6d62fa6314
Refactor: Organize Obsidian MCP into proper package structure
...
Moved obsidian_mcp.py into mcp_servers/obsidian/ to align with other
MCP server organization (SSH, Cloudflare, Loki). This improves code
discoverability and maintains consistent package structure.
Changes:
- Moved obsidian_mcp.py → mcp_servers/obsidian/obsidian_mcp.py
- Updated lazy import in llm_interface.py (line 396)
- Updated lazy import in tools.py (line 550)
- Deleted empty scripts/ directory
All imports verified with runtime tests. Zero functional changes.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-24 13:31:25 -07:00
7697220c74
Refactor: Remove zombie code, fix bugs, and clean documentation
...
This comprehensive refactoring removes dead code, fixes bugs, and deletes
outdated documentation to make the codebase production-ready.
## Files Deleted (16 files)
### Temporary/zombie files (9 files):
- nul (Windows artifact)
- quick_start.bat (superseded by run.bat)
- scripts/proxmox_ssh.py (hardcoded credentials - security risk)
- scripts/proxmox_ssh.sh (hardcoded credentials - security risk)
- scripts/collection_output.txt (one-time audit output)
- scripts/collect-homelab-config.sh (one-off infrastructure script)
- scripts/collect-remote.sh (one-off infrastructure script)
- memory_workspace/MEMORY.md.old (backup file)
- promtail-config-optimized.yaml (misplaced homelab config)
### Outdated documentation (7 files):
- MCP_MIGRATION.md (migration complete - 2026-02-15)
- QUICK_REFERENCE_AGENT_SDK.md (orphaned from cleanup)
- SETUP.md (duplicate of README.md quick start)
- WINDOWS_QUICK_REFERENCE.md (duplicate of docs/WINDOWS_DEPLOYMENT.md)
- SUB_AGENTS.md (design doc for unimplemented feature)
- JARVIS_VOICE_INTEGRATION_PLAN.md (1300-line spec, code not implemented)
- OBSIDIAN_MCP_SETUP_INSTRUCTIONS.md (temporary troubleshooting doc)
- LOGGING.md (redundant with well-commented logging_config.py)
- docs/SECURITY_AUDIT_SUMMARY.md (completed audit from 2026-02-12)
## Critical Bug Fixes (2 bugs)
1. bot_runner.py line 122: Fixed wrong dict key reference
- Changed send_to_platform → send_to
- Bug caused scheduled task platform info to never print
2. usage_tracker.py: Added missing pricing for claude-sonnet-4-6
- Model was default but had no pricing entry
- Caused cost under-reporting in Direct API mode
## Code Removed (14 files modified, ~1200 lines deleted)
### Dead imports removed (9 imports):
- bot_runner.py: sys
- agent.py: time
- adapters/runtime.py: re
- adapters/skill_integration.py: subprocess
- tools.py: redundant Path import
- mcp_servers/loki/loki_server.py: json
- google_tools/oauth_manager.py: Thread, Dict
- google_tools/gmail_client.py: os
- google_tools/utils.py: email
### Unused functions/methods removed (9 functions):
- agent.py: MEMORY_RESPONSE_PREVIEW_LENGTH constant
- scheduled_tasks.py: integrate_scheduler_with_runtime()
- adapters/runtime.py: command_preprocessor(), markdown_postprocessor()
- adapters/skill_integration.py: invoke_skill_via_cli(), __main__ block
- tools.py: _extract_mcp_result()
- google_tools/oauth_manager.py: needs_refresh_soon(), revoke_authorization()
- google_tools/people_client.py: update_contact(), delete_contact()
### Code quality improvements:
- memory_system.py: Removed empty else: pass branch
- calendar_client.py: Fixed bare except: → except Exception:
- mcp_ssh.py: Updated asyncio.get_event_loop() → get_running_loop()
- calendar_client.py: Fixed deprecated datetime.utcnow() → now(timezone.utc)
## Impact
- ~1200 lines of dead code removed
- 16 obsolete files deleted
- 2 critical bugs fixed
- 3 deprecated APIs updated
- Zero functionality broken (all changes verified)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-24 12:46:56 -07:00
bb86a9eef5
Add Cloudflare and Loki MCP server integrations
...
