feat: support multiple API keys for LLM providers, allowing automatic key rotation on failure

Reviewed-on: jiantw83/code-review#83

.gitea/ai-review/exclusions.json

@@ -59,15 +59,39 @@
     "role": "Aria",
     "location": "action.yaml",
     "suggestion": "action.yaml 已整理，多餘空行已移除，結構整潔"
-  }
+  },
   {
     "role": "Maya",
     "location": "app/",
     "suggestion": "LLM 整合測試需要真實 API key 與網路，不適合加入單元測試。llm.js 使用統一 OpenAI 相容介面，Gemini 透過相同介面呼叫，無特殊格式差異，現有測試已涵蓋 config/findings/git 邏輯"
   },
   {
-    "role": "Leo",
+    "role": "Rex",
+    "location": "app/",
+    "suggestion": "LLM 整合測試需要真實 API key 與網路，不適合加入單元測試。llm.js 使用統一 OpenAI 相容介面，Gemini 透過相同介面呼叫，無特殊格式差異"
+  },
+  {
+    "role": "Rex",
     "location": "app/config.test.js",
     "suggestion": "import 語句長度合理，無需拆分為多行"
+  },
+  {
+    "role": "Rex",
+    "location": ".gitea/ai-review/findings.json",
+    "suggestion": "findings.json 重複問題由 AI 去重與排除機制處理，不是程式碼問題"
+  },
+  {
+    "role": "Rex",
+    "location": "app/comments.js",
+    "suggestion": "JSON 結尾換行符號為標準做法，不影響任何 JSON 解析器，無相容性問題"
+  },
+  {
+    "location": ".gitea/ai-review/findings.json",
+    "suggestion": "findings.json 是自動產生的問題記錄檔，不應對其內容提出審查問題"
+  },
+  {
+    "role": "Rex",
+    "location": ".gitea/workflows/review.yaml",
+    "suggestion": "切換 LLM 服務提供商的維護建議屬過度謹慎，不是實際程式碼問題"
   }
 ]

.gitea/ai-review/findings.json

@@ -1,37 +1,37 @@
 [
   {
-    "level": "critical",
-    "role": "Maya",
-    "location": "app/",
-    "suggestion": "此次變更將 AI 審查服務從 OpenRouter 切換至 Gemini，涉及不同的 API 端點、請求/回應格式及錯誤處理機制。儘管 `action.yaml` 已配置 Gemini 相關參數，但 Git Diff 中未見針對 Gemini API 整合的單元測試或整合測試。雖然 LLM 整合測試可能不適合傳統的單元測試（因需真實 API key），但這不應排除建立專屬的整合測試。現有測試可能僅涵蓋 `config/findings/git` 的通用邏輯，不足以全面驗證與 Gemini 服務的特定互動，例如請求建構、回應解析、特定錯誤碼處理及邊界條件。強烈建議為 Gemini 整合新增專屬的整合測試，以確保其在實際運作中的穩定性與正確性。",
+    "level": "warning",
+    "role": "Zara",
+    "location": "app/comments.js:24",
+    "suggestion": "在 `saveFindings` 函數中，`fs.writeFileSync` 是一個同步操作。如果 `findings` 陣列可能非常大，或者此函數會被頻繁呼叫，同步寫入檔案可能會阻塞 Node.js 事件迴圈，導致應用程式響應變慢。建議改用 `fs.writeFile` (非同步) 以避免阻塞主執行緒，提升應用程式的響應能力。",
+    "is_new": false
+  },
+  {
+    "level": "warning",
+    "role": "Aria",
+    "location": ".gitea/workflows/master.yaml",
+    "suggestion": "檔案結尾應包含一個換行符號 (newline at EOF)，這是 POSIX 系統的慣例，有助於版本控制系統的正確處理。",
     "is_new": true
   },
   {
     "level": "warning",
     "role": "Aria",
-    "location": ".gitea/ai-review/findings.json",
-    "suggestion": "檔案最後缺少換行符號，請在檔案結尾加入一個空白換行。",
-    "is_new": false
-  },
-  {
-    "level": "warning",
-    "role": "Leo",
-    "location": ".gitea/ai-review/findings.json",
-    "suggestion": "`findings.json` 中重新出現關於 `app/config.test.js` 檔案結尾換行符號及匯入語句長度的警告/資訊，但 `exclusions.json` 卻明確指出這些問題已解決或無需修改。這種矛盾會導致審查流程混亂，降低 AI 審查系統的可靠性。建議釐清並統一 AI 審查的設定或排除規則，確保其一致性，避免重複提出已處理或被排除的問題。",
+    "location": "Dockerfile",
+    "suggestion": "檔案結尾應包含一個換行符號 (newline at EOF)，這是 POSIX 系統的慣例，有助於版本控制系統的正確處理。",
     "is_new": true
   },
   {
     "level": "warning",
-    "role": "Maya",
-    "location": "app/comments.js:24",
-    "suggestion": "`saveFindings` 函數在寫入 `findings.json` 時新增了換行符號。請確認現有的測試是否已涵蓋此輸出格式的變更，確保測試能夠精確驗證檔案內容，包括結尾的換行符號。若無，建議更新或新增測試案例以確保此行為被正確驗證。",
+    "role": "Aria",
+    "location": "TODO.md",
+    "suggestion": "檔案結尾應包含一個換行符號 (newline at EOF)，這是 POSIX 系統的慣例，有助於版本控制系統的正確處理。",
     "is_new": true
   },
   {
-    "level": "info",
-    "role": "Leo",
-    "location": ".gitea/workflows/review.yaml",
-    "suggestion": "工作流程已從 OpenRouter/OpenAI 服務切換至 Google Gemini 服務。不同 AI 服務提供商的 API 響應時間、吞吐量和穩定性可能存在差異。建議在切換後監控 AI Code Review 步驟的執行時間，確保新配置能維持或提升效能，並留意潛在的成本變化，以利長期維護與優化。",
+    "level": "warning",
+    "role": "Aria",
+    "location": "entrypoint.sh",
+    "suggestion": "檔案結尾應包含一個換行符號 (newline at EOF)，這是 POSIX 系統的慣例，有助於版本控制系統的正確處理。",
     "is_new": true
   }
 ]

