The task queue was completely stuck: 82 tasks trapped in pending_approval,
4 zombie tasks frozen in running, and the worker loop unable to process
anything. This removes the approval gate as the default and adds startup
recovery for orphaned tasks.
- Auto-approve all tasks by default; only task_type="escalation" requires
human review (and escalations never block the processor)
- Add reconcile_zombie_tasks() to reset RUNNING→APPROVED on startup
- Use in-memory _current_task for concurrency check instead of DB status
so stale RUNNING rows from a crash can't block new work
- Update get_next_pending_task to only query APPROVED tasks
- Update all callsites (chat route, API, form) to match new defaults
Co-authored-by: Alexander Payne <apayne@MM.local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Errors and uncaught exceptions are now automatically captured, deduplicated,
persisted to a rotating log file, and filed as bug report tasks in the
existing task queue — giving Timmy a sovereign, local issue tracker with
zero new dependencies.
- Add RotatingFileHandler writing errors to logs/errors.log (5MB rotate, 5 backups)
- Add error capture module with stack-trace hashing and 5-min dedup window
- Add FastAPI exception middleware + global exception handler
- Instrument all background loops (briefing, thinking, task processor) with capture_error()
- Extend task queue with bug_report task type and auto-approve rule
- Fix auto-approve type matching (was ignoring task_type field entirely)
- Add /bugs dashboard page and /api/bugs JSON endpoints
- Add ERROR_CAPTURED and BUG_REPORT_CREATED event types for real-time feed
- Add BUGS nav link to desktop and mobile navigation
- Add 16 tests covering error capture, deduplication, and bug report routes
Co-authored-by: Alexander Payne <apayne@MM.local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
11 tests verify that the TaskProcessor drains all queued tasks to
completion — the core behavior needed for Timmy's stream of
consciousness. Tests cover: single/batch/burst processing, priority
ordering, mixed task types, failure recovery, timestamp tracking,
and a loop-based inbox zero assertion.
Adds an `isolated_task_db` fixture to functional conftest that gives
each test a fresh temporary SQLite database via pytest's tmp_path.
Co-authored-by: Alexander Payne <apayne@MM.local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add task queue system for Timmy - all work goes through the queue
- Add queue position tracking to task_queue models with task_type field
- Add TaskProcessor class that consumes tasks from queue one at a time
- Modify chat route to queue all messages for async processing
- Chat responses get 'high' priority to jump ahead of thought tasks
- Add queue status API endpoints for position polling
- Update UI to show queue position (x/y) and current task banner
- Replace thinking loop with task-based approach - thoughts are queued tasks
- Push responses to user via WebSocket instead of immediate HTTP response
- Add database migrations for existing tables
* feat: Timmy drains task queue on startup, backlogs unhandleable tasks
On spin-up, Timmy now iterates through all pending/approved tasks
immediately instead of waiting for the polling loop. Tasks without a
registered handler or with permanent errors are moved to a new
BACKLOGGED status with a reason, keeping the queue clear for work
Timmy can actually do.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Alexander Payne <apayne@MM.local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* test: remove hardcoded sleeps, add pytest-timeout
- Replace fixed time.sleep() calls with intelligent polling or WebDriverWait
- Add pytest-timeout dependency and --timeout=30 to prevent hangs
- Fixes test flakiness and improves test suite speed
* feat: add Aider AI tool to Forge's toolkit
- Add Aider tool that calls local Ollama (qwen2.5:14b) for AI coding assist
- Register tool in Forge's code toolkit
- Add functional tests for the Aider tool
* config: add opencode.json with local Ollama provider for sovereign AI
* feat: Timmy fixes and improvements
## Bug Fixes
- Fix read_file path resolution: add ~ expansion, proper relative path handling
- Add repo_root to config.py with auto-detection from .git location
- Fix hardcoded llama3.2 - now dynamic from settings.ollama_model
## Timmy's Requests
- Add communication protocol to AGENTS.md (read context first, explain changes)
- Create DECISIONS.md for architectural decision documentation
- Add reasoning guidance to system prompts (step-by-step, state uncertainty)
- Update tests to reflect correct model name (llama3.1:8b-instruct)
## Testing
- All 177 dashboard tests pass
- All 32 prompt/tool tests pass
* feat: Timmy system introspection, delegation, and session logging
## System Introspection (Sovereign Self-Knowledge)
- Add get_system_info() tool - Timmy can now query his runtime environment
- Add check_ollama_health() - verify Ollama status
- Add get_memory_status() - check memory tier status
- True introspection vs hardcoded prompts
## Path Resolution Fix
- Fix all toolkits to use settings.repo_root consistently
- Now uses Path(settings.repo_root) instead of Path.cwd()
## Inter-Agent Delegation
- Add delegate_task() tool - Timmy can dispatch to Seer, Forge, Echo, etc.
