refactor: update commitAndPush function to accept repoDir parameter and adjust related tests

Reviewed-on: #89

.gitea/ai-review/exclusions.json

@@ -213,5 +213,15 @@
     "role": "Leo",
     "location": "app/comments.js",
     "suggestion": "buildTable 函式已在 comments.js 第 13 行定義，非未定義或未匯入，不會導致執行時錯誤"
+  },
+  {
+    "role": "Maya",
+    "location": "app/gitea.js",
+    "suggestion": "filterDiff 的單元測試已在 gitea.test.js 補齊，涵蓋過濾 .gitea/、不誤過濾其他路徑、全部排除、空 diff 四種情境"
+  },
+  {
+    "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"
   }
 ]

.gitea/ai-review/findings.json

@@ -1,16 +1,16 @@
 [
   {
-    "level": "critical",
-    "role": "Leo",
-    "location": "app/comments.js:66",
-    "suggestion": "`buildTable` 函式在此檔案中被呼叫，但未見其定義或匯入。這將導致執行時錯誤。請確保 `buildTable` 函式已被正確定義或從其他模組匯入，以確保程式碼的正確執行。",
+    "level": "warning",
+    "role": "Rex",
+    "location": "app/gitea.js:10",
+    "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，可能忘記或錯誤地應用過濾，導致 `.gitea/` 等敏感路徑的內容（可能包含工作流程設定或機密資訊）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。建議考慮將過濾邏輯保留在 `getPRDiff` 內部，或提供一個明確的 `getFilteredPRDiff` 函數，以降低誤用的風險。",
     "is_new": true
   },
   {
     "level": "warning",
-    "role": "Maya",
-    "location": "app/gitea.js:11, app/main.js:42-45",
-    "suggestion": "`filterDiff` 函數的邏輯已從正規表達式比對改為 `startsWith`，並將其呼叫從 `getPRDiff` 移至 `main.js`。雖然 `startsWith` 可能更高效精確，但這是一個行為變更與職責重分配。請確保為 `filterDiff` 函數撰寫足夠的單元測試，以驗證：\n1. 正確過濾 `.gitea/` 路徑下的檔案。\n2. 不會錯誤過濾非 `.gitea/` 路徑下的檔案。\n3. 處理空 diff 內容。\n4. 處理僅包含 `.gitea/` 檔案的 diff 內容（應返回空字串）。",
+    "role": "Zara",
+    "location": "app/git.js, app/main.js",
+    "suggestion": "在 `app/main.js` 中，`commitAndPush` 函數內部會再次呼叫 `cloneRepo`。然而，`main.js` 在此之前已經呼叫過 `cloneRepo` 以取得 `repoDir`。這導致了重複的 `git fetch` 和 `git checkout` 操作，即使 `cloneRepo` 內部有檢查機制，仍會造成不必要的資源消耗和時間延遲。建議修改 `commitAndPush` 函數，使其接收已存在的 `repoDir` 作為參數，避免重複執行 `cloneRepo`。",
     "is_new": true
   }
 ]

README.md

@@ -24,6 +24,7 @@
 6. API Key 支援逗號分隔傳入多個，隨機順序各嘗試一次，全部失敗則 exit 1
 7. 讀取 Git Diff 時排除 `.gitea/` 資料夾內的所有檔案，避免 AI 分析 workflow 設定等非業務程式碼
 8. 階段五完成後驗證 `findings.json` 與 `exclusions.json` 是否為合法 JSON 格式，格式錯誤時先嘗試重置為空陣列並備份原檔，修正失敗才 exit 1
+9. 傳給 AI 的 findings 只保留必要欄位（level、role、location、suggestion），排除 `is_new` 等內部欄位；system prompt 精簡為指令核心；exclusions hint 只傳 location 與 suggestion，減少 token 用量
 
 # 使用說明
 

TODO.md

@@ -49,3 +49,8 @@
 - 目標：所有平台的 API Key 支援逗號分隔傳入多個，隨機順序各嘗試一次，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。
 - 未驗收
+
+## 階段十一：壓縮 AI 傳入內容減少 token 用量
+- 目標：傳給 AI 的 findings 只保留必要欄位（level、role、location、suggestion）；system prompt 精簡為指令核心；exclusions hint 只傳 location 與 suggestion；AI 回傳後補回原始完整欄位（含 is_new）。
+- 驗收：AI 呼叫的 payload 不含 is_new 等內部欄位，去重與誤報過濾後的 findings 仍保有完整欄位供後續流程使用。
+- 未驗收

app/findings.js

@@ -76,22 +76,26 @@ function fallback(label, findings, e) {
   return findings;
 }
 
