT_DONE mail missed):\nCreate one to trigger the cleanup flow:\n```bash\nbd create --wisp --title \"cleanup:<polecat>\" --description \"Discovered done polecat without cleanup wisp\" --labels cleanup,polecat:<name>,state:pending\n```\nThis ensures done polecats eventually get cleaned up even if mail was lost.\n\n**Step 5: Execute nudges**\n```bash\ngt nudge <rig>/polecats/<name> \"How's progress? Need help?\"\n```\n\n**Step 6: Escalate if needed**\n```bash\ngt mail send mayor/ -s \"Escalation: <polecat> stuck\" \\\n -m \"Polecat <name> reports stuck. Please intervene.\"\n```\n\n**Parallelism**: Use Task tool subagents to inspect multiple polecats concurrently.\n\n**ZFC Principle**: Trust agent_state from beads. Don't infer state from PID/tmux."
description="Survey all polecats using agent beads (ZFC: trust what agents report).\n\n**Step 1: List polecat agent beads**\n\n```bash\nbd list --type=agent --json\n```\n\nFilter the JSON output for entries where description contains `role_type: polecat`.\nEach polecat agent bead has fields in its description:\n- `role_type: polecat`\n- `rig: <rig-name>`\n- `agent_state: running|idle|stuck|done`\n- `hook_bead: <current-work-id>`\n\n**Step 2: For each polecat, check agent_state**\n\n| agent_state | Meaning | Action |\n|-------------|---------|--------|\n| running | Actively working | Check progress (Step 3) |\n| idle | No work assigned | Auto-nuke if clean (Step 3a) |\n| stuck | Self-reported stuck | Handle stuck protocol |\n| done | Work complete | Verify cleanup triggered (see Step 4a) |\n\n**Step 3: For running polecats, assess progress**\n\nCheck the hook_bead field to see what they're working on:\n```bash\nbd show <hook_bead> # See current step/issue\n```\n\nYou can also verify they're responsive:\n```bash\ntmux capture-pane -t gt-<rig>-<name> -p | tail -20\n```\n\nLook for:\n- Recent tool activity → making progress\n- Idle at prompt → may need nudge\n- Error messages → may need help\n\n**Step 3a: For idle polecats, auto-nuke if clean**\n\nWhen agent_state=idle, the polecat has no work assigned. Check if it's safe to nuke:\n\n```bash\n# Check git status in the polecat's worktree\ncd polecats/<name>\ngit status --porcelain # Should be empty (clean)\ngit log origin/main..HEAD # Should have no unpushed commits\n```\n\n**If clean** (no uncommitted changes, no unpushed commits):\n```bash\n# Safe to nuke - no work to lose\ngt polecat nuke <name>\n```\nLog the auto-nuke for audit purposes. No escalation needed.\n\n**If dirty** (uncommitted or unpushed work):\n```bash\n# Escalate to Mayor - polecat has work that might be valuable\ngt mail send mayor/ -s \\\"IDLE_DIRTY: <polecat> has uncommitted work\\\" \\\n -m \\\"Polecat: <name>\nState: idle (no hook_bead)\nGit status: <uncommitted-files>\nUnpushed commits: <count>\n\nPlease advise: recover work or discard?\\\"\n```\n\n**Rationale**: Idle polecats with clean git state are pure overhead. They have\nno work and no state worth preserving. Nuking them immediately frees resources\nand reduces noise. Only escalate when there's actual work at risk.\n\n**Step 4: Decide action**\n\n| Observation | Action |\n|-------------|--------|\n| agent_state=running, recent activity | None |\n| agent_state=running, idle 5-15 min | Gentle nudge |\n| agent_state=running, idle 15+ min | Direct nudge with deadline |\n| agent_state=stuck | Assess and help or escalate |\n| agent_state=done | Verify cleanup triggered (see Step 4a) |\n\n**Step 4a: Handle agent_state=done**\n\nIn the ephemeral model, polecats with agent_state=done and cleanup_status=clean\nshould already be nuked by HandlePolecatDone. Finding one here indicates:\n\n1. **Stale agent bead** - polecat was nuked but bead remains\n ```bash\n # Verify polecat doesn't exist anymore\n lspolecats/<name> 2>/dev/null || echo \"Already nuked\"\n ```\n If nuked, the agent bead is stale. Clean it up or ignore.\n\n2. **Cleanup wisp exists** - polecat has dirty state needing intervention\n ```bash\n bd list --wisp --labels=polecat:<name> --status=open\n ```\n Process in process-cleanups step.\n\n3. **No wisp, polecat exists** - POLECAT_DONE mail was missed\n Try auto-nuke directly (ephemeral model):\n ```bash\n # Check cleanup_status and nuke if clean\n gt polecat nuke <name> # Will fail if dirty\n ```\n If nuke fails (dirty state), create cleanup wisp for investigation.\n\n**Step 5: Execute nudges**\n```bash\ngt nudge <rig>/polecats/<name> \"How's progress? Need help?\"\n```\n\n**Step 6: Escalate if needed**\n```bash\ngt mail send mayor/ -s \"Escalation: <polecat> stuck\" \\\n -m \"Polecat <name> reports stuck. Please intervene.\"\n```\n\n**Parallelism**: Use Task tool subagents to inspect multiple polecats concurrently.\n\n**ZFC Principle**: Trust agent_state from beads. Don't infer state from PID/tmux."
