jpmschweitzer/tatlock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 5 Wiki Activity
31 Commits 1 Branch 47 Tags
tatlock-code-model-stable
Commit Graph
3 Commits
Author SHA1 Message Date
jpmschweitzer 67481515cc feat: integrate Tatlock agent with PydanticAI and Ollama 
Convert Tatlock from mock to real PydanticAI agent:
- Connect to Ollama backend (mistral-nemo:latest)
- British butler personality with research-oriented mindset
- Lazy initialization pattern for better testability
- Register permanent tools (calculator, date/time, search)
- Streaming response support with reasoning output
- Error handling for PydanticAI exceptions
- Update registry tests for tools capability
- Add integration test for streaming functionality
 2025-12-07 00:12:39 +01:00
jpmschweitzer f3e2681a6c feat: implement permanent tools (calculator, date/time, search) 
Add three permanent tools for Tatlock agent:
- Calculator: Safe math expression evaluation (arithmetic, algebra, trig, log)
- Date/Time toolkit: Current time, relative dates, time differences
- Web Search: SearXNG integration for privacy-preserving search

Tools use PydanticAI @agent.tool decorator pattern with:
- Clear docstrings visible to LLM
- Error handling with string-based messages
- Async support for I/O operations (web search)
- 26 comprehensive tool tests
 2025-12-07 00:10:49 +01:00
jpmschweitzerandClaude 4e6ca4466b Add agent interface and model implementations 
Implements Phase 1: Agent abstraction layer with multiple model support

Features:
- Abstract AgentInterface base class with standard contract
- LoremTesterAgent: Full-featured mock agent with realistic behavior
  - Configurable reasoning effort levels (none to xhigh)
  - Random tool/function call generation
  - Error triggers for testing (rate_limit, context_overflow)
  - Temperature-based response variation
- TatlockAgent: Placeholder for future PydanticAI integration
- ModelRegistry: Centralized model management and discovery

Testing:
- 9 unit tests for lorem-tester agent behavior
- 9 unit tests for registry operations
- Coverage: Agent abstraction fully tested

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-12-06 19:36:53 +01:00