copilot-api-plus 1.0.40 → 1.0.42

package/README.md

@@ -1,7 +1,5 @@
 # Copilot API Plus
 
-> **Fork of [ericc-ch/copilot-api](https://github.com/ericc-ch/copilot-api)** with bug fixes and improvements.
-
 将 GitHub Copilot、OpenCode Zen、Google Antigravity 等 AI 服务转换为 **OpenAI** 和 **Anthropic** 兼容 API，支持与 [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview)、[opencode](https://github.com/sst/opencode) 等工具无缝集成。
 
 ---
@@ -18,7 +16,9 @@
 - [Claude Code 集成](#-claude-code-集成)
 - [opencode 集成](#-opencode-集成)
 - [API 端点](#-api-端点)
-- [命令行参考](#-命令行参考)
+- [API Key 认证](#-api-key-认证)
+- [技术细节](#-技术细节)
+- [命令行参考](#️-命令行参考)
 - [Docker 部署](#-docker-部署)
 - [常见问题](#-常见问题)
 
@@ -36,6 +36,10 @@
 | ⚡ **速率限制** | 内置请求频率控制，避免触发限制 |
 | 🌐 **代理支持** | 支持 HTTP/HTTPS 代理，配置持久化 |
 | 🐳 **Docker 支持** | 提供完整的 Docker 部署方案 |
+| 🔑 **API Key 认证** | 可选的 API Key 鉴权，保护公开部署的服务 |
+| ✂️ **智能上下文压缩** | Prompt 超过模型 Token 限制时自动截断，保留系统消息和最近对话 |
+| 🔍 **智能模型匹配** | 自动处理模型名格式差异（日期后缀、dash/dot 版本号等） |
+| 🔁 **Antigravity 端点容错** | 双端点自动切换，按模型族追踪速率限制，指数退避重试 |
 
 ---
 
@@ -558,6 +562,7 @@ curl http://localhost:4141/v1/messages \
 | `--github-token` | `-g` | - | 直接提供 GitHub Token |
 | `--show-token` | - | false | 显示 Token 信息 |
 | `--proxy-env` | - | false | 从环境变量读取代理 |
+| `--api-key` | - | - | API Key 鉴权（可多次指定） |
 
 ### proxy 命令参数
 
@@ -604,6 +609,72 @@ npx copilot-api-plus@latest antigravity clear    # 清除所有账户
 
 ---
 
+## 🔑 API Key 认证
+
+如果你将服务暴露到公网，可以启用 API Key 认证来保护接口：
+
+```bash
+# 单个 Key
+npx copilot-api-plus@latest start --api-key my-secret-key
+
+# 多个 Key
+npx copilot-api-plus@latest start --api-key key1 --api-key key2
+```
+
+启用后，所有请求需要携带 API Key：
+
+```bash
+# OpenAI 格式 - 通过 Authorization header
+curl http://localhost:4141/v1/chat/completions \
+  -H "Authorization: Bearer my-secret-key" \
+  -H "Content-Type: application/json" \
+  -d '{"model": "claude-sonnet-4", "messages": [{"role": "user", "content": "Hello"}]}'
+
+# Anthropic 格式 - 通过 x-api-key header
+curl http://localhost:4141/v1/messages \
+  -H "x-api-key: my-secret-key" \
+  -H "Content-Type: application/json" \
+  -d '{"model": "claude-sonnet-4", "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello"}]}'
+```
+
+在 Claude Code 中使用时，将 `ANTHROPIC_AUTH_TOKEN` 设为你的 API Key 即可。
+
+---
+
+## 🔧 技术细节
+
+### 智能上下文压缩
+
+当 Prompt Token 数量超过模型的上下文窗口限制时，代理层会自动截断消息以避免上游 API 返回 400 错误：
+
+- **保留系统/开发者消息**：system 和 developer 角色的消息始终保留
+- **保留最近对话**：优先丢弃最早的消息，保留最近的上下文
+- **工具调用分组**：assistant 的 tool_calls 和对应的 tool result 消息作为一组，不会被拆散
+- **5% 安全余量**：实际限制为模型上下文窗口的 95%，避免边界情况
+
+### 智能模型名匹配
+
+Anthropic 格式的模型名（如 `claude-opus-4-6`）和 Copilot 的模型列表 ID 可能存在格式差异。代理使用多策略精确匹配：
+
+| 策略 | 示例 |
+|------|------|
+| 精确匹配 | `claude-opus-4-6` → `claude-opus-4-6` |
+| 去日期后缀 | `claude-opus-4-6-20251101` → `claude-opus-4-6` |
+| Dash → Dot | `claude-opus-4-5` → `claude-opus-4.5` |
+| Dot → Dash | `claude-opus-4.5` → `claude-opus-4-5` |
+
+对于 Anthropic 端点（`/v1/messages`），还会先通过 `translateModelName` 做格式转换（包括旧格式 `claude-3-5-sonnet` → `claude-sonnet-4.5` 的映射），再通过上述策略匹配。
+
+### Antigravity 端点容错
+
+Google Antigravity 模式内置了可靠性保障：
+
+- **双端点自动切换**：daily sandbox 和 production 两个端点，一个失败自动切换到另一个
+- **按模型族速率追踪**：分别追踪 Gemini 和 Claude 模型族的速率限制状态
+- **指数退避重试**：429/503 等限流错误自动退避重试，短间隔走同端点，长间隔切换端点
+
+---
+
 ## 🐳 Docker 部署
 
