@jeffreycao/copilot-api 1.13.11 → 1.13.14

package/README.md

@@ -553,9 +553,9 @@ Use `copilot-api auth login --provider custom` to add or update another third-pa
     - `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`. `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. For providers whose name is `dashscope` or whose `baseUrl` contains `aliyuncs.com`, the request-derived `thinking_budget` (from Anthropic `thinking.budget_tokens`) is forwarded upstream; for other OpenAI-compatible providers the request-derived `thinking_budget` is stripped, while an `extraBody` `thinking_budget` is still honored.
+    - `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. For providers whose name is `dashscope` or whose `baseUrl` contains `aliyuncs.com`, the request-derived `thinking_budget` (from Anthropic `thinking.budget_tokens`) is forwarded upstream; for other OpenAI-compatible providers the request-derived `thinking_budget` is stripped, while an `extraBody` `thinking_budget` is still honored. For DashScope providers, `preserve_thinking` defaults to `true` when not explicitly set in `extraBody` or the request body.
     - `pricing` (optional): Per-model token prices, in the provider `pricingCurrency`, per 1M tokens. Supported fields are `input`, `output`, `cachedInput` (implicit cache read), `explicitCachedInput` (explicit cache read), and `cacheCreationInput`. Use `tiers` with `maxInputTokens` for input-size tiered pricing.
-    - `contextCache` (optional): Defaults to `true` for providers whose name is `dashscope` or whose `baseUrl` contains `aliyuncs.com`; defaults to `false` for other 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. Set this to `true` for non-DashScope providers that support the same explicit-cache extension.
+    - `contextCache` (optional): Defaults to `true` for providers whose name is `dashscope` or whose `baseUrl` contains `aliyuncs.com`; defaults to `false` for other 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. Set this to `true` for non-DashScope providers that support the same explicit-cache extension. Applied on both `/v1/messages` and `/v1/chat/completions` routes.
     - `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.
     - `type` (optional): Per-model override of the provider protocol type. Supports `anthropic`, `openai-compatible`, and `openai-responses`. When set, the provider's `/v1/messages` route uses this model's type instead of the provider-level type for request routing, auth header resolution, and upstream endpoint selection. This is useful for providers like OpenCode Go whose upstream supports both OpenAI-compatible and Anthropic Messages APIs for different models. When the type is overridden, the auth header is resolved from the overridden type's default (Anthropic defaults to `x-api-key`; OpenAI-compatible/Responses default to `authorization`).

package/README.zh-CN.md

@@ -559,9 +559,9 @@ 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。`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。对于 provider name 为 `dashscope` 或 `baseUrl` 包含 `aliyuncs.com` 的 provider，请求派生的 `thinking_budget`（来自 Anthropic `thinking.budget_tokens`）会转发给上游；其他 OpenAI 兼容 provider 会移除请求派生的 `thinking_budget`，但 `extraBody` 中的 `thinking_budget` 仍然生效。
+    - `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。对于 provider name 为 `dashscope` 或 `baseUrl` 包含 `aliyuncs.com` 的 provider，请求派生的 `thinking_budget`（来自 Anthropic `thinking.budget_tokens`）会转发给上游；其他 OpenAI 兼容 provider 会移除请求派生的 `thinking_budget`，但 `extraBody` 中的 `thinking_budget` 仍然生效。对于 DashScope provider，当 `preserve_thinking` 未在 `extraBody` 或请求体中显式设置时，默认为 `true`。
     - `pricing`：可选，按模型配置 token 单价，币种使用 provider 的 `pricingCurrency`，单位为每 100 万 tokens。支持 `input`、`output`、`cachedInput`（隐式缓存读）、`explicitCachedInput`（显式缓存读）和 `cacheCreationInput`。如需按输入 token 总量分档，可用带 `maxInputTokens` 的 `tiers`。
-    - `contextCache`：可选，provider name 为 `dashscope` 或 `baseUrl` 包含 `aliyuncs.com` 时默认 `true`，其他 OpenAI 兼容 provider 默认 `false`。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`。支持相同显式缓存扩展的非 DashScope provider 可设为 `true`。
+    - `contextCache`：可选，provider name 为 `dashscope` 或 `baseUrl` 包含 `aliyuncs.com` 时默认 `true`，其他 OpenAI 兼容 provider 默认 `false`。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`。支持相同显式缓存扩展的非 DashScope provider 可设为 `true`。同时适用于 `/v1/messages` 和 `/v1/chat/completions` 路由。
     - `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。
     - `type`：可选，按模型覆盖 provider 的协议类型。支持 `anthropic`、`openai-compatible` 和 `openai-responses`。设置后，provider 的 `/v1/messages` 路由会使用该模型的 type 替代 provider 级别的 type 进行请求路由、认证头解析和上游端点选择。适用于 OpenCode Go 等上游对不同模型同时支持 OpenAI 兼容和 Anthropic Messages API 的 provider。覆盖 type 时，认证头按覆盖后 type 的默认值解析（Anthropic 默认 `x-api-key`；OpenAI 兼容/Responses 默认 `authorization`）。

