fix: clone repo before Step3/4 to read findings and exclusions from head branch

Co-authored-by: Copilot <copilot@github.com>

.gitea/ai-review/exclusions.json

@@ -0,0 +1,7 @@
+[
+  {
+    "role": "Rex",
+    "location": "app/git.js",
+    "suggestion": "請避免將敏感資料（如 GITEA_TOKEN）直接寫入環境變數"
+  }
+]

.gitea/ai-review/findings.json

@@ -1,79 +1,142 @@
 [
   {
-    "level": "critical",
-    "role": "Rex",
-    "location": "app/config.js:7",
-    "suggestion": "請確保 EXCLUSIONS_PATH 的值不包含敏感資訊，並使用環境變數來管理敏感資料。",
+    "level": "warning",
+    "role": "Leo",
+    "location": "app/findings.js:93",
+    "suggestion": "建議在 loadExclusions 函式中增加對於 JSON 格式的驗證，確保讀取的資料符合預期格式，避免潛在的錯誤。",
+    "is_new": true
+  },
+  {
+    "level": "warning",
+    "role": "Leo",
+    "location": "app/findings.js:40",
+    "suggestion": "在 applyExclusions 函式中，建議增加對於 findings 和 exclusions 參數的有效性檢查，以提高程式的健壯性。",
     "is_new": true
   },
   {
     "level": "warning",
     "role": "Zara",
     "location": "app/findings.js:40",
-    "suggestion": "在 applyExclusions 函數中，使用 filter 和 some 方法的組合可能會導致效能問題，特別是當 findings 和 exclusions 的數量很大時。考慮使用更有效的資料結構（如 HashSet）來加速查詢。",
+    "suggestion": "在 applyExclusions 函數中，使用 Array.prototype.some 進行過濾時，可能會導致性能問題，特別是當 findings 和 exclusions 的數量都很大時。建議使用更高效的資料結構（如 HashSet）來加速查詢。",
     "is_new": true
   },
   {
     "level": "warning",
     "role": "Rex",
-    "location": "app/findings.js:40",
-    "suggestion": "在讀取排除問題檔案時，建議加入對檔案內容的驗證，以防止不正確的格式導致潛在的錯誤或漏洞。",
+    "location": ".gitea/ai-review/exclusions.json",
+    "suggestion": "請避免將敏感資料（如 GITEA_TOKEN）直接寫入環境變數",
     "is_new": true
   },
   {
     "level": "warning",
     "role": "Aria",
     "location": "README.md:4",
-    "suggestion": "建議將列表項目從數字改為符號，因為這樣可以更清晰地表示步驟，並避免數字錯位的問題。",
+    "suggestion": "建議將「讀取排除問題檔案，用來過濾PR問題表格中不需要處理的問題」的描述改為「讀取排除問題檔案，過濾 PR 問題表格中不需要處理的問題」，以保持一致性。",
     "is_new": true
   },
   {
-    "level": "info",
-    "role": "Leo",
-    "location": "app/findings.js:1",
-    "suggestion": "建議在檔案開頭添加檔案的功能描述，以提高可讀性。",
-    "is_new": true
-  },
-  {
-    "level": "info",
-    "role": "Leo",
+    "level": "warning",
+    "role": "Maya",
     "location": "app/findings.js:40",
-    "suggestion": "建議為 loadExclusions 函式添加詳細的文件說明，以便未來的開發者能更快理解其功能。",
+    "suggestion": "建議在 applyExclusions 函數中增加對 findings 內容的驗證，確保其格式正確，以提高測試的穩定性和可靠性。",
     "is_new": true
   },
   {
     "level": "info",
     "role": "Leo",
-    "location": "app/findings.js:93",
-    "suggestion": "建議為 deduplicateWithAI 函式添加詳細的文件說明，以便未來的開發者能更快理解其功能。",
+    "location": "README.md",
+    "suggestion": "建議在 README 中增加對於新功能（如排除問題過濾）的詳細說明，以便未來的維護者能快速了解其功能。",
+    "is_new": true
+  },
+  {
+    "level": "info",
+    "role": "Leo",
+    "location": "app/main.js",
