@jeffreycao/copilot-api 1.10.8 → 1.10.9

package/README.md

@@ -382,7 +382,7 @@ The following command line options are available for the `start` command:
     - `temperature` (optional): Default temperature value used when the request does not specify one.
     - `topP` (optional): Default top_p value used when the request does not specify one.
     - `topK` (optional): Default top_k value used when the request does not specify one.
-    - `extraBody` (optional): Dynamic fields merged into the upstream request body for that model. Request body fields with the same name take precedence. OpenAI-compatible providers can use this for fields such as `enable_thinking`, `preserve_thinking`, `reasoning_effort`.
+    - `extraBody` (optional): Dynamic fields merged into the upstream request body for that model. Request body fields with the same name take precedence. OpenAI-compatible providers can use this for fields such as `enable_thinking`, `preserve_thinking`, `reasoning_effort`. `thinking_budget` is a special OpenAI-compatible provider override: when configured in `extraBody`, it is forced after Anthropic `thinking.budget_tokens` translation and overrides the request-derived budget.
     - `contextCache` (optional): Defaults to `true` for OpenAI-compatible providers. This enables Alibaba Cloud Model Studio/DashScope explicit context cache by injecting `cache_control: { "type": "ephemeral" }` on up to 4 content blocks using the Context Cache format. The cache breakpoint strategy matches opencode's main provider flow: the first 2 system messages plus the last 2 non-system messages. Marked string content is converted to text content part arrays for `system` / `user` / `assistant` / `tool` messages; existing array content is marked on the last part. Set this to `false` when the model already supports implicit caching, or when the upstream does not accept this explicit-cache extension field.
     - `supportPdf` (optional): Controls whether the model supports PDF/document content. Defaults to `false`; unsupported PDFs are converted to a text notice. Set it to `true` to send PDF/document blocks as OpenAI Chat Completions file parts.
     - `toolContentSupportType` (optional): Tool result content capabilities for that model, as an array of `array`, `image`, and `pdf`. Provider routes default to string-only tool content when omitted. If `supportPdf` is `true` but this list does not include `pdf`, file parts in tool results are moved to user role messages. This provider default does not change the Copilot main flow, which continues to support array + image and not PDF.

package/README.zh-CN.md

@@ -386,7 +386,7 @@ Copilot API 现在使用子命令结构，主要命令包括：
     - `temperature`：可选，当请求未指定时使用的默认温度。
     - `topP`：可选，当请求未指定时使用的默认 `top_p`。
     - `topK`：可选，当请求未指定时使用的默认 `top_k`。
-    - `extraBody`：可选，按模型合入上游请求体的动态字段；请求体显式同名字段优先。OpenAI 兼容 provider 可用它配置 `enable_thinking`、`preserve_thinking`、`reasoning_effort` 等字段。
+    - `extraBody`：可选，按模型合入上游请求体的动态字段；请求体显式同名字段优先。OpenAI 兼容 provider 可用它配置 `enable_thinking`、`preserve_thinking`、`reasoning_effort` 等字段。`thinking_budget` 是 OpenAI 兼容 provider 的特殊覆盖项：配置在 `extraBody` 后，会在 Anthropic `thinking.budget_tokens` 翻译之后强制写入，并覆盖请求派生出的预算值。
     - `contextCache`：可选，OpenAI 兼容 provider 默认 `true`，用于启用阿里云百炼/DashScope 的显式缓存（explicit context cache），会按其 Context Cache 格式在最多 4 个 content block 上注入 `cache_control: { "type": "ephemeral" }`。缓存断点策略与 opencode 主链路保持一致：前 2 条 system 消息 + 最后 2 条非 system 消息。标记字符串 content 时会把 `system` / `user` / `assistant` / `tool` 消息转换为 text content part 数组；已有数组 content 则标记最后一个 part。如果模型本身已经支持隐式缓存，或上游不支持该显式缓存扩展字段，可在模型配置中设为 `false`。
     - `supportPdf`：可选，控制该模型是否支持 PDF/document content。默认 `false`，不支持时会把 PDF 转成提示文本；设为 `true` 时会把 PDF/document 转成 OpenAI Chat Completions 的 file part。
     - `toolContentSupportType`：可选，配置该模型的 tool result content 支持能力，值为 `array`、`image`、`pdf` 的数组。provider 侧未配置时默认只发送 string tool content。若 `supportPdf` 为 `true` 但这里不包含 `pdf`，tool result 里的 file part 会被转成 user role 消息。Copilot 主链路不使用这个 provider 默认，仍按 array + image 且不支持 PDF 的能力处理。

