feat: Timmy system introspection, delegation, and session logging (#74)
* 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>
2026-02-27 00:11:53 -05:00
|
|
|
"""System introspection tools for Timmy to query his own environment.
|
|
|
|
|
|
|
|
|
|
This provides true sovereignty - Timmy introspects his environment rather than
|
|
|
|
|
being told about it in the system prompt.
|
|
|
|
|
"""
|
|
|
|
|
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
import logging
|
feat: Timmy system introspection, delegation, and session logging (#74)
* 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>
2026-02-27 00:11:53 -05:00
|
|
|
import platform
|
|
|
|
|
import sys
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
from datetime import datetime, timezone
|
feat: Timmy system introspection, delegation, and session logging (#74)
* 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>
2026-02-27 00:11:53 -05:00
|
|
|
from pathlib import Path
|
|
|
|
|
from typing import Any
|
|
|
|
|
|
|
|
|
|
import httpx
|
|
|
|
|
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
feat: Timmy system introspection, delegation, and session logging (#74)
* 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>
2026-02-27 00:11:53 -05:00
|
|
|
|
|
|
|
|
def get_system_info() -> dict[str, Any]:
|
|
|
|
|
"""Introspect the runtime environment to discover system information.
|
|
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
|
Dict containing:
|
|
|
|
|
- python_version: Python version
|
|
|
|
|
- platform: OS platform
|
|
|
|
|
- model: Current Ollama model (queried from API)
|
|
|
|
|
- model_backend: Configured backend (ollama/airllm/grok)
|
|
|
|
|
- ollama_url: Ollama host URL
|
|
|
|
|
- repo_root: Repository root path
|
|
|
|
|
- grok_enabled: Whether GROK is enabled
|
|
|
|
|
- spark_enabled: Whether Spark is enabled
|
|
|
|
|
- memory_vault_exists: Whether memory vault is initialized
|
|
|
|
|
"""
|
|
|
|
|
from config import settings
|
|
|
|
|
|
|
|
|
|
info = {
|
|
|
|
|
"python_version": f"{sys.version_info.major}.{sys.version_info.minor}.{sys.version_info.micro}",
|
|
|
|
|
"platform": platform.system(),
|
|
|
|
|
"model_backend": settings.timmy_model_backend,
|
|
|
|
|
"ollama_url": settings.ollama_url,
|
|
|
|
|
"repo_root": settings.repo_root,
|
|
|
|
|
"grok_enabled": settings.grok_enabled,
|
|
|
|
|
"spark_enabled": settings.spark_enabled,
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
# Query Ollama for current model
|
|
|
|
|
model_name = _get_ollama_model()
|
|
|
|
|
info["model"] = model_name
|
|
|
|
|
|
|
|
|
|
# Check if memory vault exists
|
|
|
|
|
vault_path = Path(settings.repo_root) / "memory" / "self"
|
|
|
|
|
info["memory_vault_exists"] = vault_path.exists()
|
|
|
|
|
|
|
|
|
|
return info
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _get_ollama_model() -> str:
|
|
|
|
|
"""Query Ollama API to get the current model."""
|
|
|
|
|
from config import settings
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
# First try to get tags to see available models
|
|
|
|
|
response = httpx.get(f"{settings.ollama_url}/api/tags", timeout=5)
|
|
|
|
|
if response.status_code == 200:
|
|
|
|
|
models = response.json().get("models", [])
|
|
|
|
|
# Check if configured model is available
|
|
|
|
|
for model in models:
|
2026-03-08 12:50:44 -04:00
|
|
|
if model.get("name", "").startswith(settings.ollama_model.split(":")[0]):
|
feat: Timmy system introspection, delegation, and session logging (#74)
* 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>
2026-02-27 00:11:53 -05:00
|
|
|
return settings.ollama_model
|
|
|
|
|
|
|
|
|
|
# Fallback: return configured model
|
|
|
|
|
return settings.ollama_model
|
|
|
|
|
except Exception:
|
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
# Fallback to configured model
|
|
|
|
|
return settings.ollama_model
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def check_ollama_health() -> dict[str, Any]:
|
|
|
|
|
"""Check if Ollama is accessible and healthy.
