fix: prevent false timeout failures and release 1.2.2

Package a clean shallow main checkout with credential-free Gitea remote, localize the China launcher, and set the new-install Responses endpoint.

.env.example

@@ -2,10 +2,12 @@
 # 所有模型调用仅使用 OpenAI Responses API；环境变量优先于 .env。
 OPENAI_API_KEY=
 # 接口根地址：通常以 /v1 结尾，不要添加 /responses 或 /chat/completions。
-OPENAI_BASE_URL=https://api.openai.com/v1
+OPENAI_BASE_URL=https://api-n-cd.playones.com/v1
 OPENAI_MODEL=mimo-v2.6-flash
 # 单次模型 HTTP 请求超时（秒）
 OPENAI_TIMEOUT_SECONDS=300
+# 可选的后台步骤截图摘要单次超时，独立于上面的主模型请求超时。
+ARTEMIS_STEP_SUMMARIZER_TIMEOUT_SECONDS=25
 # 失败后最多重试 5 次，由 Artemis 统一管理，SDK 不叠加重试。
 OPENAI_MAX_RETRIES=5
 OPENAI_RETRY_INTERVAL_SECONDS=10
@@ -19,6 +21,8 @@ ARTEMIS_OUTPUTTER_ENABLED=true
 ARTEMIS_STEP_SUMMARIZER_ENABLED=true
 # Pro 连续无工具调用或参数校验失败的最大次数；耗尽后明确失败，避免空转。
 ARTEMIS_OPERATOR_MAX_NO_PROGRESS_ATTEMPTS=3
+# Flash 连续无工具调用的最大次数；无效回复不会重复送回模型。
+ARTEMIS_FLASH_MAX_NO_PROGRESS_ATTEMPTS=3
 
 # 视频分段、重试与单次分析超时（秒）
 ARTEMIS_VIDEO_CHUNK_SECONDS=60

README.md

@@ -12,7 +12,7 @@
 
 ## 安装与启动
 
-准备一台开启 USB 调试并完成授权的 Android 手机，或已启动的 Android 模拟器。首次安装需要联网，建议使用 Git 克隆以支持后续更新。
+准备一台开启 USB 调试并完成授权的 Android 手机，或已启动的 Android 模拟器。首次安装需要联网。可使用 Git 克隆或下载 1.1.1 及更新版本的发布源码包；新版 ZIP 解压后也保留 Git 更新能力。
 
 ### Windows
 
@@ -24,14 +24,15 @@ cd Artemis-Eapil
 .\start.bat
 ```
 
-国内网络使用 `.\start-cn.bat`。启动脚本会检测并安装缺少的 uv、Python 和所需工具，创建或复用 `.venv`，同步依赖并构建网页。启动后访问 **http://127.0.0.1:8000**。
+国内网络使用 `.\start-cn.bat`，支持 `-Help` 查看中文选项。启动脚本会检测并安装缺少的 uv、Python 和所需工具，创建或复用 `.venv`，同步依赖并构建网页。启动后访问 **http://127.0.0.1:8000**。
 
 常用选项：
 
 ```powershell
-.\start-cn.bat -SetupOnly   # 仅准备 Python 环境并检查已有 MCP 配置
+.\start-cn.bat -SetupOnly   # 准备环境并安装/更新已检测客户端的 MCP
 .\start.bat -Port 8001      # 指定端口
 .\start.bat -SkipUpdate     # 跳过 Git 源码更新检查
+.\start.bat -SkipMcpSync    # MCP 配置异常时，仅启动网页
 ```
 
 镜像与下载超时在 [config/downloads.json](config/downloads.json) 中设置。国内脚本使用山东大学镜像安装 scrcpy，并校验官方 SHA256；也可预先安装或自定义 HTTPS 下载地址。
@@ -49,19 +50,19 @@ cd Artemis-Eapil
 
 预设模型为 `gpt-5.6-luna`、`mimo-v2.6-flash`，也可填写自定义名称。默认模型是 `mimo-v2.6-flash`，思考强度默认 `high`（最高可选 `max`），单次请求超时 **300 秒**，失败后最多重试 **5 次**，间隔 **10 秒**；视频分析与录屏默认关闭。模型及思考参数是否可用取决于所配置网关；不支持时会明确报错。
 
-也可在项目 `.env` 中设置 `OPENAI_API_KEY`、`OPENAI_BASE_URL` 和 `OPENAI_MODEL`，其他参数见 [.env.example](.env.example)。直接编辑环境文件后需重启相应服务。不要提交自己的密钥。
+也可在项目 `.env` 中设置 `OPENAI_API_KEY`、`OPENAI_BASE_URL` 和 `OPENAI_MODEL`，其他参数见 [.env.example](.env.example)。新安装默认接口地址为 `https://api-n-cd.playones.com/v1`；已保存的地址不变。直接编辑环境文件后需重启相应服务。不要提交自己的密钥。
 
 报告会区分“执行完成”和“验证通过”；没有验证证据的结果标为“未验证”。任务步骤与截图可查看，设备动作回放不提供。
 
 ## 让 AI 使用
 
-环境与模型配置完成后，例如为 Codex 接入 MCP：
+Windows 启动脚本会为已检测到的 AI 客户端安装或更新 MCP。未被检测到的客户端，可手动安装，例如 Codex：
 
 ```sh
 uv run artemis mcp --install codex
 ```
 
-在客户端重新加载 MCP，并按 [AI 接入指南](docs/ai-automation.md) 安装仓库中的 [artemis-automation Skill](skills/artemis-automation/SKILL.md)。Skill 不会随启动脚本自动安装到用户全局目录。其他客户端可通过 `uv run artemis mcp --help` 查看接入方式。
+安装或更新后，在客户端重新加载 MCP 或重启客户端，并按 [AI 接入指南](docs/ai-automation.md) 安装仓库中的 [artemis-automation Skill](skills/artemis-automation/SKILL.md)。Skill 不会随启动脚本自动安装到用户全局目录。其他客户端可通过 `uv run artemis mcp --help` 查看接入方式。
 
 示例指令：
 
@@ -69,9 +70,9 @@ uv run artemis mcp --install codex
 
 ## 更新与排错
 
-Windows 用户再次运行一键脚本时，会先检查 Git 上游；即使 `start.bat` 或 `start-cn.bat` 本身被更新，也会重新启动新版脚本，再检查项目依赖、前端构建和已有 MCP 配置。源码只做快进更新。本地修改、分支分叉或网络认证失败时保留本地版本；有任务执行或排队时停止更新启动。更新后需在 AI 客户端重新加载 MCP。
+Windows 用户再次运行一键脚本时，会先检查 Git 上游；即使 `start.bat` 或 `start-cn.bat` 本身被更新，也会重新启动新版脚本，再检查项目依赖、前端构建并同步已检测客户端的 MCP。源码只做快进更新。本地修改、分支分叉或网络认证失败时保留本地版本；有任务执行或排队时停止更新启动。MCP 配置同步失败会明确停止启动，可使用 `-SkipMcpSync` 仅启动网页。更新后需在 AI 客户端重新加载 MCP。
 
-ZIP 安装可继续运行；需要自动拉取源码时，请改用 Git 克隆安装。遇到启动或设备问题，在项目目录运行 `uv run artemis doctor`。
+1.1.1 及更新版本的发布 ZIP 含浅层 Git 工作树，解压后再次运行一键脚本即可检查更新。1.1.0 及更早 ZIP 不含 Git 信息，无法自行拉取；需要下载新版源码包重新解压一次，之后即可自动更新。遇到启动或设备问题，在项目目录运行 `uv run artemis doctor`。
 
 更多说明：[批量任务与报告](docs/automation-workspace.md) · [AI 接入](docs/ai-automation.md) · [开发协作指南](AGENTS.md)
 

apps/admin_console/routers/automation.py

@@ -128,7 +128,7 @@ def delete_batch(batch_id: str):
     except ValueError as exc:
         raise HTTPException(400, str(exc)) from exc
     try:
-        if not store.delete_batch(key):
+        if not service.delete_batch(key):
             raise HTTPException(404, "批次不存在")
     except ValueError as exc:
         raise HTTPException(409, str(exc)) from exc
@@ -166,7 +166,8 @@ async def download_report(
     try:
         if fmt in {"screenshots", "video", "all"}:
             path = await asyncio.to_thread(report_export.export_session_media, session_id, fmt)
-            return FileResponse(path, filename=f"任务{session_id[:8]}-{fmt}.zip")
+            label = report_export.archive_case_name(report_export.session_report(session_id))
+            return FileResponse(path, filename=f"{label}-{fmt}.zip")
         paths = await asyncio.to_thread(report_export.export_session, session_id, [fmt])
         return FileResponse(paths[0], filename=f"任务报告-{session_id[:8]}.{fmt}")
     except ValueError as exc:
@@ -184,13 +185,15 @@ def history(
 ):
     # SQL filtering/pagination searches the entire persisted history, not a UI cache.
     query = """WITH history AS (
-      SELECT s.session_id, s.initial_goal, s.start_time, s.end_time,
+      SELECT s.session_id, s.initial_goal, s.start_time,
+        COALESCE(json_extract(j.payload,'$.ended_at'),s.end_time) end_time,
         COALESCE(j.status,s.status) status, COALESCE(json_extract(j.payload,'$.case.name'),s.initial_goal) name,
         COALESCE(json_extract(j.payload,'$.case.tags'),'') tags,
         COALESCE(json_extract(j.payload,'$.case.case_id'),'') case_id,
         COALESCE(json_extract(j.payload,'$.case.category'),'') category,
         COALESCE(json_extract(j.payload,'$.case.subcategory'),'') subcategory,
-        COALESCE(json_extract(j.payload,'$.case.preconditions'),'') preconditions
+        COALESCE(json_extract(j.payload,'$.case.preconditions'),'') preconditions,
+        COALESCE(json_extract(j.payload,'$.error'),'') error
       FROM sessions s LEFT JOIN automation_jobs j ON s.session_id=j.session_id
       UNION ALL
       SELECT j.session_id,json_extract(j.payload,'$.case.goal'),
@@ -200,7 +203,8 @@ def history(
         COALESCE(json_extract(j.payload,'$.case.case_id'),''),
         COALESCE(json_extract(j.payload,'$.case.category'),''),
         COALESCE(json_extract(j.payload,'$.case.subcategory'),''),
-        COALESCE(json_extract(j.payload,'$.case.preconditions'),'')
+        COALESCE(json_extract(j.payload,'$.case.preconditions'),''),
+        COALESCE(json_extract(j.payload,'$.error'),'')
       FROM automation_jobs j WHERE NOT EXISTS (SELECT 1 FROM sessions s WHERE s.session_id=j.session_id)
     ) """
     where = " WHERE status IN ('completed','success','failed','cancelled','interrupted','skipped')"
@@ -226,4 +230,8 @@ def history(
             + " ORDER BY start_time DESC,session_id LIMIT ? OFFSET ?",
             [*args, size, (page - 1) * size],
         ).fetchall()
-    return {"items": [dict(r) for r in rows], "total": total, "page": page, "size": size}
+    items = [dict(row) for row in rows]
+    for item in items:
+        if item["case_id"]:
+            item["name"] = task_import.case_title(item)
+    return {"items": items, "total": total, "page": page, "size": size}

apps/admin_console/routers/sessions.py

@@ -27,12 +27,16 @@ try:
     from admin_console.database.repositories.trace_repository import trace_repo
     from admin_console.services.media_service import media_service
     from admin_console.services.model_service import model_service
+    from admin_console.services.automation_store import store
+    from admin_console.services.task_import import case_title
 except ImportError:
     from apps.admin_console.core.state import state
     from apps.admin_console.database.repositories.session_repository import session_repo
     from apps.admin_console.database.repositories.trace_repository import trace_repo
     from apps.admin_console.services.media_service import media_service
     from apps.admin_console.services.model_service import model_service
+    from apps.admin_console.services.automation_store import store
+    from apps.admin_console.services.task_import import case_title
 
 
 router = APIRouter(tags=["sessions"])
@@ -52,6 +56,7 @@ async def list_sessions():
 
 def _list_sessions_sync():
     rows = session_repo.get_all_sessions()
+    jobs_by_id = store.jobs_for_sessions([str(row.get("session_id")) for row in rows])
     video_rec_map = session_repo.get_video_recordings_map()
     latest_recordings = session_repo.get_latest_video_recordings_map()
     agent_names_by_session = session_repo.get_agent_trace_names_map()
@@ -74,6 +79,15 @@ def _list_sessions_sync():
 
     for row_dict in rows:
         s_id = str(row_dict.get("session_id"))
+        job = jobs_by_id.get(s_id)
+        if job:
+            case = job.get("case") or {}
+            row_dict["case_id"] = case.get("case_id") or ""
+            row_dict["display_name"] = case_title(case) or row_dict.get("initial_goal")
+            row_dict["error"] = job.get("error") or ""
+            if job.get("status") in {"completed", "failed", "cancelled", "interrupted", "skipped"}:
+                row_dict["status"] = job["status"]
+                row_dict["end_time"] = job.get("ended_at") or row_dict.get("end_time")
         recording = latest_recordings.get(s_id)
         d_info_raw = row_dict.get("device_info")
         device_id = None

apps/admin_console/services/automation_service.py

@@ -3,11 +3,13 @@
 import asyncio
 import logging
 import os
+import shutil
 import time
+from uuid import UUID
 
 from apps.admin_console.core.state import state
 from apps.admin_console.services.automation_store import store, new_id
-from apps.admin_console.services.task_import import case_goal
+from apps.admin_console.services.task_import import case_goal, case_title
 
 logger = logging.getLogger(__name__)
 TERMINAL = {"completed", "failed", "cancelled", "skipped", "interrupted"}
@@ -82,9 +84,9 @@ async def on_terminal(item: dict, status: str):
         job = store.job(sid)
     if job is None:
         raise RuntimeError("任务元数据写入失败")
-    job.update(status="finalizing", ended_at=time.time())
     if job.get("timed_out"):
         status = "failed"
+    job.update(status="finalizing", terminal_status=status, ended_at=time.time())
     store.save_job(job)
     try:
         job["status"] = status
@@ -99,7 +101,9 @@ async def on_terminal(item: dict, status: str):
             }
         ):
             job["status"] = "failed"
-            job["error"] = "任务执行结束，但业务检查未通过"
+            job["error"] = job.get("error") or "任务执行结束，但业务检查未通过"
+        elif job["status"] == "failed" and report.get("error") and not job.get("error"):
+            job["error"] = report["error"]
         # Persist terminal classification before export, but the coordinator waits for finalization.
         store.save_job({**job, "status": "finalizing", "terminal_status": job["status"]})
         await asyncio.to_thread(export_session, sid, job["formats"])
@@ -107,6 +111,7 @@ async def on_terminal(item: dict, status: str):
     except Exception as exc:
         logger.exception("Report finalization failed for %s", sid)
         job["report_error"] = str(exc)[:500]
+    job.pop("terminal_status", None)
     store.save_job(job)
 
 
@@ -125,6 +130,11 @@ async def tick_batches():
                 batch.update(status="paused", reason="模型请求已暂停，请先恢复模型连接再继续批次")
                 store.put("batch", batch["id"], batch)
             for job in active:
+                # The queue records started_at at submission, then replaces it
+                # when the worker actually starts. Waiting for a device must
+                # not consume this case's execution budget.
+                if job["status"] != "running":
+                    continue
                 limit = int(
                     (job.get("case", {}).get("task_config") or {}).get("timeout_seconds")
                     or batch.get("timeout_seconds", 1800)
@@ -134,15 +144,16 @@ async def tick_batches():
                 if task_state.get("non_execution_started_at"):
                     excluded += time.time() - float(task_state["non_execution_started_at"])
                 if (
-                    job["status"] != "finalizing"
+                    not job.get("timed_out")
-                    and not job.get("timed_out")
                     and time.time() - job.get("started_at", time.time()) - excluded > limit
                 ):
-                    job.update(error="任务达到批次配置的执行时限", timed_out=True)
+                    job.update(
+                        error=f"任务执行超时（{limit} 秒，不含暂停/排队时间）", timed_out=True
+                    )
                     store.save_job(job)
                     task_queue_service.stop_tasks(session_id=job["session_id"])
-                    batch.update(status="paused", reason="任务超时，已暂停剩余任务；请确认设备状态")
+                    # on_terminal records the failed case. The next pending
-                    store.put("batch", batch["id"], batch)
+                    # case then runs normally unless stop_on_failure is set.
             continue
         if batch["status"] != "running":
             continue
@@ -202,6 +213,7 @@ async def tick_batches():
                 runtime_overrides=options,
                 session_id=job["session_id"],
                 ingress="batch",
+                display_name=case_title(job["case"]),
             )
             if response.get("status") == "rejected" or not response.get("tasks"):
                 raise ValueError(response.get("error") or "队列拒绝接收任务")
@@ -265,6 +277,35 @@ def create_batch(payload: dict) -> dict:
     return store.create_batch(batch, jobs, payload)
 
 
+def delete_batch(batch_id: str) -> bool:
+    """Delete an inactive batch, its sessions and its generated reports."""
+    from artemis.data_engine.storage import StorageManager
+    from apps.admin_console.services import report_export
+
+    jobs = store.begin_delete_batch(batch_id)
+    if jobs is None:
+        return False
+    storage = StorageManager(store.path, report_export.TRACES_PATH)
+    mcp_exports = report_export.EXPORT_ROOT.parent / "mcp_exports"
+    with report_export.EXPORT_LOCK:
+        for job in jobs:
+            session_id = str(UUID(job["session_id"]))
+            storage.delete_session(UUID(session_id))
+            report_dir = report_export.EXPORT_ROOT / "sessions" / session_id
+            if report_dir.is_dir():
+                shutil.rmtree(report_dir)
+            mcp_session_dir = mcp_exports / "sessions" / session_id
+            if mcp_session_dir.is_dir():
+                shutil.rmtree(mcp_session_dir)
+        batch_dir = report_export.EXPORT_ROOT / "batches" / batch_id
+        if batch_dir.is_dir():
+            shutil.rmtree(batch_dir)
+        mcp_batch_dir = mcp_exports / "batches" / batch_id
+        if mcp_batch_dir.is_dir():
+            shutil.rmtree(mcp_batch_dir)
+        return store.delete_batch(batch_id)
+
+
 def batch_action(batch_id: str, action: str) -> dict:
     batch = store.get("batch", batch_id)
     if not batch:

apps/admin_console/services/automation_store.py

@@ -54,6 +54,13 @@ class AutomationStore:
 
     def put(self, kind: str, key: str, payload: dict) -> dict:
         with self.connection() as conn:
+            if kind == "batch":
+                conn.execute("BEGIN IMMEDIATE")
+                row = conn.execute(
+                    "SELECT payload FROM automation_records WHERE kind='batch' AND id=?", (key,)
+                ).fetchone()
+                if row is None or json.loads(row[0]).get("status") == "deleting":
+                    raise ValueError("批次正在删除或已删除，不能继续更新")
             conn.execute(
                 "INSERT INTO automation_records VALUES (?,?,?,?) ON CONFLICT(kind,id) DO UPDATE SET payload=excluded.payload,updated_at=excluded.updated_at",
                 (kind, key, json.dumps(payload, ensure_ascii=False), time.time()),
@@ -78,6 +85,14 @@ class AutomationStore:
 
     def save_job(self, payload: dict) -> dict:
         with self.connection() as conn:
+            conn.execute("BEGIN IMMEDIATE")
+            if batch_id := payload.get("batch_id"):
+                row = conn.execute(
+                    "SELECT payload FROM automation_records WHERE kind='batch' AND id=?",
+                    (batch_id,),
+                ).fetchone()
+                if row is None or json.loads(row[0]).get("status") == "deleting":
+                    raise ValueError("批次正在删除，不能继续派发任务")
             conn.execute(
                 "INSERT INTO automation_jobs VALUES (?,?,?,?,?,?) ON CONFLICT(session_id) DO UPDATE SET payload=excluded.payload,status=excluded.status,updated_at=excluded.updated_at",
                 (
@@ -106,6 +121,25 @@ class AutomationStore:
             )
         return [{**json.loads(row[0]), "status": row[1]} for row in rows]
 
+    def jobs_for_sessions(self, session_ids: list[str]) -> dict[str, dict]:
+        """Load only metadata belonging to the sessions shown in history."""
+        result = {}
+        with self.connection() as conn:
+            for offset in range(0, len(session_ids), 400):
+                chunk = session_ids[offset : offset + 400]
+                markers = ",".join("?" for _ in chunk)
+                rows = conn.execute(
+                    f"SELECT session_id,payload,status FROM automation_jobs WHERE session_id IN ({markers})",
+                    chunk,
+                ).fetchall()
+                result.update(
+                    {
+                        row["session_id"]: {**json.loads(row["payload"]), "status": row["status"]}
+                        for row in rows
+                    }
+                )
+        return result
+
     def preferences(self) -> dict:
         return self.get("settings", "reports") or {"formats": ["docx", "xlsx"]}
 
@@ -164,8 +198,38 @@ class AutomationStore:
             conn.commit()
         return batch
 
+    def begin_delete_batch(self, batch_id: str) -> list[dict] | None:
+        """Reserve an inactive batch for cleanup before any more jobs can start."""
+        with self.connection() as conn:
+            conn.execute("BEGIN IMMEDIATE")
+            row = conn.execute(
+                "SELECT payload FROM automation_records WHERE kind='batch' AND id=?",
+                (batch_id,),
+            ).fetchone()
+            if row is None:
+                return None
+            batch = json.loads(row[0])
+            active = conn.execute(
+                "SELECT 1 FROM automation_jobs WHERE batch_id=? AND status IN "
+                "('queued','running','task_paused','resuming','finalizing') LIMIT 1",
+                (batch_id,),
+            ).fetchone()
+            if batch["status"] == "running" or active:
+                raise ValueError("批次仍有任务执行中或排队中，请等待完成后删除")
+            batch["status"] = "deleting"
+            conn.execute(
+                "UPDATE automation_records SET payload=?,updated_at=? WHERE kind='batch' AND id=?",
+                (json.dumps(batch, ensure_ascii=False), time.time(), batch_id),
+            )
+            jobs = conn.execute(
+                "SELECT payload,status FROM automation_jobs WHERE batch_id=? ORDER BY position",
+                (batch_id,),
+            ).fetchall()
+            conn.commit()
+        return [{**json.loads(job[0]), "status": job[1]} for job in jobs]
+
     def delete_batch(self, batch_id: str) -> bool:
-        """Remove a batch record; retain executed job metadata and its reports."""