 ### 快速启动

package/dist/{auth-T55-Bhoo.js → auth-BrdL89xk.js}

@@ -15,7 +15,7 @@ function getZenAuthPath() {
 async function saveZenAuth(auth) {
 	await ensurePaths();
 	const authPath = getZenAuthPath();
-	await (await import("node:fs/promises")).writeFile(authPath, JSON.stringify(auth, null, 2), "utf-8");
+	await (await import("node:fs/promises")).writeFile(authPath, JSON.stringify(auth, null, 2), "utf8");
 	consola.success("Zen API key saved to", authPath);
 }
 /**
@@ -30,7 +30,7 @@ async function loadZenAuth() {
 		} catch {
 			return null;
 		}
-		const content = await fs.readFile(authPath, "utf-8");
+		const content = await fs.readFile(authPath);
 		return JSON.parse(content);
 	} catch {
 		return null;
@@ -74,4 +74,4 @@ async function setupZenApiKey(force = false) {
 
 //#endregion
 export { clearZenAuth, getZenAuthPath, loadZenAuth, saveZenAuth, setupZenApiKey };
-//# sourceMappingURL=auth-T55-Bhoo.js.map
+//# sourceMappingURL=auth-BrdL89xk.js.map

package/dist/auth-BrdL89xk.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"auth-BrdL89xk.js","names":[],"sources":["../src/services/zen/auth.ts"],"sourcesContent":["/**\n * OpenCode Zen Authentication\n *\n * Handles API key authentication for OpenCode Zen.\n * API keys are created at https://opencode.ai/zen\n */\n\nimport consola from \"consola\"\n\nimport { PATHS, ensurePaths } from \"~/lib/paths\"\n\nexport interface ZenAuth {\n  apiKey: string\n}\n\nconst ZEN_AUTH_FILENAME = \"zen-auth.json\"\n\n/**\n * Get the path to the Zen auth file\n */\nexport function getZenAuthPath(): string {\n  return `${PATHS.DATA_DIR}/${ZEN_AUTH_FILENAME}`\n}\n\n/**\n * Save Zen API key to file\n */\nexport async function saveZenAuth(auth: ZenAuth): Promise<void> {\n  await ensurePaths()\n  const authPath = getZenAuthPath()\n  const fs = await import(\"node:fs/promises\")\n  await fs.writeFile(authPath, JSON.stringify(auth, null, 2), \"utf8\")\n  consola.success(\"Zen API key saved to\", authPath)\n}\n\n/**\n * Load Zen API key from file\n */\nexport async function loadZenAuth(): Promise<ZenAuth | null> {\n  try {\n    const authPath = getZenAuthPath()\n    const fs = await import(\"node:fs/promises\")\n\n    // Check if file exists\n    try {\n      await fs.access(authPath)\n    } catch {\n      return null\n    }\n\n    const content = await fs.readFile(authPath)\n    return JSON.parse(content) as ZenAuth\n  } catch {\n    return null\n  }\n}\n\n/**\n * Clear Zen API key\n */\nexport async function clearZenAuth(): Promise<void> {\n  try {\n    const authPath = getZenAuthPath()\n    const