id='survey-workers'
needs=['check-refinery']
title='Inspect all active polecats'
[[steps]]
description="Check for expired timer gates and escalate as needed.\n\nTimer gates are async wait conditions with a timeout. When the timeout expires,\nthe gate should be escalated to the overseer for human intervention.\n\n**Step 1: Run timer gate check**\n```bash\nbd gate check --type=timer --escalate\n```\n\nThis command:\n1. Finds all open gate issues with await_type=timer\n2. Checks if `now > created_at + timeout`\n3. Escalates expired gates via `gt escalate` (HIGH severity)\n4. Reports summary of gate status\n\n**Step 2: Review output**\n\nIf expired gates were found and escalated:\n- The escalation creates an audit trail bead\n- Overseer will be notified via mail\n- Gate remains open until manually resolved\n\nIf no expired gates:\n- Continue patrol normally\n\n**Note**: Timer gates do NOT auto-close on expiration. They escalate.\nThis ensures human oversight of timeout conditions.\n\n**Parallelism**: This is a single command, no parallel execution needed."
id='check-timer-gates'
needs=['survey-workers']
title='Check timer gates for expiration'
[[steps]]
description="If Mayor started a batch (SWARM_START), check if all polecats have completed.\n\n**Step 1: Find active swarm tracking wisps**\n```bash\nbd list --wisp --labels=swarm --status=open\n```\nIf no active swarm, skip this step.\n\n**Step 2: Count completed polecats for this swarm**\n\nExtract from wisp labels: swarm_id, total, completed, start timestamp.\nCheck how many cleanup wisps have been closed for this swarm's polecats.\n\n**Step 3: If all complete, notify Mayor**\n```bash\ngt mail send mayor/ -s \"SWARM_COMPLETE: <swarm_id>\" -m \"All <total> polecats merged.\nDuration: <minutes> minutes\nSwarm: <swarm_id>\"\n\n# Close the swarm tracking wisp\nbd close <swarm-wisp-id> --reason \"All polecats merged\"\n```\n\nNote: Runs every patrol cycle. Notification sent exactly once when all complete."
description="Verify inbox hygiene before ending patrol cycle.\n\n**Step 1: Check inbox state**\n```bash\ngt mail inbox\n```\n\nInbox should contain ONLY:\n- Unprocessed messages (just arrived, will handle next cycle)\n- Active work markers (POLECAT_DONE waiting for MERGED confirmation)\n\n**Step 2: Archive any stale messages**\n\nLook for messages that were processed but not archived:\n- POLECAT_STARTED older than this cycle → archive\n- HELP/Blocked that was escalated → archive\n- SWARM_START that created tracking wisp → archive\n\n```bash\n# For each stale message found:\ngt mail archive <message-id>\n```\n\n**Step 3: Verify cleanup wisp hygiene**\n\nCheck that all cleanup wisps are in valid states:\n```bash\nbd list --wisp --labels=cleanup --status=open\n```\n\n- state:pending → Will be processed next cycle\n- state:merge-requested → Waiting for refinery\n\nIf any cleanup wisp is older than expected (>1 hour in merge-requested state),\nthe refinery may be stuck. This was checked in check-refinery step.\n\n**Goal**: Inbox should have ≤5 active messages at end of cycle."