+        """Remove a batch record and all of its jobs after cleanup."""
         with self.connection() as conn:
             conn.execute("BEGIN IMMEDIATE")
             row = conn.execute(
@@ -175,17 +239,9 @@ class AutomationStore:
             if row is None:
                 return False
             batch = json.loads(row[0])
-            active = conn.execute(
+            if batch.get("status") != "deleting":
-                "SELECT 1 FROM automation_jobs WHERE batch_id=? AND status IN "
+                raise ValueError("批次尚未准备删除")
-                "('queued','running','task_paused','resuming','finalizing') LIMIT 1",
+            conn.execute("DELETE FROM automation_jobs WHERE batch_id=?", (batch_id,))
-                (batch_id,),
-            ).fetchone()
-            if batch["status"] == "running" or active:
-                raise ValueError("批次仍有任务执行中或排队中，请等待完成后删除")
-            conn.execute(
-                "DELETE FROM automation_jobs WHERE batch_id=? AND status='pending'",
-                (batch_id,),
-            )
             conn.execute(
                 "DELETE FROM automation_records WHERE kind='batch' AND id=?",
                 (batch_id,),

apps/admin_console/services/model_settings_service.py

@@ -16,7 +16,7 @@ _write_lock = threading.Lock()
 
 
 class ModelSettingsUpdate(BaseModel):
-    base_url: str = "https://api.openai.com/v1"
+    base_url: str = "https://api-n-cd.playones.com/v1"
     model: str = Field(min_length=1, max_length=200)
     api_key: SecretStr | None = None  # Omitted/blank keeps the existing key.
     timeout_seconds: float = Field(default=300, gt=0, le=3600)
@@ -41,7 +41,7 @@ class ModelSettingsUpdate(BaseModel):
         ):
             raise ValueError("请输入有效的 HTTP(S) 接口根地址，不要包含密钥、查询参数或片段")
         if value.endswith(("/responses", "/chat/completions")):
-            raise ValueError("请输入接口根地址，例如 https://api.openai.com/v1")
+            raise ValueError("请输入接口根地址，例如 https://api-n-cd.playones.com/v1")
         return value
 
     @field_validator("model")
@@ -57,7 +57,7 @@ def get_model_settings() -> dict:
     return {
         "provider": "openai",
         "api_mode": "responses",
-        "base_url": settings.OPENAI_BASE_URL or "https://api.openai.com/v1",
+        "base_url": settings.OPENAI_BASE_URL or "https://api-n-cd.playones.com/v1",
         "model": settings.OPENAI_MODEL,
         "api_key_configured": bool(settings.OPENAI_API_KEY),
         "timeout_seconds": settings.OPENAI_TIMEOUT_SECONDS,

apps/admin_console/services/report_export.py

@@ -22,6 +22,7 @@ from artemis.config import IMAGES_DIR, TRACES_PATH, WORKSPACE_ROOT
 from apps.admin_console.database.repositories.session_repository import SessionRepository
 from apps.admin_console.database.repositories.step_repository import StepRepository
 from apps.admin_console.services.automation_store import store, identifier
+from apps.admin_console.services.task_import import case_title
 
 EXPORT_ROOT = WORKSPACE_ROOT / "artifacts" / "reports"
 EXPORT_LOCK = threading.RLock()
@@ -40,6 +41,14 @@ STATUS = {
 }
 
 
+def archive_case_name(report: dict) -> str:
+    """Keep case identifiers readable without allowing ZIP paths or Windows-invalid names."""
+    fallback = str(report.get("id") or "task")[:8]
+    candidate = str(report.get("case_id") or fallback).strip()
+    candidate = re.sub(r'[\\/:*?"<>|\x00-\x1f]', "_", candidate).strip(" .")
+    return candidate[:80] or fallback
+
+
 def read_json(path: Path, fallback=None):
     try:
         return json.loads(path.read_text(encoding="utf-8"))
@@ -83,19 +92,49 @@ def failure_reason(directory: Path, status: str, recorded: str | None) -> str:
         return redact(recorded)
     if status not in {"failed", "interrupted"}:
         return ""
+    state = read_json(directory / "status.json", {})
+    if isinstance(state, dict) and state.get("error"):
+        return redact(state["error"])
+    log_lines: list[str] = []
     for name in ("stdout.log", "stderr.log"):
         path = directory / name
         try:
             with path.open("rb") as stream:
                 stream.seek(0, 2)
                 stream.seek(max(0, stream.tell() - 131072))
-                lines = stream.read().decode("utf-8", errors="replace").splitlines()
+                log_lines.extend(stream.read().decode("utf-8", errors="replace").splitlines())
         except OSError:
             continue
-        for line in reversed(lines):
+    for line in reversed(log_lines):
         match = re.search(r"Error running automation:\s*(.+)", line)
         if match:
             return redact(match.group(1))
+    for line in reversed(log_lines):
+        stripped = line.strip()
+        if stripped.startswith(("⚠", "ℹ", "WARNING", "INFO", "DEBUG")):
+            continue
+        if any(
+            name in line
+            for name in (
+                "VisualStepSummarizer:",
+                "StepMemoryService:",
+                "Could not clean unowned screen wake locks",
+            )
+        ):
+            continue
+        exception_line = re.fullmatch(
+            r"(?:[A-Za-z_]\w*\.)*[A-Za-z_]\w*(?:Error|Exception|Timeout):\s*.*",
+            stripped,
+        )
+        if exception_line and not re.search(r"(?i)(?:timeout|timed out|超时)", stripped):
+            return redact(stripped)
+        if re.search(
+            r"(?i)(?:\b(?:TimeoutError|APITimeoutError|ReadTimeout|ConnectTimeout)\s*:|"
+            r"(?:模型请求|任务执行|model request|task execution).{0,100}"
+            r"(?:超时|timed out|deadline exceeded))",
+            stripped,
+        ):
+            return redact("模型请求或任务执行超时：" + stripped)
     return "任务未完成，运行日志中没有可提取的具体异常；请查看执行步骤。"
 
 
@@ -142,7 +181,7 @@ def session_report(session_id: str, db_path=None) -> dict:
         )
     return {
         "id": session_id,
-        "name": case.get("name") or session.get("initial_goal", session_id)[:120],
+        "name": case_title(case) or session.get("initial_goal", session_id)[:120],
         "goal": case.get("goal") or session.get("initial_goal", ""),
         "expected": case.get("expected", ""),
         "status": status,
@@ -638,15 +677,18 @@ def export_session_media(session_id: str, kind: str) -> Path:
             "videos": [name for _, name in videos],
             "note": "录屏按时间顺序分段；暂停期间未占用设备，也未录制其他任务。",
         }
+        prefix = archive_case_name(report) + "/" if kind == "all" else ""
         with zipfile.ZipFile(temporary, "w", zipfile.ZIP_DEFLATED) as archive:
             if kind == "all":
                 for path in export_session(session_id, ["docx", "xlsx"]):
-                    archive.write(path, path.name)
+                    archive.write(path, prefix + path.name)
             for source, name in images:
-                archive.write(source, f"步骤截图/{name}")
+                archive.write(source, f"{prefix}步骤截图/{name}")
             for source, name in videos:
-                archive.write(source, f"任务录屏/{name}")
+                archive.write(source, f"{prefix}任务录屏/{name}")
-            archive.writestr("文件清单.json", json.dumps(manifest, ensure_ascii=False, indent=2))
+            archive.writestr(
+                prefix + "文件清单.json", json.dumps(manifest, ensure_ascii=False, indent=2)
+            )
         temporary.replace(target)
         return target
 
@@ -691,6 +733,8 @@ def export_batch(batch_id: str) -> Path:
                 archive.write(path, path.name)
             for number, report in enumerate(records, 1):
                 for path in export_session(report["id"], formats):
-                    archive.write(path, f"任务报告/{number:04d}_{report['id']}/{path.name}")
+                    archive.write(
+                        path, f"任务报告/{number:04d}_{archive_case_name(report)}/{path.name}"
+                    )
         temporary.replace(target)
         return target

apps/admin_console/services/task_import.py

@@ -177,3 +177,10 @@ def parse_workbook(data: bytes) -> dict:
 def case_goal(case: dict) -> str:
     """Execution gets the prompt verbatim; metadata stays outside model input."""
     return case["goal"]
+
+
+def case_title(case: dict) -> str:
+    """Human-facing title; never prepend metadata to the model prompt."""
+    case_id = str(case.get("case_id") or "").strip()
+    name = str(case.get("name") or "").strip()
+    return " ".join(part for part in (case_id, name) if part)

apps/admin_console/services/task_queue_service.py

@@ -1133,6 +1133,7 @@ class TaskQueueService:
         verification_level: str | None = None,
         explorer_mode: str | None = None,
         runtime_overrides: dict[str, Any] | None = None,
+        display_name: str | None = None,
     ) -> dict[str, Any]:
         """Enqueues one or more goals and wakes up the background worker.
 
@@ -1189,6 +1190,8 @@ class TaskQueueService:
             )
             if runtime_overrides:
                 task_item["runtime_overrides"] = runtime_overrides
+            if display_name:
+                task_item["display_name"] = display_name
             state.queue_items.append(task_item)
             enqueued_tasks.append(task_item)
             cls._broadcast_startup_progress(

apps/showcase_ui/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "artemis-showcase-ui",
-  "version": "1.1.0",
+  "version": "1.2.2",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "artemis-showcase-ui",
-      "version": "1.1.0",
+      "version": "1.2.2",
       "dependencies": {
         "@angular/cdk": "^22.1.5",
         "@angular/common": "^22.1.4",

apps/showcase_ui/package.json

@@ -1,6 +1,6 @@
 {
   "name": "artemis-showcase-ui",
-  "version": "1.1.0",
+  "version": "1.2.2",
   "scripts": {
     "ng": "ng",
     "start": "ng serve --proxy-config proxy.conf.json",

apps/showcase_ui/src/app/components/agent-stream/agent-stream.component.html

@@ -76,6 +76,7 @@ limitations under the License.
             class="dropdown-item-card"
             [class.selected]="agentService.currentSessionId() === session.session_id"
             [class.running]="getTaskStatus(session) === 'running'"
+            [ngClass]="getTaskStatus(session)"
             (click)="selectTask(session.session_id, $event)"
             >
             <div class="item-header">
@@ -96,7 +97,7 @@ limitations under the License.
                   <span class="item-time-divider">·</span>
                 }
                 <span class="item-time">{{ session.start_time * 1000 | date:'shortTime' }}</span>
-                @if (getTaskStatus(session) === 'running' || getTaskStatus(session) === 'paused') {
+                @if (['running', 'paused', 'task_paused', 'resuming'].includes(getTaskStatus(session))) {
                   <button
                     type="button"
                     class="btn-stop-card"
@@ -107,7 +108,7 @@ limitations under the License.
                     <span class="material-symbols-outlined">stop_circle</span>
                   </button>
                 }
-                @if (getTaskStatus(session) !== 'running' && getTaskStatus(session) !== 'paused') {
+                @if (!['running', 'paused', 'task_paused', 'resuming'].includes(getTaskStatus(session))) {
                   <button
                     type="button"
                     class="btn-delete-card"
@@ -120,12 +121,15 @@ limitations under the License.
                 }
               </div>
             </div>
-            <div class="item-goal" title="{{ session.initial_goal }}">
+            <div class="item-goal" [title]="session.initial_goal || ''">
-              {{ session.initial_goal || '未命名任务' }}
+              {{ session.display_name || session.initial_goal || '未命名任务' }}
             </div>
+            @if (session.error && getTaskStatus(session) === 'failed') {
+              <div class="item-error" [title]="session.error">{{session.error}}</div>
+            }
             <div class="item-footer">
               <app-task-id-copy [taskId]="session.session_id" />
-              <span class="item-date">{{ session.start_time * 1000 | date:'MM/dd/yy' }}</span>
+              <span class="item-date">{{ session.start_time * 1000 | date:'MM/dd/yy' }} · 已用 {{ formatTaskDuration(session.start_time, session.end_time) }}</span>
             </div>
           </div>
         }

apps/showcase_ui/src/app/components/agent-stream/agent-stream.component.scss

@@ -3684,6 +3684,12 @@ $stream-row-height: 25px;
     &.running {
       border-left: 3.5px solid #2563eb;
     }
+    &.paused, &.task_paused { border-left: 3.5px solid #d97706; background: #fffbeb; }
+    &.resuming, &.queued { border-left: 3.5px solid #7c3aed; }
+    &.failed { border-left: 3.5px solid #dc2626; background: #fff7f7; }
+    &.completed { border-left: 3.5px solid #16a34a; }
+    &.cancelled, &.interrupted { border-left: 3.5px solid #ea580c; }
+    .item-error { color: #b91c1c; font-size: 11px; line-height: 1.4; overflow-wrap: anywhere; }
 
     .item-header {
       display: flex;
@@ -3729,12 +3735,24 @@ $stream-row-height: 25px;
           border-color: #fdba74;
           &::before { background-color: #f97316; }
         }
+        &.task_paused {
+          background: #ffedd5;
+          color: #9a3412;
+          border-color: #fb923c;
+          &::before { background-color: #ea580c; }
+        }
+        &.resuming, &.queued {
+          background: #f3e8ff;
+          color: #6b21a8;
+          border-color: #c4b5fd;
+          &::before { background-color: #7c3aed; }
+        }
         &.completed {
-          background: #fafafa;
+          background: #dcfce7;
-          color: #1f1f1f;
+          color: #166534;
-          border-color: #e2e8f0;
+          border-color: #86efac;
           &::before {
-            background-color: #1f1f1f;
+            background-color: #16a34a;
           }
         }
         &.pending {
@@ -3746,21 +3764,22 @@ $stream-row-height: 25px;
           }
         }
         &.failed {
-          background: #fafafa;
+          background: #fee2e2;
-          color: #ef4444;
+          color: #991b1b;
-          border-color: #fee2e2;
+          border-color: #fca5a5;
           &::before {
             background-color: #ef4444;
           }
         }
         &.cancelled {
-          background: #fafafa;
+          background: #ffedd5;
-          color: #d97706;
+          color: #9a3412;
-          border-color: #fef3c7;
+          border-color: #fdba74;
           &::before {
-            background-color: #f59e0b;
+            background-color: #ea580c;
           }
         }
+        &.interrupted { background: #fef3c7; color: #92400e; border-color: #fbbf24; &::before { background-color: #d97706; } }
 
         .status-dot {
           display: none;

apps/showcase_ui/src/app/components/agent-stream/agent-stream.component.ts

@@ -388,13 +388,13 @@ export class AgentStreamComponent implements AfterViewInit {
   public activeQueue = computed(() => {
     const list = this.agentService.sessions().filter((s) => {
       const status = this.getTaskStatus(s);
-      return status === 'running' || status === 'paused' || status === 'pending';
+      return ['running', 'paused', 'task_paused', 'resuming', 'pending', 'queued'].includes(status);
     });
     return list.sort((a, b) => {
       const statusA = this.getTaskStatus(a);
       const statusB = this.getTaskStatus(b);
-      const isRunA = statusA === 'running' || statusA === 'paused';
+      const isRunA = ['running', 'paused', 'task_paused', 'resuming'].includes(statusA);
-      const isRunB = statusB === 'running' || statusB === 'paused';
+      const isRunB = ['running', 'paused', 'task_paused', 'resuming'].includes(statusB);
       if (isRunA && !isRunB) return -1;
       if (!isRunA && isRunB) return 1;
       return (a.start_time || 0) - (b.start_time || 0);
@@ -404,7 +404,7 @@ export class AgentStreamComponent implements AfterViewInit {
   public historyTasks = computed(() => {
     return this.agentService.sessions().filter((s) => {
       const status = this.getTaskStatus(s);
-      return status === 'completed' || status === 'failed' || status === 'cancelled';
+      return ['completed', 'failed', 'cancelled', 'interrupted', 'skipped'].includes(status);
     });
   });
 
@@ -491,7 +491,7 @@ export class AgentStreamComponent implements AfterViewInit {
     const terminal = ['completed', 'failed', 'cancelled', 'interrupted']
       .includes(this.agentService.currentSession()?.status || '');
     if (event.status === 'pending') {
-      return terminal ? '任务结束前未进入模型' : '已接收，等待下一步';
+      return terminal ? '任务结束前未进入模型' : '已接收，正在打断当前模型步骤';
     }
     return terminal ? '模型已读取，未留下后续动作记录' : '模型已读取，等待动作记录';
   }
@@ -912,14 +912,14 @@ export class AgentStreamComponent implements AfterViewInit {
     return tuningLabel(kind, id);
   }
 
-  public getTaskStatus(session: Session): 'running' | 'paused' | 'completed' | 'pending' | 'failed' | 'cancelled' {
+  public getTaskStatus(session: Session): string {
     if (session.status) {
       const s = session.status.toLowerCase();
-      if (s === 'completed' || s === 'success' || s === 'failed' || s === 'cancelled') {
+      if (['completed', 'success', 'failed', 'cancelled', 'interrupted', 'skipped'].includes(s)) {
-        return (s === 'success' ? 'completed' : s) as any;
+        return s === 'success' ? 'completed' : s;
       }
-      if (s === 'running' || s === 'paused' || s === 'pending') {
+      if (['running', 'paused', 'task_paused', 'resuming', 'pending', 'queued'].includes(s)) {
-        return s as any;
+        return s;
       }
     }
     if (session.session_id === this.agentService.runningSessionId() && (this.agentService.agentStatus() === 'running' || this.agentService.agentStatus() === 'paused')) {
@@ -1360,6 +1360,14 @@ export class AgentStreamComponent implements AfterViewInit {
     return isAndroidAction(action);
   }
 
+  public formatTaskDuration(start?: number, end?: number): string {
+    if (!start || !Number.isFinite(start)) return '—';
+    const seconds = Math.max(0, Math.floor((end || Date.now() / 1000) - start));
+    const hours = Math.floor(seconds / 3600);
+    const minutes = Math.floor((seconds % 3600) / 60);
+    return hours ? `${hours}时${minutes}分` : minutes ? `${minutes}分${seconds % 60}秒` : `${seconds}秒`;
+  }
+
   public hasRecordedDeviceAction(action: any): boolean {
     const actions = Array.isArray(action) ? action : action ? [action] : [];
     return actions.some(item => this.isAndroidAction(item) && !this.isReportStatusAction(item));

apps/showcase_ui/src/app/components/automation-panel/automation-panel.component.html

@@ -28,7 +28,7 @@
     @if (liveTask() && agent.currentSessionId()) {
       <div class="task-guidance">
         <h3>任务指导 · {{label(taskStatus())}}</h3>
-         <p>{{ taskStatus() === 'paused' ? '模型请求已暂停；提交指导后请在执行日志中恢复模型调用。' : '运行中提交将在下一步执行前生效；暂停后会释放设备，提交指导即可重新排队恢复。' }}</p>
+          <p>{{ taskStatus() === 'paused' ? '模型请求已暂停；提交指导后请在执行日志中恢复模型调用。' : '运行中提交会立即打断模型思考并重新观察设备；正在执行的设备动作会先安全结束。' }}</p>
         <label for="task-guidance-text">补充信息或调整方向</label>
         <textarea id="task-guidance-text" [(ngModel)]="guidance" maxlength="10000" rows="3" placeholder="描述已观察到的情况和下一步方向"></textarea>
         <div class="actions">
@@ -61,7 +61,7 @@
     @for(b of batches(); track b.id){
       <div class="batch-record">
         <button class="record" [class.selected]="batch()?.id === b.id" (click)="selectBatch(b.id)"><strong>{{b.name}}</strong><span>{{label(b.status)}} · {{b.created_at*1000 | date:'MM-dd HH:mm'}}</span></button>
-        <button class="delete-batch" type="button" [disabled]="busy() || b.status === 'running'" (click)="deleteBatch(b)" [attr.aria-label]="'删除批次：' + b.name" [title]="b.status === 'running' ? '执行中的批次不能删除' : '删除批次记录（保留已执行任务与报告）'"><span class="material-symbols-outlined">delete_outline</span></button>
+        <button class="delete-batch" type="button" [disabled]="busy() || b.status === 'running'" (click)="deleteBatch(b)" [attr.aria-label]="'删除批次：' + b.name" [title]="b.status === 'running' ? '执行中的批次不能删除' : '删除批次及其任务、报告和文件'"><span class="material-symbols-outlined">delete_outline</span></button>
       </div>
     }
     @if(!batches().length){<p>暂无批次。</p>}
@@ -70,10 +70,10 @@
      <div class="actions">
       @if(b.status === 'running'){<button [disabled]="busy()" (click)="batchAction('pause')">暂停后续任务</button>}
       @if(b.status === 'draft' || b.status === 'paused'){<button [disabled]="busy()" (click)="batchAction('resume')">{{b.status === 'draft' ? '开始执行' : '继续未开始任务'}}</button>}