+    "suggestion": "建議在 main 函式中增加對於每個步驟的詳細註解，讓未來的維護者能更容易理解程式邏輯。",
+    "is_new": true
+  },
+  {
+    "level": "info",
+    "role": "Zara",
+    "location": "app/findings.js:39",
+    "suggestion": "在過濾 findings 時，建議將過濾條件的邏輯提取為獨立函數，以提高可讀性和可維護性。",
+    "is_new": true
+  },
+  {
+    "level": "info",
+    "role": "Zara",
+    "location": "app/main.js:64",
+    "suggestion": "在讀取排除問題檔案時，建議考慮使用非同步方法（如 fs.promises.readFile）來避免阻塞事件循環，提升效能。",
     "is_new": true
   },
   {
     "level": "info",
     "role": "Aria",
-    "location": "README.md:10",
-    "suggestion": "建議在每個步驟後添加簡短的描述，以提高可讀性和理解性。",
+    "location": "README.md:8",
+    "suggestion": "建議將「如果PR問題表格中有嚴重問題，則不要讓 workflow 執行成功(exit 1)」的描述改為「如果 PR 問題表格中有嚴重問題，則不要讓 workflow 執行成功（exit 1）」以提高可讀性。",
     "is_new": true
   },
   {
     "level": "info",
     "role": "Aria",
-    "location": "app/config.js:7",
-    "suggestion": "建議在常數命名中使用全大寫字母和底線分隔，以提高可讀性。",
+    "location": "TODO.md:4",
+    "suggestion": "建議將「階段四：findings 寫入與 comment 發布」的標題改為「階段四：排除問題過濾」，以更清楚地反映內容。",
+    "is_new": true
+  },
+  {
+    "level": "info",
+    "role": "Aria",
+    "location": "TODO.md:6",
+    "suggestion": "建議將「階段五：findings 寫入與 comment 發布」的標題改為「階段五：findings 寫入與 comment 發布」，以保持一致性。",
+    "is_new": true
+  },
+  {
+    "level": "info",
+    "role": "Aria",
+    "location": "TODO.md:8",
+    "suggestion": "建議將「階段六：記憶區 commit/push 與錯誤處理」的標題改為「階段六：記憶區 commit/push 與錯誤處理」，以保持一致性。",
+    "is_new": true
+  },
+  {
+    "level": "info",
+    "role": "Aria",
+    "location": "TODO.md:10",
+    "suggestion": "建議將「階段七：阻擋嚴重問題 PR（第 8 點）」的標題改為「階段七：阻擋嚴重問題 PR（第 8 點）」以保持一致性。",
+    "is_new": true
+  },
+  {
+    "level": "info",
+    "role": "Aria",
+    "location": "app/config.js",
+    "suggestion": "建議在 EXCLUSIONS_PATH 的定義上方添加註解，說明該常數的用途，以提高可讀性。",
+    "is_new": true
+  },
+  {
+    "level": "info",
+    "role": "Aria",
+    "location": "app/findings.js",
+    "suggestion": "建議在 loadExclusions 函數的開頭添加註解，說明該函數的用途，以提高可讀性。",
+    "is_new": true
+  },
+  {
+    "level": "info",
+    "role": "Aria",
+    "location": "app/findings.js",
+    "suggestion": "建議在 applyExclusions 函數的開頭添加註解，說明該函數的用途，以提高可讀性。",
     "is_new": true
   },
   {
     "level": "info",
     "role": "Maya",
-    "location": "app/main.js:42",
-    "suggestion": "建議在每個步驟完成後的 log 中，增加更多上下文資訊，讓使用者更清楚每個步驟的結果。",
+    "location": "app/findings.js:7",
+    "suggestion": "建議為 loadExclusions 和 applyExclusions 函數撰寫單元測試，以確保其功能正確並能處理邊界條件。",
     "is_new": true
   },
   {
     "level": "info",
     "role": "Maya",
-    "location": "app/main.js:50",
-    "suggestion": "建議在發佈 comment 失敗時，記錄具體的錯誤原因，以便後續調試。",
+    "location": "app/main.js:48",
+    "suggestion": "建議在每個主要步驟之後增加測試用例，以驗證每個步驟的輸出是否符合預期。",
     "is_new": true
   }
 ]

