| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(#104)
Resolves the user-visible bug where editing a directive's goal mid-flight
shows "saved" but does not actually replan: the running planner kept emitting
add-step calls based on the OLD goal while a fresh planner was supposed to
take over, and the user had to wait up to 15s for the next reconciler tick
before any replanning even started.
## What was happening
PUT /api/v1/directives/{id}/goal already had two paths:
- Small change + planner running → SendMessage interrupt + KEEP orchestrator.
- Everything else → clear orchestrator_task_id and let phase_replanning
spawn a new planner on the next 15s tick.
The "everything else" path cleared the directive's pointer to the planner
task but never cancelled the task itself. The task kept executing and could
race the new planner by adding more steps from the stale plan. Worse, those
new steps could push MAX(steps.created_at) past the just-bumped
goal_updated_at, suppressing phase_replanning entirely.
## Fix
1. New helper `try_cancel_running_planner()` (orchestration/directive.rs):
sends `InterruptTask { graceful: true }` to the daemon owning the
orchestrator task and marks the task `interrupted` in the DB. All errors
are logged and swallowed so the goal update still completes.
2. update_goal handler calls the helper whenever it is about to take the
"clear orchestrator_task_id" branch, so the orphaned planner stops
producing stale-plan steps before its DB linkage is cut.
3. New `AppState::directive_kick` (tokio::sync::Notify) lets the handler
signal the reconciler to run a tick immediately. The reconciler loop in
server/mod.rs now selects between its 15s interval and the notify, so the
user no longer waits up to 15s after editing a goal before replanning
actually starts. update_goal calls `kick_directive_reconciler()` after
the goal is persisted (both paths).
## Why not also loosen `get_directives_needing_replanning`
The query already covers the common cases once the orphan-cancel lands —
without a still-running orphan adding fresh steps, goal_updated_at reliably
exceeds MAX(steps.created_at) after a goal edit. Loosening the predicate
risked spurious replans for directives that legitimately have no steps yet
(those are handled by `phase_planning`).
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
| |
|
|
|
|
|
|
|
|
|
| |
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Backend: feature flag + goal-edit interrupt messaging
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Frontend: Lexical document editor with step blocks, context menu, countdown
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(#100)
* revert: roll back PRs #93-#98 to pre-Lexical baseline
Reverts the entire chain of directive document UI work and the homepage redesign,
restoring the working tree to the state at 3679ceb (before c8b169d / PR #93).
PRs reverted:
- #93 c8b169d feat: Document UI for directive orchestration with Lexical editor
- #94 d6f01a6 fix: compilation error and warnings already merged via PR #93
- #95 5aa3faf fix: resolve compilation error and warnings in Rust backend
- #97 d513f93 feat: document UI with contract blocks, expandable logs, and interaction controls
- #96 6366941 feat: Redesign homepage with professional PC-98 styling
- #98 d1fdfb1 feat: revert broken directive PRs, re-implement Lexical document orchestrator
The directive Document UI experiments produced fragile output and merge artifacts;
follow-up commits in this PR change orchestration to favor strictly linear DAGs and
add goal/conflict verification so future runs do not require this kind of cleanup.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* feat(directive): strict-linear-DAG planning + mandatory `directive verify`
Tightens directive orchestration so the final PR almost never needs a hand-merge:
1. Planning prompts now strongly bias toward strictly linear DAGs.
Parallel steps are reserved for genuinely independent work (e.g. disjoint
modules); the default for "in doubt" is sequential. Linear chains inherit
each previous step's worktree, so the final merge is typically just a
rebase against the base branch.
2. New CLI command `makima directive verify` does a local in-memory
`git merge-tree` of HEAD against `<remote>/<base>` and exits non-zero
with a list of conflicting files if the PR would not merge cleanly.
Pure-local — no API call, no working-tree mutation.
3. Completion / PR-creation prompts now mandate three pre-push checks:
a. build (`cargo check` and/or `tsc --noEmit`),
b. `makima directive verify --base <base_branch>` must exit 0, and
c. an explicit goal-alignment self-check against the diff.
The orchestrator is told NOT to push, create the PR, or call
`makima directive update` until all three pass. Skipping any of them
is documented as a directive failure.