package/dist/main.js

@@ -25,7 +25,7 @@ bindElectronFetch();
 const { auth } = await import("./auth-CfRmN-aH.js");
 const { debug } = await import("./debug-JJUz1hBb.js");
 const { mcp } = await import("./mcp-BseuqgHR.js");
-const { start } = await import("./start-CDw9cq41.js");
+const { start } = await import("./start-BP0GcUF7.js");
 await runMain(defineCommand({
 	meta: {
 		name: "copilot-api",

package/dist/{server-JtVsUm_H.js → server-977yOyfA.js}

@@ -1342,6 +1342,55 @@ function mergeAnthropicUsage(current, next) {
 	};
 }
 //#endregion
+//#region src/lib/dashscope.ts
+const OPENAI_COMPATIBLE_CONTEXT_CACHE_MARKER_LIMIT = 4;
+const OPENAI_COMPATIBLE_CONTEXT_CACHE_CONTROL = { type: "ephemeral" };
+const OPENAI_COMPATIBLE_CONTEXT_CACHE_ROLES = new Set([
+	"system",
+	"user",
+	"assistant",
+	"tool"
+]);
+const isDashScopeAliyunProvider = (providerConfig) => providerConfig.name === "dashscope" || providerConfig.baseUrl.includes("aliyuncs.com");
+const applyDashScopePreserveThinkingDefault = (payload, providerConfig) => {
+	if (!isDashScopeAliyunProvider(providerConfig)) return;
+	if (!Object.hasOwn(payload, "preserve_thinking")) payload.preserve_thinking = true;
+};
+const applyOpenAICompatibleContextCache = (payload) => {
+	const messageIndexes = selectContextCacheMessageIndexes(payload.messages);
+	for (const messageIndex of messageIndexes) applyContextCacheControl(payload.messages[messageIndex]);
+};
+const selectContextCacheMessageIndexes = (messages) => {
+	const cacheableIndexes = messages.flatMap((message, index) => isContextCacheMarkerEligible(message) ? [index] : []);
+	const systemIndexes = cacheableIndexes.filter((index) => messages[index]?.role === "system").slice(0, 2);
+	const finalIndexes = cacheableIndexes.filter((index) => messages[index]?.role !== "system").slice(-1);
+	return uniqueIndexes$1([...systemIndexes, ...finalIndexes]).sort((a, b) => a - b);
+};
+const uniqueIndexes$1 = (indexes) => [...new Set(indexes)].slice(0, OPENAI_COMPATIBLE_CONTEXT_CACHE_MARKER_LIMIT);
+const isContextCacheMarkerEligible = (message) => {
+	if (!OPENAI_COMPATIBLE_CONTEXT_CACHE_ROLES.has(message.role)) return false;
+	if (typeof message.content === "string") return message.content.length > 0;
+	return Array.isArray(message.content) && message.content.length > 0;
+};
+const applyContextCacheControl = (message) => {
+	if (!message) return;
+	if (typeof message.content === "string") {
+		message.content = [{
+			type: "text",
+			text: message.content,
+			cache_control: { ...OPENAI_COMPATIBLE_CONTEXT_CACHE_CONTROL }
+		}];
+		return;
+	}
+	if (!Array.isArray(message.content)) return;
+	const lastPart = message.content.at(-1);
+	if (!lastPart) return;
+	setContextCacheControl(lastPart);
+};
+const setContextCacheControl = (part) => {
+	part.cache_control = { ...OPENAI_COMPATIBLE_CONTEXT_CACHE_CONTROL };
+};
+//#endregion
 //#region src/lib/provider-resolver.ts
 function isMissingCodexCredentialsError(error) {
 	return error instanceof Error && error.message === "Codex credentials not found. Run `copilot-api auth login --provider codex` first.";
@@ -1455,6 +1504,8 @@ async function handleProviderChatCompletionsForProvider(c, options) {
 	applyProviderModelDefaults(payload, modelConfig);
 	applyMissingExtraBody$1(payload, { extraBody: modelConfig?.extraBody });
 	applyProviderStreamOptions(payload);
+	applyDashScopePreserveThinkingDefault(payload, providerConfig);
+	applyProviderContextCache(payload, modelConfig, providerConfig);
 	debugJson(logger$9, "provider.chat_completions.request", {
 		payload,
 		provider
@@ -1493,6 +1544,10 @@ const applyProviderStreamOptions = (payload) => {
 		include_usage: true
 	};
 };
+const applyProviderContextCache = (payload, modelConfig, providerConfig) => {
+	const isDashScopeProvider = isDashScopeAliyunProvider(providerConfig);
+	if (modelConfig?.contextCache ?? isDashScopeProvider) applyOpenAICompatibleContextCache(payload);
+};
 const createProviderChatCompletionsUsageRecorder = (payload, provider, modelConfig, pricingCurrency) => createProviderTokenUsageRecorder({
 	endpoint: "chat_completions",
 	model: payload.model,
