@jeffreycao/copilot-api 1.10.23 → 1.10.24

package/README.md

@@ -16,9 +16,7 @@ English | [简体中文](./README.zh-CN.md)
 >
 > 3. **Built-in `codex` provider:** Run `npx @jeffreycao/copilot-api@latest auth login --provider codex` once and the gateway will persist and refresh Codex OAuth credentials automatically.
 >
-> 4. **Disable multi agent when using codex:** If you're using codex via GitHub Copilot, disable multi agent. Copilot currently charges codex traffic based on whether the last message is a user role, and that billing logic has not been adjusted.
->
-> 5. **Note:** See [GitHub Copilot Security Notice](./NOTICE.md#github-copilot-security-notice) for the warning removed from the README header.
+> 4. **Note:** See [GitHub Copilot Security Notice](./NOTICE.md#github-copilot-security-notice) for the warning removed from the README header.
 
 ---
 
@@ -94,7 +92,7 @@ https://github.com/caozhiyuan/copilot-api/releases
 
 Download the installer for your platform, sign in inside the app, choose a port, start the server, then point your client at the local endpoint shown in the app. Packaged desktop builds use the bundled Electron runtime, so normal desktop usage does not require installing Node.js separately. Token usage history is enabled when that bundled runtime supports SQLite.
 
-The desktop app's Advanced Config page reads and writes model mappings through `GET/POST /admin/config/model-mappings`. It uses `auth.adminApiKey` instead of the regular `auth.apiKeys`, and the app reads that key directly from `config.json` after the server has generated it on startup.
+The desktop app's Advanced Config page reads and writes the shared model mappings through `GET/POST /admin/config/model-mappings`. The same mappings apply across `POST /v1/messages`, `POST /v1/messages/count_tokens`, `POST /v1/responses`, and `POST /v1/chat/completions` instead of being split per interface. It uses `auth.adminApiKey` instead of the regular `auth.apiKeys`, and the app reads that key directly from `config.json` after the server has generated it on startup.
 