- Add list_swarm_agents() - query available agents
## Session Logging
- Add SessionLogger for comprehensive interaction logging
- Records messages, tool calls, errors, decisions
- Writes to /logs/session_{date}.jsonl
## Tests
- Add tests for introspection tools
- Add tests for delegation tools
- Add tests for session logging
- Add tests for path resolution
- All 18 new tests pass
- All 177 dashboard tests pass
---------
Co-authored-by: Alexander Payne <apayne@MM.local>
Add /api/chat, /api/upload, and /api/chat/history endpoints to the
FastAPI dashboard so the Expo mobile app talks directly to Timmy's
brain (Ollama) instead of a non-existent Node.js server.
Backend:
- New src/dashboard/routes/chat_api.py with 4 endpoints
- Mount /uploads/ for serving chat attachments
- Same context injection and session management as HTMX chat
Mobile app fixes:
- Point API base URL at port 8000 (FastAPI) instead of 3000
- Create lib/_core/theme.ts (was referenced but never created)
- Fix shared/types.ts (remove broken drizzle/errors re-exports)
- Remove broken server/chat.ts and 1,235-line template README
- Clean package.json (remove express, mysql2, drizzle, tRPC deps)
- Remove debug console.log from theme-provider
Tests: 13 new tests covering all API endpoints (all passing).
https://claude.ai/code/session_01XqErDoh2rVsPY8oTj21Lz2
Co-authored-by: Claude <noreply@anthropic.com>
* test: remove hardcoded sleeps, add pytest-timeout
- Replace fixed time.sleep() calls with intelligent polling or WebDriverWait
- Add pytest-timeout dependency and --timeout=30 to prevent hangs
- Fixes test flakiness and improves test suite speed
* feat: add Aider AI tool to Forge's toolkit
- Add Aider tool that calls local Ollama (qwen2.5:14b) for AI coding assist
- Register tool in Forge's code toolkit
- Add functional tests for the Aider tool
* config: add opencode.json with local Ollama provider for sovereign AI
* feat: Timmy fixes and improvements
## Bug Fixes
- Fix read_file path resolution: add ~ expansion, proper relative path handling
- Add repo_root to config.py with auto-detection from .git location
- Fix hardcoded llama3.2 - now dynamic from settings.ollama_model
## Timmy's Requests
- Add communication protocol to AGENTS.md (read context first, explain changes)
- Create DECISIONS.md for architectural decision documentation
- Add reasoning guidance to system prompts (step-by-step, state uncertainty)
- Update tests to reflect correct model name (llama3.1:8b-instruct)
## Testing
- All 177 dashboard tests pass
- All 32 prompt/tool tests pass
---------
Co-authored-by: Alexander Payne <apayne@MM.local>
* test: remove hardcoded sleeps, add pytest-timeout
- Replace fixed time.sleep() calls with intelligent polling or WebDriverWait
- Add pytest-timeout dependency and --timeout=30 to prevent hangs
- Fixes test flakiness and improves test suite speed
* feat: add Aider AI tool to Forge's toolkit
- Add Aider tool that calls local Ollama (qwen2.5:14b) for AI coding assist
- Register tool in Forge's code toolkit
- Add functional tests for the Aider tool
---------
Co-authored-by: Alexander Payne <apayne@MM.local>
- Replace fixed time.sleep() calls with intelligent polling or WebDriverWait
- Add pytest-timeout dependency and --timeout=30 to prevent hangs
- Fixes test flakiness and improves test suite speed
Co-authored-by: Alexander Payne <apayne@MM.local>
- Add `requests` to conftest.py module stubs so patch("requests.post") works
in reward scoring tests without the package installed
- Use sys.executable instead of bare "python" in git safety tests so the
subprocess finds pytest from the venv rather than system python
https://claude.ai/code/session_012Ye9nyFEiw2QQfx4bZeDmn
Test fixtures that create temporary git repos now set commit.gpgsign=false
to avoid failures in environments with global commit signing configured.
