Merge czy-all into dev

Author: cuipengfei

.github/workflows/ci.yml

@@ -24,7 +24,7 @@ jobs:
           bun-version: latest
 
       - name: Install dependencies
-        run: bun install
+        run: bun install --frozen-lockfile
 
       - name: Run linter
         run: bun run lint:all

.github/workflows/release-desktop.yml

@@ -21,7 +21,7 @@ jobs:
           bun-version: latest
 
       - name: Install root dependencies
-        run: bun install
+        run: bun install --frozen-lockfile
 
       - name: Build server
         run: bun run build
@@ -32,7 +32,7 @@ jobs:
 
       - name: Install desktop dependencies
         working-directory: desktop
-        run: npm install
+        run: npm ci
 
       - name: Build macOS arm64 package
         working-directory: desktop
@@ -58,7 +58,7 @@ jobs:
           bun-version: latest
 
       - name: Install root dependencies
-        run: bun install
+        run: bun install --frozen-lockfile
 
       - name: Build server
         run: bun run build
@@ -69,7 +69,7 @@ jobs:
 
       - name: Install desktop dependencies
         working-directory: desktop
-        run: npm install
+        run: npm ci
 
       - name: Build Windows package
         working-directory: desktop

.github/workflows/release.yml

@@ -22,7 +22,7 @@ jobs:
           bun-version: latest
 
       - name: Install dependencies
-        run: bun install
+        run: bun install --frozen-lockfile
 
       - name: Run linter
         run: bun run lint:all

README.md

@@ -62,7 +62,7 @@ Compared with routing everything through plain Chat Completions compatibility, t
 - **Opencode OAuth Support**: Use opencode GitHub Copilot authentication by setting `COPILOT_API_OAUTH_APP=opencode` environment variable or using `--oauth-app=opencode` command line option.
 - **GitHub Enterprise Support**: Connect to GHE.com by setting `COPILOT_API_ENTERPRISE_URL` environment variable (e.g., `company.ghe.com`) or using `--enterprise-url=company.ghe.com` command line option.
 - **Custom Data Directory**: Change the default data directory (where tokens and config are stored) by setting `COPILOT_API_HOME` environment variable or using `--api-home=/path/to/dir` command line option.
-- **Multi-Provider Messages Proxy Routes**: Add global provider configs and call external Anthropic-compatible or OpenAI-compatible APIs via `/:provider/v1/messages` and `/:provider/v1/models`.
+- **Multi-Provider Messages Proxy Routes**: Add global provider configs and call external Anthropic-compatible or OpenAI-compatible APIs via `/:provider/v1/messages` and `/:provider/v1/models`, or send `model: "provider/model"` to the top-level `/v1/messages` API.
 - **Accurate Claude Token Counting**: Optionally forward `/v1/messages/count_tokens` requests for Claude models to Anthropic's free token counting endpoint for exact counts instead of GPT tokenizer estimation.
 - **GPT Context Management**: Configurable context compaction for long-running GPT conversations via `responsesApiContextManagementModels`, reducing unnecessary premium requests when approaching token limits. See [Configuration](#configuration-configjson) for details.
 