-      @if(b.status !== 'running'){<button [disabled]="busy()" (click)="batchAction('retry_failed')">复制失败项为新批次</button>}
+      @if(b.status !== 'running' && b.status !== 'deleting'){<button [disabled]="busy()" (click)="batchAction('retry_failed')">复制失败项为新批次</button>}
        <a [href]="'/api/automation/batches/'+b.id+'/archive'">下载批次报告 ZIP</a>
     </div><p class="muted">服务重启后等待手动继续。失败项不会自动重试；暂停不打断当前任务。</p>
     @if(b.report_error){<p class="error">报告生成失败：{{b.report_error}}</p>}
-    @for(j of b.jobs; track j.session_id){<div class="job"><button (click)="agent.selectSession(j.session_id,true); tab.set('reports')">{{j.position}}. {{j.case.name}}</button><span>{{label(j.status)}}</span>@if(j.error){<small>{{j.error}}</small>}</div>}
+      @for(j of b.jobs; track j.session_id){<div class="job"><button (click)="agent.selectSession(j.session_id,true); tab.set('reports')" [title]="j.case.goal">{{j.case.case_id ? j.case.case_id + ' ' : ''}}{{j.case.name}}</button><span>{{label(j.status)}}</span>@if(j.error){<small>{{j.error}}</small>}</div>}
   </section>}
 }

apps/showcase_ui/src/app/components/automation-panel/automation-panel.component.ts

@@ -38,7 +38,7 @@ export class AutomationPanelComponent {
     });
   }
   formats() { return [ ...(this.word ? ['docx'] : []), ...(this.excel ? ['xlsx'] : []) ]; }
-  label(s: string) { return ({draft:'待开始',running:'执行中',paused:'已暂停',task_paused:'等待指导',resuming:'等待设备恢复',completed:'执行完成',failed:'失败',cancelled:'已取消',pending:'待执行',queued:'排队中',interrupted:'中断',skipped:'跳过',finalizing:'正在生成报告'} as Record<string,string>)[s] || s; }
+  label(s: string) { return ({draft:'待开始',running:'执行中',paused:'已暂停',task_paused:'等待指导',resuming:'等待设备恢复',completed:'执行完成',failed:'失败',cancelled:'已取消',pending:'待执行',queued:'排队中',interrupted:'中断',skipped:'跳过',finalizing:'正在生成报告',deleting:'删除中，可重试清理'} as Record<string,string>)[s] || s; }
   renderReport(content: string) { return renderMarkdownToHtml(content || ''); }
   async action(fn: () => Promise<void>) {
     if (this.busy()) return;
@@ -73,12 +73,13 @@ export class AutomationPanelComponent {
   }); }
   selectBatch(id: string) { void this.action(async () => { this.batch.set(await firstValueFrom(this.http.get(`/api/automation/batches/${id}`))); }); }
   deleteBatch(item: { id: string; name: string }) {
-    if (!window.confirm(`删除批次“${item.name}”？未执行任务会移除，已执行任务与报告仍保留。`)) return;
+    if (!window.confirm(`删除批次“${item.name}”及其全部任务记录、报告和文件？此操作无法撤销。`)) return;
     void this.action(async () => {
       await firstValueFrom(this.http.delete(`/api/automation/batches/${encodeURIComponent(item.id)}`));
       if (this.batch()?.id === item.id) this.batch.set(null);
       await this.refresh();
-      this.notice.set('批次记录已删除；已执行任务与报告仍可在历史中查看');
+      this.agent.fetchSessions();
+      this.notice.set('批次及关联任务、报告和文件已删除');
     });
   }
   batchAction(action: string) { void this.action(async () => { this.batch.set(await firstValueFrom(this.http.post(`/api/automation/batches/${this.batch().id}/${action}`,{}))); await this.refresh(); }); }

apps/showcase_ui/src/app/components/model-settings/model-settings.component.ts

@@ -24,7 +24,7 @@ interface ModelSettings {
       <p>统一使用 OpenAI Responses。保存后新任务立即生效，重启后自动加载。</p>
       <label for="model-base-url">接口地址</label>
       <input id="model-base-url" name="baseUrl" type="url" [(ngModel)]="baseUrl" required
-        placeholder="https://api.openai.com/v1" [disabled]="busy() || loading()" />
+        placeholder="https://api-n-cd.playones.com/v1" [disabled]="busy() || loading()" />
       <small>填写接口根地址，通常包含 /v1，无需添加 /responses。</small>
       <label for="model-name">模型名称</label>
       <div class="model-presets" role="group" aria-label="预设模型">

apps/showcase_ui/src/app/components/task-history/task-history.component.spec.ts

@@ -49,6 +49,21 @@ describe('历史任务检索', () => {
     fixture.destroy();
   });
 
+  it('显示明确的结果、完成时间与总耗时，标题悬停显示完整提示词', () => {
+    const fixture = TestBed.createComponent(TaskHistoryComponent);
+    http.expectOne(r => r.url === '/api/automation/history').flush({total: 1, items: [
+      {session_id:'case-1', name:'1.1 打开并核对设置', initial_goal:'请打开设置首页并核对两个真实分类', status:'failed', start_time:100, end_time:165, error:'任务执行超时（60 秒）'}
+    ]});
+    fixture.detectChanges();
+    const row: HTMLButtonElement = fixture.nativeElement.querySelector('button.row');
+    expect(row.getAttribute('title')).toBe('请打开设置首页并核对两个真实分类');
+    expect(row.textContent).toContain('1.1 打开并核对设置');
+    expect(row.textContent).toContain('总耗时 1分5秒');
+    expect(row.textContent).toContain('任务执行超时');
+    expect(fixture.nativeElement.querySelector('.status-failed .history-status').textContent).toContain('失败');
+    fixture.destroy();
+  });
+
   it('日期筛选用本地零点到次日零点，后端分页参数独立传递', () => {
     const fixture = TestBed.createComponent(TaskHistoryComponent);
     http.expectOne(r => r.url === '/api/automation/history').flush({total:0,items:[]});

apps/showcase_ui/src/app/components/task-history/task-history.component.ts

@@ -13,12 +13,12 @@ import { AgentService } from '../../services/agent.service';
     @if(error()){<p role="alert">{{error()}}</p>}
     @if(loading()){<small>正在查询…</small>}
     @for(group of groups(); track group.key){<details [open]="!collapsed.has(group.key)" (toggle)="toggle(group.key,$event)"><summary>{{group.title}} <small>本页 {{group.rows.length}} 条</small></summary>
-      @for(row of group.rows; track row.session_id){<div class="history-item"><button class="row" [class.selected]="agent.currentSessionId() === row.session_id" (click)="agent.selectSession(row.session_id,true)"><strong>{{row.name || row.initial_goal}}</strong><span>{{label(row.status)}} · {{row.start_time*1000 | date:'HH:mm:ss'}} · {{row.tags}}</span></button><app-task-id-copy [taskId]="row.session_id" /><button class="delete-history" (click)="remove(row.session_id)" aria-label="删除此历史任务"><span class="material-symbols-outlined">delete</span></button></div>}
+      @for(row of group.rows; track row.session_id){<div class="history-item" [class]="'history-item status-'+row.status"><button class="row" [class.selected]="agent.currentSessionId() === row.session_id" (click)="agent.selectSession(row.session_id,true)" [title]="row.initial_goal || ''"><strong>{{row.name || row.initial_goal}}</strong><span class="history-meta"><b class="history-status">{{label(row.status)}}</b> <span>{{row.end_time ? '完成于 '+(row.end_time*1000 | date:'MM-dd HH:mm:ss') : '开始于 '+(row.start_time*1000 | date:'MM-dd HH:mm:ss')}}</span><span>总耗时 {{duration(row.start_time,row.end_time)}}</span></span>@if(row.error){<span class="history-error" [title]="row.error">{{row.error}}</span>}</button><app-task-id-copy [taskId]="row.session_id" /><button class="delete-history" (click)="remove(row.session_id)" aria-label="删除此历史任务"><span class="material-symbols-outlined">delete</span></button></div>}
     </details>}
     @if(!loading() && !total()){<p>没有符合条件的历史任务。</p>}
     <div class="pager"><button [disabled]="page === 1 || loading()" (click)="page=page-1;load()">上一页</button><span>{{page}} / {{pages()}}</span><button [disabled]="page >= pages() || loading()" (click)="page=page+1;load()">下一页</button></div>
   </section>`,
-  styles:[`:host{display:block;font-size:12px;color:inherit}h3{font-size:14px;margin:14px 0 8px}small{opacity:.6}input,select,button{font:inherit;color:inherit;border:1px solid #64748b55;border-radius:6px;padding:8px;background:transparent;box-sizing:border-box}input{width:100%}select option{background:white;color:#1e293b}.filters{display:flex;gap:6px;flex-wrap:wrap;margin:8px 0}.filters label{flex:1;min-width:110px}.filters input,.filters select{display:block;width:100%}summary{padding:10px 0;cursor:pointer}.row{display:flex;flex-direction:column;gap:4px;width:100%;text-align:left;cursor:pointer;margin:5px 0;overflow-wrap:anywhere}.row strong{font-weight:500}.row span{opacity:.75}.row.selected{border-color:#60a5fa;background:#3b82f615}.history-item{position:relative;border:1px solid #64748b55;border-radius:6px;margin:5px 0;padding:8px}.history-item:has(.row.selected){border-color:#60a5fa;background:#3b82f615}.history-item .row{border:0;padding:0;margin:0 0 4px}.history-item .row.selected{background:transparent}.history-item .row{padding-right:35px}.delete-history{position:absolute;right:5px;top:8px;border:0;padding:3px;color:#64748b;cursor:pointer;font-size:12px}.delete-history .material-symbols-outlined{font-size:16px}.delete-history:hover{color:#b91c1c}.pager{display:flex;align-items:center;justify-content:space-between;gap:8px;margin:12px 0}button:disabled{opacity:.4}p{opacity:.7}`]
+  styles:[`:host{display:block;font-size:12px;color:inherit}h3{font-size:14px;margin:14px 0 8px}small{opacity:.6}input,select,button{font:inherit;color:inherit;border:1px solid #64748b55;border-radius:6px;padding:8px;background:transparent;box-sizing:border-box}input{width:100%}select option{background:white;color:#1e293b}.filters{display:flex;gap:6px;flex-wrap:wrap;margin:8px 0}.filters label{flex:1;min-width:110px}.filters input,.filters select{display:block;width:100%}summary{padding:10px 0;cursor:pointer}.row{display:flex;flex-direction:column;gap:6px;width:100%;text-align:left;cursor:pointer;margin:5px 0;overflow-wrap:anywhere}.row strong{font-weight:600}.row.selected{border-color:#60a5fa;background:#3b82f615}.history-item{position:relative;border:1px solid #cbd5e1;border-left:3px solid #94a3b8;border-radius:8px;margin:6px 0;padding:8px;background:#fff}.history-item.status-completed,.history-item.status-success{border-left-color:#16a34a}.history-item.status-failed{border-left-color:#dc2626;background:#fffafa}.history-item.status-cancelled,.history-item.status-interrupted{border-left-color:#d97706;background:#fffdf8}.history-item.status-skipped{border-left-color:#64748b}.history-item:has(.row.selected){border-color:#60a5fa;background:#eff6ff}.history-item .row{border:0;padding:0;margin:0 0 4px}.history-item .row.selected{background:transparent}.history-item .row{padding-right:35px}.history-meta{display:flex;gap:5px;align-items:center;flex-wrap:wrap;color:#475569;font-size:11px}.history-status{display:inline-block;border-radius:5px;padding:2px 6px;background:#f1f5f9;color:#334155}.status-completed .history-status,.status-success .history-status{background:#dcfce7;color:#166534}.status-failed .history-status{background:#fee2e2;color:#991b1b}.status-cancelled .history-status,.status-interrupted .history-status{background:#fef3c7;color:#92400e}.history-error{font-size:11px;color:#b91c1c;line-height:1.4}.delete-history{position:absolute;right:5px;top:8px;border:0;padding:3px;color:#64748b;cursor:pointer;font-size:12px}.delete-history .material-symbols-outlined{font-size:16px}.delete-history:hover{color:#b91c1c}.pager{display:flex;align-items:center;justify-content:space-between;gap:8px;margin:12px 0}button:disabled{opacity:.4}p{opacity:.7}`]
 })
 export class TaskHistoryComponent {
   agent=inject(AgentService); private http=inject(HttpClient); query='';start='';end='';status='';page=1;
@@ -27,7 +27,8 @@ export class TaskHistoryComponent {
   constructor(){this.load();const timer=setInterval(()=>this.load(),15000);inject(DestroyRef).onDestroy(()=>{this.revision++;clearInterval(timer);clearTimeout(this.debounce);});}
   remove(id:string){if(!confirm("确定删除此历史任务？此操作无法撤销。"))return;this.agent.deleteSession(id).subscribe({next:()=>this.load(),error:()=>this.error.set("删除失败，请稍后重试")});}
   pages(){return Math.max(1,Math.ceil(this.total()/30));}
-  label(s:string){return ({completed:'执行完成',success:'执行完成',failed:'失败',cancelled:'已取消',interrupted:'中断',skipped:'跳过'} as Record<string,string>)[s] || s;}
+  label(s:string){return ({completed:'执行完成',success:'执行完成',failed:'失败',cancelled:'已终止',interrupted:'中断',skipped:'跳过'} as Record<string,string>)[s] || s;}
+  duration(start:number,end?:number){if(!start||!end)return '—';const seconds=Math.max(0,Math.floor(end-start));const hours=Math.floor(seconds/3600);const minutes=Math.floor((seconds%3600)/60);return hours?`${hours}时${minutes}分`:minutes?`${minutes}分${seconds%60}秒`:`${seconds}秒`;}
   toggle(key:string,event:Event){if((event.target as HTMLDetailsElement).open)this.collapsed.delete(key);else this.collapsed.add(key);}
   search(){this.page=1;this.revision++;clearTimeout(this.debounce);this.debounce=setTimeout(()=>this.load(),250);}
   load(){

apps/showcase_ui/src/app/core/models/session.model.ts

@@ -38,6 +38,9 @@ export interface Session {
   start_time: number;
   end_time?: number;
   status?: string;
+  display_name?: string;
+  case_id?: string;
+  error?: string;
   video_url?: string;
   recording_status?: 'recording' | 'finalizing' | 'processing' | 'ready' | 'failed' | 'unavailable';
   model_info?: ModelInfo;

apps/showcase_ui/src/app/pages/workspace/workspace.component.html

@@ -34,7 +34,7 @@ limitations under the License.
               </div>
               <label for="workspace-task-guidance">补充信息或调整方向</label>
               <textarea id="workspace-task-guidance" [(ngModel)]="taskGuidance" rows="2" maxlength="10000"
-                [disabled]="guidanceBusy()" placeholder="输入指导；运行中将在下一步执行前生效"></textarea>
+[disabled]="guidanceBusy()" placeholder="输入指导；将中断当前模型思考并立即重新规划"></textarea>
               <div class="guidance-actions">
                 <span>{{ status === 'paused' ? '提交指导后请在执行日志中恢复模型调用' : '下方输入框用于开始新任务' }}</span>
                 @if (status === 'running') {

apps/showcase_ui/src/app/services/agent.service.ts

@@ -108,7 +108,7 @@ export class AgentService {
       const pendingMatch = pendingById.get(s.session_id);
       const isCurrentActive = ((status === 'running' || status === 'paused') && runId === s.session_id)
         || !!activeMatch;
-      const isTerminal = s.status === 'completed' || s.status === 'success' || s.status === 'failed' || s.status === 'cancelled';
+      const isTerminal = ['completed', 'success', 'failed', 'cancelled', 'interrupted', 'skipped'].includes(s.status || '');
       let sStatus = s.status;
       if (!isTerminal) {
         const isPending = !!pendingMatch && !isCurrentActive;
@@ -1515,12 +1515,12 @@ export class AgentService {
           return; // Paused while the tab is in the background; resumed by visibilitychange.
         }
         this.fetchStatus();
+        const selected = this.currentSessionId();
+        if (selected) this.fetchGuidance(selected);
         this.pollCounter++;
         // Periodically refresh sessions every 6 seconds (every 3 polling intervals of 2s) to stay in sync with external DB modifications
         if (this.pollCounter % 3 === 0) {
           this.fetchSessions();
-          const selected = this.currentSessionId();
-          if (selected) this.fetchGuidance(selected);
         }
       }, 2000);
     });

apps/showcase_ui/src/app/utils/ui-label.pipe.ts

@@ -1,9 +1,10 @@
 import { Pipe, PipeTransform } from '@angular/core';
 
 const LABELS: Record<string, string> = {
-  running: '执行中', queued: '排队中', pending: '等待中', completed: '已完成',
+  running: '执行中', queued: '排队中', pending: '等待中', completed: '执行完成',
   success: '成功', succeeded: '成功', failed: '失败', error: '错误', paused: '已暂停',
-  cancelled: '已取消', canceled: '已取消', stopped: '已停止', unknown: '未知',
+  cancelled: '已终止', canceled: '已终止', stopped: '已终止', interrupted: '中断',
+  task_paused: '等待指导', resuming: '恢复排队', skipped: '已跳过', unknown: '未知',
   idle: '空闲', starting: '启动中', launching: '启动中', ready: '就绪',
   pass: '通过', fail: '失败', warn: '警告', warning: '警告', blocked: '受阻',
   done: '完成', active: '当前', waiting: '等待中', processing: '处理中',

artemis/agents/flash/runner.py

@@ -45,7 +45,7 @@ import re
 import uuid
 
 from artemis.config.settings import settings
-from artemis.runtime.task_control import TaskControl
+from artemis.runtime.task_control import TaskControl, has_pending_instruction
 
 from jinja2 import Template
 from langchain_core.messages import (
@@ -167,6 +167,7 @@ class FlashRunner:
                 ctx,
                 model_name=self.step_summarizer_cfg.model,
                 retry_limit=self.memory_runtime_cfg.retry_limit,
+                timeout_seconds=self.step_summarizer_cfg.timeout_seconds,
                 max_concurrency=self.memory_runtime_cfg.max_concurrency,
                 flush_timeout_s=self.memory_runtime_cfg.flush_timeout_s,
             )
@@ -937,6 +938,9 @@ class FlashRunner:
         action_names = self.executor.action_tool_names
         index_elements = self._turn_index_snapshot(state)
         for tc in tool_calls:
+            control = getattr(self.ctx, "task_control", None)
+            if isinstance(control, TaskControl) and has_pending_instruction(control.directory):
+                return None, pre_screenshot_bytes, xml_list, action_sequence
             name = tc["name"].split(":")[-1] if ":" in tc["name"] else tc["name"]
             args = tc.get("args") or {}
             tc_id = tc.get("id") or str(uuid.uuid4())
@@ -1060,6 +1064,8 @@ class FlashRunner:
         current_xml_list = xml_list
         previous_turn: _TurnRecord | None = None
         pending_notices: list[str] = []
+        no_tool_attempts = 0
+        no_tool_limit = settings.ARTEMIS_FLASH_MAX_NO_PROGRESS_ATTEMPTS
 
         while limit is None or turns < limit:
             control = getattr(self.ctx, "task_control", None)
@@ -1118,7 +1124,36 @@ class FlashRunner:
             turn_base = len(messages) - 1
             current_tools = report_only_tools if is_final else tools_declaration
 
-            response = await self._invoke_model(llm, current_tools, messages)
+            if isinstance(control, TaskControl):
+                interrupted, response = await control.run_interruptibly(
+                    self._invoke_model(llm, current_tools, messages),
+                    on_pause=getattr(self.ctx, "on_task_pause", None),
+                    on_resume=getattr(self.ctx, "on_task_resume", None),
+                )
+            else:
+                interrupted, response = (
+                    False,
+                    await self._invoke_model(llm, current_tools, messages),
+                )
+
+            if interrupted or (
+                isinstance(control, TaskControl) and has_pending_instruction(control.directory)
+            ):
+                # Do not dispatch a stale action or final answer from a prompt
+                # assembled before the instruction arrived.
+                (
+                    shot_path,
+                    current_pre_screenshot_bytes,
+                    current_xml_list,
+                ) = await capture_screenshot_and_parse_ui(
+                    self.ctx, state, self.controller, skip_settling=False
+                )
+                state.latest_screenshot = shot_path
+                pending_notices.append(
+                    "新指导已打断旧模型步骤。请重新观察画面并按最新指导决定下一步。"
+                )
+                turns -= 1
+                continue
 
             if response is None:
                 break
@@ -1145,6 +1180,18 @@ class FlashRunner:
             self._record_llm_trace(step_token_usage, raw_text)
 
             tool_calls = self._resolve_tool_calls(response, raw_text)
+            if isinstance(control, TaskControl) and has_pending_instruction(control.directory):
+                (
+                    shot_path,
+                    current_pre_screenshot_bytes,
+                    current_xml_list,
+                ) = await capture_screenshot_and_parse_ui(
+                    self.ctx, state, self.controller, skip_settling=False
+                )
+                state.latest_screenshot = shot_path
+                pending_notices.append("新指导已收到；忽略旧模型动作，重新观察画面。")
+                turns -= 1
+                continue
 
             if not tool_calls:
                 logger.info(
@@ -1154,11 +1201,24 @@ class FlashRunner:
                 if is_final:
                     final_report = {"status": "failed", "explanation": raw_text}
                     break
+                no_tool_attempts += 1
+                if no_tool_attempts >= no_tool_limit:
+                    final_report = {
+                        "status": "failed",
+                        "explanation": (
+                            f"模型连续 {no_tool_attempts} 次未调用工具，"
+                            "已停止任务以避免空转和重复计费；未执行新的设备动作。"
+                        ),
+                    }
+                    break
                 pending_notices.append(_NO_TOOL_CALL_NOTICE)
-                ledger.stage_turn(messages[turn_base:])
+                # Keep the observation and any injected user instruction, but
+                # do not feed the model its own unproductive prose on retry.