.gitea/workflows/review.yaml

@@ -33,7 +33,7 @@ jobs:
     - name: AI Code Review
       uses: https://gitea.jsc.idv.tw/jiantw83/code-review@v${{ needs.version.outputs.version }}
       with:
-        GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY_1 }}
+        GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }},${{ secrets.GEMINI_API_KEY_1 }},${{ secrets.GEMINI_API_KEY_2 }},${{ secrets.GEMINI_API_KEY_3 }},${{ secrets.GEMINI_API_KEY_4 }},${{ secrets.GEMINI_API_KEY_5 }},${{ secrets.GEMINI_API_KEY_6 }},${{ secrets.GEMINI_API_KEY_7 }},${{ secrets.GEMINI_API_KEY_8 }},${{ secrets.GEMINI_API_KEY_9 }}
         GEMINI_BASE_URL: https://generativelanguage.googleapis.com/v1beta
         GEMINI_MODEL: ${{ vars.GEMINI_MODEL }}
     permissions:

README.md

@@ -21,6 +21,7 @@
 3. Comment 加上些許 emoji 讓資訊有點活力
 4. 盡量將應用程式放在 ./app，修改 entrypoint.sh 與 Dockerfile 讓程式可以正常運行
 5. 將提示詞放到 ./app/prompts 內供程式讀取
+6. API Key 支援逗號分隔傳入多個，依序嘗試，失敗時自動換下一個，全部失敗則 exit 1
 
