soryu/makima/src/daemon/cli/supervisor.rs, branch makima/fix-hf-cli-command

Fix makima supervisor pr CLI command

2026-01-29T01:14:17+00:00

Default to shared worktree and add worktree endpoint

2026-01-27T01:25:40+00:00

Add completion phases

2026-01-26T20:19:30+00:00

feat: Add client-side polling for CLI wait command (#23)

2026-01-23T19:49:58+00:00

* [WIP] Heartbeat checkpoint - 2026-01-23 03:34:44 UTC * feat: Add client-side polling for CLI wait command When contracts wait for tasks in makima, the CLI now polls and returns once the task has changed state. This provides resilient task status detection even if: - Server's broadcast channels miss a notification - Network connections are intermittent - Long-polling HTTP requests timeout at load balancers The implementation uses a hybrid approach: 1. First tries server-side wait with short timeout (30s) 2. Falls back to polling via supervisor_get_task endpoint 3. Configurable poll_interval (default 5s) via --poll-interval flag Co-Authored-By: Claude Opus 4.5 --------- Co-authored-by: Claude Opus 4.5

Add non-blocking persistent contract completion questions (#14)

2026-01-20T23:20:32+00:00

* [WIP] Heartbeat checkpoint - 2026-01-20 22:40:37 UTC * Task completion checkpoint

Clean contract lifecycle: Add supervisor complete command (#13)

2026-01-20T17:19:18+00:00

* feat: Add contract lifecycle management commands (complete and resume-contract) Add supervisor commands for properly managing contract lifecycle: - `makima supervisor complete` - Mark a contract as complete and stop the supervisor - `makima supervisor resume-contract` - Resume a completed contract (reactivate it) Also adds `api_key` field to TaskConfig for authenticated API calls. This consolidates the lifecycle management features from the contract-lifecycle-cleanup branch. Co-Authored-By: Claude Opus 4.5 * Fix: prevent supervisor auto-start for completed contracts When viewing a completed contract, the supervisor was auto-starting on component mount. This would resurrect completed contracts and cause them to continue running. Changes: - Add contract.status !== 'completed' check to the auto-start condition - Add contract.status to the useEffect dependency array Co-Authored-By: Claude Opus 4.5 * Task completion checkpoint --------- Co-authored-by: Claude Opus 4.5

Add pushed heartbeats and multi-question select

2026-01-18T18:55:04+00:00

Add phaseguard flag for supervisor questions to wait indefinitely (#4)

2026-01-18T17:44:18+00:00

* Add phaseguard flag to supervisor ask command When phaseguard is enabled (--phaseguard flag), the supervisor's ask command will block indefinitely waiting for user response instead of timing out after the default 1 hour. This ensures that phase transitions requiring user confirmation cannot proceed without explicit approval. Changes: - Add phaseguard field to AskQuestionRequest in server handler - Add phaseguard field to AskQuestionRequest in API client - Add --phaseguard CLI flag to AskArgs - Update supervisor_ask() to accept phaseguard parameter - Modify ask_question handler to skip timeout check when phaseguard=true Co-Authored-By: Claude Opus 4.5 * Task completion checkpoint --------- Co-authored-by: Claude Opus 4.5

Fixup: use default api.makima.jp URL and fix default branch detection

2026-01-16T12:23:49+00:00

Also add checkpointing/history

Add resume and history system for makima (#1)

2026-01-15T22:33:47+00:00

This PR implements a comprehensive resume and history system that enables: 1. **History Viewing** - View complete conversation history for contracts across all phases - View conversation history for individual tasks - View task output/tool call history with timestamps - View checkpoint history - Timeline view showing all activities 2. **Resume System** - Resume interrupted supervisor conversations with full context - Resume interrupted task conversations - Resume from specific checkpoints - Continue tasks from previous task state (worktree inheritance) 3. **Rewind/Restore Features** - Rewind code to any checkpoint (git restore) - Rewind conversation to any point - Create new branches from historical points - Fork tasks from any point in history - New migration: 20250117000000_history_tables.sql - conversation_snapshots table for storing conversation state - history_events table for unified timeline - Added forking fields to tasks table - Added conversation_snapshot_id to task_checkpoints - ConversationSnapshot, HistoryEvent, ConversationMessage - Request/response types for resume and rewind operations - Query filter types for history endpoints - CRUD functions for conversation_snapshots - CRUD functions for history_events - Task conversation retrieval from task_events - GET /api/v1/contracts/{id}/history - GET /api/v1/contracts/{id}/supervisor/conversation - GET /api/v1/mesh/tasks/{id}/conversation - GET /api/v1/timeline - POST /api/v1/contracts/{id}/supervisor/resume - POST /api/v1/mesh/tasks/{id}/rewind - POST /api/v1/mesh/tasks/{id}/fork - POST /api/v1/mesh/tasks/{id}/checkpoints/{cid}/resume - POST /api/v1/mesh/tasks/{id}/checkpoints/{cid}/branch - POST /api/v1/contracts/{id}/supervisor/conversation/rewind - task-history: View task conversation history - task-checkpoints: List task checkpoints - resume: Resume supervisor after interruption - task-resume-from: Resume task from checkpoint - task-rewind: Rewind task code to checkpoint - task-fork: Fork task from historical point - rewind-conversation: Rewind supervisor conversation