fs = await import(\"node:fs/promises\")\n    await fs.unlink(authPath)\n    consola.success(\"Zen API key cleared\")\n  } catch {\n    // File might not exist, ignore\n  }\n}\n\n/**\n * Setup Zen API key interactively\n */\nexport async function setupZenApiKey(force = false): Promise<string> {\n  const existingAuth = await loadZenAuth()\n\n  if (existingAuth && !force) {\n    consola.info(\"Using existing Zen API key\")\n    return existingAuth.apiKey\n  }\n\n  consola.info(\"OpenCode Zen gives you access to all the best coding models\")\n  consola.info(\"Get your API key at: https://opencode.ai/zen\")\n  consola.info(\"\")\n\n  const apiKey = await consola.prompt(\"Enter your OpenCode Zen API key:\", {\n    type: \"text\",\n  })\n\n  if (!apiKey || typeof apiKey !== \"string\") {\n    throw new Error(\"API key is required\")\n  }\n\n  // Validate the API key by fetching models\n  try {\n    const response = await fetch(\"https://opencode.ai/zen/v1/models\", {\n      headers: {\n        Authorization: `Bearer ${apiKey}`,\n      },\n    })\n\n    if (!response.ok) {\n      throw new Error(\n        `Invalid API key: ${response.status} ${response.statusText}`,\n      )\n    }\n\n    consola.success(\"API key validated successfully\")\n  } catch (error) {\n    consola.error(\"Failed to validate API key:\", error)\n    throw error\n  }\n\n  await saveZenAuth({ apiKey })\n  return apiKey\n}\n"],"mappings":";;;;AAeA,MAAM,oBAAoB;;;;AAK1B,SAAgB,iBAAyB;AACvC,QAAO,GAAG,MAAM,SAAS,GAAG;;;;;AAM9B,eAAsB,YAAY,MAA8B;AAC9D,OAAM,aAAa;CACnB,MAAM,WAAW,gBAAgB;AAEjC,QADW,MAAM,OAAO,qBACf,UAAU,UAAU,KAAK,UAAU,MAAM,MAAM,EAAE,EAAE,OAAO;AACnE,SAAQ,QAAQ,wBAAwB,SAAS;;;;;AAMnD,eAAsB,cAAuC;AAC3D,KAAI;EACF,MAAM,WAAW,gBAAgB;EACjC,MAAM,KAAK,MAAM,OAAO;AAGxB,MAAI;AACF,SAAM,GAAG,OAAO,SAAS;UACnB;AACN,UAAO;;EAGT,MAAM,UAAU,MAAM,GAAG,SAAS,SAAS;AAC3C,SAAO,KAAK,MAAM,QAAQ;SACpB;AACN,SAAO;;;;;;AAOX,eAAsB,eAA8B;AAClD,KAAI;EACF,MAAM,WAAW,gBAAgB;AAEjC,SADW,MAAM,OAAO,qBACf,OAAO,SAAS;AACzB,UAAQ,QAAQ,sBAAsB;SAChC;;;;;AAQV,eAAsB,eAAe,QAAQ,OAAwB;CACnE,MAAM,eAAe,MAAM,aAAa;AAExC,KAAI,gBAAgB,CAAC,OAAO;AAC1B,UAAQ,KAAK,6BAA6B;AAC1C,SAAO,aAAa;;AAGtB,SAAQ,KAAK,8DAA8D;AAC3E,SAAQ,KAAK,+CAA+C;AAC5D,SAAQ,KAAK,GAAG;CAEhB,MAAM,SAAS,MAAM,QAAQ,OAAO,oCAAoC,EACtE,MAAM,QACP,CAAC;AAEF,KAAI,CAAC,UAAU,OAAO,WAAW,SAC/B,OAAM,IAAI,MAAM,sBAAsB;AAIxC,KAAI;EACF,MAAM,WAAW,MAAM,MAAM,qCAAqC,EAChE,SAAS,EACP,eAAe,UAAU,UAC1B,EACF,CAAC;AAEF,MAAI,CAAC,SAAS,GACZ,OAAM,IAAI,MACR,oBAAoB,SAAS,OAAO,GAAG,SAAS,aACjD;AAGH,UAAQ,QAAQ,iCAAiC;UAC1C,OAAO;AACd,UAAQ,MAAM,+BAA+B,MAAM;AACnD,QAAM;;AAGR,OAAM,YAAY,EAAE,QAAQ,CAAC;AAC7B,QAAO"}

