VERA cleanup (FPLAN-0410): - Remove all /home/aipass hardcoded paths (portability) - Remove internal Telegram bot code from public repo (6k+ lines) - Remove runtime logs, .claude/settings.local.json, stale files - Clean READMEs across all branches - Restructure spawn handlers into proper 3-layer architecture - Add __init__.py files for proper package imports - Update seedgo standards for public repo context - Add log_structure standard to seedgo Integration test bug fixes: - Fix double @@ display in drone introspection output - Fix spawn registry resolving to wrong file (walk up from package root) - Fix email sender identity always showing as @ai_mail (pass AIPASS_CALLER_CWD) - Fix branch_detection.py relative path resolution against CWD instead of registry dir - Add .trinity/passport.json detection for spawned agents - Archive duplicate json_ops.py, update imports to canonical json_handler - Update .gitignore for runtime logs and .claude/ dirs Tested end-to-end in Docker container (aipass-test:latest): - Spawn → register → send email → receive → reply all verified working Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
API
Purpose: LLM API access layer with provider abstraction, key management, model routing, and usage tracking.
Module: aipass.api
Overview
What I Do
- Manage API keys for LLM providers (currently OpenRouter)
- Route requests to LLM models with provider-level abstraction
- Track API usage metrics and provide statistics
- Validate credentials and test provider connectivity
- Discover available models from configured providers
How I Work
- Entry Point:
apps/api.py-- auto-discovers and routes to modules - Pattern: Standard AIPass 3-tier architecture (entry point / modules / handlers)
CLI
drone @api get-key # Retrieve API key for provider
drone @api validate # Validate API credentials and connection
drone @api test # Test OpenRouter connection status
drone @api models # List available models from provider
drone @api track # Track API usage metrics
drone @api stats # Display API usage statistics
drone @api --help # Full help output
Architecture
api/
├── __init__.py # Public API exports
├── apps/
│ ├── api.py # Entry point (module discovery, command routing)
│ ├── modules/
│ │ ├── api_key.py # Key retrieval and validation logic
│ │ ├── openrouter_client.py # OpenRouter API client
│ │ └── usage_tracker.py # Usage metrics tracking
│ └── handlers/
│ ├── auth/
│ │ ├── env.py # Environment variable credential loading
│ │ └── keys.py # API key storage and retrieval
│ ├── config/
│ │ └── provider.py # Provider configuration management
│ ├── json/
│ │ └── json_handler.py # JSON operation logging
│ ├── openrouter/
│ │ ├── caller.py # HTTP request execution
│ │ ├── client.py # OpenRouter client implementation
│ │ ├── models.py # Model discovery and listing
│ │ └── provision.py # Provider provisioning
│ └── usage/
│ ├── aggregation.py # Usage data aggregation
│ ├── cleanup.py # Usage data cleanup
│ └── tracking.py # Usage event tracking
└── README.md
Integration Points
Depends On
aipass.prax-- structured logging viasystem_loggeraipass.cli-- Rich console output formatting
Provides To
- All modules -- LLM API access for any branch that needs model inference
- System-wide API key management and credential validation