Features:
- Cloudflare Code Mode MCP: Exposes entire Cloudflare API (2,500+ endpoints)
via remote MCP server at https://mcp.cloudflare.com/mcp
* Two tools: search() to query OpenAPI spec, execute() to run JS code
* Uses npx mcp-remote as stdio bridge
* Auth via CLOUDFLARE_API_TOKEN as Bearer header
- Loki MCP Server: Log querying and analysis via Loki HTTP API
* Query logs with LogQL syntax
* Real-time log streaming support
* Label introspection and metrics queries
* Configurable via LOKI_URL environment variable
Technical changes:
- Created mcp_servers/cloudflare/ with config and connection logic
- Created mcp_servers/loki/ with HTTP client and MCP tool wrappers
- Added promtail-config-optimized.yaml for syslog ingestion config
- Updated .env.example with Cloudflare and Loki configuration templates
Both integrations:
- Use environment variables for configuration (no hardcoded credentials)
- Include feature flags (CLOUDFLARE_MCP_ENABLED, LOKI_MCP_ENABLED)
- Follow existing MCP server patterns for consistency
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-24 12:35:04 -07:00
58de3e55dc
Add SSH MCP server and Gmail attachment download
...
Features:
- SSH MCP server with two tools:
* ssh_execute: Run commands on remote hosts via SSH
* ssh_file_upload: Upload files via SFTP
- Support for both password and SSH key authentication
- Auto-accept SSH host keys (AutoAddPolicy) for homelab use
- Gmail attachment download functionality
- Added download_attachment tool for Gmail API
Technical changes:
- Created mcp_servers/mcp_ssh.py with MCP-compliant text output
- Updated llm_interface.py to load SSH MCP server
- Added paramiko>=3.4.0 to requirements.txt
- Updated .env.example with SSH configuration template
- Enhanced gmail_client.py with download_attachment() method
- Added download_attachment tool handler in tools.py
SSH credentials configured via environment variables:
- PROXMOX_SSH_HOST, PROXMOX_SSH_USER, PROXMOX_SSH_PORT
- PROXMOX_SSH_PASSWORD (or) PROXMOX_SSH_KEY_FILE
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-24 12:32:05 -07:00
a9efdc0a01
feat: Add Loki MCP server scaffold, fix adapter blocking, upgrade model
...
- Scaffold mcp_servers/loki/ with config and async HTTP client
- Fix Slack/Telegram adapters to use non-blocking connections
- Upgrade default model to claude-sonnet-4-6
- Improve Agent SDK message collection for empty ResultMessage cases
- Add Message-ID to email summaries, increase body truncation limit
- Fix .gitignore inline comments that broke sensitive file exclusions
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-22 21:19:28 -07:00
fe7c146dc6
feat: Add Gitea MCP integration and project cleanup
...
## New Features
- **Gitea MCP Tools** (zero API cost):
- gitea_read_file: Read files from homelab repo
- gitea_list_files: Browse directories
- gitea_search_code: Search by filename
- gitea_get_tree: Get directory tree
- **Gitea Client** (gitea_tools/client.py): REST API wrapper with OAuth
- **Proxmox SSH Scripts** (scripts/): Homelab data collection utilities
- **Obsidian MCP Support** (obsidian_mcp.py): Advanced vault operations
- **Voice Integration Plan** (JARVIS_VOICE_INTEGRATION_PLAN.md)
## Improvements
- **Increased timeout**: 5min → 10min for complex tasks (llm_interface.py)
- **Removed Direct API fallback**: Gitea tools are MCP-only (zero cost)
- **Updated .env.example**: Added Obsidian MCP configuration
- **Enhanced .gitignore**: Protect personal memory files (SOUL.md, MEMORY.md)
## Cleanup
- Deleted 24 obsolete files (temp/test/experimental scripts, outdated docs)
- Untracked personal memory files (SOUL.md, MEMORY.md now in .gitignore)
- Removed: AGENT_SDK_IMPLEMENTATION.md, HYBRID_SEARCH_SUMMARY.md,
IMPLEMENTATION_SUMMARY.md, MIGRATION.md, test_agent_sdk.py, etc.
## Configuration
- Added config/gitea_config.example.yaml (Gitea setup template)
- Added config/obsidian_mcp.example.yaml (Obsidian MCP template)
- Updated scheduled_tasks.yaml with new task examples
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-18 20:31:32 -07:00
0271dea551
Add comprehensive structured logging system
...
