feat(app): 移除内置agents并添加CORS支持和技能上传优化

移除了agents/registry.json中的所有内置agents配置，将agents数组清空。
为web应用添加了CORS中间件支持，允许指定的前端地址跨域访问。
重构了技能上传功能，增加了LLM重写机制，自动规范化上传的技能格式。
新增了工具名称提取逻辑，从技能正文中自动识别Required Tools段落。
更新了技能学习候选者和草稿的载荷结构，添加评估报告统计信息。
修改了意图路由技能的说明，改进任务状态管理逻辑。

app-instance/backend/tests/unit/test_phase5_skills_runtime.py

@@ -184,7 +184,7 @@ def test_skill_lifecycle_publish_revision_and_rollback(tmp_path: Path) -> None:
     assert published.version == "v0002"
     assert store.get_current_version("release-checklist") == "v0002"
 
-    with pytest.raises(ValueError, match="approved"):
+    with pytest.raises(ValueError, match="submitted for review"):
         publisher.publish("release-checklist", revision.draft_id, publisher="reviewer", notes="duplicate")
 
     rolled_back = publisher.rollback("release-checklist", "v0001", actor="reviewer", reason="regression")
@@ -529,6 +529,66 @@ def test_skill_learning_service_generates_new_skill_for_task_without_published_s
     assert candidates[0].source_run_ids == ["task-run-1"]
 
 
+def test_skill_learning_service_uses_original_task_text_for_new_skill_theme(tmp_path: Path) -> None:
+    store = SkillSpecStore(tmp_path)
+    run_store = RunMemoryStore(tmp_path / "memory" / "runs")
+    learning_store = SkillLearningStore(tmp_path / "memory" / "skills")
+    service = SkillLearningService(
+        run_store=run_store,
+        learning_store=learning_store,
+        draft_service=DraftService(store),
+        evidence_selector=EvidenceSelector(run_store),
+    )
+    now = datetime.now(timezone.utc).isoformat()
+    run_store.append_run_record(
+        RunRecord(
+            run_id="task-run-1",
+            session_id="session-task",
+            task_id="task-1",
+            attempt_index=1,
+            task_text="Compare direct production restart with staging rollout",
+            started_at=now,
+            ended_at=now,
+            success=False,
+            finish_reason="stop",
+            feedback={"feedback_type": "revise", "comment": "I do not see the docs"},
+            activated_skills=[],
+            validation_result=None,
+        )
+    )
+    run_store.append_run_record(
+        RunRecord(
+            run_id="task-run-2",
+            session_id="session-task",
+            task_id="task-1",
+            attempt_index=2,
+            task_text="I do not see the docs",
+            started_at=now,
+            ended_at=now,
+            success=True,
+            finish_reason="stop",
+            feedback={"feedback_type": "satisfied", "acceptance_type": "accept"},
+            activated_skills=[],
+            validation_result={"accepted": True, "score": 0.9},
+        )
+    )
+
+    candidates = service.build_learning_candidates_for_task("task-1", trigger_run_id="task-run-2")
+
+    assert [candidate.candidate_id for candidate in candidates] == ["new:task:task-1"]
+    assert candidates[0].evidence["theme"] == "Compare direct production restart with staging rollout"
+    assert candidates[0].evidence["task_text"] == "Compare direct production restart with staging rollout"
+
+
+def test_task_theme_uses_first_sentence_for_chinese_text() -> None:
+    assert (
+        SkillLearningService._task_theme(
+            "帮我比较两种发布流程的风险：A 是直接重启线上容器，B 是先部署 staging 再切 production。请给出推荐方案、原因、验证步骤和回滚策略。"
+        )
+        == "帮我比较两种发布流程的风险：A 是直接重启线上容器，B 是先部署 staging 再切 production"
+    )
+
+
 def test_agent_loop_records_skill_receipts_and_effects(tmp_path: Path) -> None:
     skill = SkillContext(
         name="docker-debug",