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>
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>