Features:
- JSON-formatted logs for easy parsing and analysis
- Rotating log files (prevents disk space issues)
* ajarbot.log: All events, 10MB rotation, 5 backups
* errors.log: Errors only, 5MB rotation, 3 backups
* tools.log: Tool execution tracking, 10MB rotation, 3 backups
Tool Execution Tracking:
- Every tool call logged with inputs, outputs, duration
- Success/failure status tracking
- Performance metrics (execution time in milliseconds)
- Error messages captured with full context
Logging Integration:
- tools.py: All tool executions automatically logged
- Structured logger classes with context preservation
- Console output (human-readable) + file logs (JSON)
- Separate error log for quick issue identification
Log Analysis:
- JSON format enables programmatic analysis
- Easy to search for patterns (max tokens, iterations, etc.)
- Performance tracking (slow tools, failure rates)
- Historical debugging with full context
Documentation:
- LOGGING.md: Complete usage guide
- Log analysis examples with jq commands
- Error pattern reference
- Maintenance and integration instructions
Benefits:
- Quick error diagnosis with separate errors.log
- Performance monitoring and optimization
- Historical analysis for troubleshooting
- Automatic log rotation (max 95MB total)
Updated .gitignore to exclude logs/ directory
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-16 16:32:18 -07:00
50cf7165cb
Add sub-agent orchestration, MCP tools, and critical bug fixes
...
Major Features:
- Sub-agent orchestration system with dynamic specialist spawning
* spawn_sub_agent(): Create specialists with custom prompts
* delegate(): Convenience method for task delegation
* Cached specialists for reuse
* Separate conversation histories and focused context
- MCP (Model Context Protocol) tool integration
* Zettelkasten: fleeting_note, daily_note, permanent_note, literature_note
* Search: search_vault (hybrid search), search_by_tags
* Web: web_fetch for real-time data
* Zero-cost file/system operations on Pro subscription
Critical Bug Fixes:
- Fixed max tool iterations (15 → 30, configurable)
- Fixed max_tokens error in Agent SDK query() call
- Fixed MCP tool routing in execute_tool()
* Routes zettelkasten + web tools to async handlers
* Prevents "Unknown tool" errors
Documentation:
- SUB_AGENTS.md: Complete guide to sub-agent system
- MCP_MIGRATION.md: Agent SDK migration details
- SOUL.example.md: Sanitized bot identity template
- scheduled_tasks.example.yaml: Sanitized task config template
Security:
- Added obsidian vault to .gitignore
- Protected SOUL.md and MEMORY.md (personal configs)
- Sanitized example configs with placeholders
Dependencies:
- Added beautifulsoup4, httpx, lxml for web scraping
- Updated requirements.txt
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-16 07:43:31 -07:00
911d362ba2
Optimize for Claude Agent SDK: Memory, context, and model selection
...
## Memory & Context Optimizations
### agent.py
- MAX_CONTEXT_MESSAGES: 10 → 20 (better conversation coherence)
- MEMORY_RESPONSE_PREVIEW_LENGTH: 200 → 500 (richer memory storage)
- MAX_CONVERSATION_HISTORY: 50 → 100 (longer session continuity)
- search_hybrid max_results: 2 → 5 (better memory recall)
- System prompt: Now mentions tool count and flat-rate subscription
- Memory format: Changed "User (username)/Agent" to "username/Garvis"
### llm_interface.py
- Added claude_agent_sdk model (Sonnet) to defaults
- Mode-based model selection:
* Agent SDK → Sonnet (best quality, flat-rate)
* Direct API → Haiku (cheapest, pay-per-token)
- Updated logging to show active model
## SOUL.md Rewrite
- Added Garvis identity (name, email, role)
- Listed all 17 tools (was missing 12 tools)
- Added "Critical Behaviors" section
- Emphasized flat-rate subscription benefits
- Clear instructions to always check user profiles
## Benefits
With flat-rate Agent SDK:
- ✅ Use Sonnet for better reasoning (was Haiku)
- ✅ 2x context messages (10 → 20)
- ✅ 2.5x memory results (2 → 5)
- ✅ 2.5x richer memory previews (200 → 500 chars)
- ✅ Bot knows its name and all capabilities
- ✅ Zero marginal cost for thoroughness
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-15 10:22:23 -07:00
ce2c384387
Migrate to Claude Agent SDK framework (v0.2.0)
...