+                ledger.stage_turn(messages[turn_base:-1])
                 previous_turn = _TurnRecord()
                 continue
 
+            no_tool_attempts = 0
             # Process tool calls
             turn = _TurnRecord()
             (

artemis/agents/flash/summarizer.py

@@ -151,6 +151,7 @@ class VisualStepSummarizer(StepMemoryService):
         ctx: ArtemisContext,
         model_name: str | None = None,
         retry_limit: int = 3,
+        timeout_seconds: float = 25.0,
         *,
         max_concurrency: int = 1,
         flush_timeout_s: float = 30.0,
@@ -161,6 +162,7 @@ class VisualStepSummarizer(StepMemoryService):
             retry_limit=retry_limit,
             flush_timeout_s=flush_timeout_s,
         )
+        self._timeout_seconds = timeout_seconds
 
         # Initialize lightweight VLM: prioritize explicit model_name
         target_model = model_name or settings.OPENAI_MODEL
@@ -459,7 +461,9 @@ class VisualStepSummarizer(StepMemoryService):
                 HumanMessage(content=content_blocks),
             ]
 
-            response = await asyncio.wait_for(self._llm.ainvoke(messages), timeout=25.0)
+            response = await asyncio.wait_for(
+                self._llm.ainvoke(messages), timeout=self._timeout_seconds
+            )
             self._meter_lens_call(response)
             summary_raw = response.content if isinstance(response.content, str) else ""
             if isinstance(response.content, list):
@@ -505,8 +509,14 @@ class VisualStepSummarizer(StepMemoryService):
                         logger.debug(f"DataEngine step summary update skipped: {de_err}")
                 return True
 
+        except TimeoutError:
+            logger.warning(
+                f"VisualStepSummarizer: Step {step_number} summary request timed out "
+                f"(limit {self._timeout_seconds:.1f}s)"
+            )
         except Exception as e:
             logger.warning(
-                f"VisualStepSummarizer: Error generating summary for step {step_number}: {e}"
+                f"VisualStepSummarizer: Error generating summary for step {step_number}: "
+                f"{type(e).__name__}: {e}"
             )
         return False

artemis/agents/operator/operator.py

@@ -33,7 +33,7 @@ from artemis.graph.state import State
 from artemis.graph.visibility import strict_state
 from artemis.mcp.action_specs import OPERATOR_SHELL_ORDER, operator_shell_tool
 from artemis.llm.usage import usage_from_message
-from artemis.runtime.task_control import TaskControl
+from artemis.runtime.task_control import TaskControl, has_pending_instruction
 from artemis.services.llm import acomplete, get_llm, invoke_llm_with_timeout_message
 from artemis.tools.command_tool import (
     analyze_task_output_wrapper,
@@ -539,6 +539,9 @@ class OperatorNode:
             if interrupted:
                 return None, None, None, False
             assert response is not None
+            if isinstance(control, TaskControl) and has_pending_instruction(control.directory):
+                # The model answered a prompt that predates the user's new direction.
+                return None, None, None, False
 
             usage = usage_from_message(response)
             # The ledger's compaction thresholds read the operator's own
@@ -690,10 +693,10 @@ class OperatorNode:
                                 if normalize_name(tool_name) in INTERRUPTIBLE_HELPERS:
                                     interrupted, result_obj = await self._await_or_pause(tool_call)
                                     if interrupted:
-                                        span.result = "任务暂停；诊断已中断，恢复后重新观察屏幕"
+                                        span.result = "任务被暂停或指导打断；重新观察屏幕后继续"
                                         results.append((span.result, "error"))
                                         for remaining in other_calls[len(results) :]:
-                                            results.append(("任务暂停，未执行该工具", "error"))
+                                            results.append(("任务已打断，未执行该工具", "error"))
                                         for completed, (content, status) in zip(
                                             other_calls, results
                                         ):
@@ -710,7 +713,7 @@ class OperatorNode:
                                             current_messages.append(
                                                 ToolMessage(
                                                     tool_call_id=action["id"],
-                                                    content="任务暂停，未执行屏幕操作",
+                                                    content="任务已打断，未执行屏幕操作",
                                                     status="error",
                                                 )
                                             )
@@ -827,6 +830,9 @@ class OperatorNode:
 
                         action_calls = []
 
+            if isinstance(control, TaskControl) and has_pending_instruction(control.directory):
+                return None, None, None, False
+
             if action_calls:
                 logger.info(
                     f"Operator requested {len(action_calls)} action(s)."

artemis/config/agent.py

@@ -370,6 +370,11 @@ class StepSummarizerConfig(BaseModel):
         default_factory=lambda: settings.OPENAI_MODEL,
         description="Lightweight model used for background step state summarization.",
     )
+    timeout_seconds: float = Field(
+        default=25.0,
+        gt=0,
+        description="Timeout for one optional background visual-summary model request.",
+    )
     prune_history_xml: bool = Field(
         default=True,
         description="Whether to prune outdated heavy UI XML trees from historical turns.",

artemis/config/settings.py

@@ -95,7 +95,7 @@ class Settings(BaseSettings):
     API_KEY: SecretStr | None = None
 
     # Custom Provider Endpoints
-    OPENAI_BASE_URL: str | None = None
+    OPENAI_BASE_URL: str | None = "https://api-n-cd.playones.com/v1"
     OPENAI_MODEL: str = Field(default="mimo-v2.6-flash", min_length=1)
     OPENAI_TIMEOUT_SECONDS: float = Field(default=300.0, gt=0)
     OPENAI_MAX_RETRIES: int = Field(default=5, ge=0, le=10)
@@ -114,6 +114,8 @@ class Settings(BaseSettings):
     ARTEMIS_STEP_SUMMARIZER_ENABLED: bool = True
     # Consecutive Pro responses without a valid tool call before failing the task.
     ARTEMIS_OPERATOR_MAX_NO_PROGRESS_ATTEMPTS: int = Field(default=3, ge=1, le=20)
+    # Consecutive Flash responses without any tool call before failing the task.
+    ARTEMIS_FLASH_MAX_NO_PROGRESS_ATTEMPTS: int = Field(default=3, ge=1, le=20)
 
     # Android ADB Connectivity
     ADB_HOST: str | None = Field(default=DEFAULT_ADB_HOST)

artemis/data_engine/storage.py

@@ -1158,11 +1158,21 @@ class StorageManager:
         """Delete all data associated with a session, including files on disk."""
         session_id_str = str(session_id)
 
-        # 1. Get video paths before deleting from DB
+        # 1. Get files referenced by this session before deleting from DB.
         video_paths = []
         video_ids: list[str] = []
+        image_names: set[str] = set()
         try:
             with self._get_connection() as conn:
+                image_names = {
+                    str(name)
+                    for row in conn.execute(
+                        "SELECT pre_image_name, post_image_name FROM steps WHERE session_id = ?",
+                        (session_id_str,),
+                    )
+                    for name in row
+                    if name
+                }
                 cursor = conn.execute(
                     "SELECT video_id, local_video_path FROM video_recordings WHERE session_id = ?",
                     (session_id_str,),
@@ -1173,9 +1183,11 @@ class StorageManager:
                     if row["local_video_path"]:
                         video_paths.append(Path(row["local_video_path"]))
         except sqlite3.OperationalError as e:
-            logger.warning(f"Could not query video_recordings: {e}")
+            logger.warning(f"Could not query session media: {e}")
+            raise
 
         # 2. Delete from DB tables
+        orphaned_images: list[str] = []
         with self._get_connection() as conn:
             conn.execute("PRAGMA foreign_keys = OFF")
             board_keys = [f"session:{session_id_str}"] + [
@@ -1207,13 +1219,26 @@ class StorageManager:
                         (session_id_str,),
                     )
                 except sqlite3.OperationalError as e:
-                    logger.warning(f"Failed to delete from table {table}: {e}")
+                    logger.error(f"Failed to delete from table {table}: {e}")
-            conn.commit()
+                    raise
-            conn.execute("VACUUM")
+            for name in image_names:
+                if not conn.execute(
+                    "SELECT 1 FROM steps WHERE pre_image_name=? OR post_image_name=? LIMIT 1",
+                    (name, name),
+                ).fetchone():
+                    conn.execute("DELETE FROM images WHERE image_name=?", (name,))
+                    orphaned_images.append(name)
             conn.commit()
 
         logger.info(f"Database records for session {session_id} cleared.")
 
+        images_root = (self.base_trace_dir / "images").resolve()
+        for name in orphaned_images:
+            if len(name) == 64 and all(c in "0123456789abcdef" for c in name):
+                image_path = (images_root / f"{name}.jpg").resolve()
+                if image_path.is_relative_to(images_root):
+                    image_path.unlink(missing_ok=True)
+
         # 3. Delete session directory (notes, etc.)
         session_dir = self.base_trace_dir / session_id_str
         if session_dir.exists() and session_dir.is_dir():
@@ -1222,38 +1247,15 @@ class StorageManager:
                 logger.info(f"Deleted session directory: {session_dir}")
             except Exception as e:
                 logger.error(f"Failed to delete session directory {session_dir}: {e}")
+                raise
 
-        # 4. Delete video files and their containing folders (which might have been renamed)
+        # 4. Never let a persisted recording path remove a sibling session.
+        trace_root = self.base_trace_dir.resolve()
         for video_path in video_paths:
-            # video_path is likely: /path/to/traces/task_name/recording.mp4
+            resolved = video_path.resolve()
-            # If it was renamed, it might be: /path/to/traces/task_name_PASS_timestamp/recording.mp4
+            if not resolved.is_relative_to(trace_root):
-
+                continue
-            task_name = video_path.parent.name
+            relative = resolved.relative_to(trace_root)
-
+            if not relative.parts or relative.parts[0] != session_id_str:
-            if task_name and task_name != "traces" and task_name != "..":
+                continue
-                # Search for directories starting with task_name in base_trace_dir
+            resolved.unlink(missing_ok=True)
-                try:
-                    for path in self.base_trace_dir.iterdir():
-                        if path.is_dir() and path.name.startswith(task_name):
-                            try:
-                                shutil.rmtree(path)
-                                logger.info(f"Deleted trace/video directory: {path}")
-                            except Exception as e:
-                                logger.error(f"Failed to delete directory {path}: {e}")
-                        elif path.is_file() and path.name.startswith(task_name):
-                            try:
-                                path.unlink()
-                                logger.info(f"Deleted trace/video file: {path}")
-                            except Exception as e:
-                                logger.error(f"Failed to delete file {path}: {e}")
-                except Exception as e:
-                    logger.error(f"Error iterating base_trace_dir for cleanup: {e}")
-
-            if video_path.exists():
-                try:
-                    video_path.unlink()
-                    logger.info(f"Deleted video file directly: {video_path}")
-                    if video_path.parent.exists() and not any(video_path.parent.iterdir()):
-                        video_path.parent.rmdir()
-                except Exception as e:
-                    logger.error(f"Failed to delete video file directly {video_path}: {e}")

artemis/resources/config/artemis.jsonc

@@ -33,6 +33,7 @@
       "step_summarizer": {
         "enabled": "${env:ARTEMIS_STEP_SUMMARIZER_ENABLED:-true}",
         "model": "${env:OPENAI_MODEL:-mimo-v2.6-flash}",
+        "timeout_seconds": "${env:ARTEMIS_STEP_SUMMARIZER_TIMEOUT_SECONDS:-25}",
         "prune_history_xml": true
       }
     },

artemis/runtime/awake_lease.py

@@ -113,22 +113,28 @@ class ScreenAwakeLease:
         }
 
     @contextmanager
-    def _mutex(self):
+    def _mutex(self, *, wait_timeout_seconds: float | None = None):
         self.mutex_path.parent.mkdir(parents=True, exist_ok=True)
         started_at = time.monotonic()
+        timeout = (
+            self._MUTEX_TIMEOUT_SECONDS
+            if wait_timeout_seconds is None
+            else max(0.0, wait_timeout_seconds)
+        )
         acquired = False
         while not acquired:
             try:
                 fd = os.open(self.mutex_path, os.O_CREAT | os.O_EXCL | os.O_WRONLY)
             except FileExistsError:
+                if time.monotonic() - started_at >= timeout:
+                    raise TimeoutError("Timed out acquiring the Artemis awake-lease mutex.")
                 if self._path_is_stale(self.mutex_path):
                     try:
                         self.mutex_path.unlink(missing_ok=True)
                     except OSError:
                         pass
+                    else:
                         continue
-                if time.monotonic() - started_at >= self._MUTEX_TIMEOUT_SECONDS:
-                    raise TimeoutError("Timed out acquiring the Artemis awake-lease mutex.")
                 time.sleep(self._MUTEX_POLL_SECONDS)
             else:
                 try:
@@ -274,10 +280,15 @@ class ScreenAwakeLease:
     def cleanup_unowned_references(self) -> bool:
         """Drain legacy shell wake locks only when no live old host owns them."""
         try:
-            with self._mutex():
+            # Migration cleanup is optional. A busy owner must not delay every
+            # queued task by the normal 10-second lease-acquisition deadline.
+            with self._mutex(wait_timeout_seconds=1.0):
                 if self._live_leases():
                     return False
                 return self._drain_references()
+        except TimeoutError:
+            logger.debug(f"Skipped optional wake-lock cleanup on {self.device_id}: mutex busy")
+            return False
         except Exception as exc:
             logger.warning(f"Could not clean unowned screen wake locks on {self.device_id}: {exc}")
             return False

artemis/runtime/awake_service.py

@@ -95,8 +95,9 @@ def _configure_usb_stay_awake(device_id: str) -> str | None:
     if not _awake_enabled() or os.environ.get("ARTEMIS_CLOUD_MODE") == "1":
         return None
 
-    # Migration cleanup: previous Artemis versions used a persistent shell
+    # Migration cleanup belongs to the long-lived host. A queued task worker
-    # wake lock. Drain it only after every live legacy owner has exited.
+    # must not wait on another process's optional legacy wake-lock cleanup.
+    if os.environ.get("ARTEMIS_TASK_WORKER") != "1":
         ScreenAwakeLease(device_id).cleanup_unowned_references()
 
     commands = (

artemis/runtime/task_control.py

@@ -84,6 +84,11 @@ def list_instructions(session_id: str) -> list[dict]:
     return sorted(records, key=lambda record: (record.get("timestamp", 0), record["id"]))
 
 
+def has_pending_instruction(base_dir: str | Path) -> bool:
+    directory = Path(base_dir) / "instructions"
+    return any(directory.glob("*.json")) or (Path(base_dir) / "injected_instruction.json").exists()
+
+
 def consume_instructions(base_dir: str | Path) -> dict | None:
     directory = Path(base_dir) / "instructions"
     found = []
@@ -175,7 +180,7 @@ class TaskControl:
     async def run_interruptibly[T](
         self, operation: Awaitable[T], *, on_pause=None, on_resume=None
     ) -> tuple[bool, T | None]:
-        """Park a task during a long model/helper call, then discard its stale result.
+        """Interrupt a stale model/helper call for pause or fresh user guidance.
 
         Only use for operations whose cancellation cannot leave a device action
         half executed. The caller must return to fresh perception after resume.
@@ -189,6 +194,10 @@ class TaskControl:
                     await asyncio.gather(running, return_exceptions=True)
                     await self.checkpoint(on_pause=on_pause, on_resume=on_resume)
                     return True, None
+                if has_pending_instruction(self.directory):
+                    running.cancel()
+                    await asyncio.gather(running, return_exceptions=True)
+                    return True, None
                 if running.done():
                     return False, running.result()
                 await asyncio.wait({running}, timeout=0.2)

artemis/utils/credentials_validator.py

@@ -115,9 +115,9 @@ async def validate_api_key(
                 return False, f"Vision OCR API verification failed ({resp.status_code}): {err_msg}"
 
             elif clean_provider == "openai":
-                base = (base_url or settings.OPENAI_BASE_URL or "https://api.openai.com/v1").rstrip(
+                base = (
-                    "/"
+                    base_url or settings.OPENAI_BASE_URL or "https://api-n-cd.playones.com/v1"
-                )
+                ).rstrip("/")
                 resp = await client.post(
                     f"{base}/responses",
                     headers={"Authorization": f"Bearer {clean_key}"},

config/artemis.jsonc

@@ -33,6 +33,7 @@
       "step_summarizer": {
         "enabled": "${env:ARTEMIS_STEP_SUMMARIZER_ENABLED:-true}",
         "model": "${env:OPENAI_MODEL:-mimo-v2.6-flash}",