The combination means that with a linear DAG the final PR-creation task
should almost never see a real conflict — when it does, that is treated as
a planning bug to escalate rather than something to paper over with
`-X theirs`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(frontend): TS errors pre-existing on master
- TaskSlideOutPanel: declare missing `selectedFileDiff` / `selectedFilePath`
state hooks that were referenced everywhere but never created, and
re-balance the JSX so the `<>...</>` fragment in the non-diff branch is
closed (the previous indentation/braces would not parse).
- api.ts: add a `getWorktreeDiff` thin wrapper around `getTaskDiff` so
TaskDetail's per-file click handler type-checks (the per-file slice is a
future improvement; today both return the full task diff).
- WorktreeFilesPanel: remove unused `isClickable` local; the gating already
reads `onFileClick` directly inline.
Run after revert: `npx tsc --noEmit` exits 0.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
orchestrator (#98)
* feat: soryu-co/soryu - makima: Revert broken directive PRs and verify clean build
* feat: soryu-co/soryu - makima: Re-implement frontend: Lexical document editor with feature flag and base components
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Add contract blocks, expandable log rows, and interaction controls
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: End-to-end build verification and integration polish
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Save previous goal on update and include history in re-planning prompt
* feat: soryu-co/soryu - makima: Install Lexical and create base document editor component
* feat: soryu-co/soryu - makima: Create directive file system sidebar and document layout
* feat: soryu-co/soryu - makima: Create custom Lexical step diagram block
* feat: soryu-co/soryu - makima: Add context menu and goal auto-update integration
* WIP: heartbeat checkpoint
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
* feat: soryu-co/soryu - makima: Fix worktree info failing when origin ref is missing
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Add worktree commit endpoint and diff endpoint for regular users
* feat: soryu-co/soryu - makima: Add frontend diff viewing with clickable worktree files
|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
steps, rename Mesh to Exec (#84)
* feat: soryu-co/soryu - makima: Rename Mesh to Exec in navigation
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Add contract-backed steps to directive flow
* WIP: heartbeat checkpoint
|
| |
|
|
|
|
|
|
|
|
|
| |
* feat: soryu-co/soryu - makima: Remove aarch64-unknown-linux-gnu from release workflow
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Implement non-blocking ask with client-side polling for reconcile mode
|
| |
|
|
|
|
|
|
|
|
|
| |
* feat: soryu-co/soryu - makima: Add server-side daemon binary download endpoint
* feat: soryu-co/soryu - makima: Create Kubernetes daemon manifests and Dockerfile
* feat: soryu-co/soryu - makima: Create dedicated Daemons page with health monitoring UI
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Integrate daemon platform availability into frontend downloads
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
* feat: soryu-co/soryu: Reorder navigation: move Orders before Contracts
* feat: soryu-co/soryu: Generate PR titles from step content instead of directive title
* feat: soryu-co/soryu: Add orderId field to step creation and link orders to steps
* feat: soryu-co/soryu: Handle completed orders during plan-orders flow
* WIP: heartbeat checkpoint
* Merge origin/makima/soryu-co-soryu--handle-completed-orders-during-pla-5aa9a15b (resolved conflicts)
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
name (#65)
* feat: soryu-co/soryu - makima: Add frontend pick-up-orders button and API integration
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Remove contract link from orders and add directive name to order metadata (frontend)
* fix: contracts page overflow - use contained scrolling layout
Changed the contracts page to use contained scrolling matching the
orders/directives pages, preventing the page from growing beyond
viewport height.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: resolve completion_task_id FK violation and duplicate button
The completion_task_id column has an FK to tasks(id), but
claim_directive_for_completion was being called with a placeholder UUID
that did not exist in the tasks table, causing FK constraint violations.
Fix: Create the task FIRST via create_task_for_owner, then use the real
task.id when calling claim_directive_for_completion. Applied in all three
locations: phase_completion Part 1 (idle directives), Part 3 (verification
tasks), and trigger_completion_task (manual PR creation).
Also removes a duplicate "Pick Up Orders" button in DirectiveDetail.tsx.