BREAKING CHANGE: Replaced FastAPI server wrapper with direct Claude Agent SDK integration
## Major Changes
### Architecture
- **OLD:** Bot → FastAPI Server → claude-code-sdk → Claude
- **NEW:** Bot → Claude Agent SDK → Claude (Pro subscription OR API)
- Eliminated HTTP server overhead
- Single-process architecture
### LLM Backend (llm_interface.py)
- Implemented Claude Agent SDK as DEFAULT mode
- Added three-mode architecture:
- agent-sdk (default) - Uses Pro subscription
- direct-api - Pay-per-token Anthropic API
- legacy-server - Backward compat with old setup
- Created async/sync bridge using anyio
- Preserved all existing functionality (17 tools, memory, scheduling)
### Dependencies (requirements.txt)
- Replaced: claude-code-sdk → claude-agent-sdk>=0.1.0
- Added: anyio>=4.0.0 for async bridging
- Removed: fastapi, uvicorn (no longer needed for default mode)
### New Files
- ajarbot.py - Unified launcher with pre-flight checks
- run.bat - Windows one-command launcher (auto-setup)
- pyproject.toml - Python package metadata
- MIGRATION.md - Upgrade guide from old setup
- AGENT_SDK_IMPLEMENTATION.md - Technical documentation
- QUICK_REFERENCE_AGENT_SDK.md - Quick reference card
- test_agent_sdk.py - Comprehensive test suite
### Updated Documentation
- CLAUDE_CODE_SETUP.md - Rewritten for Agent SDK
- README.md - Updated quick start for new default
- .env.example - Added AJARBOT_LLM_MODE configuration
### Deleted Files
- claude_code_server.py - Replaced by agent-sdk integration
- heartbeat.py - Superseded by scheduled_tasks.py
- pulse_brain.py - Unused in production
## Migration Path
Old setup:
1. Start FastAPI server: python claude_code_server.py
2. Start bot: python bot_runner.py
3. Set USE_CLAUDE_CODE_SERVER=true
New setup:
1. Run: run.bat (or python ajarbot.py)
- That's it! Single command.
## Benefits
✅ Zero API costs (uses Claude Pro subscription)
✅ Simplified deployment (no separate server)
✅ Single-command launch (run.bat)
✅ Faster response times (no HTTP overhead)
✅ All functionality preserved (17 tools, memory, adapters)
✅ Backward compatible (old env vars still work)
## Compatibility
- Python 3.10+ required
- Node.js required (for Claude Code CLI bundled with SDK)
- Windows 11 tested and optimized
- All existing tools, memory system, and adapters unchanged
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-15 10:03:11 -07:00
a8665d8c72
Refactor: Clean up obsolete files and organize codebase structure
...
This commit removes deprecated modules and reorganizes code into logical directories:
Deleted files (superseded by newer systems):
- claude_code_server.py (replaced by agent-sdk direct integration)
- heartbeat.py (superseded by scheduled_tasks.py)
- pulse_brain.py (unused in production)
- config/pulse_brain_config.py (obsolete config)
Created directory structure:
- examples/ (7 example files: example_*.py, demo_*.py)
- tests/ (5 test files: test_*.py)
Updated imports:
- agent.py: Removed heartbeat module and all enable_heartbeat logic
- bot_runner.py: Removed heartbeat parameter from Agent initialization
- llm_interface.py: Updated deprecated claude_code_server message
Preserved essential files:
- hooks.py (for future use)
- adapters/skill_integration.py (for future use)
- All Google integration tools (Gmail, Calendar, Contacts)
- GLM provider code (backward compatibility)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-15 09:57:39 -07:00
f018800d94
Implement self-healing system Phase 1: Error capture and logging
...
- Add SelfHealingSystem with error observation infrastructure
- Capture errors with full context: type, message, stack trace, intent, inputs
- Log to MEMORY.md with deduplication (max 3 attempts per error signature)
- Integrate error capture in agent, tools, runtime, and scheduler
- Non-invasive: preserves all existing error handling behavior
- Foundation for future diagnosis and auto-fixing capabilities
Phase 1 of 4-phase rollout - observation only, no auto-fixing yet.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-14 18:03:42 -07:00
0eb5d2cab4
Add Google Contacts integration and fix critical Windows issues
...
- Add People API integration with contact management tools (create, list, get)
- Fix OAuth flow: replace deprecated OOB with localhost callback
- Fix Ctrl+C handling with proper signal handlers for graceful shutdown
- Fix UTF-8 encoding in scheduled_tasks.py for Windows compatibility
- Add users/ directory to gitignore to protect personal data
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-14 15:12:01 -07:00
19af20e700
Fix syntax error in OAuth callback handler reference
2026-02-14 11:42:37 -07:00
dc14baf426
Add Gmail and Google Calendar integration
...