@@ -357,7 +357,7 @@ The following command line options are available for the `start` command:
   ```
 - **auth.apiKeys:** API keys used for request authentication. Supports multiple keys for rotation. Requests can authenticate with either `x-api-key: <key>` or `Authorization: Bearer <key>`. If empty or omitted, authentication is disabled.
 - **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 `custom`) becomes a route prefix (`/custom/v1/messages`). Supports `type: "anthropic"` and `type: "openai-compatible"`.
+- **providers:** Global upstream provider map. Each provider key (for example `custom`) becomes a route prefix (`/custom/v1/messages`). Supports `type: "anthropic"` and `type: "openai-compatible"`. Top-level Anthropic clients can also use `model: "custom/model-id"` with `/v1/messages` and `/v1/messages/count_tokens`; the proxy strips the `custom/` prefix before forwarding upstream. `GET /v1/models` does not aggregate provider models; use `GET /custom/v1/models` for provider model lists.
   - `enabled` defaults to `true` if omitted.
   - `baseUrl` should be provider API base URL without the final endpoint. For Anthropic providers, omit `/v1/messages`; for OpenAI-compatible providers, omit `/v1/chat/completions`.
   - `apiKey` is used as the upstream credential value.
@@ -419,8 +419,8 @@ These endpoints are designed to be compatible with the Anthropic Messages API.
 
 | Endpoint                         | Method | Description                                                  |
 | -------------------------------- | ------ | ------------------------------------------------------------ |
-| `POST /v1/messages`              | `POST` | Creates a model response for a given conversation.           |
-| `POST /v1/messages/count_tokens` | `POST` | Calculates the number of tokens for a given set of messages. |
+| `POST /v1/messages`              | `POST` | Creates a model response for a given conversation. Supports `provider/model` aliases for configured providers. |
+| `POST /v1/messages/count_tokens` | `POST` | Calculates the number of tokens for a given set of messages. Supports `provider/model` aliases for configured providers. |
 | `POST /:provider/v1/messages`       | `POST` | Proxies Anthropic Messages requests to the configured Anthropic or OpenAI-compatible provider. |
 | `GET /:provider/v1/models`          | `GET`  | Proxies model listing requests to the configured provider.   |
 | `POST /:provider/v1/messages/count_tokens` | `POST` | Calculates tokens locally for provider route requests. |

README.zh-CN.md

@@ -62,7 +62,7 @@
 - **支持 opencode OAuth**：可通过设置环境变量 `COPILOT_API_OAUTH_APP=opencode` 或使用命令行参数 `--oauth-app=opencode` 来启用 opencode GitHub Copilot 认证。
 - **支持 GitHub Enterprise**：可通过设置环境变量 `COPILOT_API_ENTERPRISE_URL`（例如 `company.ghe.com`）或命令行参数 `--enterprise-url=company.ghe.com` 连接到 GHE.com。
 - **自定义数据目录**：可通过环境变量 `COPILOT_API_HOME` 或命令行参数 `--api-home=/path/to/dir` 修改默认数据目录（存放 token 和配置）。
-- **多 Provider Messages 代理路由**：可以添加全局 provider 配置，并通过 `/:provider/v1/messages` 与 `/:provider/v1/models` 调用外部 Anthropic 或 OpenAI 兼容 API。
+- **多 Provider Messages 代理路由**：可以添加全局 provider 配置，并通过 `/:provider/v1/messages` 与 `/:provider/v1/models` 调用外部 Anthropic 或 OpenAI 兼容 API，也可以把 `model` 写成 `"provider/model"` 后直接发到顶层 `/v1/messages`。
 - **精确的 Claude Token 计数**：可以选择将 Claude 模型的 `/v1/messages/count_tokens` 请求转发到 Anthropic 的免费 token counting 端点，以获得精确计数，而不是依赖 GPT tokenizer 估算。
 - **GPT 上下文管理**：可通过 `responsesApiContextManagementModels` 为长上下文 GPT 对话启用可配置的上下文压缩，在接近 token 限制时减少不必要的 Premium 请求。详见 [配置](#configuration-configjson)。
 
@@ -361,7 +361,7 @@ Copilot API 现在使用子命令结构，主要命令包括：
   ```
 - **auth.apiKeys：** 用于请求认证的 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，则禁用认证。
 - **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 `custom`）都会变成一个路由前缀（`/custom/v1/messages`）。支持 `type: "anthropic"` 和 `type: "openai-compatible"`。
+- **providers：** 全局上游 provider 映射。每个 provider key（例如 `custom`）都会变成一个路由前缀（`/custom/v1/messages`）。支持 `type: "anthropic"` 和 `type: "openai-compatible"`。顶层 Anthropic 客户端也可以在 `/v1/messages` 和 `/v1/messages/count_tokens` 中使用 `model: "custom/model-id"`；代理会在转发上游前移除 `custom/` 前缀。`GET /v1/models` 不聚合 provider 模型；provider 模型列表请使用 `GET /custom/v1/models`。
   - `enabled`：可选，若省略则默认为 `true`。
   - `baseUrl`：provider API 的基础 URL，不要带结尾的 endpoint。Anthropic provider 不要带 `/v1/messages`；OpenAI 兼容 provider 不要带 `/v1/chat/completions`。
   - `apiKey`：作为上游凭据值使用。
@@ -423,8 +423,8 @@ curl http://localhost:4141/v1/models \
 
 | 端点 | 方法 | 说明 |
 | --- | --- | --- |
-| `POST /v1/messages` | `POST` | 为给定对话创建模型响应。 |
-| `POST /v1/messages/count_tokens` | `POST` | 计算一组消息的 token 数。 |
+| `POST /v1/messages` | `POST` | 为给定对话创建模型响应。支持已配置 provider 的 `provider/model` 别名。 |
+| `POST /v1/messages/count_tokens` | `POST` | 计算一组消息的 token 数。支持已配置 provider 的 `provider/model` 别名。 |
 | `POST /:provider/v1/messages` | `POST` | 将 Anthropic Messages 请求代理到已配置的 Anthropic 或 OpenAI 兼容 provider。 |
 | `GET /:provider/v1/models` | `GET` | 将模型列表请求代理到已配置的 provider。 |
 | `POST /:provider/v1/messages/count_tokens` | `POST` | 为 provider 路由请求在本地计算 token 数。 |