Merge pull request '整理程式碼' (#93) from 整理程式碼 into develop

Reviewed-on: #93

.gitea/ai-review/exclusions.json

@@ -223,5 +223,25 @@
     "role": "Leo",
     "location": "TODO.md",
     "suggestion": "TODO.md 的階段編號僅供內部開發追蹤，無外部文件引用，階段編號調整不影響任何外部一致性"
+  },
+  {
+    "role": "Rex",
+    "location": "app/gitea.js",
+    "suggestion": "getPRDiff 函數現在回傳未經過濾的原始 Git Diff 內容。雖然 main.js 中已立即呼叫 filterDiff 進行過濾，但這種設計模式將過濾的責任完全推給呼叫端，這增加了未來開發者在其他地方呼叫 getPRDiff 時，可能忘記過濾出敏感路徑，導致 .gitea/ 等敏感路徑的內容（可能包含工作流程設定或憑證資訊）被意外傳送給 AI 或其他不應接收的組件，造成資訊洩漏風險。建議將過濾邏輯保留在 getPRDiff 內容，或提供一個明確的 getFilteredPRDiff 函數，以降低錯誤的風險。"
+  },
+  {
+    "role": "Zara",
+    "location": "app/git.js",
+    "suggestion": "在 main.js 中，commitAndPush 函數內部會再次呼叫 cloneRepo，然而 main.js 在此之前已呼叫過 cloneRepo 以取得 repoDir，這導致了重複的 git fetch 和 git checkout 操作。即使 cloneRepo 內容有檢查環境變數，仍會造成不必要的清潔和時間延遲。建議修改 commitAndPush 邏輯，使其接收已存在的 repoDir 作為參數，避免重複執行 cloneRepo。"
+  },
+  {
+    "role": "Aria",
+    "location": "app/main.js",
+    "suggestion": "在 main.js 中，表達式 repoDir。"
+  },
+  {
+    "role": "Zara",
+    "location": "app/gitea.js:L20-L21",
+    "suggestion": "將 filterDiff 中的正規表達式比對（RegExp.match）替換為 String.startsWith 是一個重要的效能改進。startsWith 是一個更輕量且高效的字串操作，尤其在處理大型 Git Diff 內容時，此修改已顯著提升過濾效率。"
   }
 ]

.gitea/ai-review/findings.json

@@ -1,23 +1 @@
-[
-  {
-    "level": "info",
-    "role": "Rex",
-    "location": "app/gitea.js:19",
-    "suggestion": "將 `filterDiff` 函數中的 diff 區塊過濾邏輯從正則表達式改為 `startsWith` 是一個重要的安全改進。這可以有效防止潛在的正則表達式注入攻擊，即使 `excludePrefixes` 參數未來可能受到外部控制，也能確保過濾邏輯的安全性。",
-    "is_new": false
-  },
-  {
-    "level": "info",
-    "role": "Rex",
-    "location": "app/main.js:46",
-    "suggestion": "在將 Git Diff 內容傳遞給 AI 進行分析之前，明確呼叫 `filterDiff` 函數以排除 `.gitea/` 等敏感路徑，是一個良好的安全實踐。這有助於避免 AI 分析到不必要的或包含敏感配置的非業務程式碼，降低潛在的資訊洩漏風險。",
-    "is_new": false
-  },
-  {
-    "level": "info",
-    "role": "Rex",
-    "location": "app/main.js:98",
-    "suggestion": "新增對 `findings.json` 和 `exclusions.json` 檔案進行 JSON 格式驗證的步驟，並在格式錯誤時嘗試重置和備份，這是一個重要的健壯性與安全措施。它能防止因檔案損壞或惡意修改導致的服務中斷或行為異常，確保系統的穩定性和資料的完整性。",
-    "is_new": false
-  }
-]
+[]

app/git.js

@@ -47,12 +47,10 @@ export function cloneRepo(workspace, _spawnSync = spawnSync) {
   });
 }
 
-export async function commitAndPush(workspace, _spawnSync = spawnSync) {
+export async function commitAndPush(workspace, repoDir, _spawnSync = spawnSync) {
   const run = makeRunner(_spawnSync);
 
   try {
-    const repoDir = cloneRepo(workspace, _spawnSync);
-
     await withAskpass(workspace, async credEnv => {
       run(['config', 'user.email', 'ai-review[bot]@gitea'], repoDir);
       run(['config', 'user.name', 'AI Review Bot'], repoDir);

app/git.test.js

@@ -38,7 +38,6 @@ describe('commitAndPush', () => {
   before(() => { workspace = makeTmpWorkspace(); });
   after(() => { fs.rmSync(workspace, { recursive: true, force: true }); });
   beforeEach(() => {
-    // Remove leftover askpass scripts between tests
     for (const f of fs.readdirSync(workspace)) {
       if (f.endsWith('.git-askpass.sh')) fs.unlinkSync(path.join(workspace, f));
     }
@@ -46,7 +45,7 @@ describe('commitAndPush', () => {
 