* fix: restore Order type changes lost during rebase conflict resolution
Re-apply changes from the orders-refactor commit that were dropped when
resolving rebase conflicts with --ours:
- Replace contractId with directiveName in Order interface
- Make directiveId required in CreateOrderRequest
- Remove contractId from UpdateOrderRequest
- Change listOrders parameter from contractId to search
- Remove linkOrderToContract function
- Simplify convertOrderToStep to single argument
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
| | |
|
| |
|
|
|
|
|
|
|
| |
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Add frontend pick-up-orders button and API integration
* feat: soryu-co/soryu - makima: Add pick-up-orders backend endpoint and repository functions
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
bug fixes (#62)
* feat: soryu-co/soryu - makima: Fix directive goal update bug - stale closure issue
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Create Orders database schema and backend API
* feat: soryu-co/soryu - makima: Fix task Claude instance not receiving user inputs from input box
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Build Orders frontend page replacing the Board page
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* feat: soryu-co/soryu - makima: Fix directive PR creation system
|
| | |
|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* feat: makima: Add an optional memory system for directives: Add directive_memories database table and migration
* feat: makima: Add an optional memory system for directives: Update directive skill documentation with memory commands
* feat: makima: Add an optional memory system for directives: Add repository functions for directive memory CRUD
* feat: makima: Add an optional memory system for directives: Add frontend API functions and types for directive memory
* feat: makima: Add an optional memory system for directives: Add Rust models for directive memory
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* WIP: heartbeat checkpoint
* feat: makima: Add an optional memory system for directives: Add memory panel to frontend DirectiveDetail component
* Merge remote-tracking branch 'origin/makima/makima--add-an-optional-memory-system-for-directiv-5de1e06d' into combined branch
* Merge remote-tracking branch 'origin/makima/makima--add-an-optional-memory-system-for-directiv-c8298c6c' into combined branch
* feat: makima: Add an optional memory system for directives: Create useMultiTaskSubscription hook for multi-output WebSocket streaming
* feat: makima: Add an optional memory system for directives: Create DirectiveLogStream component for stern-like multi-task output viewing
* feat: makima: Add an optional memory system for directives: Integrate log stream panel into directive detail page
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Redesigns the chain system with a directive-first architecture where
Directive is the top-level entity (the "why/what") and Chains are
generated execution plans (the "how") that can be dynamically modified.
Backend:
- Add database migration for directive system tables
- Add Directive, DirectiveChain, ChainStep, DirectiveEvent models
- Add DirectiveVerifier and DirectiveApproval models
- Add orchestration module with engine, planner, and verifier
- Add comprehensive API handlers for directives
- Add daemon CLI commands for directive management
- Add directive skill documentation
- Integrate contract completion with directive engine
- Add SSE endpoint for real-time directive events
Frontend:
- Add directives route with split-view layout
- Add 6-tab detail view (Overview, Chain, Events, Evaluations, Approvals, Verifiers)
- Add React Flow DAG visualization for chain steps
- Add SSE subscription hook for real-time event updates
- Add useDirectives and useDirectiveEventSubscription hooks
- Add directive types and API functions
Fixes:
- Fix test failures in ws/protocol, task_output, completion_gate, patch
- Fix word boundary matching in looks_like_task()
- Fix parse_last() to find actual last completion gate
- Fix create_export_patch when merge-base equals HEAD
- Clean up clippy warnings in new code
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Chains can now have multiple repositories attached, with one marked as
primary. Repositories are used by contracts created from chain definitions.