description="Verify inbox hygiene before ending patrol cycle.\n\n**Step 1: Check inbox state**\n```bash\ngt mail inbox\n```\n\nIn the ephemeral model, most POLECAT_DONE messages are handled immediately\n(auto-nuke) and archived. Inbox should contain ONLY:\n- Unprocessed messages (just arrived, will handle next cycle)\n- MERGED notifications (informational, archive after reading)\n\n**Step 2: Archive any stale messages**\n\nLook for messages that were processed but not archived:\n- POLECAT_STARTED older than this cycle → archive\n- POLECAT_DONE that was auto-nuked → should be archived already\n- MERGED notifications → archive after acknowledging\n- HELP/Blocked that was escalated → archive\n- SWARM_START that created tracking wisp → archive\n\n```bash\n# For each stale message found:\ngt mail archive <message-id>\n```\n\n**Step 3: Verify cleanup wisp hygiene**\n\nIn the ephemeral model, cleanup wisps should be rare (only for dirty polecats):\n```bash\nbd list --wisp --labels=cleanup --status=open\n```\n\n- state:pending → Needs investigation in process-cleanups\n- state:merge-requested → Legacy state, handle in inbox-check\n\nIf cleanup wisps are accumulating, investigate why polecats aren't clean.\n\n**Goal**: Inbox should be nearly empty. Cleanup wisps should be rare."
id='patrol-cleanup'
needs=['ping-deacon']
title='End-of-cycle inbox hygiene'
@@ -50,7 +56,7 @@ needs = ['patrol-cleanup']
title='Check own context limit'
[[steps]]
description="End of patrol cycle decision.\n\n**If context LOW**:\n- Sleep briefly to avoid tight loop (30-60 seconds)\n- Return to inbox-check step\n- Continue patrolling\n\n**If context HIGH**:\n- Write handoff mail to self with any notable observations:\n```bash\ngt handoff -s \"Witness patrol handoff\" -m \"<observations>\"\n```\n- Exit cleanly (daemon respawns fresh Witness)\n\nThe daemon ensures Witness is always running."
description="End of patrol cycle decision.\n\n**If context LOW** (can continue patrolling):\n1. Generate a brief summary of this patrol cycle\n2. Squash the current wisp:\n```bash\nbd mol squash <mol-id> --summary \"<patrol-summary>\"\n```\n3. Create a new patrol wisp:\n```bash\nbd mol wisp mol-witness-patrol\n```\n4. Continue executing from the inbox-check step of the new wisp\n\n**If context HIGH** (approaching limit):\n1. Write handoff mail with notable observations:\n```bash\ngt handoff -s \"Witness patrol handoff\" -m \"<observations>\"\n```\n2. Exit cleanly - the daemon will respawn a fresh Witness session\n\n**IMPORTANT**: You must either create a new wisp (context LOW) or exit (context HIGH).\nNever leave the session idle without work on your hook."
@@ -5,6 +5,363 @@ All notable changes to the Gas Town project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [Unreleased]
## [0.2.3] - 2026-01-09
Worker safety release - prevents accidental termination of active agents.
> **Note**: The Deacon safety improvements are believed to be correct but have not
> yet been extensively tested in production. We recommend running with
> `gt deacon pause` initially and monitoring behavior before enabling full patrol.
> Please report any issues. A 0.3.0 release will follow once these changes are
> battle-tested.
### Critical Safety Improvements
- **Kill authority removed from Deacon** - Deacon patrol now only detects zombies via `--dry-run`, never kills directly. Death warrants are filed for Boot to handle interrogation/execution. This prevents destruction of worker context, mid-task progress, and unsaved state (#gt-vhaej)
- **Bulletproof pause mechanism** - Multi-layer pause for Deacon with file-based state, `gt deacon pause/resume` commands, and guards in `gt prime` and heartbeat (#265)
- **Doctor warns instead of killing** - `gt doctor` now warns about stale town-root settings rather than killing sessions (#243)
- **Orphan process check informational** - Doctor's orphan process detection is now informational only, not actionable (#272)
### Added
- **`gt account switch` command** - Switch between Claude Code accounts with `gt account switch <handle>`. Manages `~/.claude` symlinks and updates default account
- **`gt crew list --all`** - Show all crew members across all rigs (#276)
Multi-agent orchestrator for Claude Code. Track work with convoys; sling to agents.