   it('does not embed token in any git command argument', async () => {
     const spawn = makeSpawn();
-    await commitAndPush(workspace, spawn);
+    await commitAndPush(workspace, path.join(workspace, 'repo'), spawn);
 
     for (const { args } of spawn.calls) {
       assert.ok(!args.join(' ').includes('test-token'), `Token leaked in git args: ${args.join(' ')}`);
@@ -55,7 +54,7 @@ describe('commitAndPush', () => {
 
   it('uses GIT_ASKPASS env for network operations (fetch, push, clone)', async () => {
     const spawn = makeSpawn();
-    await commitAndPush(workspace, spawn);
+    await commitAndPush(workspace, path.join(workspace, 'repo'), spawn);
 
     const networkOps = ['fetch', 'push', 'clone'];
     const networkCalls = spawn.calls.filter(c => networkOps.includes(c.args[0]));
@@ -67,28 +66,28 @@ describe('commitAndPush', () => {
   });
 
   it('cleans up askpass script after successful run', async () => {
-    await commitAndPush(workspace, makeSpawn());
+    await commitAndPush(workspace, path.join(workspace, 'repo'), makeSpawn());
     const leftover = fs.readdirSync(workspace).filter(f => f.endsWith('.git-askpass.sh'));
     assert.equal(leftover.length, 0, 'askpass script was not cleaned up');
   });
 
   it('cleans up askpass script even when git fails', async () => {
     const failSpawn = () => ({ status: 1, stdout: '', stderr: 'fatal: error', error: null });
-    await commitAndPush(workspace, failSpawn);
+    await commitAndPush(workspace, path.join(workspace, 'repo'), failSpawn);
     const leftover = fs.readdirSync(workspace).filter(f => f.endsWith('.git-askpass.sh'));
     assert.equal(leftover.length, 0, 'askpass script was not cleaned up after failure');
   });
 
   it('skips commit when status shows no changes', async () => {
     const spawn = makeSpawn({ status: () => ({ status: 0, stdout: '', stderr: '', error: null }) });
-    await commitAndPush(workspace, spawn);
+    await commitAndPush(workspace, path.join(workspace, 'repo'), spawn);
     const commitCalled = spawn.calls.some(c => c.args[0] === 'commit');
     assert.equal(commitCalled, false, 'commit should not run when there are no changes');
   });
 
   it('does not throw when git command fails', async () => {
     const failSpawn = () => ({ status: 1, stdout: '', stderr: 'fatal: error', error: null });
-    await assert.doesNotReject(() => commitAndPush(workspace, failSpawn));
+    await assert.doesNotReject(() => commitAndPush(workspace, path.join(workspace, 'repo'), failSpawn));
   });
 });
 

app/gitea.js

@@ -7,12 +7,11 @@ const headers = () => ({ Authorization: `token ${GITEA_TOKEN}`, 'Content-Type':
 const api = (path) => `${GITEA_SERVER_URL.replace(/\/$/, '')}/api/v1${path}`;
 
 /**
- * 取得 PR 的原始 Git Diff 內容。
- * 注意：回傳值未經路徑過濾，呼叫端須使用 filterDiff 排除敏感路徑（如 .gitea/）後再傳給 AI。
+ * 取得 PR 的 Git Diff 內容，已自動排除 .gitea/ 資料夾。
  */
 export async function getPRDiff() {
   const resp = await axios.get(api(`/repos/${GITEA_REPOSITORY}/pulls/${PR_NUMBER}.diff`), { headers: headers(), timeout: 60000, httpsAgent });
-  return resp.data;
+  return filterDiff(resp.data, ['.gitea/']);
 }
 
 /**

app/main.js

@@ -2,7 +2,7 @@ import fs from 'fs';
 import path from 'path';
 import { GITEA_REPOSITORY, PR_NUMBER, PR_HEAD_BRANCH, PR_BASE_BRANCH, getLLMConfig, FINDINGS_PATH, EXCLUSIONS_PATH } from './config.js';
 import { loadRoles, getRoleIntro } from './roles.js';
-import { getPRDiff, filterDiff, postComment } from './gitea.js';
+import { getPRDiff, postComment } from './gitea.js';
 import { analyzeWithRole, loadOldFindings, mergeFindings, sortByLevel, deduplicateWithAI, loadExclusions, applyExclusions, filterFalsePositivesWithAI } from './findings.js';
 import { saveFindings, postOldFindingsComment, postNewNonCriticalComment, postNewCriticalComments } from './comments.js';
 import { cloneRepo, commitAndPush } from './git.js';
@@ -47,18 +47,8 @@ async function main() {
     console.log(`  ⚠️  comment 發布失敗（繼續執行）: ${e.message}`);
   }
 