Implements on-demand Google tools (not adapter) for email and calendar access via OAuth2.
Features:
- OAuth2 user consent flow with automatic token refresh
- 3 Gmail tools: send_email, read_emails, get_email
- 3 Calendar tools: read_calendar, create_calendar_event, search_calendar
- Lazy loading pattern for Google clients
- Secure token storage with file permissions
- Browser-based setup: python bot_runner.py --setup-google
Architecture:
- Tools-only approach (zero API calls when not in use)
- User-initiated actions only (no continuous polling)
- MIME message creation for emails with threading support
- HTML to text conversion for email parsing
- ISO 8601 timestamp handling for calendar events
Files added:
- google_tools/oauth_manager.py: OAuth2 flow and token management
- google_tools/gmail_client.py: Gmail API wrapper
- google_tools/calendar_client.py: Calendar API wrapper
- google_tools/utils.py: Email/MIME helpers
- config/scheduled_tasks.yaml: Example scheduled tasks config
Files modified:
- tools.py: Added 6 Google tool handlers with lazy initialization
- bot_runner.py: Added --setup-google command for OAuth authorization
- requirements.txt: Added Google API dependencies
- .gitignore: Added google_credentials.yaml and google_oauth_token.json
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-14 10:29:28 -07:00
8afff96bb5
Add API usage tracking and dynamic task reloading
...
Features:
- Usage tracking system (usage_tracker.py)
- Tracks input/output tokens per API call
- Calculates costs with support for cache pricing
- Stores data in usage_data.json (gitignored)
- Integrated into llm_interface.py
- Dynamic task scheduler reloading
- Auto-detects YAML changes every 60s
- No restart needed for new tasks
- reload_tasks() method for manual refresh
- Example cost tracking scheduled task
- Daily API usage report
- Budget tracking ($5/month target)
- Disabled by default in scheduled_tasks.yaml
Improvements:
- Fixed tool_use/tool_result pair splitting bug (CRITICAL)
- Added thread safety to agent.chat()
- Fixed N+1 query problem in hybrid search
- Optimized database batch queries
- Added conversation history pruning (50 messages max)
Updated .gitignore:
- Exclude user profiles (memory_workspace/users/*.md)
- Exclude usage data (usage_data.json)
- Exclude vector index (vectors.usearch)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-13 23:38:44 -07:00
ab3a5afd59
Documentation cleanup and consolidation
...
Removed redundant/outdated files:
- docs/HEARTBEAT_HOOKS.md (legacy, disabled by default)
- docs/QUICK_START_PULSE.md (merged into PULSE_BRAIN.md)
- docs/MONITORING_COMPARISON.md (merged into PULSE_BRAIN.md)
Consolidated monitoring docs:
- Merged 3 monitoring files into comprehensive PULSE_BRAIN.md
- Added Quick Start section to PULSE_BRAIN.md
- Added "Why Pulse & Brain?" comparison section
- Added deprecation notices for Heartbeat system
Updated README.md:
- Clarified Haiku is default model (12x cheaper)
- Added prompt caching info (90% savings on Sonnet)
- Removed duplicate setup instructions
- Linked to SETUP.md for detailed instructions
- Added model switching commands section
Simplified WINDOWS_QUICK_REFERENCE.md:
- Reduced from 224 lines to ~160 lines
- Removed redundant development/deployment sections
- Kept essential quick commands
- Added model switching commands
Updated docs/README.md navigation:
- Removed references to deleted files
- Added deprecation notice for Heartbeat
- Updated learning paths
- Cleaned up file organization section
Result:
- Removed 300+ lines of redundant documentation
- Consolidated 3 monitoring files into 1
- Improved accuracy and clarity
- Easier navigation and maintenance
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-13 21:06:15 -07:00
a99799bf3d
Initial commit: Ajarbot with optimizations
...
Features:
- Multi-platform bot (Slack, Telegram)
- Memory system with SQLite FTS
- Tool use capabilities (file ops, commands)
- Scheduled tasks system
- Dynamic model switching (/sonnet, /haiku)
- Prompt caching for cost optimization
Optimizations:
- Default to Haiku 4.5 (12x cheaper)
- Reduced context: 3 messages, 2 memory results
- Optimized SOUL.md (48% smaller)
- Automatic caching when using Sonnet (90% savings)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com >
2026-02-13 19:06:28 -07:00