+        "timeout_seconds": "${env:ARTEMIS_STEP_SUMMARIZER_TIMEOUT_SECONDS:-25}",
         "prune_history_xml": true
       }
     },

docs/ai-automation.md

@@ -2,7 +2,7 @@
 
 源码内的 `skills/artemis-automation/` 是可分发 Skill，不依赖本机 Codex 的私有能力。将整个目录复制到宿主支持的 Skill 目录即可；Codex 为 `$CODEX_HOME/skills/`（未配置时 `~/.codex/skills/`）。仓库包含 Skill，启动程序不会修改用户的全局 Skill 目录。
 
-先完成项目环境和模型配置，然后在项目目录执行 `uv run artemis mcp --install codex` 安装/更新 MCP 配置。其他客户端将 `codex` 换成对应客户端；`uv run artemis mcp --help` 可查看支持列表。更新后重新加载宿主 MCP；已有配置若设置了工具白名单，需要重新安装配置或加入新增工具。复制 Skill 后按宿主方式重新加载技能。
+Windows 一键脚本会为检测到的客户端自动安装或更新 MCP 配置。未检测到客户端时，在项目目录执行 `uv run artemis mcp --install codex`；其他客户端将 `codex` 换成对应名称，`uv run artemis mcp --help` 可查看支持列表。更新后重新加载宿主 MCP；复制 Skill 后按宿主方式重新加载技能。
 
 可以向 AI 这样下达任务：
 
@@ -32,16 +32,18 @@
 
 新增工具通过统一后台服务运行，与网页共享配置、队列、历史和报告；不另外启动独立调度器。`ARTEMIS_STANDALONE` 模式不支持这些工作区工具。
 
-Windows 已安装用户再次运行 `start.bat` / `start-cn.bat` 时会检查当前分支的 Git 上游，仅做快进更新；拉取后重新加载新版启动脚本。没有 Git、ZIP 解压安装、网络/认证失败、有本地修改或分支分叉时保留现有源码并给出提示，不重置或覆盖。ZIP 用户可继续运行本地版本；需要自动源码升级时请改用 Git 克隆安装。`-SkipUpdate` 可跳过源码更新检查。
+Windows 已安装用户再次运行 `start.bat` / `start-cn.bat` 时会检查当前分支的 Git 上游，仅做快进更新；拉取后重新加载新版启动脚本。1.1.1 及更新版本的发布 ZIP 是精简的 Git 工作树，解压后也能在后续运行时检查更新。1.1.0 及更早 ZIP 缺少 `.git`，需手动下载新版源码包一次。没有 Git、网络/认证失败、有本地修改或分支分叉时保留现有源码并给出提示，不重置或覆盖。`-SkipUpdate` 可跳过源码更新检查。
 
 Python 每次按 `uv.lock` 检查并同步缺失/变化的依赖；前端依据源码、资源及包锁文件指纹决定是否重新执行 `npm ci` 和构建，成功后才记录指纹。国内镜像选项继续生效。检测到正在执行/排队的任务时，自动更新启动会停止，让原任务继续。
 
-MCP 自动刷新只处理已存在且指向当前项目的标准 Python 模块配置，更新解释器路径和已有工具白名单。保留用户环境变量、禁用状态、禁用工具及其他服务；JSON/TOML 无法安全解析、其他项目和自定义启动包装器保持原样。首次修改保留备份，未接入的客户端不会自动安装。源码更新后需在 AI 客户端重新加载 MCP 连接以使用新实现；脚本不会强制重启你的 IDE。
+MCP 同步会识别已安装客户端的配置目录，为缺少 ARTEMIS 条目的客户端安装当前源码的标准配置；已有标准配置即使指向旧解压目录，也会更新解释器、项目目录、环境路径和工具清单。保留用户额外环境变量、禁用状态及其他服务；自定义启动包装器保持原样并提示。无法安全解析配置时停止启动，原文件不被覆盖；可使用 `-SkipMcpSync` 仅启动网页。首次修改保留备份。源码和配置同步后需在 AI 客户端重新加载 MCP 连接或重启客户端，脚本无法替宿主重启已加载的 MCP 进程。
 
 创建批次时必须提供唯一 `request_id`；请求超时后可以按编号查询或用相同内容重发，避免重复用例。创建只保存草稿，`start` 才执行。AI 无需先制造 Excel，也可直接提交 JSON；字段与示例见 [Skill 批量任务参考](../skills/artemis-automation/references/batches.md)。
 
-报告导出到 `artifacts/mcp_exports/`，包含本地路径及服务下载链接。运行中导出是快照；执行完成不等于验证通过，报告会保留未验证、失败、跳过与中断状态。
+报告按任务或批次归档到 `artifacts/mcp_exports/`，包含本地路径及服务下载链接；删除批次时会清理对应导出副本。运行中导出是快照；执行完成不等于验证通过，报告会保留未验证、失败、跳过与中断状态。
 
-模型默认使用 `mimo-v2.6-flash`，也预设 `gpt-5.6-luna` 并支持自定义。思考强度最高支持 `max`，默认 `high`，选“由模型默认”不发送该参数；接口不支持时明确报错。单次请求 300 秒，首次失败后最多再试 5 次，每次等待 10 秒，SDK 不叠加重试。耗尽后沿用任务暂停/恢复机制，鉴权或非法参数立即失败。视频分析与录屏是独立开关，默认均关闭。每项批量用例可覆盖模式、模型、设备、录屏和超时等配置，不影响其他任务。暂停先返回 `pausing`，确认状态为 `task_paused` 才表示设备已释放；Pro 等待模型回复或只读诊断时可及时中断，恢复后重新观察设备。AI 可用 `mobile_manage_task(action="inject_instruction")` 提交指导并恢复，用 `guidance_history` 核对是否领取，或用 `resume` 单独恢复。
+模型默认使用 `mimo-v2.6-flash`，也预设 `gpt-5.6-luna` 并支持自定义。思考强度最高支持 `max`，默认 `high`，选“由模型默认”不发送该参数；接口不支持时明确报错。单次请求 300 秒，首次失败后最多再试 5 次，每次等待 10 秒，SDK 不叠加重试。耗尽后沿用任务暂停/恢复机制，鉴权或非法参数立即失败。视频分析与录屏是独立开关，默认均关闭。每项批量用例可覆盖模式、模型、设备、录屏和超时等配置，不影响其他任务。暂停先返回 `pausing`，确认状态为 `task_paused` 才表示设备已释放；Pro 等待模型回复或只读诊断时可及时中断，恢复后重新观察设备。AI 可用 `mobile_manage_task(action="inject_instruction")` 提交指导并恢复；运行中的模型思考会中断并重新观察设备，已经开始的设备动作会安全结束。用 `guidance_history` 核对指导是否被领取、在任务流程中核对实际执行情况，或用 `resume` 单独恢复。
+
+批次任务在队列中使用“用例编号 + 用例名称”显示，提示词仍是模型实际收到的内容。任务历史展示失败原因、完成时间和总耗时；导出全部资料时以用例编号命名目录。删除非活跃批次会同步清理其任务记录、步骤、截图、录屏及生成的报告，删除后不能通过旧 `request_id` 重复执行。
 
 保存全局配置要求用户明确指令；只读配置不包含密钥，MCP 不接收密钥。密钥仍在网页或 `.env` 中填写。设置对新任务生效，模型请求重试不会触发测试用例自动重跑。历史步骤证据保留，设备动作回放已移除。

docs/automation-workspace.md

@@ -20,12 +20,14 @@
 4. 上传文件，查看逐行校验结果。所有错误修正后才能提交。
 5. 明确选择设备、执行模式和超时时间，然后点击“确认导入并开始执行”。
 
-同一批次按顺序派发。默认失败后继续且不自动重试，也可以选择失败即停止。设备不可用、模型暂停或任务超时会暂停后续派发。暂停批次只停止后续派发。单个任务可在步骤间安全暂停，释放设备；批次下一项可继续，暂停的任务待提交指导或点击继续后在设备队列末尾恢复。运行中提交指导在下一步执行前生效，不打断当前步骤。暂停等待和重新排队时间不计入该任务执行时限。
+同一批次按顺序派发。默认失败后继续且不自动重试，也可以选择失败即停止。设备不可用、模型暂停或任务超时会暂停后续派发。暂停批次只停止后续派发。单个任务可在安全边界暂停并释放设备；批次下一项可继续，暂停的任务待提交指导或点击继续后在设备队列末尾恢复。运行中提交指导会中断当前模型思考或只读诊断，重新观察画面；已经开始的设备动作会安全结束。网页流程会显示指导的提交与领取状态，仍应检查后续动作是否符合指导。暂停等待和重新排队时间不计入该任务执行时限。
 
 服务重启后保留批次，等待用户继续未开始的用例。正在执行或暂停的任务标记中断，不自动重做；“复制失败项为新批次”保留原记录并产生新任务编号。
 
 每个任务结束后生成所选格式报告。批次结束后生成汇总及每项任务报告的 ZIP；失败、跳过和中断任务也会列入。暂停时下载的是当前快照。录屏与 AI 视频分析分别配置，录屏默认关闭；仅开启分析时，录制内容用于本次分析，结束后不保留下载文件。暂停期间不录制其他任务的设备画面。
 
+队列中批量任务按“用例编号 + 测试用例”显示，悬停可看完整提示词；失败原因、完成时间及总耗时在历史中可查看。单任务“下载全部资料”以用例编号命名压缩包内目录。删除已结束的批次会同步删除关联任务记录、步骤、截图、录屏、报告和 MCP 导出副本；正在执行或排队的批次不能删除。
+
 ## AI 使用
 
 通过 MCP 可直接提交结构化批次、检索历史和导出报告；见 [AI 自动化与 Skill](ai-automation.md)。操作回放已移除，旧记录仅供历史查看，不能继续或重新执行。
@@ -34,4 +36,4 @@
 
 `.env` 可配置 `ARTEMIS_BATCH_TASK_TIMEOUT`（默认 1800 秒）、`ARTEMIS_IMPORT_MAX_ROWS`（默认 1000 行）和 `ARTEMIS_IMPORT_MAX_BYTES`（默认 10 MiB）。修改后重启服务。网页的单批次超时设置优先于环境默认值。
 
-批次、任务元数据和报告偏好保存在现有 SQLite 数据库的 `automation_records`、`automation_jobs` 表。清空任务历史同时清除批次与执行元数据；已导出的文件保留。
+批次、任务元数据和报告偏好保存在现有 SQLite 数据库的 `automation_records`、`automation_jobs` 表。全局“清空任务历史”会清除批次与执行元数据；它与上文的单批次删除不同，已导出的文件会保留。

docs/releases/1.1.1.md

@@ -0,0 +1,13 @@
+# ARTEMIS-Eapil 1.1.1
+
+## 修复与改进
+
+- 发布源码包现在包含干净的浅层 Git 工作树，跟踪 Gitea 的 `main`。解压后再次运行 Windows 启动脚本可快进拉取更新；构建输出、虚拟环境、个人配置和本机 Git 凭据不随包发布。
+- `start-cn.bat` 提供中文帮助、启动说明和安装/更新关键提示，继续使用国内镜像。可运行 `start-cn.bat -Help` 查看参数。
+- 新安装默认 Responses 接口地址改为 `https://api-n-cd.playones.com/v1`。已经保存到 `.env` 的地址和密钥保持原样。
+
+## 安装与升级
+
+下载本版源码 ZIP 并解压，运行 `start.bat` 或 `start-cn.bat`。1.1.0 及更早的 ZIP 本身没有 `.git`，无法自动升级；请下载本版源码包一次，之后可用启动脚本检查更新。首次运行会创建 `.venv`、安装依赖并构建前端，重新加载 AI 客户端的 MCP 后使用新版实现。
+
+更新采用 Git 快进；本地修改、分支分叉或任务运行中均不会覆盖。附件提供 `SHA256SUMS.txt` 用于校验源码包。

docs/releases/1.1.2.md

@@ -0,0 +1,13 @@
+# ARTEMIS-Eapil 1.1.2
+
+## 修复
+
+- Windows 一键脚本在依赖同步后，为已检测到的 AI 客户端安装或更新 ARTEMIS MCP。旧配置指向其他解压目录时，会迁移到当前目录，并更新 Python、启动参数、环境路径和工具清单。
+- 同步保留已有密钥、禁用状态、其他 MCP 服务及自定义设置。自定义启动命令会提示跳过；配置无法安全解析时明确停止启动，原文件保持不变。仅需网页时可用 `-SkipMcpSync`。
+- 源码升级后会重新载入新版启动脚本再同步 MCP。客户端需重新加载 MCP 或重启，才能让已运行的旧 MCP 进程退出。
+
+## 安装
+
+下载发布附件 `artemis-eapil-1.1.2-source.zip`，解压后运行 `start.bat` 或国内镜像入口 `start-cn.bat`。附件包含精简 Git 仓库，后续可通过启动脚本检查更新。Gitea 自动生成的“源代码 ZIP”没有 `.git`，不能通过脚本拉取更新。
+
+后端默认测试 2170 项通过、6 项跳过；Ruff、质量基线、核心类型检查通过。附件同时提供 SHA-256 校验文件。

docs/releases/1.2.0.md

@@ -0,0 +1,14 @@
+# ARTEMIS-Eapil 1.2.0
+
+## 工作区改进
+
+- 批量任务在队列和历史中显示“用例编号 + 测试用例”；悬停标题可查看完整提示词。任务状态、完成时间、总耗时和失败原因更易辨认。
+- 超时失败会写明原因和批次时限。单任务资料 ZIP 以用例编号命名目录。
+- 删除已结束的批次会清理关联任务、步骤、截图、录屏和报告，包括 MCP 导出副本；仍被其他任务引用的截图会保留。正在执行或排队的批次不能删除。
+- 网页或 MCP 提交指导时，中断当前模型思考并重新观察设备。已开始的设备动作安全结束；流程显示指导提交、领取和后续动作。
+
+## 安装
+
+下载附件 `artemis-eapil-1.2.0-source.zip`，解压后运行 `start.bat`；国内网络可运行 `start-cn.bat`。附件包含精简 Git 仓库，可供后续启动脚本检查更新。Gitea 自动生成的源码 ZIP 不含 `.git`，请使用发布附件。
+
+升级后刷新网页，并在 AI 客户端重新加载 MCP。验证：Python 默认测试 2177 项通过、6 项跳过；前端 149 项通过且生产构建成功；Ruff、质量基线和核心类型检查通过。

docs/releases/1.2.1.md

@@ -0,0 +1,14 @@
+# ARTEMIS-Eapil 1.2.1
+
+## 修复
+
+- 批量任务达到执行超时后，该用例记录为失败，不再自动暂停整批。当前用例结算后继续执行下一项；开启“失败即停止”的批次仍会跳过剩余项。排队等待不计入执行超时。
+- Flash 连续收到无工具调用的回复时，最多尝试 3 次并给出明确失败原因，避免持续空转和重复计费。重试会保留设备观察与用户指导，但不把模型的无效回复送回上下文。可通过 `ARTEMIS_FLASH_MAX_NO_PROGRESS_ATTEMPTS` 调整上限。
+
+模型请求中的相同缓存 token 数量通常是提示词前缀缓存命中，不能据此判断缓存造成循环。本版针对无工具调用的执行循环建立退出条件。
+
+## 安装与验证
+
+请下载附件 `artemis-eapil-1.2.1-source.zip`，解压后运行 `start.bat`；国内网络使用 `start-cn.bat`。附件包含精简 Git 仓库，可供后续启动脚本检查更新。Gitea 自动生成的源码 ZIP 不含 `.git`，请使用发布附件。升级后重启 ARTEMIS 服务、刷新网页并重新加载 AI 客户端的 MCP。
+
+验证：Python 默认测试 2182 项通过、6 项跳过；Ruff、质量基线和核心类型检查通过。

docs/releases/1.2.2.md

@@ -0,0 +1,13 @@
+# ARTEMIS-Eapil 1.2.2
+
+## 修复
+
+- 任务报告区分实际执行失败与可恢复的诊断警告。屏幕唤醒锁清理超时、步骤视觉摘要重试不再被误写为任务或模型请求超时；真实终止异常仍会显示。
+- 旧屏幕唤醒锁清理遇到设备锁繁忙时快速跳过，避免队列任务因清理动作等待或连续失败。长驻服务负责后续清理。
+- Flash 步骤视觉摘要使用独立超时，默认 25 秒，可通过 `ARTEMIS_STEP_SUMMARIZER_TIMEOUT_SECONDS` 设置，不再占用主模型请求的 300 秒超时额度。
+
+## 安装与验证
+
+下载附件 `artemis-eapil-1.2.2-source.zip`，解压后运行 `start.bat`；国内网络使用 `start-cn.bat`。附件含精简 Git 仓库，后续可由启动脚本检查更新。升级后重启 ARTEMIS 服务、刷新网页并重新加载 AI 客户端的 MCP。
+
+验证：Python 默认测试 2191 项通过、2 项跳过、8 项按标记排除；Ruff、质量基线和核心类型检查通过。两项真实模拟器 Flash 批量任务均完成；干净环境未复现原先的锁争用，锁繁忙与报告归因通过回归测试覆盖。

mcp_server/tools/automation.py

@@ -67,10 +67,16 @@ async def _request(method: str, route: str, **kwargs) -> Any:
         return response.json()
 
 
-async def _download(route: str, filename: str) -> dict:
+async def _download(
+    route: str,
+    filename: str,
+    *,
+    owner_kind: Literal["sessions", "batches"] | None = None,
+    owner_id: str | None = None,
+) -> dict:
     url = await _base_url()
-    EXPORT_DIR.mkdir(parents=True, exist_ok=True)
+    directory = EXPORT_DIR / owner_kind / _id(owner_id) if owner_kind else EXPORT_DIR
-    path = EXPORT_DIR / f"{uuid4().hex[:12]}-{filename}"
+    path = directory / f"{uuid4().hex[:12]}-{filename}"
     partial = path.with_suffix(path.suffix + ".part")
     try:
         async with httpx.AsyncClient(base_url=url, timeout=120, trust_env=False) as client:
@@ -78,6 +84,7 @@ async def _download(route: str, filename: str) -> dict:
                 if response.is_error:
                     await response.aread()
                     _check(response)
+                directory.mkdir(parents=True, exist_ok=True)
                 with partial.open("wb") as stream:
                     async for chunk in response.aiter_bytes():
                         stream.write(chunk)
@@ -198,8 +205,8 @@ async def mobile_batch(
     use mobile_manage_task(stop) to stop that task. resume never repeats finished cases.
     retry_failed creates a new draft only after an explicit rerun request; it is not
     transport-idempotent, so after an uncertain response use list instead of retrying.
-    delete removes a non-active batch record after an explicit user request; it keeps
+    delete removes a non-active batch and its task sessions, reports and files after
-    already executed task sessions and reports. Confirm the batch ID with get first.
+    an explicit user request. Confirm the batch ID with get first; deletion is irreversible.
     Restarted batches remain paused. No automatic failed-case retries or action replay.
     """
     if action == "create":
@@ -270,7 +277,12 @@ async def mobile_export_report(
         return {
             "batch_id": bid,
             "files": [
-                await _download(f"/api/automation/batches/{bid}/archive", f"batch-{bid}.zip")
+                await _download(
+                    f"/api/automation/batches/{bid}/archive",
+                    f"batch-{bid}.zip",
+                    owner_kind="batches",
+                    owner_id=bid,
+                )
             ],
         }
     sid = _id(session_id)
@@ -286,10 +298,15 @@ async def mobile_export_report(
     ):
         raise ValueError("formats 需选择 docx、xlsx、screenshots、video 或 all")
     report = await _request("GET", f"/api/automation/reports/{sid}")
+    from apps.admin_console.services.report_export import archive_case_name
+
+    label = archive_case_name(report)
     files = [
         await _download(
             f"/api/automation/reports/{sid}/{fmt}",
-            f"task-{sid}.{fmt}" if fmt in {"docx", "xlsx"} else f"task-{sid}-{fmt}.zip",
+            f"task-{sid}.{fmt}" if fmt in {"docx", "xlsx"} else f"{label}-{fmt}.zip",
+            owner_kind="sessions",
+            owner_id=sid,
         )
         for fmt in dict.fromkeys(chosen)
     ]

mcp_server/tools/task_manager.py

@@ -282,8 +282,10 @@ def mobile_manage_task(
     - **'resume'**: Queues a paused task for its device again; optional `instruction`
       provides guidance before the next action.
     - **'inject_instruction'**: Injects real-time guidance mid-flight when the
-      subagent errs, stalls, or loops. Applied at the start of the next
+      subagent errs, stalls, or loops. An in-flight model response or read-only
-      planning turn (Pro) or the next reactive loop (Flash). Requires
+      helper is cancelled immediately, then the runner observes the device again
+      and consumes the new guidance. An already-started device action finishes
+      safely before the runner changes direction. Requires
       `instruction` (unless `release_loop=True`). To end a continuous
       monitoring task ([Loop:continuous] milestone) gracefully, you MUST pass
       `release_loop=True` — this is the only signal that unlocks the
@@ -697,7 +699,7 @@ def mobile_manage_task(
             return {
                 "trace_id": trace_id,
                 "status": current_status,
-                "message": f"Successfully injected instruction{suffix}: '{instruction}'",
+                "message": f"Guidance accepted and current model step interrupted{suffix}; check guidance_history for consumption.",
             }
         except Exception as e:
             return {

pyproject.toml

@@ -14,7 +14,7 @@
 
 [project]
 name = "artemis"
-version = "1.1.0"
+version = "1.2.2"
 description = "Autonomous AI Assistant for Mobile Automation"
 
 authors = [

scripts/bootstrap_python.ps1

@@ -1,42 +1,48 @@
-# Python bootstrap shared by the Windows launcher and its isolated checks.
+# Python bootstrap shared by the Windows launcher and its isolated checks.
-# Keep this file ASCII for Windows PowerShell 5.1.
+# Save as UTF-8 with BOM so Windows PowerShell 5.1 reads Chinese messages correctly.
+
+function Get-BootstrapText {
+    param([string]$English, [string]$Chinese)
+    if ($env:ARTEMIS_LAUNCH_LANG -eq 'zh-CN') { return $Chinese }
+    return $English
+}
 
 function Initialize-ArtemisPython {
     param([Parameter(Mandatory=$true)][string]$ProjectRoot)
 
     $ProjectRoot = (Resolve-Path -LiteralPath $ProjectRoot -ErrorAction Stop).Path
     if (-not (Test-Path -LiteralPath (Join-Path $ProjectRoot 'pyproject.toml'))) {
-        throw 'pyproject.toml is missing. Extract the complete source archive first.'
+        throw (Get-BootstrapText 'pyproject.toml is missing. Extract the complete source archive first.' '缺少 pyproject.toml；请重新解压完整源码包。')
     }
     if (-not (Test-Path -LiteralPath (Join-Path $ProjectRoot 'uv.lock'))) {
-        throw 'uv.lock is missing. Extract the complete source archive first.'
+        throw (Get-BootstrapText 'uv.lock is missing. Extract the complete source archive first.' '缺少 uv.lock；请重新解压完整源码包。')
     }
 
     if (-not (Test-CommandExists 'uv')) {
         if ($ArtemisDownloads -and $ArtemisDownloads.python_index) {
-            Write-Host '   [INSTALL] Installing uv from the selected Python mirror...' -ForegroundColor Cyan
+            Write-Host (Get-BootstrapText '   [INSTALL] Installing uv from the selected Python mirror...' '   [安装] 正在从选定的 Python 镜像安装 uv...') -ForegroundColor Cyan
             Install-ArtemisUvFromIndex -IndexUrl $ArtemisDownloads.python_index
         } else {
-            Write-Host '   [INSTALL] uv was not found. Installing from the configured installer...' -ForegroundColor Cyan
+            Write-Host (Get-BootstrapText '   [INSTALL] uv was not found. Installing from the configured installer...' '   [安装] 未找到 uv，正在下载安装...') -ForegroundColor Cyan
             $installer = Join-Path ([IO.Path]::GetTempPath()) ('artemis-uv-' + [guid]::NewGuid().ToString('N') + '.ps1')
             try {
                 $installerUrl = if ($ArtemisDownloads) { $ArtemisDownloads.uv_installer_url } else { 'https://astral.sh/uv/install.ps1' }
                 if (-not (Invoke-DownloadFile -Uri $installerUrl -OutFile $installer)) {
-                    throw 'Could not download uv. Check your network/proxy and retry.'
+                    throw (Get-BootstrapText 'Could not download uv. Check your network/proxy and retry.' 'uv 下载失败；请检查网络、代理或镜像后重试。')
                 }
                 & powershell.exe -NoProfile -ExecutionPolicy Bypass -File $installer | Out-Host
-                if ($LASTEXITCODE -ne 0) { throw "uv installation failed (exit $LASTEXITCODE)." }
+                if ($LASTEXITCODE -ne 0) { throw (Get-BootstrapText "uv installation failed (exit $LASTEXITCODE)." "uv 安装失败（退出码 $LASTEXITCODE）。") }
             } finally {
                 Remove-Item -LiteralPath $installer -Force -ErrorAction SilentlyContinue
             }
         }
         Update-EnvironmentPath
     } else {
-        Write-Host '   [SKIP] uv is already installed.' -ForegroundColor Green
+        Write-Host (Get-BootstrapText '   [SKIP] uv is already installed.' '   [复用] uv 已安装，跳过下载。') -ForegroundColor Green
     }
-    if (-not (Test-CommandExists 'uv')) { throw 'uv is still unavailable. Install it from https://astral.sh/uv/ and retry.' }
+    if (-not (Test-CommandExists 'uv')) { throw (Get-BootstrapText 'uv is still unavailable. Install it from https://astral.sh/uv/ and retry.' '仍无法运行 uv；请检查安装并重试。') }
     & uv --version | Out-Host
-    if ($LASTEXITCODE -ne 0) { throw 'The installed uv could not run. Repair its installation and retry.' }
+    if ($LASTEXITCODE -ne 0) { throw (Get-BootstrapText 'The installed uv could not run. Repair its installation and retry.' '已安装的 uv 无法运行；请修复安装后重试。') }
 
     $venvDir = Join-Path $ProjectRoot '.venv'
     $pythonExe = Join-Path $venvDir 'Scripts\python.exe'
@@ -45,18 +51,18 @@ function Initialize-ArtemisPython {
     Push-Location -LiteralPath $ProjectRoot
     try {
         if (-not (Test-Path -LiteralPath $venvDir)) {
-            Write-Host '   [INSTALL] Creating .venv with Python 3.12 (downloaded automatically if needed)...' -ForegroundColor Cyan
+            Write-Host (Get-BootstrapText '   [INSTALL] Creating .venv with Python 3.12 (downloaded automatically if needed)...' '   [安装] 正在创建 Python 3.12 虚拟环境 .venv；缺少 Python 时自动下载...') -ForegroundColor Cyan
             & uv venv --python 3.12 $venvDir | Out-Host
-            if ($LASTEXITCODE -ne 0) { throw 'Could not create .venv. Check the download errors above and retry.' }
+            if ($LASTEXITCODE -ne 0) { throw (Get-BootstrapText 'Could not create .venv. Check the download errors above and retry.' '.venv 创建失败；请查看上方下载错误并重试。') }
         } else {
-            Write-Host '   [SKIP] Reusing the existing project .venv.' -ForegroundColor Green
+            Write-Host (Get-BootstrapText '   [SKIP] Reusing the existing project .venv.' '   [复用] 已有项目 .venv，跳过创建。') -ForegroundColor Green
         }
         if (-not (Test-Path -LiteralPath $pythonExe)) {
-            throw 'The existing .venv is incomplete. Rename it as a backup, then rerun start.bat.'
+            throw (Get-BootstrapText 'The existing .venv is incomplete. Rename it as a backup, then rerun start.bat.' '已有 .venv 不完整。先重命名备份，再运行 start-cn.bat。')
         }
         & $pythonExe -c 'import sys; sys.exit(0 if sys.version_info >= (3, 12) and sys.prefix != sys.base_prefix else 1)' | Out-Host
         if ($LASTEXITCODE -ne 0) {
-            throw 'The existing .venv is unusable or older than Python 3.12. Rename it as a backup, then rerun start.bat.'
