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

..

__init__.py

perf: cut startup latency — lazy import surface, langgraph dev keepalive, indexed thread listing (#407)

2026-08-11 08:37:58 +01:00

context_window.py

release: v0.2.7 (#430)

2026-08-14 19:30:26 +01:00

deepseek.py

fix(llm): use native langchain-deepseek SDK (#349)

2026-07-15 17:13:33 +01:00

errors.py

Add Atlas Cloud LLM provider (#388)

2026-07-29 14:09:44 +01:00

models.py

fix(llm): bound routed reasoning and surface empty truncation (#425)

2026-08-18 08:28:19 +01:00

ollama_discovery.py

feat: Enhance ModelPickerWidget for Ollama integration (#187)

2026-04-25 00:37:48 +01:00

openai_compat.py

fix(llm): use native langchain-deepseek SDK (#349)

2026-07-15 17:13:33 +01:00

patches.py

fix: prevent session-emptying crash on resume commands (#428)

2026-08-17 07:10:37 +00:00

registry.py

release: v0.2.7 (#430)

2026-08-14 19:30:26 +01:00