You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Fix duplicate reasoning_effort kwargs for GPT-5.4 xhigh runs #12
Category: bug Summary: Fix reasoning_effort collisions for OpenAI-compatible GPT-5.4 runs, and allow explicit xhigh reasoning effort from the workspace.
Current behavior:
When a model configured with langchain_openai:ChatOpenAI has a config-level reasoning_effort default and the frontend also sends reasoning_effort through run context, model construction fails with ChatOpenAI() got multiple values for keyword argument 'reasoning_effort'. Separately, the workspace only models reasoning effort up to high, so a user who needs xhigh cannot express it explicitly in the UI and the frontend's mode-derived defaults cap out at high.
Desired behavior:
OpenAI-compatible model construction should accept both a config default and a runtime reasoning_effort override without duplicate-keyword failures. Runtime context should override config defaults when thinking is enabled, while any internally forced thinking-disabled behavior should still win when thinking is disabled. The workspace should also be able to represent and send xhigh explicitly so GPT-5.4-style runs can stay at xhigh end-to-end instead of being truncated to high.
Key interfaces:
create_chat_model() runtime/config merge semantics for OpenAI-compatible BaseChatModel providers
The run-context shape that carries reasoning_effort from the frontend into the Gateway
Workspace reasoning-effort types and selector UI, which currently cap the value set at high
Acceptance criteria:
A config-level reasoning_effort default plus a runtime reasoning_effort override no longer raises duplicate-keyword TypeError for langchain_openai:ChatOpenAI
When thinking is enabled, runtime reasoning_effort overrides the config default for OpenAI-compatible models
When thinking is disabled, any forced disable-path reasoning_effort still takes precedence over a runtime override
The workspace types and UI can explicitly represent and send xhigh
Regression coverage exists for both the backend merge behavior and the frontend xhigh support path
Out of scope:
Changing non-OpenAI provider semantics unrelated to reasoning_effort
Redesigning the workspace mode system beyond the minimum needed to support xhigh
Activity
lgxyc commentedon Jun 30, 2026
Agent Brief
Category: bug
Summary: Fix
reasoning_effortcollisions for OpenAI-compatible GPT-5.4 runs, and allow explicitxhighreasoning effort from the workspace.Current behavior:
When a model configured with
langchain_openai:ChatOpenAIhas a config-levelreasoning_effortdefault and the frontend also sendsreasoning_effortthrough run context, model construction fails withChatOpenAI() got multiple values for keyword argument 'reasoning_effort'. Separately, the workspace only models reasoning effort up tohigh, so a user who needsxhighcannot express it explicitly in the UI and the frontend's mode-derived defaults cap out athigh.Desired behavior:
OpenAI-compatible model construction should accept both a config default and a runtime
reasoning_effortoverride without duplicate-keyword failures. Runtime context should override config defaults when thinking is enabled, while any internally forced thinking-disabled behavior should still win when thinking is disabled. The workspace should also be able to represent and sendxhighexplicitly so GPT-5.4-style runs can stay atxhighend-to-end instead of being truncated tohigh.Key interfaces:
create_chat_model()runtime/config merge semantics for OpenAI-compatibleBaseChatModelprovidersreasoning_effortfrom the frontend into the GatewayhighAcceptance criteria:
reasoning_effortdefault plus a runtimereasoning_effortoverride no longer raises duplicate-keywordTypeErrorforlangchain_openai:ChatOpenAIreasoning_effortoverrides the config default for OpenAI-compatible modelsreasoning_effortstill takes precedence over a runtime overridexhighxhighsupport pathOut of scope:
reasoning_effortxhighlgxyc commentedon Jun 30, 2026
实现进展:
feature/12-gpt54-xhigh-reasoning-effort本次修复包含:
ChatOpenAI的reasoning_effort重复传参冲突xhigh类型、默认映射和请求级传递语义验证已完成:backend lint、backend 定向 pytest、frontend 定向单测、frontend check、frontend build、以及真实
gpt-5.4调用。fix(models): support GPT-5.4 xhigh reasoning effort (#14)