86657f22cd
enable_tools=true runs the existing server-side agentic loop with built-in tools (web_search/python/terminal). A bare tools=[...] field now triggers a client-side pass-through: client-provided tools are forwarded to llama-server and any tool_use output is returned to the caller with stop_reason=tool_use for client execution. This fixes Claude Code (and any Anthropic SDK client) which sends tools=[...] expecting client-side execution but was previously routed through execute_tool() and failing with 'Unknown tool'. Adds AnthropicPassthroughEmitter to convert llama-server OpenAI SSE chunks into Anthropic SSE events, plus unit tests covering text blocks, tool_use blocks, mixed, stop reasons, and usage. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| conftest.py | ||
| test_anthropic_messages.py | ||
| test_cache_case_resolution.py | ||
| test_data_recipe_seed.py | ||
| test_gpu_selection.py | ||
| test_gpu_selection_sandbox.py | ||
| test_kv_cache_estimation.py | ||
| test_models_get_model_config_case_resolution.py | ||
| test_native_context_length.py | ||
| test_responses_api.py | ||
| test_studio_run.py | ||
| test_transformers_version.py | ||
| test_utils.py | ||
| test_vision_cache.py | ||
| test_vram_estimation.py | ||