The permission error test is skipped when running as root since file
permissions don't apply to the root user.
https://claude.ai/code/session_018u1fAx2GihSGctYS64tD4H
Inspired by OpenClaw-RL's multi-model orchestration, this adds four
features for custom model management:
1. Custom model registry (infrastructure/models/registry.py) — SQLite-backed
registry for GGUF, safetensors, HF checkpoint, and Ollama models with
role-based lookups (general, reward, teacher, judge).
2. Per-agent model assignment — each swarm persona can use a different model
instead of sharing the global default. Resolved via registry assignment >
persona default > global default.
3. Runtime model management API (/api/v1/models) — REST endpoints to register,
list, assign, enable/disable, and remove custom models without restart.
Includes a dashboard page at /models.
4. Reward model scoring (PRM-style) — majority-vote quality evaluation of
agent outputs using a configurable reward model. Scores persist in SQLite
and feed into the swarm learner.
New config settings: custom_weights_dir, reward_model_enabled,
reward_model_name, reward_model_votes.
54 new tests covering registry CRUD, API endpoints, agent assignments,
role lookups, and reward scoring.
https://claude.ai/code/session_01V4iTozMwcE2gjfnCJdCugC
- Add GrokBackend class in src/timmy/backends.py with full sync/async
support, health checks, usage stats, and cost estimation in sats
- Add consult_grok tool to Timmy's toolkit for proactive Grok queries
- Extend cascade router with Grok provider type for failover chain
- Add Grok Mode toggle card to Mission Control dashboard (HTMX live)
- Add "Ask Grok" button on chat input for direct Grok queries
- Add /grok/* routes: status, toggle, chat, stats endpoints
- Integrate Lightning invoice generation for Grok usage monetization
- Add GROK_ENABLED, XAI_API_KEY, GROK_DEFAULT_MODEL, GROK_MAX_SATS_PER_QUERY,
GROK_FREE config settings via pydantic-settings
- Update .env.example and docker-compose.yml with Grok env vars
- Add 21 tests covering backend, tools, and route endpoints (all green)
Local-first ethos preserved: Grok is premium augmentation only,
disabled by default, and Lightning-payable when enabled.
https://claude.ai/code/session_01FygwN8wS8J6WGZ8FPb7XGV
Enable Timmy to run directly on iPhone by loading a small LLM into
the browser via WebGPU (Safari 26+ / iOS 26+). No server connection
required — fully sovereign, fully offline.
New files:
- static/local_llm.js: WebLLM wrapper with model catalogue, WebGPU
detection, streaming chat, and progress callbacks
- templates/mobile_local.html: Mobile-optimized UI with model
selector, download progress, LOCAL/SERVER badge, and chat
- tests/dashboard/test_local_models.py: 31 tests covering routes,
config, template UX, JS asset, and XSS prevention
Changes:
- config.py: browser_model_enabled, browser_model_id,
browser_model_fallback settings
- routes/mobile.py: /mobile/local page, /mobile/local-models API
- base.html: LOCAL AI nav link
Supported models: SmolLM2-360M (~200MB), Qwen2.5-0.5B (~350MB),
SmolLM2-1.7B (~1GB), Llama-3.2-1B (~700MB). Falls back to
server-side Ollama when local model is unavailable.
https://claude.ai/code/session_01Cqkvr4sZbED7T3iDu1rwSD
Add comprehensive test suite for Hands framework:
TestHandRegistry:
- Load all Hands from directory
- Get Hand by name (with not-found handling)
- Get scheduled vs all Hands
- State management (status updates)
- Approval queue operations
TestHandScheduler:
- Scheduler initialization
- Schedule Hand with cron
- Get scheduled jobs list
- Manual trigger execution
TestHandRunner:
- Load system prompts from SYSTEM.md
- Load skills from skills/ directory
- Build execution prompts
TestHandConfig:
- HandConfig creation and validation
- Cron schedule validation
TestHandModels:
- HandStatus enum values
- HandState serialization to dict
17 tests total, all passing.