 ### Desktop App Screenshots
 
@@ -195,14 +193,7 @@ The following command line options are available for the `start` command:
         "enabled": true,
         "baseUrl": "your-base-url",
         "apiKey": "sk-your-provider-key",
-        "authType": "x-api-key",
-        "adjustInputTokens": false,
-        "models": {
-          "kimi-k2.5": {
-            "temperature": 1,
-            "topP": 0.95
-          }
-        }
+        "authType": "x-api-key"
       },
       "dashscope": {
         "type": "openai-compatible",
@@ -216,8 +207,7 @@ The following command line options are available for the `start` command:
             "topK": 20,
             "extraBody": {
               "preserve_thinking": true
-            },
-            "contextCache": true
+            }
           },
           "glm-5.1": {
             "temperature": 0.7,
@@ -252,7 +242,7 @@ The following command line options are available for the `start` command:
   ```
 - **auth.apiKeys:** API keys used for request authentication on non-admin routes. Supports multiple keys for rotation. Requests can authenticate with either `x-api-key: <key>` or `Authorization: Bearer <key>`. If empty or omitted, authentication for non-admin routes is disabled.
 - **auth.adminApiKey:** Single admin key used only for `/admin/*` routes. If missing, the server generates a random key at startup and writes it back to `config.json`. Requests use the same `x-api-key` or `Authorization: Bearer` headers, but regular `auth.apiKeys` never grant access to `/admin/*`.
-- **modelMappings:** Exact `sourceModel -> targetModel` rewrites for top-level `POST /v1/messages` and `POST /v1/messages/count_tokens` requests. Omit it or leave it as `{}` to disable rewrites. Both the source and target must be non-empty strings. Targets can be regular model IDs or `provider/model` aliases such as `dashscope/qwen3.6-plus`, and the rewrite happens before provider alias parsing. The admin endpoints `GET/POST /admin/config/model-mappings` read and update only this field.
+- **modelMappings:** Exact `sourceModel -> targetModel` rewrites shared by top-level `POST /v1/messages`, `POST /v1/messages/count_tokens`, `POST /v1/responses`, and `POST /v1/chat/completions` requests. Omit it or leave it as `{}` to disable rewrites. Both the source and target must be non-empty strings. Targets can be regular model IDs or `provider/model` aliases such as `dashscope/qwen3.6-plus`, and the rewrite happens before provider alias parsing. These mappings are not split per interface. The admin endpoints `GET/POST /admin/config/model-mappings` read and update only this field.
 - **extraPrompts:** Map of `model -> prompt` appended to the first system prompt when translating Anthropic-style requests to Copilot. Use this to inject guardrails or guidance per model. Missing default entries are auto-added without overwriting your custom prompts. The built-in prompts for `gpt-5.3-codex` and `gpt-5.4` enable phase-aware commentary, which lets the model emit a short user-facing progress update before tools or deeper reasoning.
 - **providers:** Global upstream provider map. Each provider key (for example `dashscope`) becomes a route prefix (`/dashscope/v1/messages`). Supports `type: "anthropic"`, `type: "openai-compatible"`, and `type: "openai-responses"`. Top-level clients can also use `model: "dashscope/model-id"` with `/v1/messages`, `/v1/messages/count_tokens`, and `/v1/responses`; the gateway strips the `dashscope/` prefix before forwarding upstream. `GET /v1/models` does not aggregate provider models; use `GET /dashscope/v1/models` for provider model lists.
   - `enabled` defaults to `true` if omitted.
@@ -520,14 +510,14 @@ Example `~/.config/opencode/opencode.json`:
             "output": ["text"]
           },
           "limit": {
-            "context": 272000,
+            "context": 300000,
             "output": 128000
           }
         },
         "gpt-5-mini": {
           "name": "gpt-5-mini",
           "limit": {
-            "context": 128000,
+            "context": 200000,
             "output": 64000
           }
         },
@@ -539,7 +529,7 @@ Example `~/.config/opencode/opencode.json`:
             "output": ["text"]
           },          
           "limit": {
-            "context": 128000,
+            "context": 200000,
             "output": 32000
           },
           "options": {

package/README.zh-CN.md

@@ -16,9 +16,7 @@
 >