|
|
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
|
Dict with status, model, and available models
|
|
|
|
|
"""
|
|
|
|
|
from config import settings
|
|
|
|
|
|
|
|
|
|
result = {
|
|
|
|
|
"accessible": False,
|
|
|
|
|
"model": settings.ollama_model,
|
|
|
|
|
"available_models": [],
|
|
|
|
|
"error": None,
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
# Check tags endpoint
|
|
|
|
|
response = httpx.get(f"{settings.ollama_url}/api/tags", timeout=5)
|
|
|
|
|
if response.status_code == 200:
|
|
|
|
|
result["accessible"] = True
|
|
|
|
|
models = response.json().get("models", [])
|
|
|
|
|
result["available_models"] = [m.get("name", "") for m in models]
|
|
|
|
|
except Exception as e:
|
|
|
|
|
result["error"] = str(e)
|
|
|
|
|
|
|
|
|
|
return result
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def get_memory_status() -> dict[str, Any]:
|
|
|
|
|
"""Get the status of Timmy's memory system.
|
|
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
|
Dict with memory tier information
|
|
|
|
|
"""
|
|
|
|
|
from config import settings
|
|
|
|
|
|
|
|
|
|
repo_root = Path(settings.repo_root)
|
|
|
|
|
|
|
|
|
|
# Check tier 1: Hot memory
|
|
|
|
|
memory_md = repo_root / "MEMORY.md"
|
|
|
|
|
tier1_exists = memory_md.exists()
|
|
|
|
|
tier1_content = ""
|
|
|
|
|
if tier1_exists:
|
|
|
|
|
tier1_content = memory_md.read_text()[:500] # First 500 chars
|
|
|
|
|
|
|
|
|
|
# Check tier 2: Vault
|
|
|
|
|
vault_path = repo_root / "memory" / "self"
|
|
|
|
|
tier2_exists = vault_path.exists()
|
|
|
|
|
tier2_files = []
|
|
|
|
|
if tier2_exists:
|
|
|
|
|
tier2_files = [f.name for f in vault_path.iterdir() if f.is_file()]
|
|
|
|
|
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
tier1_info: dict[str, Any] = {
|
|
|
|
|
"exists": tier1_exists,
|
|
|
|
|
"path": str(memory_md),
|
feat: agentic loop for multi-step tasks + regression fixes (#148)
* fix: name extraction blocklist, memory preview escaping, and gitignore cleanup
- Add _NAME_BLOCKLIST to extract_user_name() to reject gerunds and UI-state
words like "Sending" that were incorrectly captured as user names
- Collapse whitespace in get_memory_status() preview so newlines survive
JSON serialization without showing raw \n escape sequences
- Broaden .gitignore from specific memory/self/user_profile.md to memory/self/
and untrack memory/self/methodology.md (runtime-edited file)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: catch Ollama connection errors in session.py + add 71 smoke tests
- Wrap agent.run() in session.py with try/except so Ollama connection
failures return a graceful fallback message instead of dumping raw
tracebacks to Docker logs
- Add tests/test_smoke.py with 71 tests covering every GET route:
core pages, feature pages, JSON APIs, and a parametrized no-500 sweep
— catches import errors, template failures, and schema mismatches
that unit tests miss
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: agentic loop for multi-step tasks + Round 10 regression fixes
Agentic loop (Parts 1-4):
- Add multi-step chaining instructions to system prompt
- New agentic_loop.py with plan→execute→adapt→summarize flow
- Register plan_and_execute tool for background task execution
- Add max_agent_steps config setting (default: 10)
- Discord fix: 300s timeout, typing indicator, send error handling
- 16 new unit + e2e tests for agentic loop
Round 10 regressions (R1-R5, P1):
- R1: Fix literal \n escape sequences in tool responses
- R2: Chat timeout/error feedback in agent panel
- R3: /hands infinite spinner → static empty states
- R4: /self-coding infinite spinner → static stats + journal
- R5: /grok/status raw JSON → HTML dashboard template
- P1: VETO confirmation dialog on task cards
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: briefing route 500 in CI when agno is MagicMock stub
_call_agent() returned a MagicMock instead of a string when agno is
stubbed in tests, causing SQLite "Error binding parameter 4" on save.
Ensure the return value is always an actual string.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: briefing route 500 in CI — graceful degradation at route level
When agno is stubbed with MagicMock in CI, agent.run() returns a
MagicMock instead of raising — so the exception handler never fires
and a MagicMock propagates as the summary to SQLite, which can't
bind it.
Fix: catch at the route level and return a fallback Briefing object.