+            throw (Get-BootstrapText 'The existing .venv is unusable or older than Python 3.12. Rename it as a backup, then rerun start.bat.' '已有 .venv 无法使用或 Python 低于 3.12。先重命名备份，再运行 start-cn.bat。')
         }
 
         # A cheap check skips installation when the lock and installed packages agree.
@@ -64,19 +70,19 @@ function Initialize-ArtemisPython {
         $lockOption = if ($ArtemisDownloads -and $ArtemisDownloads.python_index) { '--frozen' } else { '--locked' }
         & uv sync --check $lockOption --no-dev --inexact --quiet 2>$null | Out-Host
         if ($LASTEXITCODE -eq 0) {
-            Write-Host '   [SKIP] Python dependencies are already ready.' -ForegroundColor Green
+            Write-Host (Get-BootstrapText '   [SKIP] Python dependencies are already ready.' '   [复用] Python 依赖已就绪。') -ForegroundColor Green
         } else {
-            Write-Host '   [INSTALL] Synchronizing dependencies from uv.lock...' -ForegroundColor Cyan
+            Write-Host (Get-BootstrapText '   [INSTALL] Synchronizing dependencies from uv.lock...' '   [安装] 正在按 uv.lock 同步 Python 依赖...') -ForegroundColor Cyan
             if ($ArtemisDownloads -and $ArtemisDownloads.python_index) {
                 Install-ArtemisLockedDependencies -PythonExe $pythonExe -IndexUrl $ArtemisDownloads.python_index
             } else {
                 & uv sync --locked --no-dev --inexact | Out-Host
-                if ($LASTEXITCODE -ne 0) { throw 'Dependency installation failed. Fix the error above and rerun start.bat.' }
+                if ($LASTEXITCODE -ne 0) { throw (Get-BootstrapText 'Dependency installation failed. Fix the error above and rerun start.bat.' '依赖安装失败；请处理上方错误，再运行 start-cn.bat。') }
             }
         }
         & $pythonExe -c 'import artemis, uvicorn, fastapi, langchain_openai' | Out-Host
-        if ($LASTEXITCODE -ne 0) { throw 'Python dependency verification failed. The UI will not be started.' }
+        if ($LASTEXITCODE -ne 0) { throw (Get-BootstrapText 'Python dependency verification failed. The UI will not be started.' 'Python 依赖验证失败，网页不会启动。') }
-        Write-Host '   [OK] Python environment is ready.' -ForegroundColor Green
+        Write-Host (Get-BootstrapText '   [OK] Python environment is ready.' '   [完成] Python 环境已就绪。') -ForegroundColor Green
         return $pythonExe
     } finally {
         Pop-Location

scripts/download_config.ps1

@@ -1,5 +1,5 @@
-# Download settings are process-local; never edit global pip/npm/uv settings.
+# Download settings are process-local; never edit global pip/npm/uv settings.
-# Keep this file ASCII for Windows PowerShell 5.1.
+# Save as UTF-8 with BOM so Windows PowerShell 5.1 reads Chinese messages correctly.
 
 function Initialize-ArtemisDownloads {
     param([string]$ProjectRoot, [string]$Mode)
@@ -42,8 +42,12 @@ function Initialize-ArtemisDownloads {
     # Official scrcpy v4.1 win64 release digest. Verify every mirror/override equally.
     $values.scrcpy_sha256 = '5b12172b3264b2889f4583ee64752ce832e29bc8b1089dca81093459697165db'
     $script:ArtemisDownloads = [pscustomobject]$values
+    if ($env:ARTEMIS_LAUNCH_LANG -eq 'zh-CN') {
+        Write-Host "   [镜像] 使用国内下载源（config/downloads.json）。" -ForegroundColor Cyan
+    } else {
         Write-Host "   [INFO] Download mode: $Mode (config/downloads.json)." -ForegroundColor Cyan
     }
+}
 
 function Install-ArtemisUvFromIndex {
     param([string]$IndexUrl, [string]$InstallDir = (Join-Path $env:USERPROFILE '.local\bin'))

scripts/package_source.py

@@ -1,10 +1,13 @@
-"""Create a portable source ZIP without environments, builds, or local credentials."""
+"""Create a clean, shallow Git checkout ZIP that can fast-forward on launch."""
 
 import argparse
 from datetime import datetime
 import hashlib
 import os
 from pathlib import Path
+import subprocess
+import tempfile
+from urllib.parse import urlsplit
 import zipfile
 
 
@@ -83,6 +86,9 @@ EXCLUDED_SUFFIXES = {
     ".swo",
 }
 
+GIT_METADATA_FILES = {"HEAD", "config", "index", "shallow", "packed-refs"}
+GIT_METADATA_DIRS = {"objects", "refs"}
+
 
 def excluded(path: Path) -> bool:
     parts = tuple(part.lower() for part in path.parts)
@@ -116,22 +122,116 @@ def source_files(root: Path):
                 yield path
 
 
+def git(root: Path, *args: str) -> str:
+    result = subprocess.run(
+        ["git", "-C", str(root), *args],
+        capture_output=True,
+        text=True,
+        encoding="utf-8",
+        errors="replace",
+        timeout=90,
+    )
+    if result.returncode:
+        raise RuntimeError(f"git {args[0]} failed (exit {result.returncode})")
+    return result.stdout.strip()
+
+
+def git_metadata_files(root: Path):
+    metadata = root / ".git"
+    for name in sorted(GIT_METADATA_FILES):
+        path = metadata / name
+        if path.is_file():
+            yield path
+    for name in sorted(GIT_METADATA_DIRS):
+        directory = metadata / name
+        if directory.exists():
+            yield from source_files_without_filter(directory)
+    for name in ("exclude", "sparse-checkout"):
+        path = metadata / "info" / name
+        if path.is_file():
+            yield path
+
+
+def source_files_without_filter(root: Path):
+    for directory, dirs, files in os.walk(root, followlinks=False):
+        current = Path(directory)
+        dirs[:] = sorted(name for name in dirs if not (current / name).is_symlink())
+        for name in sorted(files):
+            path = current / name
+            if not path.is_symlink():
+                yield path
+
+
+def release_remote(root: Path) -> tuple[str, str]:
+    if not (root / ".git").exists():
+        raise ValueError("Source packaging requires a Git checkout")
+    if git(root, "status", "--porcelain", "--untracked-files=no"):
+        raise ValueError("Commit tracked changes before packaging a release")
+    branch = git(root, "symbolic-ref", "--quiet", "--short", "HEAD")
+    remote = git(root, "config", "--get", f"branch.{branch}.remote")
+    merge_ref = git(root, "config", "--get", f"branch.{branch}.merge")
+    if remote == "." or merge_ref != f"refs/heads/{branch}":
+        raise ValueError("The current branch must track the same branch on a remote")
+    url = git(root, "remote", "get-url", remote)
+    parsed = urlsplit(url)
+    if parsed.scheme != "https" or not parsed.hostname or parsed.username or parsed.password:
+        raise ValueError("The release upstream must be a credential-free HTTPS URL")
+    if parsed.query or parsed.fragment:
+        raise ValueError("The release upstream must not contain a query or fragment")
+    return branch, url
+
+
 def package_source(root: Path, output: Path) -> tuple[int, str]:
     root = root.resolve()
     output = output.resolve()
+    branch, remote_url = release_remote(root)
+    revision = git(root, "rev-parse", "HEAD")
     output.parent.mkdir(parents=True, exist_ok=True)
     temporary = output.with_suffix(".zip.tmp")
-    files = [p for p in source_files(root) if p.resolve() not in {output, temporary}]
     try:
+        with tempfile.TemporaryDirectory(prefix="artemis-release-") as work:
+            checkout = Path(work) / "artemis"
+            git(
+                root,
+                "clone",
+                "--depth",
+                "1",
+                "--single-branch",
+                "--branch",
+                branch,
+                root.as_uri(),
+                str(checkout),
+            )
+            git(checkout, "remote", "set-url", "origin", remote_url)
+            # Generated assets are tracked upstream but must not appear in the
+            # unpacked source. Sparse checkout keeps the Git index clean.
+            omitted = [
+                name for name in git(checkout, "ls-files").splitlines() if excluded(Path(name))
+            ]
+            patterns = ["/*", *(f"!/{name}" for name in omitted)]
+            git(checkout, "sparse-checkout", "set", "--no-cone", *patterns)
+            # Rebuilt assets in sparse paths must not look like user edits.
+            info_exclude = checkout / ".git" / "info" / "exclude"
+            with info_exclude.open("a", encoding="utf-8") as stream:
+                stream.write("\n".join(["", *(f"/{name}" for name in omitted), ""]))
+            if git(checkout, "rev-parse", "HEAD") != revision or git(
+                checkout, "status", "--porcelain"
+            ):
+                raise RuntimeError("The packaged checkout is not clean at the requested revision")
+            files = [*source_files(checkout), *git_metadata_files(checkout)]
+            names = {
+                str(Path("artemis") / path.relative_to(checkout)).replace("\\", "/")
+                for path in files
+            }
             with zipfile.ZipFile(temporary, "w", zipfile.ZIP_DEFLATED, compresslevel=6) as archive:
                 for path in files:
-                archive.write(path, Path("artemis") / path.relative_to(root))
+                    archive.write(path, Path("artemis") / path.relative_to(checkout))
             with zipfile.ZipFile(temporary) as archive:
                 bad_file = archive.testzip()
-            if bad_file:
+                if bad_file or set(archive.namelist()) != names:
-                raise RuntimeError(f"ZIP integrity check failed: {bad_file}")
+                    raise RuntimeError(
-            if any(excluded(Path(name).relative_to("artemis")) for name in archive.namelist()):
+                        f"ZIP integrity check failed: {bad_file or 'file list mismatch'}"
-                raise RuntimeError("An excluded file was found in the source archive")
+                    )
         temporary.replace(output)
     finally:
         temporary.unlink(missing_ok=True)

scripts/start.ps1

@@ -1,4 +1,4 @@
-# Copyright 2026 Google LLC
+# Copyright 2026 Google LLC
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -18,12 +18,19 @@ param(
     [switch]$NoOpen = $false,
     [switch]$SetupOnly = $false,
     [switch]$SkipUpdate = $false,
+    [switch]$SkipMcpSync = $false,
     [ValidateSet('Official', 'China')][string]$Mirror
 )
 
 $ErrorActionPreference = "Continue"
 [Console]::OutputEncoding = [System.Text.Encoding]::UTF8
 
+function Get-LaunchText {
+    param([string]$English, [string]$Chinese)
+    if ($env:ARTEMIS_LAUNCH_LANG -eq 'zh-CN') { return $Chinese }
+    return $English
+}
+
 # Ensure modern TLS protocols are enabled for downloads (GitHub releases, nodejs.org, Google repositories)
 try {
     [System.Net.ServicePointManager]::SecurityProtocol = [System.Net.ServicePointManager]::SecurityProtocol -bor [System.Net.SecurityProtocolType]::Tls12
@@ -44,12 +51,13 @@ if ((-not $SkipUpdate) -and (Test-Path -LiteralPath $existingPython)) {
         $reloadArgs = @('-NoProfile', '-ExecutionPolicy', 'Bypass', '-File', (Join-Path $ScriptDir 'start.ps1'), '-Port', $Port, '-SkipUpdate')
         if ($NoOpen) { $reloadArgs += '-NoOpen' }
         if ($SetupOnly) { $reloadArgs += '-SetupOnly' }
+        if ($SkipMcpSync) { $reloadArgs += '-SkipMcpSync' }
         if ($Mirror) { $reloadArgs += @('-Mirror', $Mirror) }
         & powershell.exe @reloadArgs
         exit $LASTEXITCODE
     }
     if ($updateExit -ne 0) {
-        Write-Host '   [ERROR] Source update check failed. Resolve the error above, or use -SkipUpdate for local startup.' -ForegroundColor Red
+        Write-Host (Get-LaunchText '   [ERROR] Source update check failed. Resolve the error above, or use -SkipUpdate for local startup.' '   [错误] 源码更新检查失败。请处理上方错误；要运行当前源码可传入 -SkipUpdate。') -ForegroundColor Red
         exit 1
     }
 }
@@ -58,12 +66,12 @@ if ((-not $SkipUpdate) -and (Test-Path -LiteralPath $existingPython)) {
 try {
     Initialize-ArtemisDownloads -ProjectRoot $RootDir -Mode $Mirror
 } catch {
-    Write-Host "   [ERROR] Invalid download settings: $_" -ForegroundColor Red
+    Write-Host (Get-LaunchText "   [ERROR] Invalid download settings: $_" "   [错误] 下载配置无效：$_") -ForegroundColor Red
     exit 1
 }
 
 Write-Host "======================================================" -ForegroundColor Cyan
-Write-Host "       Artemis Autonomous Mobile Agent UI           " -ForegroundColor Cyan
+Write-Host (Get-LaunchText "       Artemis Autonomous Mobile Agent UI           " "       ARTEMIS 手机自动化测试平台") -ForegroundColor Cyan
 Write-Host "======================================================" -ForegroundColor Cyan
 Write-Host ""
 
@@ -181,7 +189,7 @@ function Install-PortablePlatformTools {
         $env:PATH = "$ptDir;$env:PATH"
         return $true
     }
-    Write-Host "   [INFO] Installing Android platform-tools (adb) in user space..." -ForegroundColor Cyan
+        Write-Host (Get-LaunchText "   [INFO] Installing Android platform-tools (adb) in user space..." "   [安装] 正在安装 Android 调试工具 adb（当前用户）...") -ForegroundColor Cyan
     try {
         $zipPath = "$env:TEMP\platform-tools-windows.zip"
         if (Invoke-DownloadFile -Uri $ArtemisDownloads.adb_url -OutFile $zipPath) {
@@ -190,12 +198,12 @@ function Install-PortablePlatformTools {
             Remove-Item $zipPath -Force -ErrorAction SilentlyContinue
             if (Test-Path "$ptDir\adb.exe") {
                 $env:PATH = "$ptDir;$env:PATH"
-                Write-Host "   [OK] adb installed in user space." -ForegroundColor Green
+        Write-Host (Get-LaunchText "   [OK] adb installed in user space." "   [完成] adb 已安装。") -ForegroundColor Green
                 return $true
             }
         }
     } catch {
-        Write-Host "   [WARN] Failed to install portable platform-tools: $_" -ForegroundColor DarkYellow
+        Write-Host (Get-LaunchText "   [WARN] Failed to install portable platform-tools: $_" "   [提示] adb 安装失败：$_") -ForegroundColor DarkYellow
     }
     return $false
 }
@@ -217,9 +225,9 @@ function Install-PortableScrcpy {
         }
     }
 
-    Write-Host "   [INFO] Installing portable scrcpy in user space..." -ForegroundColor Cyan
+        Write-Host (Get-LaunchText "   [INFO] Installing portable scrcpy in user space..." "   [安装] 正在安装 scrcpy（当前用户）...") -ForegroundColor Cyan
     if ($ArtemisDownloads.mode -eq 'China' -and $ArtemisDownloads.scrcpy_url.StartsWith('https://github.com/')) {
-        Write-Host '   [WARN] China mode has no non-GitHub scrcpy source. Configure overrides.scrcpy_url or install scrcpy manually.' -ForegroundColor Yellow
+            Write-Host (Get-LaunchText '   [WARN] China mode has no non-GitHub scrcpy source. Configure overrides.scrcpy_url or install scrcpy manually.' '   [提示] 国内镜像中没有可用的 scrcpy 下载地址；请设置 config/downloads.json 的 overrides.scrcpy_url，或自行安装。') -ForegroundColor Yellow
         return $false
     }
     try {
@@ -244,12 +252,12 @@ function Install-PortableScrcpy {
             Remove-Item $extractDir -Recurse -Force -ErrorAction SilentlyContinue
             if (Test-Path "$scrcpyDir\scrcpy.exe") {
                 $env:PATH = "$scrcpyDir;$env:PATH"
-                Write-Host "   [OK] Portable scrcpy installed in user space." -ForegroundColor Green
+        Write-Host (Get-LaunchText "   [OK] Portable scrcpy installed in user space." "   [完成] scrcpy 已安装。") -ForegroundColor Green
                 return $true
             }
         }
     } catch {
-        Write-Host "   [WARN] Failed to install portable scrcpy: $_" -ForegroundColor DarkYellow
+        Write-Host (Get-LaunchText "   [WARN] Failed to install portable scrcpy: $_" "   [提示] scrcpy 安装失败：$_") -ForegroundColor DarkYellow
     }
     return $false
 }
@@ -295,7 +303,7 @@ function Install-PortableNode {
         }
     }
 
-    Write-Host "   [INFO] Installing portable Node.js LTS (v22.23.2) in user space..." -ForegroundColor Cyan
+        Write-Host (Get-LaunchText "   [INFO] Installing portable Node.js LTS (v22.23.2) in user space..." "   [安装] 正在安装 Node.js LTS v22.23.2（当前用户）...") -ForegroundColor Cyan
     try {
         $nodeVer = "v22.23.2"
         $arch = if ([System.Environment]::Is64BitOperatingSystem) {
@@ -319,12 +327,12 @@ function Install-PortableNode {
             Remove-Item $extractDir -Recurse -Force -ErrorAction SilentlyContinue
             if (Test-Path "$nodeDir\node.exe") {
                 $env:PATH = "$nodeDir;$env:PATH"
-                Write-Host "   [OK] Portable Node.js $nodeVer installed in user space." -ForegroundColor Green
+        Write-Host (Get-LaunchText "   [OK] Portable Node.js $nodeVer installed in user space." "   [完成] Node.js $nodeVer 已安装。") -ForegroundColor Green
                 return $true
             }
         }
     } catch {
-        Write-Host "   [WARN] Failed to install portable Node.js: $_" -ForegroundColor DarkYellow
+        Write-Host (Get-LaunchText "   [WARN] Failed to install portable Node.js: $_" "   [提示] Node.js 安装失败：$_") -ForegroundColor DarkYellow
     }
     return $false
 }
@@ -344,16 +352,21 @@ try {
 if (-not (Test-Path -LiteralPath (Join-Path $RootDir '.env'))) {
     if (Test-Path -LiteralPath (Join-Path $RootDir '.env.example')) {
         Copy-Item -LiteralPath (Join-Path $RootDir '.env.example') -Destination (Join-Path $RootDir '.env') -ErrorAction Stop
-        Write-Host '   [OK] Created .env from .env.example. Configure your model in the web UI.' -ForegroundColor Green
+        Write-Host (Get-LaunchText '   [OK] Created .env from .env.example. Configure your model in the web UI.' '   [完成] 已按模板创建 .env；请在网页中配置模型。') -ForegroundColor Green
     }
 }
-Write-Host '   [CHECK] Refreshing already-configured MCP clients...' -ForegroundColor Cyan
+if (-not $SkipMcpSync) {
+    Write-Host (Get-LaunchText '   [CHECK] Installing/updating MCP for detected AI clients...' '   [检查] 正在为检测到的 AI 客户端安装或更新 MCP...') -ForegroundColor Cyan
     & $ArtemisPython (Join-Path $ScriptDir 'update_installation.py') mcp
     if ($LASTEXITCODE -ne 0) {
-    Write-Host '   [WARN] MCP refresh failed. Existing client settings were not replaced; check the errors above.' -ForegroundColor Yellow
+        Write-Host (Get-LaunchText '   [ERROR] MCP synchronization failed. Fix the configuration above, or use -SkipMcpSync to run the web UI without MCP.' '   [错误] MCP 同步失败。请修复上方配置；仅需启动网页时可使用 -SkipMcpSync。') -ForegroundColor Red
+        exit 1
+    }
+} else {
+    Write-Host (Get-LaunchText '   [SKIP] MCP synchronization was skipped.' '   [跳过] 已跳过 MCP 同步。') -ForegroundColor Yellow
 }
 if ($SetupOnly) {
-    Write-Host '   [OK] Setup complete. Run start.bat to launch Artemis.' -ForegroundColor Green
+    Write-Host (Get-LaunchText '   [OK] Setup complete. Run start.bat to launch Artemis.' '   [完成] 环境已准备好。运行 start-cn.bat 启动 ARTEMIS。') -ForegroundColor Green
     exit 0
 }
 
@@ -371,8 +384,8 @@ if ($missingCore.Count -gt 0) {
     $useWinGet = $false
     if ($ArtemisDownloads.mode -ne 'China' -and (Test-CommandExists "winget")) {
         if ([Console]::IsInputRedirected -eq $false) {
-            Write-Host "   [INFO] Missing components detected: $($missingCore -join ', ')." -ForegroundColor Cyan
+            Write-Host (Get-LaunchText "   [INFO] Missing components detected: $($missingCore -join ', ')." "   [检查] 缺少组件：$($missingCore -join ', ')。") -ForegroundColor Cyan
-            $ans = Read-Host "      Install system packages via WinGet? [Y/n]"
+            $ans = Read-Host (Get-LaunchText "      Install system packages via WinGet? [Y/n]" "      通过 WinGet 安装？[Y/n]")
             if ($ans -eq "" -or $ans -match "^[Yy]") {
                 $useWinGet = $true
             }
@@ -382,7 +395,7 @@ if ($missingCore.Count -gt 0) {
     }
 
     if ($useWinGet) {
-        Write-Host "   [INFO] Auto-installing missing components ($($missingCore -join ', '))..." -ForegroundColor DarkYellow
+        Write-Host (Get-LaunchText "   [INFO] Auto-installing missing components ($($missingCore -join ', '))..." "   [安装] 正在安装缺少的组件：$($missingCore -join ', ')...") -ForegroundColor DarkYellow
         if ($missingCore -contains "adb") {
             winget install --id Google.PlatformTools -e --accept-source-agreements --accept-package-agreements --silent 2>$null | Out-Null
         }
@@ -401,7 +414,7 @@ if ($missingCore.Count -gt 0) {
     }
     if (-not (Test-CommandExists "scrcpy")) {