+/** 只保留 AI 需要的欄位，減少 token 用量 */
+function toAIPayload(findings) {
+  return findings.map(({ level, role, location, suggestion }) => ({ level, role, location, suggestion }));
+}
+
 /**
  * 呼叫 LLM 進行語意去重，失敗時降級回傳原始 findings
  */
 export async function deduplicateWithAI(findings) {
   if (findings.length === 0) return findings;
 
-  const systemPrompt = `你是一位程式碼審查問題去重專家。
-給你一份問題清單（JSON 陣列），請移除語意重複的問題（即使描述文字不同，但指的是同一個問題）。
-保留等級較高的版本，優先保留 critical > warning > info。
-只回傳去重後的 JSON 陣列，不要有其他文字。`;
+  const systemPrompt = `移除語意重複的程式碼審查問題（JSON 陣列）。保留等級較高者（critical > warning > info）。只回傳去重後的 JSON 陣列。`;
 
   try {
-    const result = await chatJSON(systemPrompt, `以下是問題清單，請去除語意重複的項目：\n\n${JSON.stringify(findings, null, 2)}`);
+    const result = await chatJSON(systemPrompt, JSON.stringify(toAIPayload(findings)));
     if (Array.isArray(result) && result.length > 0) {
       console.log(`  AI 去重: ${findings.length} -> ${result.length} 筆`);
-      return result;
+      // 以 location+suggestion 為 key，將原始 findings 的完整欄位（含 is_new）補回
+      const origMap = new Map(findings.map(f => [`${f.location}|${String(f.suggestion).slice(0, 50)}`, f]));
+      return result.map(r => origMap.get(`${r.location}|${String(r.suggestion).slice(0, 50)}`) ?? r);
     }
     throw new Error('AI 回傳空陣列');
   } catch (e) {
@@ -131,22 +135,17 @@ export async function filterFalsePositivesWithAI(findings, exclusions = []) {
   if (findings.length === 0) return findings;
 
   const exclusionHint = exclusions.length > 0
-    ? `\n\n以下是已知的誤報或不需處理的問題清單（供參考，相同檔案路徑且語意相近的問題應一併排除）：\n${JSON.stringify(exclusions, null, 2)}`
+    ? `\n已知誤報（相同路徑且語意相近者一併排除）：\n${JSON.stringify(exclusions.map(({ location, suggestion }) => ({ location, suggestion })))}`
     : '';
 
-  const systemPrompt = `你是一位資深程式碼審查專家，負責判斷審查問題是否為誤報或不需處理。
-給你一份問題清單（JSON 陣列），每筆包含 level、role、location、suggestion。
-請移除以下類型的問題：
-1. 誤報：問題描述與實際程式碼不符（例如：程式碼已正確使用環境變數或 secrets，卻被標記為硬編碼敏感資料）
-2. 不適用：問題在此專案情境下不需處理（例如：CI/CD action 本來就需要透過環境變數傳遞 token）
-3. 與已知誤報清單語意相近的問題（檔案路徑相同且建議內容相似）
-只回傳需要保留的問題 JSON 陣列，不要有其他文字。${exclusionHint}`;
+  const systemPrompt = `判斷以下程式碼審查問題是否為誤報或不適用（如已正確使用 secrets、CI/CD 必要權限等），移除後只回傳需保留的 JSON 陣列。${exclusionHint}`;
 
   try {
-    const result = await chatJSON(systemPrompt, `請判斷以下問題清單，移除誤報或不需處理的問題：\n\n${JSON.stringify(findings, null, 2)}`);
+    const result = await chatJSON(systemPrompt, JSON.stringify(toAIPayload(findings)));
     if (Array.isArray(result) && result.length > 0) {
       console.log(`  AI 誤報過濾: ${findings.length} -> ${result.length} 筆`);
-      return result;
+      const origMap = new Map(findings.map(f => [`${f.location}|${String(f.suggestion).slice(0, 50)}`, f]));
+      return result.map(r => origMap.get(`${r.location}|${String(r.suggestion).slice(0, 50)}`) ?? r);
     }
     throw new Error('AI 回傳空陣列或非陣列');
   } catch (e) {

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

@@ -6,9 +6,12 @@ const httpsAgent = GITEA_SKIP_TLS_VERIFY ? new https.Agent({ rejectUnauthorized:
 const headers = () => ({ Authorization: `token ${GITEA_TOKEN}`, 'Content-Type': 'application/json' });
 const api = (path) => `${GITEA_SERVER_URL.replace(/\/$/, '')}/api/v1${path}`;
 
+/**
+ * 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）`);