* Remove persona system, identity, and all Timmy references
Strip the codebase to pure orchestration logic:
- Delete TIMMY_IDENTITY.md and memory/self/identity.md
- Gut brain/identity.py to no-op stubs (empty returns)
- Remove all system prompts reinforcing Timmy's character, faith,
sovereignty, sign-off ("Sir, affirmative"), and agent roster
- Replace identity-laden prompts with generic local-AI-assistant prompts
- Remove "You work for Timmy" from all sub-agent system prompts
- Rename PersonaTools → AgentTools, PERSONA_TOOLKITS → AGENT_TOOLKITS
- Replace "timmy" agent ID with "orchestrator" across routes, marketplace,
tools catalog, and orchestrator class
- Strip Timmy references from config comments, templates, telegram bot,
chat API, and dashboard UI
- Delete tests/brain/test_identity.py entirely
- Fix all test assertions that checked for persona identity content
729 tests pass (2 pre-existing failures in test_calm.py unrelated).
https://claude.ai/code/session_01LjQGUE6nk9W9674zaxrYxy
* Add Taskosaur (PM + AI task execution) to docker-compose
Spins up Taskosaur alongside the dashboard on `docker compose up`:
- postgres:16-alpine (port 5432, Taskosaur DB)
- redis:7-alpine (Bull queue backend)
- taskosaur (ports 3000 API / 3001 UI)
- dashboard now depends_on taskosaur healthy
- TASKOSAUR_API_URL injected into dashboard environment
Dashboard can reach Taskosaur at http://taskosaur:3000/api on the
internal network. Frontend UI accessible at http://localhost:3001.
https://claude.ai/code/session_01LjQGUE6nk9W9674zaxrYxy
---------
Co-authored-by: Claude <noreply@anthropic.com>
UC-01: Live System Introspection Tool
- Add get_task_queue_status(), get_agent_roster(), get_live_system_status()
to timmy/tools_intro with graceful degradation
- Enhanced get_memory_status() with line counts, section headers, vault
directory listing, semantic memory row count, self-coding journal stats
- Register system_status MCP tool (creative/tools/system_status.py)
- Add system_status to Timmy's tool list + Hard Rule #7
UC-02: Fix Offline Status Bug
- Add registry.heartbeat() calls in task_processor run_loop() and
process_single_task() so health endpoint reflects actual agent status
- health.py now consults swarm registry instead of Ollama connectivity
UC-03: Message Source Tagging
- Add source field to Message dataclass (default "browser")
- Tag all message_log.append() calls: browser, api, system
- Include source in /api/chat/history response
UC-04: Discord Token Auto-Detection & Docker Fix
- Add _discord_token_watcher() background coroutine that polls every 30s
for DISCORD_TOKEN in env vars, .env file, or state file
- Add --extras discord to all three Dockerfiles (main, dashboard, test)
All 26 Phase 1 tests pass in Docker (make test-docker).
Full suite: 1889 passed, 77 skipped, 0 failed.
Co-authored-by: Alexander Payne <apayne@MM.local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Dashboard UX:
- Restructure nav from 22 flat links to 6 core + MORE dropdown
- Add mobile nav section labels (Core, Intelligence, Agents, System, Commerce)
- Defer marked.js and dompurify.js loading, consolidate CDN to jsdelivr
- Optimize font weights (drop unused 300/500), bump style.css cache buster
- Remove duplicate HTMX load triggers from sidebar and health panels
Bug fixes:
- Fix Timmy showing OFFLINE by registering after swarm recovery sweep
- Fix ThinkingEngine await bug with asyncio.run_coroutine_threadsafe
- Fix chat auto-scroll by calling scrollChat() after history partial loads
- Add missing /voice/button page and /voice/command endpoint
- Fix Grok api_key="" treated as falsy falling through to env key
- Fix self_modify PROJECT_ROOT using settings.repo_root instead of __file__
Docker test infrastructure:
- Bind-mount hands/, docker/, Dockerfiles, and compose files into test container
- Add fontconfig + fonts-dejavu-core for creative/assembler TextClip tests
- Initialize minimal git repo in Dockerfile.test for GitSafety compatibility
- Fix introspection and path resolution tests for Docker /app context
All 1863 tests pass in Docker (0 failures, 77 skipped).