 > 3. **内置 `codex` provider：** 执行一次 `npx @jeffreycao/copilot-api@latest auth login --provider codex` 后，AI gateway 会自动持久化并刷新 Codex OAuth 凭据。
 >
-> 4. **通过 codex 使用时请关闭 multi agent：** 如果你是通过 GitHub Copilot 使用 codex，请关闭 multi agent。当前 Copilot 会按最后一条消息是否为 user role 对 codex 流量计费，而这部分逻辑尚未调整。
->
-> 5. **注意事项：** README 顶部移除的 GitHub Copilot warning 见 [GitHub Copilot 安全提示](./NOTICE.md#github-copilot-security-notice)。
+> 4. **注意事项：** README 顶部移除的 GitHub Copilot warning 见 [GitHub Copilot 安全提示](./NOTICE.md#github-copilot-security-notice)。
 
 ---
 
@@ -94,7 +92,7 @@ https://github.com/caozhiyuan/copilot-api/releases
 
 下载对应平台的安装包后，在应用内登录、选择端口并启动服务，再把你的客户端指向应用里显示的本地端点即可。发布版桌面应用使用随包内置的 Electron 运行时，正常使用不需要额外安装 Node.js；token usage 历史记录会在该内置运行时支持 SQLite 时启用。
 
-桌面应用里的高级配置页会通过 `GET/POST /admin/config/model-mappings` 读写模型映射。它使用的是 `auth.adminApiKey`，不是普通的 `auth.apiKeys`；应用会在服务启动并自动生成该 key 后，直接从 `config.json` 读取它来发起请求。
+桌面应用里的高级配置页会通过 `GET/POST /admin/config/model-mappings` 读写这份共享的模型映射。同一份映射会统一作用于 `POST /v1/messages`、`POST /v1/messages/count_tokens`、`POST /v1/responses` 和 `POST /v1/chat/completions`，不再按接口区分。它使用的是 `auth.adminApiKey`，不是普通的 `auth.apiKeys`；应用会在服务启动并自动生成该 key 后，直接从 `config.json` 读取它来发起请求。
 
 ### 桌面应用截图
 
@@ -197,14 +195,7 @@ Copilot API 现在使用子命令结构，主要命令包括：
         "enabled": true,
         "baseUrl": "your-base-url",
         "apiKey": "sk-your-provider-key",
-        "authType": "x-api-key",
-        "adjustInputTokens": false,
-        "models": {
-          "kimi-k2.5": {
-            "temperature": 1,
-            "topP": 0.95
-          }
-        }
+        "authType": "x-api-key"
       },
       "dashscope": {
         "type": "openai-compatible",
@@ -218,8 +209,7 @@ Copilot API 现在使用子命令结构，主要命令包括：
             "topK": 20,
             "extraBody": {
               "preserve_thinking": true
-            },
-            "contextCache": true
+            }
           },
           "glm-5.1": {
             "temperature": 0.7,
@@ -254,7 +244,7 @@ Copilot API 现在使用子命令结构，主要命令包括：
   ```
 - **auth.apiKeys：** 用于普通非 admin 路由的 API key。支持多个 key 轮换使用。请求可通过 `x-api-key: <key>` 或 `Authorization: Bearer <key>` 进行认证。若为空或省略，则普通路由的认证会被禁用。
 - **auth.adminApiKey：** 仅用于 `/admin/*` 路由的单个 admin key。若未配置，服务会在启动时自动生成一个随机 key，并回写到 `config.json`。它同样使用 `x-api-key` 或 `Authorization: Bearer` 这两种头，但普通 `auth.apiKeys` 不能访问 `/admin/*`。
-- **modelMappings：** 用于顶层 `POST /v1/messages` 和 `POST /v1/messages/count_tokens` 请求的精确 `sourceModel -> targetModel` 重写映射。省略该字段或保留为 `{}` 时，不会做模型重写。`source` 和 `target` 都必须是非空字符串。`target` 可以是普通模型 ID，也可以是 `provider/model` 形式的别名，例如 `dashscope/qwen3.6-plus`；重写发生在 provider alias 解析之前。`GET/POST /admin/config/model-mappings` 管理接口读写的也只有这个字段。
+- **modelMappings：** 用于顶层 `POST /v1/messages`、`POST /v1/messages/count_tokens`、`POST /v1/responses` 和 `POST /v1/chat/completions` 请求的精确 `sourceModel -> targetModel` 重写映射，这几类接口共用同一份规则。省略该字段或保留为 `{}` 时，不会做模型重写。`source` 和 `target` 都必须是非空字符串。`target` 可以是普通模型 ID，也可以是 `provider/model` 形式的别名，例如 `dashscope/qwen3.6-plus`；重写发生在 provider alias 解析之前。这些映射不再按接口区分。`GET/POST /admin/config/model-mappings` 管理接口读写的也只有这个字段。
 - **extraPrompts：** `model -> prompt` 的映射。把 Anthropic 风格请求翻译给 Copilot 时，会将其附加到第一条 system prompt 后面。你可以借此为不同模型注入护栏或指引。缺失的默认项会自动补齐，但不会覆盖你自定义的 prompt。内置的 `gpt-5.3-codex` 和 `gpt-5.4` prompt 会启用带阶段感知的 commentary，让模型在工具调用或更深层推理前先发出简短的用户可见进度说明。
 - **providers：** 全局上游 provider 映射。每个 provider key（例如 `dashscope`）都会变成一个路由前缀（`/dashscope/v1/messages`）。支持 `type: "anthropic"`、`type: "openai-compatible"` 和 `type: "openai-responses"`。顶层客户端也可以在 `/v1/messages`、`/v1/messages/count_tokens` 和 `/v1/responses` 中使用 `model: "dashscope/model-id"`；AI gateway 会在转发上游前移除 `dashscope/` 前缀。`GET /v1/models` 不聚合 provider 模型；provider 模型列表请使用 `GET /dashscope/v1/models`。
   - `enabled`：可选，若省略则默认为 `true`。
@@ -524,14 +514,14 @@ npx @jeffreycao/copilot-api@latest --oauth-app=opencode start
             "output": ["text"]
           },
           "limit": {
-            "context": 272000,
+            "context": 300000,
             "output": 128000
           }
         },
         "gpt-5-mini": {
           "name": "gpt-5-mini",
           "limit": {
-            "context": 128000,
+            "context": 200000,
             "output": 64000
           }
         },
@@ -543,7 +533,7 @@ npx @jeffreycao/copilot-api@latest --oauth-app=opencode start
             "output": ["text"]
           },
           "limit": {
-            "context": 128000,
+            "context": 200000,
             "output": 32000
           },
           "options": {

