3 Commits

Author	SHA1	Message	Date
LinxXu	47c8da3e5b	fix(llm): bound routed reasoning and surface empty truncation (#425) ... * fix(llm): bound routed reasoning and surface empty truncation Default DashScope Qwen 3.8 Max requests to low reasoning effort and forward explicit reasoning controls to custom OpenAI-compatible endpoints. Detect length-limited responses that exhaust their budget during reasoning without producing content or tool calls, and surface a provider-aware error instead of ending the turn silently. Add regression coverage for routed reasoning configuration, truncated empty responses, and valid content/tool-call responses. * fix(middleware): reject empty structured text blocks * fix(llm): address reasoning truncation review feedback * fix(llm): validate DashScope reasoning effort * fix(llm): document DashScope reasoning support	2026-08-18 08:28:19 +01:00
dinos	05dfffbc73	fix(llm): use native langchain-deepseek SDK (#349)	2026-07-15 17:13:33 +01:00
jfilipiuk	88ac9f5ba1	fix: surface real exception class+message in SSE error events (#315) ... * fix: surface real exception class+message in SSE error events * fix: tighten SSE error patch scope and key redaction * fix: redact base64-style secret suffixes fully * style: remove notes/ reference from the dosctring * fix: rebuild env cache on each error call * fix: route BaseException through serde.default on SSE/webhook paths * fix: distinguish routed providers by request URL host * feat: normalize provider-SDK exceptions via ErrorNormalizationMiddleware * refactor: drop json_dumpb dataclass-bypass wrappers, superseded by middleware * fix: guard _extract_host against SDK properties that raise * refactor: derive provider tag from ModelRequest.model, not the exception * refactor: drop serde.default patch and exception-based inference; ProviderStreamError.model_dump handles the emit * refactor: move envelope helpers from patches.py to errors.py * feat: extend ErrorNormalizationMiddleware coverage to every model-call path * chore: clean up review findings from middleware pivot * fix: pass through all langgraph.errors * fix: move langgraph.errors pass-through into _normalize * fix: pass through ContextOverflowError in _normalize	2026-07-13 14:17:56 +01:00