@jeffreycao/copilot-api 2.3.4 → 2.3.7

package/README.md

@@ -245,6 +245,7 @@ base_url = "http://localhost:4141"
 env_key = "GITHUB_COPILOT_API_KEY"
 requires_openai_auth = true
 supports_websockets = false
+supports_standalone_web_search = true
 wire_api = "responses"
 request_max_retries = 3
 stream_max_retries = 3
@@ -254,6 +255,7 @@ stream_idle_timeout_ms = 300000
 remote_compaction_v2 = true
 # optional: set false only when the model does not support tool_search
 apps = false
+standalone_web_search = true
 
 [analytics]
 enabled = false
@@ -263,6 +265,8 @@ enabled = false
 > `name` must be set to `"OpenAI"`.
 >
 > For third-party models that do not support `tool_search`, we recommend disabling features.apps. Otherwise, each prompt may consume an additional 20,000 or more tokens.
+>
+> `supports_standalone_web_search` and `[features] standalone_web_search` must both be enabled to expose the standalone `web.run` search tool.
 
 ### If Codex Is Not Signed In to a GPT Account
 
@@ -272,11 +276,15 @@ name = "OpenAI"
 base_url = "http://localhost:4141"
 requires_openai_auth = false
 supports_websockets = false
+supports_standalone_web_search = true
 wire_api = "responses"
 request_max_retries = 3
 stream_max_retries = 3
 stream_idle_timeout_ms = 300000
 
+[features]
+standalone_web_search = true
+
 [model_providers.copilot_api.auth]
 command = "powershell.exe"
 args = [
@@ -300,7 +308,7 @@ args = [
 
 Without this configuration, Codex cannot fetch `/v1/models` while not signed in to a GPT account, so custom models are unavailable in the model picker.
 
-When a Codex client (`User-Agent` starts with `codex`) requests the top-level `GET /v1/models`, the gateway merges native Codex models with models available through the Messages adapter. The latter advertise `use_responses_lite: true`: `/v1/responses` uses **Responses → Messages** for Anthropic providers, while OpenAI-compatible providers and Chat-only Copilot models reuse the existing Messages route for **Responses → Messages → Chat Completions**, then translate streaming or JSON results back to Responses.
+When a Codex client (`User-Agent` starts with `codex`) requests the top-level `GET /v1/models`, the gateway merges native Codex models with models available through the Messages adapter. The latter advertise `use_responses_lite: true`, except DeepSeek models, which use `use_responses_lite: false` and `tool_mode: null`. For other models, `/v1/responses` uses **Responses → Messages** for Anthropic providers, while OpenAI-compatible providers and Chat-only Copilot models reuse the existing Messages route for **Responses → Messages → Chat Completions**, then translate streaming or JSON results back to Responses.
 
 The merged catalog is what Codex shows in its model picker, including the models exposed by your configured providers:
 
@@ -694,7 +702,7 @@ Gateway API keys live under `auth.apiKeys` in `config.json`. Manage them with `c
 - **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 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 Responses API. Use this to inject guardrails or guidance per model. Missing default entries are auto-added without overwriting your custom prompts. For GPT-5.3+ models (e.g. `gpt-5.3-codex`, `gpt-5.4`, `gpt-5.5`), a built-in commentary prompt is used as fallback when not explicitly configured. The built-in prompts 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`, `/v1/responses`, and `/v1/chat/completions`; the gateway strips the `dashscope/` prefix before forwarding upstream. The `/v1/responses` route for `anthropic` and `openai-compatible` providers uses the Responses Lite → Messages adapter; `openai-compatible` providers then reuse the Messages → Chat translation. Codex clients (`User-Agent` starting with `codex`) also use the adapter for non-`gpt-*` models on `openai-responses` providers. `GET /v1/models` aggregates enabled provider models with `provider/model-id` IDs, while the top-level Codex-UA catalog also merges these adaptable models as `use_responses_lite` entries. Use `GET /dashscope/v1/models` for a single provider's raw model list.
+- **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`, `/v1/responses`, and `/v1/chat/completions`; the gateway strips the `dashscope/` prefix before forwarding upstream. The `/v1/responses` route for `anthropic` and `openai-compatible` providers uses the Responses Lite → Messages adapter; `openai-compatible` providers then reuse the Messages → Chat translation. Codex clients (`User-Agent` starting with `codex`) also use the adapter for non-`gpt-*` models on `openai-responses` providers. `GET /v1/models` aggregates enabled provider models with `provider/model-id` IDs, while the top-level Codex-UA catalog also merges these adaptable models as `use_responses_lite` entries (except DeepSeek models, which use `use_responses_lite: false` and `tool_mode: null`). Use `GET /dashscope/v1/models` for a single provider's raw model list.
   - `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`; for OpenAI Responses providers, omit `/v1/responses`.
   - `apiKey` is used as the upstream credential value and is required for regular providers.