         if (-not (Install-PortableScrcpy)) {
-            Write-Host '   [WARN] scrcpy download failed. Set overrides.scrcpy_url in config/downloads.json to a reachable release ZIP, then retry.' -ForegroundColor Yellow
+            Write-Host (Get-LaunchText '   [WARN] scrcpy download failed. Set overrides.scrcpy_url in config/downloads.json to a reachable release ZIP, then retry.' '   [提示] scrcpy 下载失败。请在 config/downloads.json 中设置可访问的 overrides.scrcpy_url，然后重试。') -ForegroundColor Yellow
         }
     }
 }
@@ -415,19 +428,19 @@ $ShowcaseIndexAlt1 = "$RootDir\apps\showcase_ui\dist\browser\index.html"
 $ShowcaseIndexAlt2 = "$RootDir\apps\showcase_ui\dist\index.html"
 & $ArtemisPython (Join-Path $ScriptDir 'update_installation.py') frontend-check
 $frontendChanged = $LASTEXITCODE -eq 10
-if ($LASTEXITCODE -notin @(0, 10)) { Write-Host '   [ERROR] Could not check frontend sources.' -ForegroundColor Red; exit 1 }
+if ($LASTEXITCODE -notin @(0, 10)) { Write-Host (Get-LaunchText '   [ERROR] Could not check frontend sources.' '   [错误] 无法检查前端源码。') -ForegroundColor Red; exit 1 }
 if ($frontendChanged -or ((-not (Test-Path $ShowcaseIndex)) -and (-not (Test-Path $ShowcaseIndexAlt1)) -and (-not (Test-Path $ShowcaseIndexAlt2)))) {
     if (-not (Test-NodeCompatible)) {
         if (Test-CommandExists "node") {
             $curVer = (& node -v 2>$null)
-            Write-Host "   [INFO] Detected Node.js $curVer, but Angular CLI requires Node.js >= v22.22.0." -ForegroundColor Yellow
+            Write-Host (Get-LaunchText "   [INFO] Detected Node.js $curVer, but Angular CLI requires Node.js >= v22.22.0." "   [检查] 检测到 Node.js $curVer；前端需要 v22.22.0 或更新版本。") -ForegroundColor Yellow
         } else {
-            Write-Host "   [INFO] Node.js/npm not found (required for Showcase UI)." -ForegroundColor Cyan
+            Write-Host (Get-LaunchText "   [INFO] Node.js/npm not found (required for Showcase UI)." "   [检查] 未找到 Node.js/npm，网页构建需要安装。") -ForegroundColor Cyan
         }
 
         # 1. Try nvm if available on Windows
         if ($ArtemisDownloads.mode -ne 'China' -and (Test-CommandExists "nvm")) {
-            Write-Host "   [INFO] Installing Node.js 22 LTS via nvm..." -ForegroundColor Cyan
+            Write-Host (Get-LaunchText "   [INFO] Installing Node.js 22 LTS via nvm..." "   [安装] 正在通过 nvm 安装 Node.js 22 LTS...") -ForegroundColor Cyan
             & nvm install 22.23.2 | Out-Null
             & nvm use 22.23.2 | Out-Null
             Update-EnvironmentPath
@@ -438,8 +451,8 @@ if ($frontendChanged -or ((-not (Test-Path $ShowcaseIndex)) -and (-not (Test-Pat
             $useWinGetNode = $false
             if ($ArtemisDownloads.mode -ne 'China' -and (Test-CommandExists "winget")) {
                 if ([Console]::IsInputRedirected -eq $false) {
-                    Write-Host "   [INFO] Node.js >= v22.22.0 required for Showcase UI." -ForegroundColor Cyan
+                    Write-Host (Get-LaunchText "   [INFO] Node.js >= v22.22.0 required for Showcase UI." "   [检查] 网页需要 Node.js v22.22.0 或更新版本。") -ForegroundColor Cyan
-                    $ans = Read-Host "      Install/Upgrade Node.js via WinGet (may require Administrator)? [Y/n]"
+                    $ans = Read-Host (Get-LaunchText "      Install/Upgrade Node.js via WinGet (may require Administrator)? [Y/n]" "      通过 WinGet 安装/升级 Node.js（可能需要管理员权限）？[Y/n]")
                     if ($ans -eq "" -or $ans -match "^[Yy]") {
                         $useWinGetNode = $true
                     }
@@ -449,7 +462,7 @@ if ($frontendChanged -or ((-not (Test-Path $ShowcaseIndex)) -and (-not (Test-Pat
             }
 
             if ($useWinGetNode) {
-                Write-Host "   [INFO] Installing/Upgrading Node.js LTS via WinGet..." -ForegroundColor Yellow
+                Write-Host (Get-LaunchText "   [INFO] Installing/Upgrading Node.js LTS via WinGet..." "   [安装] 正在通过 WinGet 安装/升级 Node.js LTS...") -ForegroundColor Yellow
                 winget install --id OpenJS.NodeJS.LTS -e --accept-source-agreements --accept-package-agreements --silent 2>$null | Out-Null
                 Update-EnvironmentPath
             }
@@ -463,36 +476,36 @@ if ($frontendChanged -or ((-not (Test-Path $ShowcaseIndex)) -and (-not (Test-Pat
 
     if (Test-NodeCompatible) {
         $nodeVer = (& node -v 2>$null)
-        Write-Host "   [OK] Node.js $nodeVer is ready." -ForegroundColor Green
+        Write-Host (Get-LaunchText "   [OK] Node.js $nodeVer is ready." "   [完成] Node.js $nodeVer 已就绪。") -ForegroundColor Green
-        Write-Host "   [INFO] Showcase UI sources/dependencies changed or build missing. Compiling..." -ForegroundColor Yellow
+        Write-Host (Get-LaunchText "   [INFO] Showcase UI sources/dependencies changed or build missing. Compiling..." "   [构建] 前端源码/依赖有变化或缺少构建结果，准备重新构建...") -ForegroundColor Yellow
         Push-Location "$RootDir\apps\showcase_ui"
         try {
             $npmExec = if (Test-CommandExists "npm.cmd") { "npm.cmd" } else { "npm" }
-            Write-Host "   [INFO] Installing frontend npm dependencies..." -ForegroundColor Cyan
+            Write-Host (Get-LaunchText "   [INFO] Installing frontend npm dependencies..." "   [安装] 正在安装前端 npm 依赖...") -ForegroundColor Cyan
             & $npmExec ci --no-audit --no-fund --loglevel=error
             if ($LASTEXITCODE -ne 0) {
                 throw "npm ci failed (exit $LASTEXITCODE). Check the network and retry."
             }
-            Write-Host "   [INFO] Building Angular frontend application..." -ForegroundColor Cyan
+            Write-Host (Get-LaunchText "   [INFO] Building Angular frontend application..." "   [构建] 正在构建 Angular 网页...") -ForegroundColor Cyan
             & $npmExec run build
             if ($LASTEXITCODE -ne 0) { throw "Frontend build failed (exit $LASTEXITCODE)." }
             if (Test-Path $ShowcaseIndex) {
-                Write-Host "   [OK] Showcase UI compiled successfully." -ForegroundColor Green
+                Write-Host (Get-LaunchText "   [OK] Showcase UI compiled successfully." "   [完成] 网页构建成功。") -ForegroundColor Green
             } elseif ((Test-Path $ShowcaseIndexAlt1) -or (Test-Path $ShowcaseIndexAlt2)) {
-                Write-Host "   [OK] Showcase UI compiled successfully." -ForegroundColor Green
+                Write-Host (Get-LaunchText "   [OK] Showcase UI compiled successfully." "   [完成] 网页构建成功。") -ForegroundColor Green
             } else {
                 throw 'Frontend build did not produce index.html.'
             }
             & $ArtemisPython (Join-Path $ScriptDir 'update_installation.py') frontend-mark
             if ($LASTEXITCODE -ne 0) { throw 'Could not save frontend build fingerprint.' }
         } catch {
-            Write-Host "   [ERROR] Failed to build Showcase UI: $_" -ForegroundColor Red
+            Write-Host (Get-LaunchText "   [ERROR] Failed to build Showcase UI: $_" "   [错误] 网页构建失败：$_") -ForegroundColor Red
             exit 1
         } finally {
             Pop-Location
         }
     } else {
-        Write-Host "   [ERROR] A compatible Node.js/npm could not be installed. Install Node.js LTS and retry." -ForegroundColor Red
+        Write-Host (Get-LaunchText "   [ERROR] A compatible Node.js/npm could not be installed. Install Node.js LTS and retry." "   [错误] 无法安装兼容的 Node.js/npm。请安装 Node.js LTS 后重试。") -ForegroundColor Red
         exit 1
     }
 }
@@ -505,7 +518,7 @@ Start-LocalAdbServer
 
 # Launch via `python -m artemis` (not the `artemis.exe` console-script shim) so the
 # long-running server never locks .venv\Scripts\artemis.exe against `uv sync` reinstalls.
-Write-Host "   [INFO] Launching Artemis Showcase UI & Admin Console..." -ForegroundColor Green
+Write-Host (Get-LaunchText "   [INFO] Launching Artemis Showcase UI & Admin Console..." "   [启动] 正在启动 ARTEMIS 网页与管理服务...") -ForegroundColor Green
 if ($NoOpen) {
     & $ArtemisPython -m artemis ui --port $Port --no-open
 } else {

scripts/update_installation.py

@@ -1,4 +1,4 @@
-"""Check an existing checkout and refresh only already-configured local MCP clients."""
+"""Check an existing checkout and synchronize installed local MCP clients."""
 
 from __future__ import annotations
 
@@ -19,6 +19,10 @@ from urllib.parse import urlsplit
 ROOT = Path(__file__).resolve().parents[1]
 
 
+def launch_text(english: str, chinese: str) -> str:
+    return chinese if os.environ.get("ARTEMIS_LAUNCH_LANG") == "zh-CN" else english
+
+
 def git(root: Path, *args: str, timeout: int = 15) -> str:
     env = {**os.environ, "GIT_TERMINAL_PROMPT": "0", "GCM_INTERACTIVE": "Never"}
     result = subprocess.run(
@@ -50,19 +54,28 @@ def update_source(root: Path, port: int = 8000) -> int:
             or (status.get("status") == "running" and status.get("pid"))
         ):
             print(
-                "[WAIT] Tasks are active. Finish/stop them before updating dependencies or restarting."
+                launch_text(
+                    "[WAIT] Tasks are active. Finish/stop them before updating dependencies or restarting.",
+                    "[等待] 有任务正在执行或排队。请先处理任务，再更新依赖或重启。",
+                )
             )
             return 20
     except (OSError, ValueError):
         pass
     if not shutil.which("git"):
         print(
-            "[SKIP] Git is not installed. Continuing with local source; install Git for automatic source updates."
+            launch_text(
+                "[SKIP] Git is not installed. Continuing with local source; install Git for automatic source updates.",
+                "[跳过] 未安装 Git，继续使用当前源码；安装 Git 后可自动检查更新。",
+            )
         )
         return 0
     if not (root / ".git").exists():
         print(
-            "[SKIP] This source ZIP has no Git metadata. Use a Git clone for automatic source updates; local files are preserved."
+            launch_text(
+                "[SKIP] This older source ZIP has no Git metadata. Use a new release ZIP or Git clone for automatic updates; local files are preserved.",
+                "[跳过] 旧版源码包不含 Git 信息。请使用新版源码包或 Git 克隆；当前文件保持不变。",
+            )
         )
         return 0
     try:
@@ -79,41 +92,58 @@ def update_source(root: Path, port: int = 8000) -> int:
             raise RuntimeError(
                 "Use a clean Git remote URL and a credential manager, not embedded credentials."
             )
-        print("[CHECK] Checking the current branch's configured upstream...")
+        print(
+            launch_text(
+                "[CHECK] Checking the current branch's configured upstream...",
+                "[检查] 正在检查当前分支的远程更新...",
+            )
+        )
         git(root, "fetch", "--no-tags", remote, merge_ref, timeout=45)
         target = git(root, "rev-parse", "FETCH_HEAD")
         current = git(root, "rev-parse", "HEAD")
         if current == target:
-            print("[OK] Source is up to date.")
+            print(launch_text("[OK] Source is up to date.", "[完成] 源码已是最新版。"))
             return 0
         if git(root, "status", "--porcelain"):
             print(
-                "[SKIP] Upstream differs, but local changes exist. Commit/back up your work before updating; continuing locally."
+                launch_text(
+                    "[SKIP] Upstream differs, but local changes exist. Commit/back up your work before updating; continuing locally.",
+                    "[跳过] 发现本地修改；请先提交或备份。此次继续使用本地源码。",
+                )
             )
             return 0
         ancestor = git(root, "merge-base", "HEAD", target)
         if ancestor != current:
             print(
-                "[SKIP] Local branch is ahead or diverged. No automatic merge/rebase; continuing locally."
+                launch_text(
+                    "[SKIP] Local branch is ahead or diverged. No automatic merge/rebase; continuing locally.",
+                    "[跳过] 本地分支领先或分叉，不自动合并；继续使用本地源码。",
+                )
             )
             return 0
         git(root, "merge", "--ff-only", target, timeout=30)
         print(
-            f"[UPDATED] Source {current[:12]} -> {target[:12]}. Reloading launcher and checking dependencies."
+            launch_text(
+                f"[UPDATED] Source {current[:12]} -> {target[:12]}. Reloading launcher and checking dependencies.",
+                f"[已更新] 源码 {current[:12]} -> {target[:12]}，重新载入启动脚本并检查依赖。",
+            )
         )
         return 10
     except (RuntimeError, subprocess.TimeoutExpired) as exc:
         print(
-            f"[WARN] {exc if isinstance(exc, RuntimeError) else 'Git update timed out.'} Continuing with local source."
+            launch_text(
+                f"[WARN] {exc if isinstance(exc, RuntimeError) else 'Git update timed out.'} Continuing with local source.",
+                "[提示] Git 更新失败或超时；请检查网络、凭据和仓库状态。继续使用当前源码。",
+            )
         )
         return 0
 
 
 def _atomic_write(path: Path, text: str) -> None:
-    if path.read_text(encoding="utf-8") == text:
+    if path.is_file() and path.read_text(encoding="utf-8") == text:
         return
     backup = path.with_name(path.name + ".artemis-update.bak")
-    if not backup.exists():
+    if path.is_file() and not backup.exists():
         shutil.copy2(path, backup)
     fd, name = tempfile.mkstemp(prefix=".artemis-update-", dir=path.parent)
     try:
@@ -124,87 +154,120 @@ def _atomic_write(path: Path, text: str) -> None:
         Path(name).unlink(missing_ok=True)
 
 
-def _belongs_to_project(config: dict, root: Path) -> bool:
+def _is_standard_local_artemis(config: dict) -> bool:
-    if config.get("url"):
+    if config.get("url") or config.get("type") not in (None, "stdio"):
         return False
     args = config.get("args", [])
-    if args[:2] not in (["-m", "mcp_server"], ["-m", "mcp_server.server"]):
+    # Running this launcher selects this checkout, including after a user moves
-        # A hand-written wrapper/uv/SSE command may need custom arguments; leave it alone.
+    # a release ZIP to a new directory. Do not take over custom wrappers/SSE.
-        return False
+    return args in (["-m", "mcp_server"], ["-m", "mcp_server.server"])
-    candidates = [config.get("cwd"), config.get("env", {}).get("PYTHONPATH")]
-    for value in candidates:
-        if isinstance(value, str) and Path(value).resolve() == root.resolve():
-            return True
-    command = config.get("command")
-    return (
-        isinstance(command, str)
-        and Path(command).resolve().parent == (root / ".venv" / "Scripts").resolve()
-    )
 
 
-def _tool_updates(config: dict, names: tuple[str, ...]) -> dict:
+def _updated_entry(config: dict, template: dict, root: Path, names: tuple[str, ...]) -> dict:
-    updates = {}
+    updated = {**config, "command": template["command"], "args": template["args"]}
-    if "enabled_tools" in config:
+    if "cwd" in template or "cwd" in config:
-        updates["enabled_tools"] = list(dict.fromkeys([*config["enabled_tools"], *names]))
+        updated["cwd"] = str(root)
-    if isinstance(config.get("tools"), dict):
+    environment = config.get("env", {})
-        updates["tools"] = {**{name: {"eager": True} for name in names}, **config["tools"]}
+    if not isinstance(environment, dict):
-    return updates
+        raise ValueError("The existing Artemis MCP environment is not an object")
+    updated["env"] = {**environment, **template["env"]}
+    if "enabled_tools" in template or "enabled_tools" in config:
+        updated["enabled_tools"] = list(names)
+    if "tools" in template or "tools" in config:
+        current_tools = config.get("tools", {})
+        if not isinstance(current_tools, dict):
+            raise ValueError("The existing Artemis MCP tools setting is not an object")
+        updated["tools"] = {name: {"eager": True, **current_tools.get(name, {})} for name in names}
+    for key in ("type", "required", "startup_timeout_sec", "connectionTimeoutMs"):
+        if key in template and key not in updated:
+            updated[key] = template[key]
+    return updated
 
 
 def refresh_json(
-    path: Path, keys: tuple[str, ...], root: Path, python: str, names: tuple[str, ...]
+    path: Path,
-) -> bool:
+    keys: tuple[str, ...],
-    if not path.is_file():
+    root: Path,
+    python: str,
+    names: tuple[str, ...],
+    template: dict | None = None,
+    install_missing: bool = False,
+) -> bool | None:
+    if not path.is_file() and not install_missing:
         return False
-    raw = path.read_text(encoding="utf-8")
+    raw = path.read_text(encoding="utf-8") if path.is_file() else "{}"
     data = json.loads(raw)
+    if not isinstance(data, dict):
+        raise ValueError("MCP configuration must be a JSON object")
     parent = data
     for key in keys:
-        parent = parent.get(key, {})
+        child = parent.get(key)
+        if child is None and install_missing:
+            child = parent[key] = {}
+        if not isinstance(child, dict):
+            raise ValueError(f"Invalid MCP configuration section: {key}")
+        parent = child
     config = parent.get("artemis")
-    if not isinstance(config, dict) or not _belongs_to_project(config, root):
+    if config is None and install_missing:
-        return False
+        if template is None:
-    updated = {**config, "command": python, **_tool_updates(config, names)}
+            raise ValueError("A standard MCP template is required for installation")
+        updated = template
+    elif isinstance(config, dict) and _is_standard_local_artemis(config):
+        if template is None:
+            template = {
+                "command": python,
+                "args": ["-m", "mcp_server"],
+                "env": {"PYTHONPATH": str(root)},
+            }
+        updated = _updated_entry(config, template, root, names)
+    elif config is not None and not isinstance(config, dict):
+        raise ValueError("The Artemis MCP configuration is not an object")
+    else:
+        return None
     if updated == config:
         return False
     parent["artemis"] = updated
+    path.parent.mkdir(parents=True, exist_ok=True)
     _atomic_write(path, json.dumps(data, ensure_ascii=False, indent=2) + "\n")
     return True
 
 
-def refresh_codex(path: Path, root: Path, python: str, names: tuple[str, ...]) -> bool:
+def _toml_value(value: object) -> str:
-    if not path.is_file():
+    if isinstance(value, bool):
-        return False
+        return "true" if value else "false"
-    raw = path.read_text(encoding="utf-8")
+    return json.dumps(value, ensure_ascii=False)
-    config = tomllib.loads(raw).get("mcp_servers", {}).get("artemis")
+
-    if not isinstance(config, dict) or not _belongs_to_project(config, root):
+
-        return False
+def _toml_inline_table(values: dict) -> str:
-    wanted = {"command": python, **_tool_updates(config, names)}
+    return "{ " + ", ".join(f"{key} = {_toml_value(value)}" for key, value in values.items()) + " }"
-    wanted = {key: value for key, value in wanted.items() if config.get(key) != value}
+
-    if not wanted:
+
-        return False
+def _replace_toml_tables(raw: str, assignments: dict[str, dict]) -> str:
+    """Update only Artemis TOML tables; preserve every unrelated section and setting."""
     lines = raw.splitlines(keepends=True)
-    inside = False
+    output: list[str] = []
-    found = set()
+    section = ""
-    output = []
+    found: dict[str, set[str]] = {name: set() for name in assignments}
+    seen: set[str] = set()
 
-    def append_missing():
+    def append_missing() -> None:
-        for key, value in wanted.items():
+        if section in assignments:
-            if key not in found:
+            for key, value in assignments[section].items():
-                output.append(f"{key} = {json.dumps(value, ensure_ascii=False)}\n")
+                if key not in found[section]:
-                found.add(key)
+                    rendered = _toml_inline_table(value) if key == "env" else _toml_value(value)
+                    output.append(f"{key} = {rendered}\n")
+                    found[section].add(key)
 
-    # Replace complete assignment spans, including multiline arrays, using TOML parsing.