This follows the project's graceful degradation pattern — the briefing
page always renders, even when the backend is completely unavailable.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Trip T <trip@local>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 01:46:29 -05:00
|
|
|
"preview": " ".join(tier1_content[:200].split()) if tier1_content else None,
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
}
|
|
|
|
|
if tier1_exists:
|
|
|
|
|
lines = memory_md.read_text().splitlines()
|
|
|
|
|
tier1_info["line_count"] = len(lines)
|
2026-03-08 12:50:44 -04:00
|
|
|
tier1_info["sections"] = [ln.lstrip("# ").strip() for ln in lines if ln.startswith("## ")]
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
|
|
|
|
|
# Vault — scan all subdirs under memory/
|
|
|
|
|
vault_root = repo_root / "memory"
|
|
|
|
|
vault_info: dict[str, Any] = {
|
|
|
|
|
"exists": tier2_exists,
|
|
|
|
|
"path": str(vault_path),
|
|
|
|
|
"file_count": len(tier2_files),
|
|
|
|
|
"files": tier2_files[:10],
|
|
|
|
|
}
|
|
|
|
|
if vault_root.exists():
|
|
|
|
|
vault_info["directories"] = [d.name for d in vault_root.iterdir() if d.is_dir()]
|
|
|
|
|
vault_info["total_markdown_files"] = sum(1 for _ in vault_root.rglob("*.md"))
|
|
|
|
|
|
|
|
|
|
# Tier 3: Semantic memory row count
|
|
|
|
|
tier3_info: dict[str, Any] = {"available": False}
|
|
|
|
|
try:
|
|
|
|
|
import sqlite3
|
|
|
|
|
|
|
|
|
|
sem_db = repo_root / "data" / "semantic_memory.db"
|
|
|
|
|
if sem_db.exists():
|
|
|
|
|
conn = sqlite3.connect(str(sem_db))
|
|
|
|
|
row = conn.execute(
|
2026-03-08 00:20:38 -05:00
|
|
|
"SELECT COUNT(*) FROM sqlite_master WHERE type='table' AND name='chunks'"
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
).fetchone()
|
|
|
|
|
if row and row[0]:
|
2026-03-08 00:20:38 -05:00
|
|
|
count = conn.execute("SELECT COUNT(*) FROM chunks").fetchone()
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
tier3_info["available"] = True
|
|
|
|
|
tier3_info["vector_count"] = count[0] if count else 0
|
|
|
|
|
conn.close()
|
|
|
|
|
except Exception:
|
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
|
# Self-coding journal stats
|
|
|
|
|
journal_info: dict[str, Any] = {"available": False}
|
|
|
|
|
try:
|
|
|
|
|
import sqlite3 as _sqlite3
|
|
|
|
|
|
|
|
|
|
journal_db = repo_root / "data" / "self_coding.db"
|
|
|
|
|
if journal_db.exists():
|
|
|
|
|
conn = _sqlite3.connect(str(journal_db))
|
|
|
|
|
conn.row_factory = _sqlite3.Row
|
|
|
|
|
rows = conn.execute(
|
|
|
|
|
"SELECT outcome, COUNT(*) as cnt FROM modification_journal GROUP BY outcome"
|
|
|
|
|
).fetchall()
|
|
|
|
|
if rows:
|
|
|
|
|
counts = {r["outcome"]: r["cnt"] for r in rows}
|
|
|
|
|
total = sum(counts.values())
|
|
|
|
|
journal_info = {
|
|
|
|
|
"available": True,
|
|
|
|
|
"total_attempts": total,
|
|
|
|
|
"successes": counts.get("success", 0),
|
|
|
|
|
"failures": counts.get("failure", 0),
|
|
|
|
|
"success_rate": round(counts.get("success", 0) / total, 2) if total else 0,
|
|
|
|
|
}
|
|
|
|
|
conn.close()
|
|
|
|
|
except Exception:
|
|
|
|
|
pass
|
|
|
|
|
|
feat: Timmy system introspection, delegation, and session logging (#74)
* 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>
2026-02-27 00:11:53 -05:00
|
|
|
return {
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
"tier1_hot_memory": tier1_info,
|
|
|
|
|
"tier2_vault": vault_info,
|
|
|
|
|
"tier3_semantic": tier3_info,
|
|
|
|
|
"self_coding_journal": journal_info,
|
feat: Timmy system introspection, delegation, and session logging (#74)
* 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>
2026-02-27 00:11:53 -05:00
|
|
|
}
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def get_task_queue_status() -> dict[str, Any]:
|
2026-03-07 22:34:30 -05:00
|
|
|
"""Get current task queue status.