package/README.zh-CN.md

@@ -261,6 +261,7 @@ base_url = "http://localhost:4141"
 env_key = "GITHUB_COPILOT_API_KEY"
 requires_openai_auth = true
 supports_websockets = false
+supports_standalone_web_search = true
 wire_api = "responses"
 request_max_retries = 3
 stream_max_retries = 3
@@ -270,6 +271,7 @@ stream_idle_timeout_ms = 300000
 remote_compaction_v2 = true
 # optional: set false only when the model does not support tool_search
 apps = false
+standalone_web_search = true
 
 [analytics]
 enabled = false
@@ -279,6 +281,8 @@ enabled = false
 > `name` 一定要配置为 `"OpenAI"`。
 >
 > 对于不支持 `tool_search` 的第三方模型，我们建议禁用 features.apps。否则，每个提示可能会额外消耗 20,000 多个 token。
+>
+> 必须同时启用 `supports_standalone_web_search` 和 `[features] standalone_web_search`，Codex 才会暴露独立的 `web.run` 搜索工具。
 
 ### Codex 未登录 GPT 账号时
 
@@ -288,11 +292,15 @@ name = "OpenAI"
 base_url = "http://localhost:4141"
 requires_openai_auth = false
 supports_websockets = false
+supports_standalone_web_search = true
 wire_api = "responses"
 request_max_retries = 3
 stream_max_retries = 3
 stream_idle_timeout_ms = 300000
 
+[features]
+standalone_web_search = true
+
 [model_providers.copilot_api.auth]
 command = "powershell.exe"
 args = [
@@ -316,7 +324,7 @@ args = [
 
 未按上述方式配置时，Codex 未登录 GPT 账号拉不到 `/v1/models`，无法选择自定义模型。
 
-Codex 客户端（`User-Agent` 以 `codex` 开头）请求顶层 `GET /v1/models` 时，网关会把原生 Codex 模型与可通过 Messages 适配的模型合并返回。后者会声明 `use_responses_lite: true`：调用 `/v1/responses` 后，Anthropic provider 走 **Responses → Messages**，OpenAI 兼容 provider 以及只支持 Chat 的 Copilot 模型则复用现有 Messages 路由继续走 **Responses → Messages → Chat Completions**，最终统一翻译回 Responses（包括流式事件）。
+Codex 客户端（`User-Agent` 以 `codex` 开头）请求顶层 `GET /v1/models` 时，网关会把原生 Codex 模型与可通过 Messages 适配的模型合并返回。除 DeepSeek 模型外，后者会声明 `use_responses_lite: true`；DeepSeek 模型使用 `use_responses_lite: false` 和 `tool_mode: null`。调用 `/v1/responses` 后，Anthropic provider 走 **Responses → Messages**，OpenAI 兼容 provider 以及只支持 Chat 的 Copilot 模型则复用现有 Messages 路由继续走 **Responses → Messages → Chat Completions**，最终统一翻译回 Responses（包括流式事件）。
 