**Multi-agent orchestration system for Claude Code with persistent work tracking**
## Why Gas Town?
## Overview
| Without | With Gas Town |
|---------|---------------|
| Agents forget work after restart | Work persists on hooks - survives crashes, compaction, restarts |
| Manual coordination | Agents have mailboxes, identities, and structured handoffs |
| 4-10 agents is chaotic | Comfortably scale to 20-30 agents |
| Work state in agent memory | Work state in Beads (git-backed ledger) |
Gas Town is a workspace manager that lets you coordinate multiple Claude Code agents working on different tasks. Instead of losing context when agents restart, Gas Town persists work state in git-backed hooks, enabling reliable multi-agent workflows.
## Prerequisites
### What Problem Does This Solve?
- **Go 1.23+** - [go.dev/dl](https://go.dev/dl/)
- **Git 2.25+** - for worktree support
- **beads (bd)** - [github.com/steveyegge/beads](https://github.com/steveyegge/beads) - required for issue tracking
- **tmux 3.0+** - for full stack mode (optional for minimal mode)
├── Rig (project) Container for a git project + its agents
│ ├── Polecats Workers (ephemeral, spawn → work → disappear)
│ ├── Witness Monitors workers, handles lifecycle
│ └── Refinery Merge queue processor
└── Mayor Global coordinator
### The Mayor 🎩
Your primary AI coordinator. The Mayor is a Claude Code instance with full context about your workspace, projects, and agents. **Start here** - just tell the Mayor what you want to accomplish.
### Town 🏘️
Your workspace directory (e.g., `~/gt/`). Contains all projects, agents, and configuration.
### Rigs 🏗️
Project containers. Each rig wraps a git repository and manages its associated agents.
### Crew Members 👤
Your personal workspace within a rig. Where you do hands-on work.
### Polecats 🦨
Ephemeral worker agents that spawn, complete a task, and disappear.
### Hooks 🪝
Git worktree-based persistent storage for agent work. Survives crashes and restarts.
### Convoys 🚚
Work tracking units. Bundle multiple issues/tasks that get assigned to agents.
### Beads Integration 📿
Git-backed issue tracking system that stores work state as structured data.
> **New to Gas Town?** See the [Glossary](docs/glossary.md) for a complete guide to terminology and concepts.
## Installation
### Prerequisites
- **Go 1.23+** - [go.dev/dl](https://go.dev/dl/)
- **Git 2.25+** - for worktree support
- **beads (bd) 0.44.0+** - [github.com/steveyegge/beads](https://github.com/steveyegge/beads) (required for custom type support)
| **Mayor** | AI coordinator | `gt mayor attach` |
| **Human (You)** | Crew member | Your crew directory |
| **Polecat** | Worker agent | Spawned by Mayor |
| **Hook** | Persistent storage | Git worktree |
| **Convoy** | Work tracker | `gt convoy` commands |
## Tips
- **Always start with the Mayor** - It's designed to be your primary interface
- **Use convoys for coordination** - They provide visibility across agents
- **Leverage hooks for persistence** - Your work won't disappear
- **Create formulas for repeated tasks** - Save time with Beads recipes
- **Monitor the dashboard** - Get real-time visibility
- **Let the Mayor orchestrate** - It knows how to manage agents
## Troubleshooting
### Agents lose connection
Check hooks are properly initialized:
```bash
gt hooks list
gt hooks repair
```
### Convoy stuck
Force refresh:
```bash
gt convoy refresh <convoy-id>
```
### Mayor not responding
Restart Mayor session:
```bash
gt mayor detach
gt mayor attach
```
## License
MIT
MIT License - see LICENSE file for details
---
**Getting Started:** Run `gt install ~/gt --git && cd ~/gt && gt config agent list && gt mayor attach` (or `gt mayor attach --agent codex`) and tell the Mayor what you want to build!
Gas Town is an agentic development environment for managing multiple Claude Code instances simultaneously using the `gt` and `bd` (Beads) binaries, coordinated with tmux in git-managed directories.
## Core Principles
### MEOW (Molecular Expression of Work)
Breaking large goals into detailed instructions for agents. Supported by Beads, Epics, Formulas, and Molecules. MEOW ensures work is decomposed into trackable, atomic units that agents can execute autonomously.