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
|
2026-03-07 22:34:30 -05:00
|
|
|
The swarm task queue was removed. This returns a stub indicating
|
|
|
|
|
the subsystem is not available.
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
"""
|
2026-03-07 22:34:30 -05:00
|
|
|
return {
|
|
|
|
|
"counts": {},
|
|
|
|
|
"total": 0,
|
|
|
|
|
"current_task": None,
|
|
|
|
|
"note": "Task queue not available (swarm module removed)",
|
|
|
|
|
}
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def get_agent_roster() -> dict[str, Any]:
|
2026-03-07 22:34:30 -05:00
|
|
|
"""Get the agent roster from the orchestrator's sub-agent definitions.
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
|
Dict with agent list and summary.
|
|
|
|
|
"""
|
|
|
|
|
try:
|
2026-03-07 22:34:30 -05:00
|
|
|
from timmy.agents.timmy import _PERSONAS
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
|
|
|
|
|
roster = []
|
2026-03-07 22:34:30 -05:00
|
|
|
for persona in _PERSONAS:
|
2026-03-08 12:50:44 -04:00
|
|
|
roster.append(
|
|
|
|
|
{
|
|
|
|
|
"id": persona["agent_id"],
|
|
|
|
|
"name": persona["name"],
|
|
|
|
|
"status": "available",
|
|
|
|
|
"capabilities": ", ".join(persona.get("tools", [])),
|
|
|
|
|
"role": persona.get("role", ""),
|
|
|
|
|
}
|
|
|
|
|
)
|
feat: Phase 1 autonomy upgrades — introspection, heartbeat, source tagging, Discord auto-detect (#101)
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>
2026-02-28 22:49:24 -05:00
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
"agents": roster,
|
|
|
|
|
"total": len(roster),
|
|
|
|
|
}
|
|
|
|
|
except Exception as exc:
|
|
|
|
|
logger.debug("Agent roster unavailable: %s", exc)
|
|
|
|
|
return {"error": str(exc)}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def get_live_system_status() -> dict[str, Any]:
|
|
|
|
|
"""Comprehensive live system status — Timmy's primary introspection tool.
|
|
|
|
|
|
|
|
|
|
Combines system info, task queue, agent roster, and memory status
|
|
|
|
|
into a single snapshot. Each subsystem degrades gracefully.
|
|
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
|
Dict with system, task_queue, agents, memory, and uptime sections.
|
|
|
|
|
"""
|
|
|
|
|
result: dict[str, Any] = {}
|
|
|
|
|
|
|
|
|
|
# System info
|
|
|
|
|
try:
|
|
|
|
|
result["system"] = get_system_info()
|
|
|
|
|
except Exception as exc:
|
|
|
|
|
result["system"] = {"error": str(exc)}
|
|
|
|
|
|
|
|
|
|
# Task queue
|
|
|
|
|
result["task_queue"] = get_task_queue_status()
|
|
|
|
|
|
|
|
|
|
# Agent roster
|
|
|
|
|
result["agents"] = get_agent_roster()
|
|
|
|
|
|
|
|
|
|
# Memory status
|
|
|
|
|
try:
|
|
|
|
|
result["memory"] = get_memory_status()
|
|
|
|
|
except Exception as exc:
|
|
|
|
|
result["memory"] = {"error": str(exc)}
|
|
|
|
|
|
|
|
|
|
# Uptime
|
|
|
|
|
try:
|
|
|
|
|
from dashboard.routes.health import _START_TIME
|
|
|
|
|
|
|
|
|
|
uptime = (datetime.now(timezone.utc) - _START_TIME).total_seconds()
|
|
|
|
|
result["uptime_seconds"] = int(uptime)
|
|
|
|
|
except Exception:
|
|
|
|
|
result["uptime_seconds"] = None
|
|
|
|
|
|
|
|
|
|
# Discord status
|
|
|
|
|
try:
|
|
|
|
|
from integrations.chat_bridge.vendors.discord import discord_bot
|
|
|
|
|
|
|
|
|
|
result["discord"] = {"state": discord_bot.state.name}
|
|
|
|
|
except Exception:
|
|
|
|
|
result["discord"] = {"state": "unknown"}
|
|
|
|
|
|
|
|
|
|
result["timestamp"] = datetime.now(timezone.utc).isoformat()
|
|
|
|
|
return result
|