-  // Step2: 排除 .gitea/ 資料夾內的所有檔案
-  console.log('\n🗂️  Step2: Git Diff 過濾');
-  diff = filterDiff(diff, ['.gitea/']);
-  console.log(`  排除 .gitea/ 後 diff 長度: ${diff.length} 字元`);
-
-  if (!diff.trim()) {
-    console.log('  ⚠️  過濾後 diff 為空，無需審查');
-    process.exit(0);
-  }
-
-  // Step3: 各角色分析 diff 產生新 findings
-  console.log('\n📊 Step3: Findings 產生');
+  // Step2: 各角色分析 diff 產生新 findings
+  console.log('\n📊 Step2: Findings 產生');
   const results = await Promise.allSettled(roles.map(role => analyzeWithRole(role, diff)));
   const newFindings = [];
   for (let i = 0; i < results.length; i++) {
@@ -68,10 +58,10 @@ async function main() {
       console.log(`  ⚠️  [${roles[i].name}] 分析失敗（跳過）: ${results[i].reason?.message}`);
     }
   }
-  console.log(`  Step3 完成: 新 findings 總計 ${newFindings.length} 筆`);
+  console.log(`  Step2 完成: 新 findings 總計 ${newFindings.length} 筆`);
 
   // Step4: 讀取舊 findings，合併去重（含 AI 語意去重）
-  console.log('\n🔀 Step4: Findings 合併');
+  console.log('\n🔀 Step3: Findings 合併');
   // Clone repo 以讀取舊 findings 與排除清單
   let repoDir;
   try {
@@ -81,35 +71,35 @@ async function main() {
   }
   const oldFindings = loadOldFindings(repoDir || WORKSPACE);
   const mergedFindings = mergeFindings(oldFindings, newFindings);
-  console.log(`  Step4 merged findings total=${mergedFindings.length}`);
+  console.log(`  Step3 merged findings total=${mergedFindings.length}`);
 
-  console.log('\n🤖 Step4b: AI 語意去重');
+  console.log('\n🤖 Step3b: AI 語意去重');
   const deduped = await deduplicateWithAI(mergedFindings);
   const sorted = sortByLevel(deduped);
-  console.log(`  Step4b dedup findings total=${sorted.length} (critical=${sorted.filter(f=>f.level==='critical').length} warning=${sorted.filter(f=>f.level==='warning').length} info=${sorted.filter(f=>f.level==='info').length})`);
+  console.log(`  Step3b dedup findings total=${sorted.length} (critical=${sorted.filter(f=>f.level==='critical').length} warning=${sorted.filter(f=>f.level==='warning').length} info=${sorted.filter(f=>f.level==='info').length})`);
 
   // Step5: 讀取排除問題檔案，過濾 PR 問題表格，並請 AI 判斷誤報
-  console.log('\n🚫 Step5: AI 排除問題過濾');
+  console.log('\n🚫 Step4: AI 排除問題過濾');
   // 輸入至 findings 用於 AI 誤報過濾，exclusions 同時作為已知誤報參考
   const exclusions = loadExclusions(repoDir || WORKSPACE);
   const ruleFiltered = applyExclusions(sorted, exclusions);
   const filtered = await filterFalsePositivesWithAI(ruleFiltered, exclusions);
-  console.log(`  Step5 完成: findings total=${filtered.length}`);
+  console.log(`  Step4 完成: findings total=${filtered.length}`);
 
   // Step6: 寫入 findings.json，依序發布 comment
-  console.log('\n📝 Step6: Findings 寫入與 Comment 發布');
+  console.log('\n📝 Step5: Findings 寫入與 Comment 發布');
   saveFindings(WORKSPACE, filtered);
   try {
     await postOldFindingsComment(filtered);
     await postNewNonCriticalComment(filtered);
     await postNewCriticalComments(filtered);
-    console.log('  Step6 完成');
+    console.log('  Step5 完成');
   } catch (e) {
     console.log(`  ⚠️  comment 發布失敗（繼續執行）: ${e.message}`);
   }
 
   // Step7: 驗證 findings.json 與 exclusions.json 為合法 JSON
-  console.log('\n🔎 Step7: JSON 格式驗證');
+  console.log('\n🔎 Step6: JSON 格式驗證');
   for (const relPath of [FINDINGS_PATH, EXCLUSIONS_PATH]) {
     const fullPath = path.join(repoDir || WORKSPACE, relPath);
     if (!fs.existsSync(fullPath)) {
@@ -133,12 +123,12 @@ async function main() {
     }
   }
 
-  // Step8: commit/push findings.json 到來源分支
-  console.log('\n💾 Step8: 記憶區 Commit/Push');
-  await commitAndPush(WORKSPACE);
+  // Step7: commit/push findings.json 到來源分支
+  console.log('\n💾 Step7: 記憶區 Commit/Push');
+  await commitAndPush(WORKSPACE, repoDir);
 
   // Step9: 有 critical 問題則 exit 1
-  console.log('\n🚦 Step9: 嚴重問題檢查');
+  console.log('\n🚦 Step8: 嚴重問題檢查');
   const criticalCount = filtered.filter(f => f.level === 'critical').length;
   if (criticalCount > 0) {
     console.log(`  ❌ 發現 ${criticalCount} 個嚴重問題，workflow 結束（exit 1）`);