Co-authored-by: Alexander Payne <apayne@MM.local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Replace the stub `handle_bug_report` handler with a real implementation
that logs a decision trail and dispatches code_fix tasks to Forge for
automated fixing. Add `POST /api/bugs/submit` endpoint and `timmy
ingest-report` CLI command so AI test runners (Comet) can submit
structured bug reports without manual copy-paste.
- POST /api/bugs/submit: accepts JSON reports, creates bug_report tasks
- timmy ingest-report: CLI for file/stdin JSON ingestion with --dry-run
- handle_bug_report: logs decision trail to event_log, dispatches
code_fix task to Forge with parent_task_id linking back to the bug
- 18 TDD tests covering endpoint, handler, and CLI
Co-authored-by: Alexander Payne <apayne@MM.local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
The chat WebSocket return path was broken by two bugs that prevented
Timmy's responses from appearing in the live chat feed:
1. Frontend checked msg.type instead of msg.event for 'timmy_response'
events — the WSEvent dataclass uses 'event' as the field name.
2. Frontend accessed msg.response instead of msg.data.response — the
response payload is nested in the data field.
Additional fixes:
- Queue acknowledgment ("Message queued...") no longer logged as an
agent message in chat history; the real response is logged by the
task processor when it completes, eliminating duplicate messages.
- Chat message template now carries data-task-id so the WS handler
can find and replace the placeholder with the actual response.
- appendMessage() uses DOM APIs (textContent) instead of innerHTML
for safer content insertion before markdown rendering.
- Fixed chat_message.html script targeting when queue-status div is
present between the agent message and the inline script.
https://claude.ai/code/session_011cJfexqBBuGhSRQU8qwKcR
Co-authored-by: Claude <noreply@anthropic.com>
* fix: resolve portal startup hangs with non-blocking init
- Add socket_connect_timeout/socket_timeout (3s) to Redis connection in
SwarmComms to prevent infinite hangs when Redis is unreachable
- Defer reconcile_on_startup() from SwarmCoordinator.__init__() to an
explicit initialize() call during app lifespan, unblocking the
module-level singleton creation
- Make Ollama health checks non-blocking via asyncio.to_thread() so they
don't freeze the event loop for 2s per call
- Fix _check_redis() to reuse coordinator's SwarmComms singleton instead
of creating a new connection on every health check
- Move discord bot platform registration from lifespan critical path
into background task to avoid heavy import before yield
- Increase Docker healthcheck start_period from 10s/15s to 30s to give
the app adequate time to complete startup
https://claude.ai/code/session_016t5jNBYsUAQuyoR7sXe7Ux
* fix: disable commit signing in git_tools test fixture
The git_repo fixture inherits global gpgsign config, causing git_commit
to fail when the signing server rejects unsigned source context.
Disable signing in the temp repo's local config.
https://claude.ai/code/session_016t5jNBYsUAQuyoR7sXe7Ux
* fix: add dev extras for pip-based CI install
The CI workflow runs `pip install -e ".[dev]"` but after the Poetry
migration there was no `dev` extra defined — only a Poetry dev group.
This caused pytest to not be installed, resulting in exit code 127
(command not found) on every CI run.
Add a pip-compatible `dev` extra that mirrors the Poetry dev group
so both `pip install -e ".[dev]"` and `poetry install` work.
https://claude.ai/code/session_016t5jNBYsUAQuyoR7sXe7Ux
---------
Co-authored-by: Claude <noreply@anthropic.com>
Migrate from Hatchling to Poetry for dependency management, fixing the
Docker build failure caused by .dockerignore excluding README.md that
Hatchling needed for metadata. Poetry export strategy bypasses this
entirely. Creative extras removed from main build (separate service).