package/dist/{auth-CCwbOOQN.js → auth-pRwfByMF.js}

@@ -1,4 +1,4 @@
 import "./paths-CVYLp61D.js";
-import { clearZenAuth, getZenAuthPath, loadZenAuth, saveZenAuth, setupZenApiKey } from "./auth-T55-Bhoo.js";
+import { clearZenAuth, getZenAuthPath, loadZenAuth, saveZenAuth, setupZenApiKey } from "./auth-BrdL89xk.js";
 
 export { loadZenAuth, setupZenApiKey };

package/dist/main.js

@@ -3,9 +3,9 @@ import { PATHS, ensurePaths } from "./paths-CVYLp61D.js";
 import { state } from "./state-CcLGr8VN.js";
 import { GITHUB_API_BASE_URL, copilotBaseUrl, copilotHeaders, githubHeaders } from "./get-user-BzIEATcF.js";
 import { HTTPError, forwardError } from "./error-CvU5otz-.js";
-import { cacheModels, cacheVSCodeVersion, clearGithubToken, isNullish, setupCopilotToken, setupGitHubToken, sleep } from "./token-ClgudjZm.js";
+import { cacheModels, cacheVSCodeVersion, clearGithubToken, findModel, isNullish, setupCopilotToken, setupGitHubToken, sleep } from "./token-B777vbx8.js";
 import { clearAntigravityAuth, disableCurrentAccount, getAntigravityAuthPath, getApiKey, getCurrentProjectId, getValidAccessToken, rotateAccount } from "./auth-CWGl6kMf.js";
-import { clearZenAuth, getZenAuthPath } from "./auth-T55-Bhoo.js";
+import { clearZenAuth, getZenAuthPath } from "./auth-BrdL89xk.js";
 import { getAntigravityModels, getAntigravityUsage, isThinkingModel } from "./get-models-uEbEgq0L.js";
 import { createRequire } from "node:module";
 import { defineCommand, runMain } from "citty";
@@ -1194,6 +1194,15 @@ const apiKeyAuthMiddleware = async (c, next) => {
 //#endregion
 //#region src/lib/model-logger.ts
 /**
+* Global token usage store for passing usage info from handlers to logger.
+* Handlers call setTokenUsage() when usage is available,
+* logger reads and clears it after await next().
+*/
+let pendingTokenUsage;
+function setTokenUsage(usage) {
+	pendingTokenUsage = usage;
+}
+/**
 * Get timestamp string in format HH:mm:ss
 */
 function getTime() {
@@ -1207,6 +1216,15 @@ function formatDuration(ms) {
 	return `${(ms / 1e3).toFixed(1)}s`;
 }
 /**
+* Format token usage for log output
+*/
+function formatTokenUsage(usage) {
+	const parts = [`in:${usage.inputTokens}`, `out:${usage.outputTokens}`];
+	if (usage.cacheReadTokens) parts.push(`cache_read:${usage.cacheReadTokens}`);
+	if (usage.cacheCreationTokens) parts.push(`cache_create:${usage.cacheCreationTokens}`);
+	return parts.join(" ");
+}
+/**
 * Extract model name from request body
 */
 async function extractModel(c) {
@@ -1221,7 +1239,7 @@ async function extractModel(c) {
 *
 * Output format:
 * [model] HH:mm:ss <-- METHOD /path
-* [model] HH:mm:ss --> METHOD /path STATUS DURATION
+* [model] HH:mm:ss --> METHOD /path STATUS DURATION [in:N out:N]
 */
 function modelLogger() {
 	return async (c, next) => {
@@ -1233,12 +1251,16 @@ function modelLogger() {
 		if (method === "POST" && c.req.header("content-type")?.includes("json")) model = await extractModel(c);
 		const modelPrefix = model ? `[${model}] ` : "";
 		const startTime = getTime();
+		pendingTokenUsage = void 0;
 		console.log(`${modelPrefix}${startTime} <-- ${method} ${fullPath}`);
 		const start$1 = Date.now();
 		await next();
 		const duration = Date.now() - start$1;
 		const endTime = getTime();
-		console.log(`${modelPrefix}${endTime} --> ${method} ${fullPath} ${c.res.status} ${formatDuration(duration)}`);
+		const usage = pendingTokenUsage;
+		pendingTokenUsage = void 0;
+		const usageSuffix = usage ? ` [${formatTokenUsage(usage)}]` : "";
+		console.log(`${modelPrefix}${endTime} --> ${method} ${fullPath} ${c.res.status} ${formatDuration(duration)}${usageSuffix}`);
 	};
 }
 