Resolved merge conflicts in agents.py and test_task_queue.py:
- Keep full chat-to-task pipeline (agent/priority extraction, question
filtering, context injection) over simpler main version
- Incorporate test_briefing_task_queue_summary from main
- All 64 task queue tests pass
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Addresses 14 bugs from 3 rounds of deep chat evaluation:
- Add chat-to-task pipeline in agents.py with regex-based intent detection,
agent extraction, priority extraction, and title cleaning
- Filter meta-questions ("how do I create a task?") from task creation
- Inject real-time date/time context into every chat message
- Inject live queue state when user asks about tasks
- Ground system prompts with agent roster, honesty guardrails, self-knowledge,
math delegation template, anti-filler rules, values-conflict guidance
- Add CSS for markdown code blocks, inline code, lists, blockquotes in chat
- Add highlight.js CDN for syntax highlighting in chat responses
- Reduce small-model memory context budget (4000→2000) for expanded prompt
- Add 27 comprehensive tests covering the full chat-to-task pipeline
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Chat messages like "add X to the queue" or "create a task" are
intercepted and create a task_queue entry with pending_approval
status instead of going through to the LLM
- Briefing engine now gathers task queue stats (pending, running,
completed, failed) and includes them in the morning briefing prompt
- 7 new tests covering detection patterns, chat integration, and
briefing summary
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Task Queue system:
- New /tasks page with three-column layout (Pending/Active/Completed)
- Full CRUD API at /api/tasks with approve/veto/modify/pause/cancel/retry
- SQLite persistence in task_queue table
- WebSocket live updates via ws_manager
- Create task modal with agent assignment and priority
- Auto-approve rules for low-risk tasks
- HTMX polling for real-time column updates
- HOME TASK buttons now link to task queue with agent pre-selected
- MARKET HIRE buttons link to task queue with agent pre-selected
Work Order system:
- External submission API for agents/users (POST /work-orders/submit)
- Risk scoring and configurable auto-execution thresholds
- Dashboard at /work-orders/queue with approve/reject/execute flow
- Integration with swarm task system for execution
UI & Dashboard bug fixes:
- EVENTS: add startup event so page is never empty
- LEDGER: fix empty filter params in URL
- MISSION CONTROL: LLM backend and model now read from /health
- MISSION CONTROL: agent count fallback to /swarm/agents
- SWARM: HTMX fallback loads initial data if WebSocket is slow
- MEMORY: add edit/delete buttons for personal facts
- UPGRADES: add empty state guidance with links
- BRIEFING: add regenerate button and POST /briefing/regenerate endpoint
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add sandboxed calculator tool to Timmy's toolkit so arithmetic questions
get exact answers instead of LLM hallucinations
- Update system prompts (lite + full) to instruct Timmy to always use the
calculator and never attempt multi-digit math in his head
- Add self-contradiction guard to both prompts ("commit to your facts")
- Render Timmy's chat responses as markdown via marked.js + DOMPurify
instead of raw escaped text
- Suppress empty briefing notification on startup when there are 0
pending approval items
- Add calculator to session response sanitizer regex
- 18 new calculator tests, 2 updated briefing notification tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Remove show_tool_calls kwarg (not in Agno 2.5.3), which crashed Agent.__init__
- Guard memory_search against top_k=None from model, return formatted string
- Skip Telegram/Discord startup silently when no token configured
- Replace placeholder MEMORY.md with proper structured hot memory document
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add fixtures required by functional test suite:
- docker_stack: Docker container test URL (skips if FUNCTIONAL_DOCKER != 1)
- serve_client: FastAPI TestClient for timmy-serve app
- tdd_runner: Alias for self_tdd_runner
Fixes CI errors in test_docker_swarm.py, test_l402_flow.py, test_cli.py
- Fix recall_personal_facts() call - remove unsupported limit parameter
- Replace 4 slow E2E test files with single fast test file
- All 6 E2E tests complete in ~9 seconds (was 60+ seconds)
- Reuse browser session across tests (module-scoped fixture)
- Combine related checks into single tests
- Add HTTP-only smoke test for speed
- YAML-based provider configuration (config/providers.yaml)
- Priority-ordered provider routing
- Circuit breaker pattern for failing providers
- Health check and availability monitoring
- Metrics tracking (latency, errors, success rates)
- Support for Ollama, OpenAI, Anthropic, AirLLM providers
- Automatic failover on rate limits or errors
- REST API endpoints for monitoring and control
- 41 comprehensive tests
API Endpoints:
- POST /api/v1/router/complete - Chat completion with failover
- GET /api/v1/router/status - Provider health status
- GET /api/v1/router/metrics - Detailed metrics
- GET /api/v1/router/providers - List all providers
- POST /api/v1/router/providers/{name}/control - Enable/disable/reset
- POST /api/v1/router/health-check - Run health checks
- GET /api/v1/router/config - View configuration
Timmy was exhibiting severe incoherence (no memory between messages, tool call
leakage, chain-of-thought narration, random tool invocations) due to creating
a brand new agent per HTTP request and giving a 3B model (llama3.2) a 73-line
system prompt with complex tool-calling instructions it couldn't follow.