### GUPP (Gas Town Universal Propulsion Principle)
"If there is work on your Hook, YOU MUST RUN IT." This principle ensures agents autonomously proceed with available work without waiting for external input. GUPP is the heartbeat of autonomous operation.
### NDI (Nondeterministic Idempotence)
The overarching goal ensuring useful outcomes through orchestration of potentially unreliable processes. Persistent Beads and oversight agents (Witness, Deacon) guarantee eventual workflow completion even when individual operations may fail or produce varying results.
## Environments
### Town
The management headquarters (e.g., `~/gt/`). The Town coordinates all workers across multiple Rigs and houses town-level agents like Mayor and Deacon.
### Rig
A project-specific Git repository under Gas Town management. Each Rig has its own Polecats, Refinery, Witness, and Crew members. Rigs are where actual development work happens.
## Town-Level Roles
### Mayor
Chief-of-staff agent responsible for initiating Convoys, coordinating work distribution, and notifying users of important events. The Mayor operates from the town level and has visibility across all Rigs.
### Deacon
Daemon beacon running continuous Patrol cycles. The Deacon ensures worker activity, monitors system health, and triggers recovery when agents become unresponsive. Think of the Deacon as the system's watchdog.
### Dogs
The Deacon's crew of maintenance agents handling background tasks like cleanup, health checks, and system maintenance.
### Boot (the Dog)
A special Dog that checks the Deacon every 5 minutes, ensuring the watchdog itself is still watching. This creates a chain of accountability.
## Rig-Level Roles
### Polecat
Ephemeral worker agents that produce Merge Requests. Polecats are spawned for specific tasks, complete their work, and are then cleaned up. They work in isolated git worktrees to avoid conflicts.
### Refinery
Manages the Merge Queue for a Rig. The Refinery intelligently merges changes from Polecats, handling conflicts and ensuring code quality before changes reach the main branch.
### Witness
Patrol agent that oversees Polecats and the Refinery within a Rig. The Witness monitors progress, detects stuck agents, and can trigger recovery actions.
### Crew
Long-lived, named agents for persistent collaboration. Unlike ephemeral Polecats, Crew members maintain context across sessions and are ideal for ongoing work relationships.
## Work Units
### Bead
Git-backed atomic work unit stored in JSONL format. Beads are the fundamental unit of work tracking in Gas Town. They can represent issues, tasks, epics, or any trackable work item.
### Formula
TOML-based workflow source template. Formulas define reusable patterns for common operations like patrol cycles, code review, or deployment.
### Protomolecule
A template class for instantiating Molecules. Protomolecules define the structure and steps of a workflow without being tied to specific work items.
### Molecule
Durable chained Bead workflows. Molecules represent multi-step processes where each step is tracked as a Bead. They survive agent restarts and ensure complex workflows complete.
### Wisp
Ephemeral Beads destroyed after runs. Wisps are lightweight work items used for transient operations that don't need permanent tracking.
### Hook
A special pinned Bead for each agent. The Hook is an agent's primary work queue - when work appears on your Hook, GUPP dictates you must run it.
## Workflow Commands
### Convoy
Primary work-order wrapping related Beads. Convoys group related tasks together and can be assigned to multiple workers. Created with `gt convoy create`.
### Slinging
Assigning work to agents via `gt sling`. When you sling work to a Polecat or Crew member, you're putting it on their Hook for execution.
### Nudging
Real-time messaging between agents with `gt nudge`. Nudges allow immediate communication without going through the mail system.
### Handoff
Agent session refresh via `/handoff`. When context gets full or an agent needs a fresh start, handoff transfers work state to a new session.
### Seance
Communicating with previous sessions via `gt seance`. Allows agents to query their predecessors for context and decisions from earlier work.
### Patrol
Ephemeral loop maintaining system heartbeat. Patrol agents (Deacon, Witness) continuously cycle through health checks and trigger actions as needed.
---
*This glossary was contributed by [Clay Shirky](https://github.com/cshirky) in [Issue #80](https://github.com/steveyegge/gastown/issues/80).*
**Trigger**: `gt polecat done` command generates this automatically.
**Trigger**: `gt done` command generates this automatically.
**Handler**: Witness creates a cleanup wisp for the polecat.
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.