app/git.js

@@ -14,6 +14,34 @@ function makeRunner(spawn) {
   };
 }
 
+/**
+ * Clone PR head branch to workspace/repo (idempotent)
+ */
+export function cloneRepo(workspace, _spawnSync = spawnSync) {
+  const run = makeRunner(_spawnSync);
+  const baseUrl = GITEA_SERVER_URL.replace(/\/$/, '');
+  const remoteUrl = `${baseUrl}/${GITEA_REPOSITORY}.git`;
+  const repoDir = path.join(workspace, 'repo');
+
+  const askpassScript = path.join(workspace, '.git-askpass.sh');
+  fs.writeFileSync(askpassScript, '#!/bin/sh\necho "$GIT_TOKEN"\n', { mode: 0o700 });
+  const credEnv = { ...process.env, GIT_ASKPASS: askpassScript, GIT_USERNAME: 'x-token', GIT_TOKEN: GITEA_TOKEN };
+
+  try {
+    if (!fs.existsSync(repoDir)) {
+      run(['clone', '--depth=1', '--branch', PR_HEAD_BRANCH, remoteUrl, repoDir], workspace, credEnv);
+      console.log(`  ✅ repo cloned to ${repoDir}`);
+    } else {
+      run(['fetch', 'origin', PR_HEAD_BRANCH], repoDir, credEnv);
+      run(['checkout', PR_HEAD_BRANCH], repoDir);
+      console.log(`  ✅ repo already exists, fetched latest`);
+    }
+  } finally {
+    try { fs.unlinkSync(askpassScript); } catch {}
+  }
+  return repoDir;
+}
+
 export async function commitAndPush(workspace, _spawnSync = spawnSync) {
   const run = makeRunner(_spawnSync);
 

app/main.js

@@ -3,7 +3,7 @@ import { loadRoles, getRoleIntro } from './roles.js';
 import { getPRDiff, postComment } from './gitea.js';
 import { analyzeWithRole, loadOldFindings, mergeFindings, sortByLevel, deduplicateWithAI, loadExclusions, applyExclusions } from './findings.js';
 import { saveFindings, postOldFindingsComment, postNewNonCriticalComment, postNewCriticalComments } from './comments.js';
-import { commitAndPush } from './git.js';
+import { cloneRepo, commitAndPush } from './git.js';
 
 const WORKSPACE = process.env.GITHUB_WORKSPACE || '/workspace';
 
@@ -65,7 +65,14 @@ async function main() {
 
   // Step3: 讀取舊 findings，合併去重（含 AI 語意去重）
   console.log('\n🔀 Step3: Findings 合併');
-  const oldFindings = loadOldFindings(WORKSPACE);
+  // Clone repo 以讀取舊 findings 與排除清單
+  let repoDir;
+  try {
+    repoDir = cloneRepo(WORKSPACE);
+  } catch (e) {
+    console.log(`  ⚠️  clone repo 失敗（繼續執行）: ${e.message}`);
+  }
+  const oldFindings = loadOldFindings(repoDir || WORKSPACE);
   const mergedFindings = mergeFindings(oldFindings, newFindings);
   console.log(`  Step3 merged findings total=${mergedFindings.length}`);
 
@@ -76,7 +83,7 @@ async function main() {
 
   // Step4: 讀取排除問題檔案，過濾 PR 問題表格
   console.log('\n🚫 Step4: 排除問題過濾');
-  const exclusions = loadExclusions(WORKSPACE);
+  const exclusions = loadExclusions(repoDir || WORKSPACE);
   const filtered = applyExclusions(sorted, exclusions);
   console.log(`  Step4 完成: findings total=${filtered.length}`);