Backend changes:
- Add chain_repositories table migration
- Add ChainRepository model with CRUD operations
- Add API endpoints for listing, adding, deleting repositories
- Add endpoint to set a repository as primary
- Update Chain and ChainEditorData models to use repositories
- Update chain parser to support repositories in YAML format
- Remove deprecated repository_url/local_path from Chain
Frontend changes:
- Add ChainRepository interface and API functions
- Add repository section to ChainEditor showing attached repos
- Add modal for adding new repositories (remote or local)
- Support setting primary repository and removing repositories
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
| | |
|
| | |
|
| | |
|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Implement REST API endpoints for querying supervisor status:
- GET /api/v1/contracts/{id}/supervisor/status
Returns current supervisor status including task_id, state, phase,
current_activity, progress, last_heartbeat, and pending_task_ids
- GET /api/v1/contracts/{id}/supervisor/heartbeats?limit=10
Returns paginated supervisor activity history from history_events
- POST /api/v1/contracts/{id}/supervisor/sync
Triggers a sync to refresh the supervisor's last_activity timestamp
New types added:
- SupervisorStatusResponse - Status endpoint response
- SupervisorHeartbeatEntry - Individual heartbeat history entry
- SupervisorHeartbeatHistoryResponse - Heartbeat history with pagination
- SupervisorSyncResponse - Sync endpoint response
- HeartbeatHistoryQuery - Query params for heartbeats endpoint
Repository helpers:
- get_supervisor_status() - Combined info from supervisor_states and tasks
- get_supervisor_activity_history() - Activity timeline from history_events
- count_supervisor_activity_history() - Total count for pagination
- sync_supervisor_state() - Refresh last_activity timestamp
Error handling:
- 404 for contract not found (CONTRACT_NOT_FOUND)
- 404 for no supervisor (SUPERVISOR_NOT_FOUND)
- Proper fallback when supervisor_state record doesn't exist but task does
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* Task completion checkpoint
* Task completion checkpoint
* Task completion checkpoint
* Add Qwen3-TTS research document for live TTS replacement
Research findings for replacing Chatterbox TTS with Qwen3-TTS-12Hz-0.6B-Base:
- Current TTS: Chatterbox-Turbo-ONNX with batch-only generation, no streaming
- Qwen3-TTS: 97ms end-to-end latency, streaming support, 3-second voice cloning
- Voice cloning: Requires 3s reference audio + transcript (Makima voice planned)
- Integration: Python service with WebSocket bridge (no ONNX export available)
- Languages: 10 supported including English and Japanese
Document includes:
- Current architecture analysis (makima/src/tts.rs)
- Qwen3-TTS capabilities and requirements
- Feasibility assessment for live/streaming TTS
- Audio clip requirements for voice cloning
- Preliminary technical approach with architecture diagrams
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* [WIP] Heartbeat checkpoint - 2026-01-27 03:11:15 UTC
* Add Qwen3-TTS research documentation
Comprehensive research on replacing Chatterbox TTS with Qwen3-TTS-12Hz-0.6B-Base:
- Current TTS implementation analysis (Chatterbox-Turbo-ONNX in makima/src/tts.rs)
- Qwen3-TTS capabilities: 97ms streaming latency, voice cloning with 3s reference
- Cross-lingual support: Japanese voice (Makima/Tomori Kusunoki) speaking English
- Python microservice architecture recommendation (FastAPI + WebSocket)
- Implementation phases and technical approach
- Hardware requirements and dependencies
Key findings:
- Live/streaming TTS is highly feasible with 97ms latency
- Voice cloning fully supported with 0.95 speaker similarity
- Recommended: Python microservice with WebSocket streaming
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add comprehensive Qwen3-TTS integration specification
This specification document defines the complete integration of
Qwen3-TTS-12Hz-0.6B-Base as a replacement for the existing Chatterbox-Turbo
TTS implementation. The document covers:
## Functional Requirements
- WebSocket endpoint /api/v1/speak for streaming TTS
- Voice cloning with default Makima voice (Japanese VA speaking English)
- Support for custom voice references
- Detailed client-to-server and server-to-client message protocols
- Integration with Listen page for bidirectional speech
## Non-Functional Requirements
- Latency targets: < 200ms first audio byte
- Audio quality: 24kHz, mono, PCM16/PCM32f
- Hardware requirements: CUDA GPU with 4-8GB VRAM
- Scalability: 10 concurrent sessions per GPU
## Architecture Specification
- Python TTS microservice with FastAPI/WebSocket
- Rust proxy endpoint in makima server
- Voice prompt caching mechanism (LRU cache)
- Error handling and recovery strategies
## API Contract
- Complete WebSocket message format definitions (TypeScript)
- Error codes and responses (TTS_UNAVAILABLE, SYNTHESIS_ERROR, etc.)
