Add BD_ACTOR check at start of runDone() to prevent non-polecat roles
(crew, deacon, witness, etc.) from calling gt done. Only polecats are
ephemeral workers that self-destruct after completing work.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When gt done runs inside a tmux session (e.g., after polecat task
completion), calling KillSessionWithProcesses would kill the gt done
process itself before it could complete cleanup operations like writing
handoff state.
Add KillSessionWithProcessesExcluding() function that accepts a list of
PIDs to exclude from the kill sequence. Update selfKillSession to pass
its own PID, ensuring gt done completes before the session is destroyed.
Also fix both Kill*WithProcesses functions to ignore "session not found"
errors from KillSession - when we kill all processes in a session, tmux
may automatically destroy it before we explicitly call KillSession.
Co-authored-by: julianknutsen <julianknutsen@users.noreply.github>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Previously, gt done only killed the polecat session when exitType was
COMPLETED. For DEFERRED, ESCALATED, and PHASE_COMPLETE, it would call
os.Exit(0) which only exited the gt process, leaving Claude running.
Now all exit types terminate the polecat session ("done means gone").
Only COMPLETED also nukes the worktree - other statuses preserve the
work in case it needs to be resumed.
Co-authored-by: julianknutsen <julianknutsen@users.noreply.github>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Three bugs were causing orphaned Claude processes to accumulate:
1. TTY comparison in orphan.go checked for "?" but macOS shows "??"
- Orphan cleanup never found anything on macOS
- Changed to check for both "?" and "??"
2. selfKillSession in done.go used basic tmux kill-session
- Claude Code can survive SIGHUP
- Now uses KillSessionWithProcesses for proper cleanup
3. Crew stop commands used basic KillSession
- Same issue as #2
- Updated runCrewRemove, runCrewStop, runCrewStopAll
Root cause of 383 accumulated sessions: every gt done and crew stop
left orphans, and the cleanup never worked on macOS.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Branch names like "polecat/furiosa-mkb0vq9f" don't contain the actual
issue ID, causing gt done to incorrectly parse "furiosa-mkb0vq9f" as the
issue. This broke integration branch auto-detection since the wrong issue
was used for parent epic lookup.
Changes:
- After parsing branch name, check the agent's hook_bead field which
contains the actual issue ID (e.g., "gt-845.1")
- Fix parseBranchName to not extract fake issue IDs from modern polecat branches
- Fix detectIntegrationBranch to traverse full parent chain (molecule → bug → epic)
- Include issue ID in polecat branch names when HookBead is set
Added tests covering:
- Agent hook returns correct issue ID
- Modern polecat branch format parsing
- Integration branch detection through parent chain
Fixes#411
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
done.go: Push branch to origin BEFORE creating MR bead (hq-6dk53, hq-a4ksk)
- The MR bead triggers Refinery to process the branch
- If branch isnt pushed, Refinery finds nothing to merge
- The worktree gets nuked at end of gt done, losing commits forever
- This is why polecats kept submitting MRs with empty branches
mayor.go: Restart runtime with context when attaching (hq-95xfq)
- When runtime has exited, gt may at now respawns with startup beacon
- Previously, attaching to dead session left agent with no context
- Now matches gt handoff behavior: hook check, inbox check, full prime
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Polecats now fully clean up after themselves on `gt done`:
- Step 1: Nuke worktree (existing behavior)
- Step 2: Kill own tmux session (new)
This completes the "done means gone" model - both worktree and
session are terminated. Previously the session survived as a zombie.
Audit logging added to both systems:
- townlog: EventKill for `gt log` visibility
- events: TypeSessionDeath with structured payload
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Add critical checks to prevent lost work when polecats call gt done
without having made any commits:
1. Block if working directory not available (cannot verify git state)
2. Block if uncommitted changes exist (would be lost on completion)
3. Check commits against origin/main not local main (ensures actual work)
If any check fails, refuse completion and suggest using --status DEFERRED.
This preserves the worktree so work is not lost.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
gt done now completes successfully even if the polecat's worktree is
deleted mid-operation by the Witness or another process.
Changes:
- Add FindFromCwdWithFallback() that returns townRoot from GT_TOWN_ROOT
env var when getcwd fails
- Update runDone() to use fallback paths and env vars (GT_BRANCH,
GT_POLECAT) when cwd is unavailable
- Update updateAgentStateOnDone() to use env vars (GT_ROLE, GT_RIG,
GT_POLECAT) for role detection fallback
- All bead operations are now explicitly non-fatal with warnings
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
MR beads were being created as regular beads, showing up in `bd ready`
when they should be ephemeral wisps that get cleaned up after merge.