package/dist/main.js

@@ -43,7 +43,7 @@ const { auth } = await import("./auth-BHa2OHXf.js");
 const { checkUsage } = await import("./check-usage-BdXGp1Wr.js");
 const { debug } = await import("./debug-C_TBkyUw.js");
 const { mcp } = await import("./mcp-CTb-DbQH.js");
-const { start } = await import("./start-Bzfnxzlh.js");
+const { start } = await import("./start-CbKg_0bY.js");
 await runMain(defineCommand({
 	meta: {
 		name: "copilot-api",

package/dist/{server-BRFLAT4z.js → server-FPXzFkg9.js}

@@ -2343,6 +2343,25 @@ const applyModelDefaults = (payload, modelConfig) => {
 const applyMissingExtraBody = (payload, options) => {
 	for (const [key, value] of Object.entries(options.extraBody ?? {})) if (!Object.hasOwn(payload, key)) payload[key] = value;
 };
+const getRequestThinkingBudget = (payload) => {
+	const budget = payload.thinking?.budget_tokens;
+	if (typeof budget !== "number" || !Number.isFinite(budget)) return;
+	return budget;
+};
+const applyOpenAICompatibleThinkingBudget = (payload, source) => {
+	const thinkingBudget = getRequestThinkingBudget(source);
+	if (thinkingBudget !== void 0) {
+		payload.thinking_budget = thinkingBudget;
+		return;
+	}
+	if (payload.thinking_budget === void 0) delete payload.thinking_budget;
+};
+const applyOpenAICompatibleExtraBodyThinkingBudget = (payload, options) => {
+	const { extraBody } = options;
+	if (!extraBody || !Object.hasOwn(extraBody, "thinking_budget")) return;
+	const rawPayload = payload;
+	rawPayload.thinking_budget = extraBody.thinking_budget;
+};
 const handleOpenAICompatibleProviderMessages = async (c, options) => {
 	const { modelConfig, payload, provider, providerConfig } = options;
 	const openAIPayload = createOpenAICompatiblePayload(payload, modelConfig);
@@ -2373,6 +2392,7 @@ const createOpenAICompatiblePayload = (payload, modelConfig) => {
 		supportPdf: modelConfig?.supportPdf,
 		toolContentSupportType: modelConfig?.toolContentSupportType ?? []
 	});
+	applyOpenAICompatibleThinkingBudget(openAIPayload, payload);
 	if (payload.top_k !== void 0) openAIPayload.top_k = payload.top_k;
 	if (openAIPayload.stream) openAIPayload.stream_options = { include_usage: true };
 	normalizeOpenAICompatibleReasoningContent(openAIPayload);
@@ -2381,6 +2401,7 @@ const createOpenAICompatiblePayload = (payload, modelConfig) => {
 		source: payload
 	});
 	applyMissingExtraBody(openAIPayload, { extraBody: modelConfig?.extraBody });
+	applyOpenAICompatibleExtraBodyThinkingBudget(openAIPayload, { extraBody: modelConfig?.extraBody });
 	if (!Object.hasOwn(openAIPayload, "parallel_tool_calls")) openAIPayload.parallel_tool_calls = true;
 	if (modelConfig?.contextCache !== false) applyOpenAICompatibleContextCache(openAIPayload);
 	return openAIPayload;
@@ -5019,4 +5040,4 @@ server.route("/:provider/v1/models", providerModelRoutes);
 //#endregion
 export { server };
 
-//# sourceMappingURL=server-BRFLAT4z.js.map
+//# sourceMappingURL=server-FPXzFkg9.js.map