feat: add persistent model-aware reasoning effort settings

This commit is contained in:
2026-11-15 18:45:22 -08:00
parent 91c7c0310e
commit 92a16a39c0
22 changed files with 678 additions and 36 deletions
@@ -1,3 +1,4 @@
import { getReasoningCapabilities, reasoningRequestOptions } from "../reasoning-effort.js";
import {
appendDanglingToolIntentCorrection,
buildChatToolSystemPrompt,
@@ -114,7 +115,8 @@ export async function completeWithChatCompletionsApi(params: ToolAwareCompletion
model: params.model,
messages: normalizePlainMessages(params.messages, params.userLocation),
temperature: params.temperature,
max_tokens: params.maxTokens,
...(getReasoningCapabilities(params.provider, params.model) ? { max_completion_tokens: params.maxTokens } : { max_tokens: params.maxTokens }),
...reasoningRequestOptions(params, "chat-completions"),
} as any);
const usageAcc: Required<NonNullable<ToolAwareCompletionResult["usage"]>> = { inputTokens: 0, outputTokens: 0, totalTokens: 0 };
@@ -142,7 +144,8 @@ export async function completeWithChatCompletionsApi(params: ToolAwareCompletion
model: params.model,
messages: conversation,
temperature: params.temperature,
max_tokens: params.maxTokens,
...(getReasoningCapabilities(params.provider, params.model) ? { max_completion_tokens: params.maxTokens } : { max_tokens: params.maxTokens }),
...reasoningRequestOptions(params, "chat-completions"),
tools: enabledTools,
tool_choice: "auto",
} as any);
@@ -227,7 +230,8 @@ export async function* streamWithChatCompletionsApi(params: ToolAwareCompletionP
model: params.model,
messages: normalizePlainMessages(params.messages, params.userLocation),
temperature: params.temperature,
max_tokens: params.maxTokens,
...(getReasoningCapabilities(params.provider, params.model) ? { max_completion_tokens: params.maxTokens } : { max_tokens: params.maxTokens }),
...reasoningRequestOptions(params, "chat-completions"),
stream: true,
} as any);
@@ -267,7 +271,8 @@ export async function* streamWithChatCompletionsApi(params: ToolAwareCompletionP
model: params.model,
messages: conversation,
temperature: params.temperature,
max_tokens: params.maxTokens,
...(getReasoningCapabilities(params.provider, params.model) ? { max_completion_tokens: params.maxTokens } : { max_tokens: params.maxTokens }),
...reasoningRequestOptions(params, "chat-completions"),
tools: enabledTools,
tool_choice: "auto",
stream: true,