Added Ephemeral field to CreateOptions and set it when creating MR beads.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
If the agent bead doesn't exist when gt done tries to clear the hook,
return early instead of failing. This happens for polecats created
before identity beads existed.
gt done must be resilient and forgiving - the important thing is work
gets submitted to merge queue, not that cleanup succeeds.
Fixes: hq-i26n2
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When polecats run 'gt done' without --cleanup-status, the witness may
prematurely nuke the worktree before the refinery can merge.
This fix auto-detects git state:
- uncommitted: has uncommitted changes
- stash: has stashed changes
- unpushed: branch not pushed or has unpushed commits
- clean: everything pushed
Uses BranchPushedToRemote() which properly handles polecat branches
that don't have upstream tracking (compares against origin/main).
On error, defaults to 'unpushed' to prevent accidental data loss.
Fixes: #342
Co-authored-by: mayor <mayor@gastown.local>
When a polecat runs `gt done` with COMPLETED status, it now nukes its own
worktree before exiting. This is the self-cleaning model - polecats clean
up after themselves, reducing Witness/Deacon cleanup burden.
The self-nuke is:
- Only attempted for polecats (not Mayor/Witness/Deacon/Refinery)
- Only on COMPLETED status (not ESCALATED/DEFERRED)
- Non-fatal: if it fails, Witness will handle cleanup
Closes: gt-fqcst
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
gt done now always exits the session. The --exit flag is removed since
exit is the only sensible behavior - polecats don't stay alive after
signaling completion.
Closes: gt-yrz4k
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
hq-u0ach: done.go - Add --cleanup-status flag so agents can pass cleanup
status directly. Removes computeCleanupStatus() which violated ZFC by
having Go compute cleanup status from git state.
hq-z0zqw: beads.go - Remove strings.Contains parsing for ErrNotARepo and
ErrSyncConflict. Per ZFC, Go should transport errors to agents, not parse
them to make decisions. IsBeadsRepo() now uses file existence check.
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>
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>
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>
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.
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>
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>
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>
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>
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>
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>
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>
Add CommitsAhead check after BranchPushedToRemote to prevent stale
branches (pushed but 0 commits ahead of main) from being submitted
to the merge queue.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
(gt-fpv2p)
When slinging work from town beads (hq-*) to a polecat whose agent bead
is in rig beads (gt-*), the hook_bead update was silently failing because
bd couldn't find the cross-beads reference.
Changes:
- sling.go: Use town root for routing instead of cwd, enabling cross-beads
resolution via routes.jsonl. Log warnings on failure instead of silent ignore.
- done.go: Use townRoot (already available) instead of cwd for beads client.
Log warnings on failure for both state and cleanup status updates.
Root cause: The beads client was created from current working directory,
which may not have access to routes.jsonl for cross-prefix resolution.
Town root always has routes.jsonl for proper prefix → rig directory mapping.
(gt-ohqxq)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add bidirectional cross-references between MR beads and agent beads:
1. MRFields.AgentBead - tracks which agent created the MR
2. AgentFields.ActiveMR - tracks agent's current MR
In gt done:
- Include agent_bead in MR description when creating
- Update agent bead with active_mr pointing to the new MR
In refinery merge handling:
- Clear agent bead's active_mr after successful merge
Benefits:
- Given MR, find which polecat created it
- Given polecat, find their active MR
- Orphan detection: MR without agent = stale
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add FindMRForBranch helper to check for existing MR beads before creating.
If an MR already exists for the branch, skip creation and reuse it.
This makes gt done safe to re-run if interrupted mid-execution.
Implements Option C from gt-svdsy: idempotent operations that check
if already done before doing, making it safe to retry.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The mrqueue package was aspirational 'beads-based MR automation' that was
never completed. The Refinery agent is prompt-driven and uses beads/mail
for coordination, not a Go-based polling queue.
Removed:
- internal/mrqueue/mrqueue.go (entire package)
- internal/cmd/mq_migrate.go (migration command for mrqueue)
- mrqueue submission from done.go and mq_submit.go
- Engineer.ProcessMRFromQueue() and related queue handlers
- Engineer.Run(), Stop(), processOnce() methods
- mrQueue field and stopCh from Engineer struct
- stopCh assertion from TestNewEngineer
Kept:
- Bead creation for merge-requests (audit record)
- Engineer struct and NewEngineer for potential future use
- Engineer.ProcessMR() (works with beads.Issue)
- Manager.ProcessMR() which is the working implementation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Root cause: gt done and mq submit created merge-request beads but did
not write to the .beads/mq/ directory that the refinery Engineer
polls for work.
