3 Commits

Author	SHA1	Message	Date
LZH-YS1998	b2ff565ff6	fix(llm): clamp max_tokens to the model's output limit before each call ... A generous config default (32768) hard-fails on providers that reject an oversized max_tokens (e.g. DeepSeek caps output at 8192). Clamp to litellm's max_output_tokens when known, log once per model; unknown models pass through unchanged.	2026-07-04 18:03:53 +08:00
LZH-YS1998	6c8d3f3dc9	fix(llm): resolve context window via max_input_tokens with 128k fallback for unmapped models ... - get_context_window() now reads litellm.get_model_info().max_input_tokens instead of get_max_tokens(), which returns the output cap and severely under-reported the window for every mapped model (e.g. deepseek 8k vs 1M) - models litellm cannot map fall back to 128000 with a single warning per model instead of warning on every call and returning None - raise LLMConfig.max_tokens default 8192 -> 32768 to match the template - README: configure the API key directly in llm_config.yaml; document max_tokens / context_window in the example Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-04 17:53:12 +08:00
LZH-YS1998	d78931979d	Initial commit	2026-07-01 17:56:31 +08:00