- Session state machine and lifecycle management
## Voice Asset Requirements
- Makima voice clip specifications (5-10s WAV, transcript required)
- Storage location: models/voices/makima/
- Metadata format for voice management
## Testing Strategy
- Unit tests for Python TTS service and Rust proxy
- Integration tests for WebSocket flow
- Latency benchmarks with performance targets
- Test data fixtures for various text lengths
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add Qwen3-TTS implementation plan
Comprehensive implementation plan for replacing Chatterbox-TTS with
Qwen3-TTS streaming TTS service, including:
- Task breakdown with estimated hours for each phase
- Phase 1: Python TTS microservice (FastAPI, WebSocket)
- Phase 2: Rust proxy integration (speak.rs, tts_client.rs)
- Detailed file changes and new module structure
- Testing plan with unit, integration, and latency benchmarks
- Risk assessment with mitigation strategies
- Success criteria for each phase
Based on specification in docs/specs/qwen3-tts-spec.md
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add author and research references to TTS implementation plan
Add links to research documentation and author attribution.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* [WIP] Heartbeat checkpoint - 2026-01-27 03:25:06 UTC
* Add Python TTS service project structure (Phase 1.1-1.3)
Create the initial makima-tts Python service directory structure with:
- pyproject.toml with FastAPI, Qwen-TTS, and torch dependencies
- config.py with pydantic-settings TTSConfig class
- models.py with Pydantic message models (Start, Speak, Stop, Ready, etc.)
This implements tasks P1.1, P1.2, and P1.3 from the Qwen3-TTS implementation plan.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add TTS engine and voice manager for Qwen3-TTS (Phase 1.4-1.5)
Implement core TTS functionality:
- tts_engine.py: Qwen3-TTS wrapper with streaming audio chunk generation
- voice_manager.py: Voice prompt caching with LRU eviction and TTL support
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* [WIP] Heartbeat checkpoint - 2026-01-27 03:30:06 UTC
* Add TTS proxy client and message types (Phase 2.1, 2.2, 2.4)
- Add tts_client.rs with TtsConfig, TtsCircuitBreaker, TtsError,
TtsProxyClient, and TtsConnection structs for WebSocket proxying
- Add TTS message types to messages.rs (TtsAudioEncoding, TtsPriority,
TtsStartMessage, TtsSpeakMessage, TtsStopMessage, TtsClientMessage,
TtsReadyMessage, TtsAudioChunkMessage, TtsCompleteMessage,
TtsErrorMessage, TtsStoppedMessage, TtsServerMessage)
- Export tts_client module from server mod.rs
- tokio-tungstenite already present in Cargo.toml
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add TTS WebSocket handler and route (Phase 2.3, 2.5, 2.6)
- Create speak.rs WebSocket handler that proxies to Python TTS service
- Add TtsState fields (tts_client, tts_config) to AppState
- Add with_tts() builder and is_tts_healthy() methods to AppState
- Register /api/v1/speak route in the router
- Add speak module export in handlers/mod.rs
The handler forwards WebSocket messages bidirectionally between
the client and the Python TTS microservice with proper error handling.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add Makima voice profile assets for TTS voice cloning
Creates the voice assets directory structure with:
- manifest.json containing voice configuration (voice_id, speaker,
language, reference audio path, and Japanese transcript placeholder)
- README.md with instructions for obtaining voice reference audio
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add Rust-native Qwen3-TTS integration research document
Research findings for integrating Qwen3-TTS-12Hz-0.6B-Base directly into
the makima Rust codebase without Python. Key conclusions:
- ONNX export is not viable (unsupported architecture)
- Candle (HF Rust ML framework) is the recommended approach
- Model weights available in safetensors format (2.52GB total)
- Three components needed: LM backbone, code predictor, speech tokenizer
- Crane project has Qwen3-TTS as highest priority (potential upstream)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* [WIP] Heartbeat checkpoint - 2026-01-27 11:21:43 UTC
* [WIP] Heartbeat checkpoint - 2026-01-27 11:24:19 UTC
* [WIP] Heartbeat checkpoint - 2026-01-27 11:26:43 UTC
* feat: implement Rust-native Qwen3-TTS using candle framework
Replace monolithic tts.rs with modular tts/ directory structure:
- tts/mod.rs: TtsEngine trait, TtsEngineFactory, shared types (AudioChunk,
TtsError), and utility functions (save_wav, resample, argmax)
- tts/chatterbox.rs: existing ONNX-based ChatterboxTTS adapted to implement
TtsEngine trait with Mutex-wrapped sessions for Send+Sync
- tts/qwen3/mod.rs: Qwen3Tts entry point with HuggingFace model loading