Key changes:
- Add session.py singleton with stable session_id for conversation continuity
- Add _model_supports_tools() to strip tools from small models (< 7B)
- Add two-tier prompts: lite (12 lines) for small models, full for capable ones
- Add response sanitizer to strip leaked JSON tool calls and CoT narration
- Set show_tool_calls=False to prevent raw tool JSON in output
- Wire ConversationManager for user name extraction
- Deprecate orphaned memory_layers.py (unused 4-layer system)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit replaces the previous memory_layers.py with a proper three-tier
memory system as specified by the user:
## Tier 1 — Hot Memory (MEMORY.md)
- Single flat file always loaded into system context
- Contains: current status, standing rules, agent roster, key decisions
- ~300 lines max, pruned monthly
- Managed by HotMemory class
## Tier 2 — Structured Vault (memory/)
- Directory with three namespaces:
• self/ — identity.md, user_profile.md, methodology.md
• notes/ — session logs, AARs, research
• aar/ — post-task retrospectives
- Markdown format, Obsidian-compatible
- Append-only, date-stamped
- Managed by VaultMemory class
## Handoff Protocol
- last-session-handoff.md written at session end
- Contains: summary, key decisions, open items, next steps
- Auto-loaded at next session start
- Maintains continuity across resets
## Implementation
### New Files:
- src/timmy/memory_system.py — Core memory system
- MEMORY.md — Hot memory template
- memory/self/*.md — Identity, user profile, methodology
### Modified:
- src/timmy/agent.py — Integrated with memory system
- create_timmy() injects memory context
- TimmyWithMemory class with automatic fact extraction
- tests/test_agent.py — Updated for memory context
## Key Principles
- Hot memory = small and curated
- Vault = append-only, never delete
- Handoffs = continuity mechanism
- Flat files = human-readable, portable
## Usage
All 973 tests pass.
Keep Mission Control link from this branch alongside SWARM and SPARK
links from main. All 939 tests pass.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The POST /swarm/tasks endpoint now triggers an automatic auction via
asyncio.create_task. Tests must allow tasks to be in bidding, assigned,
or failed status since the background auction may resolve before the
follow-up GET query.
All 895 tests pass.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds SelfModifyLoop — an edit→validate→test→commit cycle that can read
its own failure reports, diagnose root causes, and restart autonomously.
Key capabilities:
- Multi-backend LLM: Anthropic Claude API, Ollama, or auto-detect
- Syntax validation via compile() before writing to disk
- Autonomous self-correction loop with configurable max cycles
- XML-based output format to avoid triple-quote delimiter conflicts
- Branch creation skipped by default to prevent container restarts
- CLI: self-modify run "instruction" --backend auto --autonomous
- 939 tests passing, 30 skipped
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
selenium depends on websocket-client which installs a top-level
`websocket` package that shadows our src/websocket/ module on CI.
Renaming to ws_manager eliminates the conflict entirely — no more
sys.path hacks needed in conftest or Selenium tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