@@ -2957,9 +2979,12 @@ const createChatCompletions = async (payload) => {
 //#region src/routes/chat-completions/handler.ts
 /**
 * Calculate token count, log it, and auto-truncate if needed.
+*
+* Uses multi-strategy exact matching via findModel() to handle
+* mismatches between requested and available model names.
 */
 async function processPayloadTokens(payload) {
-	const selectedModel = state.models?.data.find((model) => model.id === payload.model);
+	const selectedModel = findModel(payload.model);
 	if (!selectedModel) {
 		consola.warn("No model selected, skipping token count calculation");
 		return payload;
@@ -2991,12 +3016,28 @@ async function handleCompletion$1(c) {
 	const response = await createChatCompletions(payload);
 	if (isNonStreaming$1(response)) {
 		consola.debug("Non-streaming response:", JSON.stringify(response));
+		if (response.usage) setTokenUsage({
+			inputTokens: response.usage.prompt_tokens,
+			outputTokens: response.usage.completion_tokens,
+			cacheReadTokens: response.usage.prompt_tokens_details?.cached_tokens
+		});
 		return c.json(response);
 	}
 	consola.debug("Streaming response");
 	return streamSSE(c, async (stream) => {
 		for await (const chunk of response) {
 			consola.debug("Streaming chunk:", JSON.stringify(chunk));
+			try {
+				const sseChunk = chunk;
+				if (sseChunk.data && sseChunk.data !== "[DONE]") {
+					const parsed = JSON.parse(sseChunk.data);
+					if (parsed.usage) setTokenUsage({
+						inputTokens: parsed.usage.prompt_tokens ?? 0,
+						outputTokens: parsed.usage.completion_tokens ?? 0,
+						cacheReadTokens: parsed.usage.prompt_tokens_details?.cached_tokens
+					});
+				}
+			} catch {}
 			await stream.writeSSE(chunk);
 		}
 	});
@@ -3085,14 +3126,6 @@ function translateModelName(model) {
 		"claude-3-5-haiku": "claude-haiku-4.5",
 		"claude-3-haiku": "claude-haiku-4.5"
 	})) if (modelBase.startsWith(oldFormat) && supportedModels.includes(newFormat)) return newFormat;
-	let modelFamily = null;
-	if (model.includes("opus")) modelFamily = "opus";
-	else if (model.includes("sonnet")) modelFamily = "sonnet";
-	else if (model.includes("haiku")) modelFamily = "haiku";
-	if (modelFamily) {
-		const familyModel = supportedModels.find((m) => m.includes(modelFamily));
-		if (familyModel) return familyModel;
-	}
 	return model;
 }
 function translateAnthropicMessagesToOpenAI(anthropicMessages, system) {
@@ -3260,16 +3293,21 @@ function getAnthropicToolUseBlocks(toolCalls) {
 //#endregion
 //#region src/routes/messages/count-tokens-handler.ts
 /**
-* Handles token counting for Anthropic messages
+* Handles token counting for Anthropic messages.
+*
+* Uses multi-strategy model matching:
+* 1. findModel(translatedName) — translated Copilot name with format variants
+* 2. findModel(originalName) — original Anthropic name with format variants
 */
 async function handleCountTokens(c) {
 	try {
 		const anthropicBeta = c.req.header("anthropic-beta");
 		const anthropicPayload = await c.req.json();
 		const openAIPayload = translateToOpenAI(anthropicPayload);
-		const selectedModel = state.models?.data.find((model) => model.id === anthropicPayload.model);
+		const translatedModelName = translateModelName(anthropicPayload.model);
+		const selectedModel = findModel(translatedModelName) ?? findModel(anthropicPayload.model);
 		if (!selectedModel) {
-			consola.warn("Model not found, returning default token count");