@@ -5094,15 +5149,6 @@ function getModels() {
 //#endregion
 //#region src/routes/provider/messages/handler.ts
 const logger$6 = createHandlerLogger("provider-messages-handler");
-const OPENAI_COMPATIBLE_CONTEXT_CACHE_MARKER_LIMIT = 4;
-const OPENAI_COMPATIBLE_CONTEXT_CACHE_CONTROL = { type: "ephemeral" };
-const OPENAI_COMPATIBLE_CONTEXT_CACHE_ROLES = new Set([
-	"system",
-	"user",
-	"assistant",
-	"tool"
-]);
-const isDashScopeAliyunProvider = (providerConfig) => providerConfig.name === "dashscope" || providerConfig.baseUrl.includes("aliyuncs.com");
 async function handleProviderMessages(c) {
 	const provider = c.req.param("provider");
 	return await handleProviderMessagesForProvider(c, {
@@ -5373,6 +5419,7 @@ const createOpenAICompatiblePayload = (payload, modelConfig, providerConfig) =>
 	});
 	applyMissingExtraBody(openAIPayload, { extraBody: modelConfig?.extraBody });
 	applyOpenAICompatibleExtraBodyThinkingBudget(openAIPayload, { extraBody: modelConfig?.extraBody });
+	applyDashScopePreserveThinkingDefault(openAIPayload, providerConfig);
 	if (!Object.hasOwn(openAIPayload, "parallel_tool_calls")) openAIPayload.parallel_tool_calls = true;
 	if (modelConfig?.contextCache ?? isDashScopeProvider) applyOpenAICompatibleContextCache(openAIPayload);
 	return openAIPayload;
@@ -5389,40 +5436,6 @@ const applyOpenAICompatibleRequestOverrides = (payload, options) => {
 	const allowedKeys = new Set(Object.keys(options.extraBody ?? {}));
 	for (const key of allowedKeys) if (Object.hasOwn(options.source, key)) payload[key] = options.source[key];
 };
-const applyOpenAICompatibleContextCache = (payload) => {
-	const messageIndexes = selectContextCacheMessageIndexes(payload.messages);
-	for (const messageIndex of messageIndexes) applyContextCacheControl(payload.messages[messageIndex]);
-};
-const selectContextCacheMessageIndexes = (messages) => {
-	const cacheableIndexes = messages.flatMap((message, index) => isContextCacheMarkerEligible(message) ? [index] : []);
-	const systemIndexes = cacheableIndexes.filter((index) => messages[index]?.role === "system").slice(0, 2);
-	const finalIndexes = cacheableIndexes.filter((index) => messages[index]?.role !== "system").slice(-2);
-	return uniqueIndexes$1([...systemIndexes, ...finalIndexes]).sort((a, b) => a - b);
-};
-const uniqueIndexes$1 = (indexes) => [...new Set(indexes)].slice(0, OPENAI_COMPATIBLE_CONTEXT_CACHE_MARKER_LIMIT);
-const isContextCacheMarkerEligible = (message) => {
-	if (!OPENAI_COMPATIBLE_CONTEXT_CACHE_ROLES.has(message.role)) return false;
-	if (typeof message.content === "string") return message.content.length > 0;
-	return Array.isArray(message.content) && message.content.length > 0;
-};
-const applyContextCacheControl = (message) => {
-	if (!message) return;
-	if (typeof message.content === "string") {
-		message.content = [{
-			type: "text",
-			text: message.content,
-			cache_control: { ...OPENAI_COMPATIBLE_CONTEXT_CACHE_CONTROL }
-		}];
-		return;
-	}
-	if (!Array.isArray(message.content)) return;
-	const lastPart = message.content.at(-1);
-	if (!lastPart) return;
-	setContextCacheControl(lastPart);
-};
-const setContextCacheControl = (part) => {
-	part.cache_control = { ...OPENAI_COMPATIBLE_CONTEXT_CACHE_CONTROL };
-};
 const streamProviderMessages = ({ c, modelConfig, payload, pricingCurrency, provider, upstreamResponse }) => {
 	logger$6.debug("provider.messages.streaming");
 	const recordUsage = createProviderMessagesUsageRecorder(payload, provider, modelConfig, pricingCurrency);
@@ -5696,7 +5709,7 @@ const createMessages = async (payload, anthropicBetaHeader, options) => {
 //#endregion
 //#region src/routes/messages/api-flows.ts
 const COPILOT_CONTEXT_CACHE_SYSTEM_MARKER_LIMIT = 2;
-const COPILOT_CONTEXT_CACHE_NON_SYSTEM_MARKER_LIMIT = 2;
+const COPILOT_CONTEXT_CACHE_NON_SYSTEM_MARKER_LIMIT = 1;
 const COPILOT_CONTEXT_CACHE_CONTROL = { type: "ephemeral" };
 const messagesApiFlowDependencies = {
 	createChatCompletions,
@@ -6661,4 +6674,4 @@ server.route("/:provider/v1/models", providerModelRoutes);
 //#endregion
 export { server };
 
-//# sourceMappingURL=server-JtVsUm_H.js.map
+//# sourceMappingURL=server-977yOyfA.js.map