- 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>
- Set overflow:hidden on mc-main to prevent page-level scrolling
- Add max-height:100% to sidebar and chat panel to contain within viewport
- Use flex-wrap:nowrap on layout row to prevent column stacking on desktop
- Move scrollChat() to hx-on::after-settle for reliable post-swap scrolling
- Use requestAnimationFrame for smooth scroll-to-bottom timing
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>
Keep both L402/privacy settings from security hardening PR and
self-modification settings. 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>
## Workset E: Swarm System Realization
- Verified PersonaNode bidding system is properly connected
- Coordinator already subscribes personas to task announcements
- Auction system works when /tasks/auction endpoint is used
## Workset F: Testing & Reliability
- Mobile nav: Add MOBILE link to desktop header (UX-01)
- Voice TTS: Verified graceful degradation already implemented
- Registry: Add proper connection cleanup with try/finally
## Workset G: Performance & Architecture
- Fix module path: websocket.handler -> ws_manager.handler
- Registry connections now properly closed after operations
All 895 tests pass.
Addresses QUALITY_ANALYSIS.md:
- UX-01: /mobile route now in desktop nav
- PERF-01: Connection cleanup improved (P3)
- FUNC-01/02: Verified bidding system operational
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>
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>
The Agno Toolkit API fix (1bc2cdc) wasn't taking effect because
Python was loading stale __pycache__/*.pyc files with the old
add_tool() calls. Now `make nuke` clears all bytecache, and
`make dev` sets PYTHONDONTWRITEBYTECODE=1 to prevent .pyc
creation during development.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
## Security (Workset A)
- XSS: Verified templates use safe DOM methods (textContent, createElement)
- Secrets: Fail-fast in production mode when L402 secrets not set
- Environment mode: Add TIMMY_ENV (development|production) validation
## Privacy (Workset C)
- Add telemetry_enabled config (default: False for sovereign AI)
- Pass telemetry setting to Agno Agent
- Update .env.example with TELEMETRY_ENABLED and TIMMY_ENV docs
## Agent Intelligence (Workset D)
- Enhanced TIMMY_SYSTEM_PROMPT with:
- Tool usage guidelines (when to use, when not to)
- Memory awareness documentation
- Operating mode documentation
- Help reduce unnecessary tool calls for simple queries
All 895 tests pass.
Telemetry disabled by default aligns with sovereign AI vision.
- Change Toolkit.add_tool() to Toolkit.register() (method was renamed in Agno)
- Fix PythonTools method: python -> run_python_code
- Fix FileTools method: write_file -> save_file
- Fix FileTools base_dir parameter: str -> Path object
- Fix Agent tools parameter: pass Toolkit wrapped in list
These fixes resolve critical startup errors that prevented Timmy agent from initializing:
- AttributeError: 'Toolkit' object has no attribute 'add_tool'
- AttributeError: 'PythonTools' object has no attribute 'python'
- TypeError: 'Toolkit' object is not iterable
All 895 tests pass after these changes.
Quality review: Agent now fully functional with working inference, memory,
and self-awareness capabilities.
- config.py: add L402_HMAC_SECRET, L402_MACAROON_SECRET, LIGHTNING_BACKEND
to pydantic-settings with startup warnings for default secrets
- l402_proxy.py, mock_backend.py, factory.py: migrate from os.environ.get()
to `from config import settings` per project convention
- Makefile: `make install-creative` now auto-installs PyTorch nightly with
Metal (MPS) support on Apple Silicon instead of just printing a note
- activate_self_tdd.sh: add PID file (.watchdog.pid) and EXIT trap so
Ctrl-C cleanly stops both the dashboard and the watchdog process
- .gitignore: add .watchdog.pid
https://claude.ai/code/session_01A81E5HMxZEPxzv2acNo35u
Adds a `nuke` target that kills stale processes on port 8000 and stops
Docker containers. `make dev` now runs `nuke` first, eliminating the
errno 48 (address already in use) error on restart.
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>
selenium depends on websocket-client which installs a top-level
`websocket` package that shadows our src/websocket/ module. Ensure
src/ is inserted at the front of sys.path in conftest so the project
module wins the import race. Fixes collection errors for
test_websocket.py and test_websocket_extended.py on GitHub Actions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
