- 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>