Docker changes:
- Multi-stage builds with poetry export → pip install
- BuildKit cache mounts for faster rebuilds
- All 3 Dockerfiles updated (root, dashboard, agent)
Bug fixes from tester audit:
- TaskStatus/TaskPriority case-insensitive enum parsing
- scrollChat() upgraded to requestAnimationFrame, removed duplicate
- Desktop/mobile nav items synced in base.html
- HTMX pointed to direct htmx.min.js URL
- Removed unused highlight.js and bootstrap.bundle.min.js
- Registered missing escalation/external task handlers in app.py
Co-authored-by: Alexander Payne <apayne@MM.local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* CI/CD Optimization: Guard Rails, Black Linting, and Pre-commit Hooks
- Fixed all test collection errors (Selenium imports, fixture paths, syntax)
- Implemented pre-commit hooks with Black formatting and isort
- Created comprehensive Makefile with test targets (unit, integration, functional, e2e)
- Added pytest.ini with marker definitions for test categorization
- Established guard rails to prevent future collection errors
- Wrapped optional dependencies (Selenium, MoviePy) in try-except blocks
- Added conftest_markers for automatic test categorization
This ensures a smooth development stream with:
- Fast feedback loops (pre-commit checks before push)
- Consistent code formatting (Black)
- Reliable CI/CD (no collection errors, proper test isolation)
- Clear test organization (unit, integration, functional, E2E)
* Fix CI/CD test failures:
- Export templates from dashboard.app
- Fix model name assertion in test_agent.py
- Fix platform-agnostic path resolution in test_path_resolution.py
- Skip Docker tests in test_docker_deployment.py if docker not available
- Fix test_model_fallback_chain logic in test_ollama_integration.py
* Add preventative pre-commit checks and Docker test skipif decorators:
- Create pre_commit_checks.py script for common CI failures
- Add skipif decorators to Docker tests
- Improve test robustness for CI environments
## Summary
Complete refactoring of Timmy Time from monolithic architecture to microservices
using Test-Driven Development (TDD) and optimized Docker builds.
## Changes
### Core Improvements
- Optimized dashboard startup: moved blocking tasks to async background processes
- Fixed model fallback logic in agent configuration
- Enhanced test fixtures with comprehensive conftest.py
### Microservices Architecture
- Created separate Dockerfiles for dashboard, Ollama, and agent services
- Implemented docker-compose.microservices.yml for service orchestration
- Added health checks and non-root user execution for security
- Multi-stage Docker builds for lean, fast images
### Testing
- Added E2E tests for dashboard responsiveness
- Added E2E tests for Ollama integration
- Added E2E tests for microservices architecture validation
- All 36 tests passing, 8 skipped (environment-specific)
### Documentation
- Created comprehensive final report
- Generated issue resolution plan
- Added interview transcript demonstrating core agent functionality
### New Modules
- skill_absorption.py: Dynamic skill loading and integration system for Timmy
## Test Results
✅ 36 passed, 8 skipped, 6 warnings
✅ All microservices tests passing
✅ Dashboard responsiveness verified
✅ Ollama integration validated
## Files Added/Modified
- docker/: Multi-stage Dockerfiles for all services
- tests/e2e/: Comprehensive E2E test suite
- src/timmy/skill_absorption.py: Skill absorption system
- src/dashboard/app.py: Optimized startup logic
- tests/conftest.py: Enhanced test fixtures
- docker-compose.microservices.yml: Service orchestration
## Breaking Changes
None - all changes are backward compatible
## Next Steps
- Integrate skill absorption system into agent workflow
- Test with microservices-tdd-refactor skill
- Deploy to production with docker-compose orchestration
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
