test(gitea): 補 filterDiff 排除 node_modules／lock 測試

src/gitea.js

@@ -54,6 +54,9 @@ export async function getPRDiff() {
     '.github/',
     'README.md',
     'TODO.md',
+    'package-lock.json',
+    'src/package-lock.json',
+    'dist/',
   ]);
 }
 
@@ -126,13 +129,16 @@ export async function shouldSkipBotCommit({ sha = PR_HEAD_SHA || process.env.GIT
  * @param {string[]} excludePrefixes - 要排除的路徑前綴陣列（資料夾以 `/` 結尾，如 `.gitea/`）。
  * @returns {string} 過濾後重新接合的 diff 文字。
  */
-export function filterDiff(diff, excludePrefixes) {
+export function filterDiff(diff, excludePrefixes = []) {
   return diff.split(/(?=^diff --git )/m)
-    .filter(block => !excludePrefixes.some(p => {
-      const prefix = `diff --git a/${p}`;
-      const singleFile = `diff --git a/${p} b/${p}`;
-      return block.startsWith(prefix) || block.startsWith(singleFile);
-    }))
+    .filter(block => {
+      const m = block.match(/^diff --git a\/(.+?) b\//);
+      const path = m ? m[1] : '';
+      if (!path) return true;
+      // 一律排除任何深度的 node_modules：vendored 依賴不是審查對象，且會撐爆 LLM 輸入上限。
+      if (/(^|\/)node_modules\//.test(path)) return false;
+      return !excludePrefixes.some(p => path === p || path.startsWith(p));
+    })
     .join('');
 }
 

src/llm.js

@@ -39,10 +39,30 @@ function cliArgs({ provider, model, promptFile = null, prompt = null }) {
   throw new Error(`不支援的 AI 助理 CLI: ${provider}`);
 }
 
+/**
+ * 從 CLI 輸出中抽出「真正有意義的錯誤」。
+ *
+ * 像 codex 這類 CLI 會先印出一大段 banner（workdir/model/...）與回顯的 prompt，
+ * 真正的失敗原因（例如 401、token 失效、額度不足）通常落在**尾端**。直接取前段
+ * 會被 banner／prompt 洗掉，因此改為：先抽出看起來像錯誤的行；抽不到再退取尾段。
+ *
+ * @param {string} raw - CLI 的原始輸出（stderr 或 stdout）。
+ * @param {number} [limit=1000] - 回傳字串長度上限。
+ * @returns {string} 最能說明失敗原因的片段。
+ */
+export function extractMeaningfulError(raw, limit = 1000) {
+  const text = String(raw || '').trim();
+  const errorLines = text
+    .split('\n')
+    .filter(l => /\bERROR\b|error:|unauthorized|invalidated|revoked|forbidden|\b40[13]\b|rate.?limit|quota|insufficient/i.test(l));
+  const picked = (errorLines.length ? errorLines.join('\n') : text).trim();
+  return picked.length > limit ? picked.slice(-limit) : picked;
+}
+
 function summarizeCliError(e) {
   const stderr = String(e.stderr || '').trim();
   const stdout = String(e.stdout || '').trim();
-  return (stderr || stdout || e.message || String(e)).slice(0, 1000);
+  return extractMeaningfulError(stderr || stdout || e.message || String(e));
 }
 
 async function runAssistantCLI({ provider, command, model }, prompt) {

src/test/gitea.test.js

@@ -241,4 +241,21 @@ describe('filterDiff', () => {
   it('returns empty string for empty diff', () => {
     assert.equal(filterDiff('', ['.gitea/']), '');
   });
+
+  it('always drops node_modules blocks at any depth (avoids blowing the LLM input limit)', () => {
+    const diff = block('src/node_modules/axios/index.js')
+      + block('node_modules/js-yaml/lib.js')
+      + block('src/main.js');
+    const result = filterDiff(diff, []);
+    assert.ok(!result.includes('node_modules'));
+    assert.ok(result.includes('src/main.js'));
+  });
+
+  it('excludes lock files and dist via the getPRDiff prefix list', () => {
+    const diff = block('src/package-lock.json') + block('dist/index.js') + block('src/main.js');
+    const result = filterDiff(diff, ['package-lock.json', 'src/package-lock.json', 'dist/']);
+    assert.ok(!result.includes('package-lock.json'));
+    assert.ok(!result.includes('dist/'));
+    assert.ok(result.includes('src/main.js'));
+  });
 });

src/test/llm.test.js

@@ -3,7 +3,7 @@ import assert from 'node:assert/strict';
 import { mkdtemp, writeFile, chmod, rm, readFile } from 'fs/promises';
 import { tmpdir } from 'os';
 import { join } from 'path';
-import { extractBalancedJSON, extractJSONText } from '../llm.js';
+import { extractBalancedJSON, extractJSONText, extractMeaningfulError } from '../llm.js';
 
 const ENV_KEYS = [
   'AI_ASSISTANT_CLI', 'MODEL', 'OPENCODE_MODEL', 'PATH', 'AI_ASSISTANT_TIMEOUT_MS', 'AI_ASSISTANT_MAX_BUFFER',
@@ -237,3 +237,39 @@ describe('extractJSONText', () => {
     assert.equal(result, 'not json at all');
   });
 });
+
+describe('extractMeaningfulError', () => {
+  it('抽出尾端真正的錯誤，而非開頭的 codex banner／回顯 prompt', () => {
+    const raw = [
+      'OpenAI Codex v0.142.5',
+      '--------',
+      'workdir: /workspace/actions/ai-code-review',
+      'model: gpt-5.4-mini',
+      'reasoning effort: none',
+      '--------',
+      'user',
+      '請依照以下系統指示處理使用者內容，並只輸出要求的最終結果。',
+      'ERROR codex_api::endpoint::responses_websocket: failed to connect to websocket: HTTP error: 401 Unauthorized',
+      'ERROR: Your access token could not be refreshed because your refresh token was revoked. Please log out and sign in again.',
+    ].join('\n');
+
+    const result = extractMeaningfulError(raw);
+
+    assert.match(result, /401 Unauthorized/);
+    assert.match(result, /refresh token was revoked/);
+    assert.doesNotMatch(result, /workdir:/);
+    assert.doesNotMatch(result, /請依照以下系統指示/);
+  });
+
+  it('抽不到錯誤行時退取尾段（不取開頭）', () => {
+    const raw = 'A'.repeat(1200) + '\nTAIL-CONTENT';
+    const result = extractMeaningfulError(raw, 100);
+    assert.ok(result.length <= 100);
+    assert.match(result, /TAIL-CONTENT$/);
+  });
+
+  it('容錯處理空輸入', () => {
+    assert.equal(extractMeaningfulError(''), '');
+    assert.equal(extractMeaningfulError(null), '');
+  });
+});