 合并后的模型列表会直接展示在 Codex 的模型选择界面中，包含各 provider 暴露的模型：
 
@@ -738,7 +746,7 @@ Copilot API 现在使用子命令结构，主要命令包括：
 - **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`、`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 风格请求翻译为 Responses API 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。对于 GPT-5.3+ 模型（如 `gpt-5.3-codex`、`gpt-5.4`、`gpt-5.5`），未显式配置时会自动使用内置的 commentary prompt。内置 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`、`/v1/responses` 和 `/v1/chat/completions` 中使用 `model: "dashscope/model-id"`；AI gateway 会在转发上游前移除 `dashscope/` 前缀。`anthropic` 和 `openai-compatible` provider 的 `/v1/responses` 会通过 Responses Lite → Messages 适配；其中 `openai-compatible` provider 再复用 Messages → Chat 翻译。Codex 客户端（`User-Agent` 以 `codex` 开头）在 `openai-responses` provider 上请求非 `gpt-*` 模型时同样走该适配路径。`GET /v1/models` 会聚合已启用 provider 的模型，并以 `provider/model-id` 形式返回；Codex UA 的顶层模型列表还会把这些可适配模型合并为 `use_responses_lite` 模型。单个 provider 的原始模型列表仍可使用 `GET /dashscope/v1/models`。
+- **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`、`/v1/responses` 和 `/v1/chat/completions` 中使用 `model: "dashscope/model-id"`；AI gateway 会在转发上游前移除 `dashscope/` 前缀。`anthropic` 和 `openai-compatible` provider 的 `/v1/responses` 会通过 Responses Lite → Messages 适配；其中 `openai-compatible` provider 再复用 Messages → Chat 翻译。Codex 客户端（`User-Agent` 以 `codex` 开头）在 `openai-responses` provider 上请求非 `gpt-*` 模型时同样走该适配路径。`GET /v1/models` 会聚合已启用 provider 的模型，并以 `provider/model-id` 形式返回；Codex UA 的顶层模型列表还会把这些可适配模型合并为 `use_responses_lite` 模型（DeepSeek 模型除外，它们使用 `use_responses_lite: false` 和 `tool_mode: null`）。单个 provider 的原始模型列表仍可使用 `GET /dashscope/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`；OpenAI Responses provider 不要带 `/v1/responses`。
   - `apiKey`：作为上游凭据值使用；普通 provider 必须配置。

package/dist/main.js

@@ -30,7 +30,7 @@ if (isMcpFastPath(process.argv)) {
 	const { auth } = await import("./auth-B-ry4rJx.js");
 	const { debug } = await import("./debug-Db0SCVSP.js");
 	const { mcp } = await import("./mcp-fpSlKZxK.js");
-	const { start } = await import("./start-DqfeTNPH.js");
+	const { start } = await import("./start-Cfg3jwGS.js");
 	await runMain(defineCommand({
 		meta: {
 			name: "copilot-api",

package/dist/{server-CKVtJPpg.js → server-DR94qLzm.js}

@@ -8011,6 +8011,12 @@ After deleting anything material, briefly tell the user what was removed and whe
 function isCodexUserAgent(userAgent) {
 	return CODEX_USER_AGENT_PATTERN.test(userAgent?.trim() ?? "");
 }
+function isDeepSeekModelId(modelId) {
+	return modelId.toLowerCase().includes("deepseek");
+}
+function shouldInjectMessagesToolCallTips(userAgent, targetModel) {
+	return isCodexUserAgent(userAgent) && !isDeepSeekModelId(targetModel);
+}
 async function logCodexModelsResponse(response) {
 	try {
 		const models = await response.clone().json();
@@ -8099,6 +8105,7 @@ function createSyntheticCodexModel(candidate, template, priority) {
 	const defaultReasoningEffort = reasoningEfforts.includes(candidate.defaultReasoningEffort) ? candidate.defaultReasoningEffort : reasoningEfforts[0];
 	const supportsReasoning = reasoningEfforts.some((effort) => effort !== "none");
 	const inputModalities = [...new Set(candidate.inputModalities)];
+	const isDeepSeekModel = isDeepSeekModelId(candidate.slug);
 	return {
 		...template,
 		slug: candidate.slug,
@@ -8114,8 +8121,8 @@ function createSyntheticCodexModel(candidate, template, priority) {
 		apply_patch_tool_type: "freeform",
 		web_search_tool_type: "text_and_image",
 		supports_search_tool: false,
-		use_responses_lite: true,
-		tool_mode: "code_mode_only",
+		use_responses_lite: isDeepSeekModel ? false : true,
+		tool_mode: isDeepSeekModel ? null : "code_mode_only",
 		multi_agent_version: "v2",
 		shell_type: "shell_command",
 		experimental_supported_tools: [],
@@ -10144,7 +10151,7 @@ async function handleResponsesViaMessages(c, options) {
 		}, {
 			model: options.targetModel,
 			publicModel: options.publicModel,
-			toolCallTips: isCodexUserAgent(c.req.header("user-agent"))
+			toolCallTips: shouldInjectMessagesToolCallTips(c.req.header("user-agent"), options.targetModel)
 		});
 		const context = translation;
 		debugJson(logger$3, "Translated Messages request:", {
@@ -10709,4 +10716,4 @@ server.route("/:provider/images", providerImageRoutes);
 //#endregion
 export { server };
 
-//# sourceMappingURL=server-CKVtJPpg.js.map
+//# sourceMappingURL=server-DR94qLzm.js.map