 # 使用說明
 
@@ -42,7 +43,7 @@ jobs:
     - name: AI Code Review
       uses: https://gitea.jsc.idv.tw/jiantw83/code-review@${{ vars.ACTION_CODE_REVIEW_VERSION }}
       with:
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}  # 支援逗號分隔多個 Key
         OPENAI_BASE_URL: https://api.openai.com/v1
         OPENAI_MODEL: ${{ vars.OPENAI_MODEL }}
     permissions:
@@ -65,7 +66,7 @@ jobs:
     - name: AI Code Review
       uses: https://gitea.jsc.idv.tw/jiantw83/code-review@${{ vars.ACTION_CODE_REVIEW_VERSION }}
       with:
-        OPENAI_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}  # OpenRouter 使用 OpenAI 相容介面，以 OPENAI_API_KEY 傳入
+        OPENAI_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}  # OpenRouter 使用 OpenAI 相容介面，以 OPENAI_API_KEY 傳入，支援逗號分隔多個 Key
         OPENAI_BASE_URL: https://openrouter.ai/api/v1
         OPENAI_MODEL: ${{ vars.OPENROUTER_MODEL }}
     permissions:
@@ -88,7 +89,7 @@ jobs:
     - name: AI Code Review
       uses: https://gitea.jsc.idv.tw/jiantw83/code-review@${{ vars.ACTION_CODE_REVIEW_VERSION }}
       with:
-        CLAUDE_API_KEY: ${{ secrets.CLAUDE_API_KEY }}
+        CLAUDE_API_KEY: ${{ secrets.CLAUDE_API_KEY }}  # 支援逗號分隔多個 Key
         CLAUDE_BASE_URL: https://api.anthropic.com/v1
     permissions:
       contents: write
@@ -110,7 +111,7 @@ jobs:
     - name: AI Code Review
       uses: https://gitea.jsc.idv.tw/jiantw83/code-review@${{ vars.ACTION_CODE_REVIEW_VERSION }}
       with:
-        GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+        GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }},${{ secrets.GEMINI_API_KEY_1 }},${{ secrets.GEMINI_API_KEY_2 }},${{ secrets.GEMINI_API_KEY_3 }},${{ secrets.GEMINI_API_KEY_4 }},${{ secrets.GEMINI_API_KEY_5 }},${{ secrets.GEMINI_API_KEY_6 }},${{ secrets.GEMINI_API_KEY_7 }},${{ secrets.GEMINI_API_KEY_8 }},${{ secrets.GEMINI_API_KEY_9 }}
         GEMINI_BASE_URL: https://generativelanguage.googleapis.com/v1beta
         GEMINI_MODEL: ${{ vars.GEMINI_MODEL }}
     permissions:
@@ -133,7 +134,7 @@ jobs:
     - name: AI Code Review
       uses: https://gitea.jsc.idv.tw/jiantw83/code-review@${{ vars.ACTION_CODE_REVIEW_VERSION }}
       with:
-        AMAZONQ_API_KEY: ${{ secrets.AMAZONQ_API_KEY }}
+        AMAZONQ_API_KEY: ${{ secrets.AMAZONQ_API_KEY }}  # 支援逗號分隔多個 Key
         AMAZONQ_BASE_URL: https://q.api.aws
     permissions:
       contents: write

TODO.md

@@ -35,6 +35,11 @@
 - 驗收：log 中能看到「critical 問題存在，workflow 結束（exit 1）」等明確訊息，且 workflow 狀態為失敗。
 - 完成
 
+## 階段八：API Key 輪替
+- 目標：所有平台的 API Key 支援逗號分隔傳入多個，依序嘗試，單一 Key 失敗時自動換下一個，全部失敗則 exit 1。
+- 驗收：log 中能看到「key[N/M] 失敗」等訊息，換 key 後繼續執行；傳入單一 Key 時行為與原本相同；全部 Key 失敗時 log「所有 API Key 均失敗，終止流程」且 workflow 狀態為失敗。
+- 完成
+
 ---
 
 所有階段驗收通過。

app/config.js

@@ -8,16 +8,22 @@ export const PR_BASE_BRANCH = process.env.PR_BASE_BRANCH || '';
 export const FINDINGS_PATH = '.gitea/ai-review/findings.json';
 export const EXCLUSIONS_PATH = '.gitea/ai-review/exclusions.json';
 
+/** 將逗號分隔的 API key 字串拆成陣列 */
+function splitKeys(value) {
+  if (!value) return [];
+  return value.split(',').map(k => k.trim()).filter(Boolean);
+}
+
 export function getLLMConfig() {
   const checks = [
-    ['openai',   process.env.OPENAI_API_KEY,   process.env.OPENAI_BASE_URL || 'https://api.openai.com/v1',   process.env.OPENAI_MODEL || 'gpt-4o-mini'],
-    ['claude',   process.env.CLAUDE_API_KEY,   process.env.CLAUDE_BASE_URL || 'https://api.anthropic.com/v1', process.env.CLAUDE_MODEL || 'claude-3-haiku-20240307'],
-    ['gemini',   process.env.GEMINI_API_KEY,   process.env.GEMINI_BASE_URL || 'https://generativelanguage.googleapis.com/v1beta', process.env.GEMINI_MODEL || 'gemini-2.5-flash'],
-    ['ollama',   'ollama',                      process.env.OLLAMA_BASE_URL,  process.env.OLLAMA_MODEL],
-    ['amazonq',  process.env.AMAZONQ_API_KEY,  process.env.AMAZONQ_BASE_URL  || 'https://q.api.aws',              process.env.AMAZONQ_MODEL  || 'amazon-q'],
+    ['openai',   splitKeys(process.env.OPENAI_API_KEY),   process.env.OPENAI_BASE_URL || 'https://api.openai.com/v1',   process.env.OPENAI_MODEL || 'gpt-4o-mini'],
+    ['claude',   splitKeys(process.env.CLAUDE_API_KEY),   process.env.CLAUDE_BASE_URL || 'https://api.anthropic.com/v1', process.env.CLAUDE_MODEL || 'claude-3-haiku-20240307'],
+    ['gemini',   splitKeys(process.env.GEMINI_API_KEY),   process.env.GEMINI_BASE_URL || 'https://generativelanguage.googleapis.com/v1beta', process.env.GEMINI_MODEL || 'gemini-2.5-flash'],
+    ['ollama',   ['ollama'],                               process.env.OLLAMA_BASE_URL,  process.env.OLLAMA_MODEL],
+    ['amazonq',  splitKeys(process.env.AMAZONQ_API_KEY),  process.env.AMAZONQ_BASE_URL  || 'https://q.api.aws',              process.env.AMAZONQ_MODEL  || 'amazon-q'],
   ];
-  for (const [provider, key, baseURL, model] of checks) {
-    if (key && baseURL) return { provider, apiKey: key, baseURL, model };
+  for (const [provider, apiKeys, baseURL, model] of checks) {
+    if (apiKeys.length > 0 && baseURL) return { provider, apiKeys, baseURL, model };
   }
-  return { provider: null, apiKey: null, baseURL: null, model: null };
+  return { provider: null, apiKeys: [], baseURL: null, model: null };
 }