+			consola.warn(`Model not found for "${anthropicPayload.model}" (translated: "${translatedModelName}"), returning default token count`);
 			return c.json({ input_tokens: 1 });
 		}
 		const tokenCount = await getTokenCount(openAIPayload, selectedModel);
@@ -3420,9 +3458,12 @@ function translateChunkToAnthropicEvents(chunk, state$1) {
 //#region src/routes/messages/handler.ts
 /**
 * Auto-truncate OpenAI payload if prompt tokens exceed model limit.
+*
+* Uses multi-strategy exact matching via findModel() to handle
+* mismatches between Anthropic and Copilot model naming conventions.
 */
 async function autoTruncatePayload(payload) {
-	const selectedModel = state.models?.data.find((model) => model.id === payload.model);
+	const selectedModel = findModel(payload.model);
 	if (!selectedModel) {
 		consola.warn("No model selected for Anthropic endpoint, skipping auto-truncation");
 		return payload;
@@ -3443,6 +3484,12 @@ async function handleCompletion(c) {
 	const response = await createChatCompletions(openAIPayload);
 	if (isNonStreaming(response)) {
 		const anthropicResponse = translateToAnthropic(response);
+		setTokenUsage({
+			inputTokens: anthropicResponse.usage.input_tokens,
+			outputTokens: anthropicResponse.usage.output_tokens,
+			cacheReadTokens: anthropicResponse.usage.cache_read_input_tokens,
+			cacheCreationTokens: anthropicResponse.usage.cache_creation_input_tokens
+		});
 		return c.json(anthropicResponse);
 	}
 	return streamSSE(c, async (stream) => {
@@ -3457,6 +3504,11 @@ async function handleCompletion(c) {
 			if (!rawEvent.data) continue;
 			const chunk = JSON.parse(rawEvent.data);
 			const events$1 = translateChunkToAnthropicEvents(chunk, streamState);
+			if (chunk.usage) setTokenUsage({
+				inputTokens: chunk.usage.prompt_tokens - (chunk.usage.prompt_tokens_details?.cached_tokens ?? 0),
+				outputTokens: chunk.usage.completion_tokens,
+				cacheReadTokens: chunk.usage.prompt_tokens_details?.cached_tokens
+			});
 			for (const event of events$1) await stream.writeSSE({
 				event: event.type,
 				data: JSON.stringify(event)
@@ -3982,7 +4034,7 @@ async function runServer(options$1) {
 			state.zenApiKey = options$1.zenApiKey;
 			consola.info("Using provided Zen API key");
 		} else {
-			const { setupZenApiKey, loadZenAuth } = await import("./auth-CCwbOOQN.js");
+			const { setupZenApiKey, loadZenAuth } = await import("./auth-pRwfByMF.js");
 			const existingAuth = await loadZenAuth();
 			if (existingAuth) {
 				state.zenApiKey = existingAuth.apiKey;
@@ -4002,7 +4054,7 @@ async function runServer(options$1) {
 		}
 		if (hasApiKey()) {
 			consola.info("Using Gemini API Key for authentication (from GEMINI_API_KEY)");
-			consola.info("API Key: " + getApiKey$1()?.slice(0, 10) + "...");
+			consola.info(`API Key: ${getApiKey$1()?.slice(0, 10) ?? ""}...`);
 		} else {
 			const existingAuth = await loadAntigravityAuth();
 			if (!existingAuth || existingAuth.accounts.length === 0) {
@@ -4048,7 +4100,7 @@ async function runServer(options$1) {
 			const { HTTPError: HTTPError$1 } = await import("./error-CsShqJjE.js");
 			if (error instanceof HTTPError$1 && error.response.status === 401) {
 				consola.error("Failed to get Copilot token - GitHub token may be invalid or Copilot access revoked");
-				const { clearGithubToken: clearGithubToken$1 } = await import("./token-sYqHiHEd.js");
+				const { clearGithubToken: clearGithubToken$1 } = await import("./token-CCg0yU7a.js");
 				await clearGithubToken$1();
 				consola.info("Please restart to re-authenticate");
 			}