Add prompt improvement button in drawer

backend/routes/test_runs.py

@@ -15,12 +15,19 @@ from db.models import (
 )
 from db.session import get_session
 from fastapi import APIRouter, Depends, HTTPException
+from models import RuntimeModelResource
 from services.auth import require_admin
 from services.config_resolver import resolve_runtime_config
 from services.runtime_variables import DynamicVariableError, prepare_dynamic_config
 from services.realtime.launcher import validate_visual_runtime
 from services.test_case_assets import canonicalize_test_assets, image_asset_ids
 from services.test_runs.orchestrator import test_run_orchestrator
+from services.test_runs.prompt_improvement import (
+    PROMPT_IMPROVEMENT_SNAPSHOT_KEY,
+    PromptImprovementAgent,
+    PromptImprovementError,
+    public_test_run_config,
+)
 from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
 from test_schemas import (
@@ -31,6 +38,7 @@ from test_schemas import (
     BatchStartupResult,
     BatchTurnResult,
     BatchEvaluationResult,
+    PromptImprovementOut,
     TestCaseDefinition,
 )
 
@@ -92,7 +100,7 @@ async def _run_out(
         status=run.status,
         title=run.title,
         assistant_name=run.assistant_name,
-        config=dict(run.config or {}),
+        config=public_test_run_config(run.config),
         cases=cases,
         started_at=run.started_at or run.created_at,
         finished_at=run.finished_at,
@@ -245,6 +253,60 @@ async def create_test_run(
     return await _run_out(session, run)
 
 
+@router.post(
+    "/{run_id}/prompt-improvement",
+    response_model=PromptImprovementOut,
+)
+async def create_prompt_improvement(
+    run_id: str,
+    session: AsyncSession = Depends(get_session),
+):
+    run = await session.get(TestRun, run_id)
+    if run is None:
+        raise HTTPException(404, "测试运行不存在")
+    rows = (
+        await session.execute(
+            select(TestRunCase)
+            .where(TestRunCase.run_id == run.id)
+            .order_by(TestRunCase.position)
+        )
+    ).scalars().all()
+    if len(rows) != 1:
+        raise HTTPException(409, "Prompt 改进仅支持单用例测试运行")
+    run_case = rows[0]
+    if run.status != "completed" or run_case.status != "fail":
+        raise HTTPException(409, "只有已完成且断言失败的用例可以生成 Prompt 改进")
+
+    config = dict(run.config or {})
+    snapshot = config.get(PROMPT_IMPROVEMENT_SNAPSHOT_KEY)
+    if not isinstance(snapshot, dict):
+        raise HTTPException(409, "该运行缺少 Prompt 配置快照，请重新测试")
+    if snapshot.get("assistantType") != "prompt" or snapshot.get("runtimeMode") != "pipeline":
+        raise HTTPException(409, "Prompt 改进仅支持 Pipeline Prompt 助手")
+
+    evaluator_id = str(config.get("evaluatorModelResourceId") or "")
+    evaluator = await session.get(ModelResource, evaluator_id)
+    if evaluator is None or evaluator.capability != "LLM" or not evaluator.enabled:
+        raise HTTPException(422, "该运行使用的评估模型已不存在或不可用")
+    resource = RuntimeModelResource(
+        id=evaluator.id,
+        name=evaluator.name,
+        capability=evaluator.capability,
+        interface_type=evaluator.interface_type,
+        values=evaluator.values or {},
+        secrets=evaluator.secrets or {},
+        support_image_input=bool(evaluator.support_image_input),
+    )
+    try:
+        return await PromptImprovementAgent(resource).improve(
+            snapshot=snapshot,
+            case_snapshot=dict(run_case.case_snapshot or {}),
+            result=dict(run_case.result or {}),
+        )
+    except PromptImprovementError as exc:
+        raise HTTPException(exc.status_code, exc.message) from exc
+
+
 @router.get("/{run_id}", response_model=BatchRunSnapshotOut)
 async def get_test_run(
     run_id: str,