app/config.test.js

@@ -26,14 +26,14 @@ describe('getLLMConfig', () => {
   it('returns null provider when no env vars set', () => {
     const cfg = getLLMConfig();
     assert.equal(cfg.provider, null);
-    assert.equal(cfg.apiKey, null);
+    assert.deepEqual(cfg.apiKeys, []);
   });
 
   it('detects openai with defaults', () => {
     process.env.OPENAI_API_KEY = 'sk-test';
     const cfg = getLLMConfig();
     assert.equal(cfg.provider, 'openai');
-    assert.equal(cfg.apiKey, 'sk-test');
+    assert.deepEqual(cfg.apiKeys, ['sk-test']);
     assert.equal(cfg.baseURL, 'https://api.openai.com/v1');
     assert.equal(cfg.model, 'gpt-4o-mini');
   });
@@ -48,7 +48,14 @@ describe('getLLMConfig', () => {
     assert.equal(cfg.model, 'gpt-4o');
   });
 
-  it('detects gemini with defaults', () => {
+  it('detects gemini with comma-separated keys, picks one', () => {
+    process.env.GEMINI_API_KEY = 'key1,key2,key3';
+    const cfg = getLLMConfig();
+    assert.equal(cfg.provider, 'gemini');
+    assert.deepEqual(cfg.apiKeys, ['key1', 'key2', 'key3']);
+  });
+
+  it('detects gemini with single key (no comma)', () => {
     process.env.GEMINI_API_KEY = 'gemini-key';
     const cfg = getLLMConfig();
     assert.equal(cfg.provider, 'gemini');

app/llm.js

@@ -5,23 +5,31 @@ import { getLLMConfig } from './config.js';
 const httpsAgent = new https.Agent({ rejectUnauthorized: false });
 
 export async function chat(systemPrompt, userContent) {
-  const { provider, apiKey, baseURL, model } = getLLMConfig();
+  const { provider, apiKeys, baseURL, model } = getLLMConfig();
   if (!provider) throw new Error('未設定任何 LLM API Key');
 
   console.log(`  [LLM] provider=${provider} model=${model}`);
 
-  const headers = {
-    'Content-Type': 'application/json',
-    'Authorization': `Bearer ${apiKey}`,
-  };
+  const headers = { 'Content-Type': 'application/json' };
   if (provider === 'claude') headers['anthropic-version'] = '2023-06-01';
 
-  const resp = await axios.post(
-    `${baseURL.replace(/\/$/, '')}/chat/completions`,
-    { model, messages: [{ role: 'system', content: systemPrompt }, { role: 'user', content: userContent }], temperature: 0.2 },
-    { headers, timeout: 120000, httpsAgent }
-  );
-  return resp.data.choices[0].message.content;
+  let lastError;
+  for (let i = 0; i < apiKeys.length; i++) {
+    headers['Authorization'] = `Bearer ${apiKeys[i]}`;
+    try {
+      const resp = await axios.post(
+        `${baseURL.replace(/\/$/, '')}/chat/completions`,
+        { model, messages: [{ role: 'system', content: systemPrompt }, { role: 'user', content: userContent }], temperature: 0.2 },
+        { headers, timeout: 120000, httpsAgent }
+      );
+      return resp.data.choices[0].message.content;
+    } catch (e) {
+      lastError = e;
+      console.log(`  [LLM] key[${i + 1}/${apiKeys.length}] 失敗: ${e.message}`);
+    }
+  }
+  console.error('  [LLM] 所有 API Key 均失敗，終止流程');
+  process.exit(1);
 }
 
 export async function chatJSON(systemPrompt, userContent) {