2 Commits

Author	SHA1	Message	Date
sleepy	dcca89d89a	fix: OpenAI API compatibility for hollama and other clients ... - Fixed ChatMessage.tool_calls to be Optional with default None (excluded when empty) - Added logprobs field to ChatCompletionChoice (always included as null) - Added stats and system_fingerprint to ChatCompletionResponse - Fixed streaming response to use delta format (not message format) - Fixed non-streaming response to include logprobs: null - Updated tool instructions to include 'NO explanations' - Added pytest-asyncio markers to async tests - All 41 tests passing This fixes the 'Cannot read properties of undefined (reading content)' error in hollama and ensures compatibility with OpenAI clients.	2026-02-25 19:39:05 +01:00
sleepy	32049c766c	refactor(models): extract hardcoded data to JSON configs ... Extracted from registry.py (437 → 194 lines): - config/models/mlx_quant_sizes.json - MLX quantization VRAM sizes - config/models/gguf_quant_sizes.json - GGUF quantization VRAM sizes - config/models/model_metadata.json - Model metadata Registry now loads from JSON files instead of hardcoded data. All 35 tests pass.	2026-02-25 13:20:29 +01:00