Changes:
- done.go: Submit to mrqueue after creating MR bead
- mq_submit.go: Submit to mrqueue after creating MR bead
- mq_migrate.go: New command to migrate existing stale MR beads
- mrqueue.go: Follow beads redirects for shared queue location
The migration command allows recovery of existing stale MRs that were
never processed because they only existed as beads.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase 1 of activity feed improvements: gt commands now log events to
~/gt/.events.jsonl. This is the raw audit log that the feed daemon
(phase 2) will curate into the user-facing feed.
Instrumented commands:
- gt sling: logs sling events with bead and target
- gt hook: logs hook events with bead
- gt handoff: logs handoff events with subject
- gt done: logs done events with bead and branch
- gt mail send: logs mail events with to and subject
Event format follows the specification:
```json
{"ts":"2025-12-30T07:36:28Z","source":"gt","type":"mail",
"actor":"gastown/crew/joe","payload":{...},"visibility":"feed"}
```
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add PrintWarning helper in internal/style/style.go
- Update 35 warning message outputs across 16 files to use consistent format
- All warnings now display as "⚠ Warning: <message>" in yellow/bold
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Instead of Go code checking git state to decide if polecat removal is safe,
the polecat now self-reports its cleanup_status via its agent bead.
Changes:
- Add CleanupStatus field to AgentFields struct
- Update FormatAgentDescription and ParseAgentFields for cleanup_status
- Add UpdateAgentCleanupStatus function to beads package
- Update gt done to compute and report git cleanup status
- Update RemoveWithOptions to read cleanup_status from agent bead first,
falling back to git check for backward compatibility
Valid cleanup_status values:
- clean: no uncommitted work
- has_uncommitted: has uncommitted changes
- has_stash: has stashed changes
- has_unpushed: has unpushed commits
- unknown: git check failed
This follows ZFC (Zero Figuring in Code) principles - the polecat is the
authority on its own state, not Go code inferring it from external signals.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously gt done wrote MRs to .beads/mq/*.json files, but gt mq list
queried beads for issue_type=merge-request. These were two different
storage systems, so MRs created by gt done never showed in gt mq list.
Now gt done creates a proper MR bead with:
- issue_type: merge-request
- Description containing branch, target, source_issue, rig, worker
Also updated mq_submit.go for consistency.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Changes:
1. prime.go: Create agent beads on first prime for all roles including crew
2. done.go: Update agent state to done/stuck/idle when work completes
3. sling.go: Populate hook_bead when work is assigned to agents
4. mol-witness-patrol.formula.toml: Document dead and spawning states
Closes: gt-hymm0, gt-0lop3, gt-59k2x, gt-c4j4j
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Organize 43 commands into 7 logical groups using cobra's built-in
AddGroup/GroupID feature:
- Work Management: spawn, sling, hook, handoff, done, mol, mq, etc.
- Agent Management: mayor, witness, refinery, deacon, polecat, etc.
- Communication: mail, nudge, broadcast, peek
- Services: daemon, start, stop, up, down, shutdown
- Workspace: rig, crew, init, install, git-init, namepool
- Configuration: account, theme, hooks, issue, completion
- Diagnostics: status, doctor, prime, version, help
Also renamed molecule to mol as the primary command name
(molecule is now an alias).
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Architecture changes:
- Refinery created as worktree of mayor clone (shares .git)
- Polecat branches stay local (never pushed to origin)
- MRs stored as wisps in .beads-wisp/mq/ (ephemeral)
- Only main gets pushed to origin after merge
New mrqueue package for wisp-based MR storage.
Updated spawn, done, mq_submit, refinery, molecule templates.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Added --exit flag for exit type (COMPLETED, ESCALATED, DEFERRED).
When polecat runs gt done, it now sends mail to Witness with:
- Exit type (COMPLETED, ESCALATED, or DEFERRED)
- Issue ID (if available)
- MR ID (for COMPLETED)
- Branch name
For ESCALATED and DEFERRED, skips MR submission but still notifies
Witness. This enables Witness patrol to see completion in inbox-check
step, verify git state, and close polecat lease.
Paired with spawn notification (gt-r6td) to bracket polecat lifecycle.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
CRITICAL FIX: Both `gt done` and `gt mq submit` were creating MR
records without pushing the branch to origin first. When polecat
worktrees were deleted, the unpushed branches were lost forever.
This caused 12 MQ items to become orphaned - merge requests existed
but their branches had vanished.
The fix adds a mandatory `git push origin <branch>` before creating
the MR record. If push fails, the MR is not created.
Fixes: gt-aqku
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