package/dist/main.js

@@ -43,7 +43,7 @@ const { auth } = await import("./auth-Qy0uU2yI.js");
 const { checkUsage } = await import("./check-usage-DDfnCA0c.js");
 const { debug } = await import("./debug-Cc-hdADF.js");
 const { mcp } = await import("./mcp-DZgcvqQY.js");
-const { start } = await import("./start-B9cpzVBW.js");
+const { start } = await import("./start-BUezzq53.js");
 await runMain(defineCommand({
 	meta: {
 		name: "copilot-api",

package/dist/{server-G5PWGqkb.js → server-BA2464Db.js}

@@ -1026,8 +1026,11 @@ const createChatCompletions = async (payload, options) => {
 //#region src/routes/chat-completions/handler.ts
 const logger$7 = createHandlerLogger("chat-completions-handler");
 async function handleCompletion$1(c) {
-	await checkRateLimit(state);
 	let payload = await c.req.json();
+	const requestedModel = payload.model;
+	payload.model = resolveMappedModel(payload.model);
+	if (payload.model !== requestedModel) logger$7.debug(`Resolved model mapping: ${requestedModel} -> ${payload.model}`);
+	await checkRateLimit(state);
 	debugJsonTail(logger$7, "Request payload:", {
 		value: payload,
 		tailLength: 400
@@ -3773,6 +3776,7 @@ const stringifyToolSearchArguments = (argumentsValue) => {
 		return;
 	}
 };
+const DEFAULT_RESPONSES_COMPACT_THRESHOLD_RATIO = .9;
 const responsesUtilsDependencies = {
 	isResponsesApiContextManagementModel,
 	isResponsesApiWebSocketEnabled
@@ -3873,18 +3877,18 @@ const isResponseFunctionCallOutputItem = (item) => {
 const isResponseInputImage = (content) => {
 	return typeof content === "object" && content !== null && "type" in content && content.type === "input_image";
 };
-const resolveResponsesCompactThreshold = (maxPromptTokens) => {
-	if (typeof maxPromptTokens === "number" && maxPromptTokens > 0) return Math.floor(maxPromptTokens * .9);
-	return 272e3 * .9;
+const resolveResponsesCompactThreshold = (maxPromptTokens, compactThresholdRatio = DEFAULT_RESPONSES_COMPACT_THRESHOLD_RATIO) => {
+	if (typeof maxPromptTokens === "number" && maxPromptTokens > 0) return Math.floor(maxPromptTokens * compactThresholdRatio);
+	return 2e5 * compactThresholdRatio;
 };
 const createCompactionContextManagement = (compactThreshold) => [{
 	type: "compaction",
 	compact_threshold: compactThreshold
 }];
-const applyResponsesApiContextManagement = (payload, maxPromptTokens) => {
+const applyResponsesApiContextManagement = (payload, maxPromptTokens, compactThresholdRatio = DEFAULT_RESPONSES_COMPACT_THRESHOLD_RATIO) => {
 	if (payload.context_management !== void 0) return;
 	if (!responsesUtilsDependencies.isResponsesApiContextManagementModel(payload.model)) return;
-	payload.context_management = createCompactionContextManagement(resolveResponsesCompactThreshold(maxPromptTokens));
+	payload.context_management = createCompactionContextManagement(resolveResponsesCompactThreshold(maxPromptTokens, compactThresholdRatio));
 };
 const compactInputByLatestCompaction = (payload) => {
 	if (!Array.isArray(payload.input) || payload.input.length === 0) return;
@@ -5020,7 +5024,7 @@ async function handleProviderResponsesForProvider(c, options) {
 		message: `Provider '${provider}' does not support the /v1/responses endpoint`,
 		type: "invalid_request_error"
 	} }, 400);
-	applyResponsesApiContextManagement(payload, (providerConfig.name === "codex" ? getModels().data.find((model) => model.id === payload.model) : void 0)?.capabilities.limits.max_prompt_tokens ?? 0);
+	applyResponsesApiContextManagement(payload, (providerConfig.name === "codex" ? getModels().data.find((model) => model.id === payload.model) : void 0)?.capabilities.limits.max_prompt_tokens ?? 0, .8);
 	const contextManagement = payload.context_management;
 	debugJson(logger$2, "Translated Responses request payload:", {
 		contextManagement,
@@ -5159,6 +5163,9 @@ const responsesHandlerDependencies = {
 };
 const handleResponses = async (c) => {
 	const payload = await c.req.json();
+	const requestedModel = payload.model;
+	payload.model = resolveMappedModel(payload.model);
+	if (payload.model !== requestedModel) logger$1.debug(`Resolved model mapping: ${requestedModel} -> ${payload.model}`);
 	const providerModelAlias = parseProviderModelAlias(payload.model);
 	if (providerModelAlias) {
 		payload.model = providerModelAlias.model;
@@ -5399,4 +5406,4 @@ server.route("/:provider/v1/models", providerModelRoutes);
 //#endregion
 export { server };
 
-//# sourceMappingURL=server-G5PWGqkb.js.map
+//# sourceMappingURL=server-BA2464Db.js.map