- tts/qwen3/config.rs: Qwen3TtsConfig parsing from HF config.json
- tts/qwen3/model.rs: 28-layer Qwen3 transformer with RoPE, GQA (16 heads,
8 KV heads), SiLU MLP, RMS norm, and KV cache
- tts/qwen3/code_predictor.rs: 5-layer MTP module predicting 16 codebooks
- tts/qwen3/speech_tokenizer.rs: ConvNet encoder/decoder with 16-layer RVQ
- tts/qwen3/generate.rs: autoregressive generation loop with streaming support
Add candle-core, candle-nn, candle-transformers, safetensors to Cargo.toml.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: integrate TTS engine into speak WebSocket handler
- Update speak.rs handler to use TTS engine directly from SharedState
instead of returning a stub "not implemented" error
- Add TtsEngine (OnceCell lazy-loaded) to AppState in state.rs with
get_tts_engine() method for lazy initialization on first connection
- Implement full WebSocket protocol: client sends JSON speak/cancel/stop
messages, server streams binary PCM audio chunks and audio_end signals
- Create voices/makima/manifest.json for Makima voice profile configuration
- All files compile successfully with zero errors
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: add /speak TTS page with WebSocket audio playback
Add a new /speak frontend page for text-to-speech via WebSocket.
The page accepts text input and streams synthesized PCM audio through
the Web Audio API. Includes model loading indicator, cancel support,
and connection status. Also adds a loading bar to the listen page
ControlPanel during WebSocket connection.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
|
| | |
|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Implements a parallel "red team" task that monitors work task outputs in
real-time, verifying implementations stick to contract requirements,
repository standards, and the execution plan.
Key features:
- New `red_team_enabled` and `red_team_prompt` contract configuration
- Red team tasks auto-spawn when first work task is created
- `makima red-team notify` CLI command for alerting supervisors
- POST /api/v1/mesh/red-team/notify and /status endpoints
- Alert delivery to supervisor via SendMessage daemon command
- Notification audit trail via history_events table
Database changes:
- Add red_team_enabled/red_team_prompt columns to contracts
- Add is_red_team flag to tasks with partial index
- Create red_team_notifications table for audit logging
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* feat: Add contract type templates API endpoint
Add a new API endpoint to provide contract type templates (workflow
definitions) separate from file templates. This enables the create
contract page to dynamically show available contract types.
Changes:
- Add ContractTypeTemplate struct in templates.rs with id, name,
description, phases, default_phase, and is_builtin fields
- Add built-in contract types: 'simple' (plan/execute) and
'specification' (research/specify/plan/execute/review)
- Add GET /api/v1/contract-types endpoint returning all contract types
- Add frontend ContractTypeTemplate interface and listContractTypes()
API function
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: Update create contract modal to use dynamic templates
- Add ContractTypeTemplate interface and listContractTypes API function
to frontend api.ts
- Add GET /api/v1/contract-types backend endpoint that returns built-in
contract types (simple, specification) with their phases and defaults
- Update create contract modal to fetch contract types dynamically when
opened, with loading state and fallback to hardcoded types on error
- Dynamically render contract type selection buttons from fetched types
- Update phase dropdown to use phases from selected contract type
- Replace static getValidPhases/getDefaultPhase calls with dynamic data
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
|
| | |
|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* Add daemon restart feature from settings
This adds the ability to restart a connected daemon from the settings page.
The feature includes:
- Backend: RestartDaemon command added to DaemonCommand enum
- Backend: New POST /api/v1/mesh/daemons/{id}/restart endpoint
- Backend: Daemon gracefully shuts down tasks and exits with code 42
(can be used by process managers like systemd to detect restart requests)
- Frontend: restartDaemon() API function
- Frontend: Restart button in Connected Daemons section of settings
- Frontend: Confirmation dialog before restart to prevent accidental restarts
When a daemon receives the restart command, it:
1. Gracefully shuts down all running Claude processes (5s timeout)
2. Exits with code 42 to signal restart requested
3. The daemon can be restarted by a process manager or manually
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
| | |
|
| | |
|
| |
|
|
| |
Also add checkpointing/history
|
| | |
|