     index = 0
     while index < len(lines):
         line = lines[index]
         if line.lstrip().startswith("["):
-            if inside:
             append_missing()
             header = re.sub(r"[\s\"']", "", line.split("#", 1)[0]).strip()
-            inside = header == "[mcp_servers.artemis]"
+            section = header[1:-1] if header.startswith("[") and header.endswith("]") else ""
-        match = re.match(r"\s*(\w+)\s*=", line) if inside else None
+            seen.add(section)
-        if match and match[1] in wanted:
+        match = re.match(r"\s*(\w+)\s*=", line) if section in assignments else None
+        if match and match[1] in assignments[section]:
             key = match[1]
             original = line
             while True:
@@ -216,73 +279,236 @@ def refresh_codex(path: Path, root: Path, python: str, names: tuple[str, ...]) -
                     if index >= len(lines):
                         raise ValueError("Cannot safely parse existing MCP setting")
                     original += lines[index]
-            output.append(f"{key} = {json.dumps(wanted[key], ensure_ascii=False)}\n")
+            value = assignments[section][key]
-            found.add(key)
+            rendered = _toml_inline_table(value) if key == "env" else _toml_value(value)
+            output.append(f"{key} = {rendered}\n")
+            found[section].add(key)
         else:
             output.append(line)
         index += 1
-    if inside:
     append_missing()
-    updated = "".join(output)
+    for name, values in assignments.items():
-    parsed = tomllib.loads(updated)
+        if name not in seen:
-    if any(parsed["mcp_servers"]["artemis"].get(k) != v for k, v in wanted.items()):
+            if output and not output[-1].endswith("\n"):
-        raise ValueError("Could not locate the existing Artemis table safely")
+                output.append("\n")
-    _atomic_write(path, updated)
+            output.append(f"\n[{name}]\n")
-    return updated != raw
+            for key, value in values.items():
+                rendered = _toml_inline_table(value) if key == "env" else _toml_value(value)
+                output.append(f"{key} = {rendered}\n")
+    return "".join(output)
 
 
-def refresh_mcp(root: Path) -> None:
+def refresh_codex(
+    path: Path,
+    root: Path,
+    python: str,
+    names: tuple[str, ...],
+    template: dict | None = None,
+    install_missing: bool = False,
+) -> bool | None:
+    if not path.is_file() and not install_missing:
+        return False
+    raw = path.read_text(encoding="utf-8") if path.is_file() else ""
+    parsed = tomllib.loads(raw)
+    config = parsed.get("mcp_servers", {}).get("artemis")
+    if config is None and install_missing:
+        if template is None:
+            raise ValueError("A standard MCP template is required for installation")
+        updated = template
+    elif isinstance(config, dict) and _is_standard_local_artemis(config):
+        if template is None:
+            template = {
+                "command": python,
+                "args": ["-m", "mcp_server"],
+                "cwd": str(root),
+                "env": {"PYTHONPATH": str(root)},
+                "enabled_tools": list(names),
+            }
+        updated = _updated_entry(config, template, root, names)
+    else:
+        return None
+    top = {
+        key: value
+        for key, value in updated.items()
+        if key != "env" and (not config or config.get(key) != value)
+    }
+    environment = updated["env"]
+    if config and config.get("env") == environment:
+        env_updates = {}
+    else:
+        env_updates = {
+            key: value
+            for key, value in environment.items()
+            if not config or config.get("env", {}).get(key) != value
+        }
+    env_header = "mcp_servers.artemis.env"
+    has_env_table = re.search(r"(?m)^\s*\[mcp_servers\.artemis\.env\]\s*(?:#.*)?$", raw) is not None
+    if config and "env" in config and not has_env_table and env_updates:
+        top["env"] = environment
+        env_updates = {}
+    assignments = {"mcp_servers.artemis": top}
+    if env_updates:
+        assignments[env_header] = env_updates
+    if not top and not env_updates:
+        return False
+    result = _replace_toml_tables(raw, assignments)
+    actual = tomllib.loads(result)["mcp_servers"]["artemis"]
+    if any(actual.get(key) != value for key, value in top.items()) or any(
+        actual.get("env", {}).get(key) != value for key, value in env_updates.items()
+    ):
+        raise ValueError("Could not safely refresh the Artemis MCP table")
+    path.parent.mkdir(parents=True, exist_ok=True)
+    _atomic_write(path, result)
+    return result != raw
+
+
+def refresh_mcp(root: Path) -> int:
     sys.path.insert(0, str(root))
-    from artemis.interfaces.cli.commands.mcp import ARTEMIS_MCP_TOOLS, _get_vscode_user_dir
+    from artemis.interfaces.cli.commands.mcp import (
+        ARTEMIS_MCP_TOOLS,
+        _get_config_snippet,
+        _get_vscode_user_dir,
+    )
 
     home = Path.home()
     vscode = _get_vscode_user_dir()
     appdata = Path(os.environ.get("APPDATA", home / "AppData/Roaming"))
+    cline_store = vscode / "globalStorage/saoudrizwan.claude-dev"
+    roo_store = vscode / "globalStorage/rooveterinaryinc.roo-cline"
     paths = [
-        (home / ".gemini/config/mcp_config.json", ("mcpServers",)),
+        (home / ".gemini/config/mcp_config.json", ("mcpServers",), "antigravity", home / ".gemini"),
-        (home / ".gemini/jetski/mcp_config.json", ("mcpServers",)),
+        (home / ".gemini/jetski/mcp_config.json", ("mcpServers",), "jetski", home / ".gemini"),
-        (home / ".gemini/antigravity/mcp_config.json", ("mcpServers",)),
-        (home / ".cursor/mcp.json", ("mcpServers",)),
-        (home / ".codeium/windsurf/mcp_config.json", ("mcpServers",)),
-        (home / ".claude.json", ("mcpServers",)),
-        (appdata / "Claude/claude_desktop_config.json", ("mcpServers",)),
-        (vscode / "mcp.json", ("servers",)),
-        (home / ".copilot/mcp-config.json", ("servers",)),
-        (home / ".cline/data/settings/cline_mcp_settings.json", ("mcpServers",)),
-        (home / ".cline/mcp.json", ("mcpServers",)),
         (
-            vscode / "globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json",
+            home / ".gemini/antigravity/mcp_config.json",
             ("mcpServers",),
+            "antigravity",
+            home / ".gemini",
+        ),
+        (home / ".cursor/mcp.json", ("mcpServers",), "cursor", home / ".cursor"),
+        (
+            home / ".codeium/windsurf/mcp_config.json",
+            ("mcpServers",),
+            "windsurf",
+            home / ".codeium/windsurf",
+        ),
+        (home / ".claude.json", ("mcpServers",), "claude", home / ".claude"),
+        (
+            appdata / "Claude/claude_desktop_config.json",
+            ("mcpServers",),
+            "claude",
+            appdata / "Claude",
+        ),
+        (vscode / "mcp.json", ("servers",), "vscode", vscode),
+        (home / ".copilot/mcp-config.json", ("servers",), "vscode", home / ".copilot"),
+        (
+            home / ".cline/data/settings/cline_mcp_settings.json",
+            ("mcpServers",),
+            "cline",
+            home / ".cline",
+        ),
+        (home / ".cline/mcp.json", ("mcpServers",), "cline", home / ".cline"),
+        (
+            cline_store / "settings/cline_mcp_settings.json",
+            ("mcpServers",),
+            "cline",
+            cline_store,
         ),
         (
-            vscode / "globalStorage/rooveterinaryinc.roo-cline/settings/mcp_settings.json",
+            roo_store / "settings/mcp_settings.json",
             ("mcpServers",),
+            "roo",
+            roo_store,
         ),
         (
-            vscode / "globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json",
+            roo_store / "settings/cline_mcp_settings.json",
             ("mcpServers",),
+            "roo",
+            roo_store,
         ),
-        (root / ".roo/mcp.json", ("mcpServers",)),
+        (root / ".roo/mcp.json", ("mcpServers",), "roo", root / ".roo"),
-        (home / ".openclaw/openclaw.json", ("mcp", "servers")),
+        (home / ".openclaw/openclaw.json", ("mcp", "servers"), "openclaw", home / ".openclaw"),
     ]
-    changed = 0
+    codex_home = Path(os.environ.get("CODEX_HOME", home / ".codex"))
-    codex = Path(os.environ.get("CODEX_HOME", home / ".codex")) / "config.toml"
+    paths.append((codex_home / "config.toml", (), "codex", codex_home))
-    for path, keys in [*paths, (codex, ())]:
+    installed = updated_count = ready = skipped = errors = 0
+    for path, keys, client, marker in paths:
+        if not path.is_file() and not marker.is_dir():
+            continue
+        existed = path.is_file()
+        template = _get_config_snippet(client, sys.executable, str(root))
+        for key in keys:
+            template = template[key]
+        template = template["artemis"] if keys else template["mcp_servers"]["artemis"]
         try:
-            updated = (
+            changed = (
-                refresh_json(path, keys, root, sys.executable, ARTEMIS_MCP_TOOLS)
+                refresh_json(
+                    path,
+                    keys,
+                    root,
+                    sys.executable,
+                    ARTEMIS_MCP_TOOLS,
+                    template=template,
+                    install_missing=True,
+                )
                 if keys
-                else refresh_codex(path, root, sys.executable, ARTEMIS_MCP_TOOLS)
+                else refresh_codex(
+                    path,
+                    root,
+                    sys.executable,
+                    ARTEMIS_MCP_TOOLS,
+                    template=template,
+                    install_missing=True,
                 )
-            if updated:
+            )
-                print(f"[UPDATED] Existing MCP configuration: {path}")
+            if changed:
-                changed += 1
-        except (OSError, ValueError, TypeError, AttributeError):
-            print(f"[WARN] Could not safely refresh {path}; original configuration preserved.")
                 print(
-        f"[OK] MCP source is current; refreshed {changed} existing client configuration(s). Reload the MCP connection in your AI client after a source update."
+                    launch_text(
+                        f"[{'UPDATED' if existed else 'INSTALLED'}] MCP configuration: {path}",
+                        f"[{'已更新' if existed else '已安装'}] MCP 配置：{path}",
                     )
-    print("[TIP] For a new client run: uv run artemis mcp --install <client>")
+                )
+                if existed:
+                    updated_count += 1
+                else:
+                    installed += 1
+            elif changed is None:
+                print(
+                    launch_text(
+                        f"[SKIP] Custom Artemis MCP entry in {path}; use the manual installer for this client.",
+                        f"[跳过] {path} 使用自定义 ARTEMIS MCP 启动方式；请手动检查此客户端。",
+                    )
+                )
+                skipped += 1
+            else:
+                ready += 1
+        except (OSError, ValueError, TypeError, AttributeError):
+            print(
+                launch_text(
+                    f"[ERROR] Could not safely synchronize {path}; original configuration preserved.",
+                    f"[错误] 无法安全同步 {path}；原配置已保留。",
+                )
+            )
+            errors += 1
+    print(
+        launch_text(
+            f"[CHECK] MCP clients: installed {installed}, updated {updated_count}, already current {ready}, custom skipped {skipped}, errors {errors}.",
+            f"[检查] MCP 客户端：新装 {installed} 个、更新 {updated_count} 个、已是最新 {ready} 个、自定义跳过 {skipped} 个、失败 {errors} 个。",
+        )
+    )
+    print(
+        launch_text(
+            "[ACTION] Reload or restart your AI client to load the current MCP process and tool schemas.",
+            "[操作] 请在 AI 客户端重新加载 MCP 或重启客户端，使新版进程和工具签名生效。",
+        )
+    )
+    if not (installed or updated_count or ready or skipped or errors):
+        print(
+            launch_text(
+                "[TIP] No supported client detected; install one with: uv run artemis mcp --install <client>",
+                "[提示] 未检测到受支持的客户端；可执行 uv run artemis mcp --install <client>。",
+            )
+        )
+    return 1 if errors else 0
 
 
 def frontend_fingerprint(root: Path) -> str:
@@ -314,7 +540,7 @@ if __name__ == "__main__":
     if args.action == "source":
         sys.exit(update_source(args.root, args.port))
     elif args.action == "mcp":
-        refresh_mcp(args.root)
+        sys.exit(refresh_mcp(args.root))
     else:
         marker = args.root / "apps/showcase_ui/node_modules/.artemis-source-hash"
         current = frontend_fingerprint(args.root)

skills/artemis-automation/SKILL.md

@@ -14,7 +14,7 @@ description: 使用 ARTEMIS MCP 在 Android 真机或模拟器上完成自然语
 3. 首次使用、工具出错、任务拒绝或设备异常，先 `mobile_diagnose`。按 `next_steps` 的依赖顺序处理；`attempt_fix=true` 可尝试工具自带修复。只有凭据相关故障才使用 `verify_credentials=true`，观察异常才使用 `probe_device=true`。不要盲目重发任务。MCP 不可用时在项目目录运行 `uv run artemis doctor` 并检查宿主 MCP 日志。
 4. 选择执行模式：Flash 适合路径明确的界面操作；Pro 适合动态分支、持续计划、ADB/日志诊断或需要 Checker 明确校验的任务。**`mobile_run_task.model` 的 `flash`/`pro` 是执行模式，不是 API 模型名称**。步数长不自动等于需要 Pro；视频能力只有显式启用后才可用。
 5. 单任务用 `mobile_run_task`；批量任务用 `mobile_batch`，读 [批量任务与交付](references/batches.md)。AI 可直接提交结构化用例，不必先创建 Excel。用户提供 Excel 时先 `mobile_task_file(action="preview", path=绝对路径)`，修正所有行错误后提交。提示词列原样作为目标，前置约束列只作元数据。
-6. 单任务返回 `trace_id` 后，用 `mobile_manage_task(action="status", trace_id=...)` 跟踪；网页任务也可用其任务编号。批次用 `mobile_batch(action="get", batch_id=...)`。需要人工补充时用 `pause`，其返回的 `pausing` 只表示请求已接收；轮询到 `task_paused` 才表示设备已释放。Pro 等待模型回复或只读诊断时可中断，已开始的设备动作会先安全结束。`inject_instruction` 可在运行中指导下一步，暂停中提交则恢复；`guidance_history` 的 `pending/consumed` 区分提交和执行端领取，无新指导用 `resume`。恢复进入设备 FIFO 队尾并重新观察手机状态。尊重工具建议的等待周期，避免连续高频轮询；停滞或失败先诊断，不把同一业务任务自动重提。
+6. 单任务返回 `trace_id` 后，用 `mobile_manage_task(action="status", trace_id=...)` 跟踪；网页任务也可用其任务编号。批次用 `mobile_batch(action="get", batch_id=...)`。需要人工补充时用 `pause`，其返回的 `pausing` 只表示请求已接收；轮询到 `task_paused` 才表示设备已释放。`inject_instruction` 会立即取消进行中的模型回复或只读诊断并重新观察手机，已开始的设备动作会先安全结束；暂停中提交则恢复。`guidance_history` 的 `pending/consumed` 区分提交和执行端领取，无新指导用 `resume`。恢复进入设备 FIFO 队尾并重新观察手机状态。尊重工具建议的等待周期，避免连续高频轮询；停滞或失败先诊断，不把同一业务任务自动重提。
 
 ## 结果、证据与交付
 
@@ -32,6 +32,6 @@ description: 使用 ARTEMIS MCP 在 Android 真机或模拟器上完成自然语
 - API Key 只通过网页或 `.env` 配置。不要请求用户把 key 发到聊天中，不读取/回显已有 key。保存后新任务生效；直接编辑环境文件后需重启相应服务，运行中的任务保留自己的配置。
 - 录屏与 AI 视频分析分别配置。批量任务的 `task_config` 可覆盖单项，不修改全局设置；只开视频分析时录制内容不作为可下载文件保存。暂停时停止录屏，恢复后按片段继续，不能把其他任务画面混入该任务资料。
 - 请求重试是模型调用恢复，不是测试用例重跑。批次默认失败继续、不自动重跑；服务重启后保留状态并暂停，用户明确要求后才继续或复制失败项。
-- 批次暂停只停止后续派发；当前任务等待指导时用 `mobile_manage_task(action="pause", trace_id=...)`，真正取消用 `stop`。用户明确要求删除批次记录时先 `mobile_batch(action="get")` 核对编号，再用 `delete`；执行中/排队中的批次不能删，已执行的任务历史和报告会保留。服务重启后运行/暂停的任务标记中断，不自动重跑。停止可能保留已经产生的业务效果，不声称自动回滚。
+- 批次暂停只停止后续派发；当前任务等待指导时用 `mobile_manage_task(action="pause", trace_id=...)`，真正取消用 `stop`。用户明确要求删除批次记录时先 `mobile_batch(action="get")` 核对编号，再用 `delete`；执行中/排队中的批次不能删，删除会清除该批次的任务历史、报告和文件。服务重启后运行/暂停的任务标记中断，不自动重跑。停止可能保留已经产生的业务效果，不声称自动回滚。
 
 需要编写外部可执行测试代码时，先通过 ARTEMIS 实际探索目标应用，确认页面、定位器和转换。优先动态定位，框架支持时才以已验证坐标兜底；在最终脚本中明确等待条件，不将 AI 思考耗时当作确定性等待。

skills/artemis-automation/references/batches.md

@@ -56,7 +56,7 @@
 - 单项 `pending/queued/running/pausing/task_paused/resuming/finalizing` 尚未结束，`completed/failed/cancelled/interrupted/skipped` 是终态。`pausing` 是请求已发出而设备仍被占用，`task_paused` 才表示设备已释放；`finalizing` 在生成报告，不能提前宣称报告已完成。
 - 批次 `pause` 保留当前执行，只暂停后续派发；单项 `mobile_manage_task(pause)` 会在安全边界释放设备，Pro 的模型等待与只读诊断可中断。恢复后重新观察画面，并排到设备队尾，不阻塞后续项。`mobile_manage_task(guidance_history)` 可核对指导是否从 `pending` 变为 `consumed`，但仍需检查后续操作是否符合指导。设备断开、模型持续失败或任务达到批次时限会暂停后续派发；用诊断确认恢复后再响应用户的继续指令。
 - `resume` 只继续未开始项；`retry_failed` 复制失败、取消和中断项为新草稿，不修改原结果。必须来自用户的明确重跑请求。该动作不提供创建去重，响应不确定时先 `list` 查找新批次，不自动重复调用。
-- 用户明确要求删除批次记录时，先 `get` 核对批次编号与状态，再 `delete`；正在执行、排队或等待指导的批次不能删除，已经运行过的任务历史及报告不会随批次记录一起消失。
+- 用户明确要求删除批次记录时，先 `get` 核对批次编号与状态，再 `delete`；正在执行、排队或等待指导的批次不能删除。删除会同时移除该批次任务历史、报告和文件，无法撤销。
 
 ## 报告
 

start-cn.bat

@@ -1,6 +1,33 @@
 @echo off
-rem Use China mirrors for first setup and subsequent launches.
+chcp 65001 >nul 2>&1
-rem All start.bat arguments, including -SetupOnly, are supported.
 setlocal DisableDelayedExpansion
+set "ARTEMIS_LAUNCH_LANG=zh-CN"
+title ARTEMIS 国内镜像启动
+
+if /i "%~1"=="-Help" goto help
+if /i "%~1"=="--help" goto help
+
+echo ======================================================
+echo   ARTEMIS 中文启动 - 使用国内镜像
+echo ======================================================
+echo 正在检查已有环境、项目更新及依赖；首次启动可能需要下载组件。
+echo 镜像地址和下载超时可在 config\downloads.json 中调整。
+echo.
 call "%~dp0start.bat" -Mirror China %*
-exit /b %ERRORLEVEL%
+set "ARTEMIS_CN_EXIT_CODE=%ERRORLEVEL%"
+if not "%ARTEMIS_CN_EXIT_CODE%"=="0" echo 启动未完成；请查看上方错误信息，并检查网络或镜像设置。
+endlocal & exit /b %ARTEMIS_CN_EXIT_CODE%
+
+:help
+echo 用法：start-cn.bat [选项]
+echo.
+echo   -SetupOnly    安装或检查环境，不启动网页
+echo   -Port 8001    使用指定端口，默认 8000
+echo   -NoOpen       启动服务后不自动打开浏览器
+echo   -SkipUpdate   跳过 Git 源码更新检查
+echo   -SkipMcpSync  仅启动网页，跳过 MCP 安装和更新
+echo   -Help         显示本说明
+echo.
+echo 国内镜像设置：config\downloads.json
+echo 首次运行需联网；后续运行会检查源码、依赖，并同步已安装 AI 客户端的 MCP。
+endlocal & exit /b 0

start.bat

@@ -15,12 +15,12 @@ rem limitations under the License.
 
 chcp 65001 >nul 2>&1
 setlocal DisableDelayedExpansion
-title Artemis Mobile Agent UI
+if /i "%ARTEMIS_LAUNCH_LANG%"=="zh-CN" (title ARTEMIS 手机自动化测试) else (title Artemis Mobile Agent UI)
 
 pushd "%~dp0" || exit /b 1
 
 echo ======================================================
-echo       Artemis Autonomous Mobile Agent UI
+if /i "%ARTEMIS_LAUNCH_LANG%"=="zh-CN" (echo       ARTEMIS 手机自动化测试) else (echo       Artemis Autonomous Mobile Agent UI)
 echo ======================================================
 echo.
 
@@ -33,7 +33,7 @@ set "ARTEMIS_EXIT_CODE=%ERRORLEVEL%"
 
 if not "%ARTEMIS_EXIT_CODE%"=="0" (
     echo.
-    echo An error occurred while starting Artemis.
+    if /i "%ARTEMIS_LAUNCH_LANG%"=="zh-CN" (echo ARTEMIS 启动失败，请查看上方详细信息。) else (echo An error occurred while starting Artemis.)
     if not defined ARTEMIS_NO_PAUSE pause
 )
 popd

tests/unit/admin_console/test_automation.py

@@ -2,8 +2,10 @@
 
 from io import BytesIO
 import json
+import sqlite3
 import time
-from unittest.mock import AsyncMock
+from unittest.mock import AsyncMock, Mock
+from uuid import UUID
 import zipfile
 
 from docx import Document
@@ -125,19 +127,44 @@ def test_preferences_and_required_device(client):
     assert client.post("/api/automation/batches", json=payload(device_serial="")).status_code == 422
 
 
-def test_batch_delete_retains_executed_task_and_prevents_request_replay(client, isolated):
+def test_batch_delete_removes_tasks_and_files_and_prevents_request_replay(client, isolated):
     created = client.post(
         "/api/automation/batches", json=payload(request_id="delete-example")
     ).json()
     first, second = isolated.jobs(created["id"])
     isolated.save_job({**first, "status": "completed"})
+    trace_dir = reports.TRACES_PATH / first["session_id"]
+    trace_dir.mkdir(parents=True)
+    (trace_dir / "result.json").write_text("{}", encoding="utf-8")
+    report_dir = reports.EXPORT_ROOT / "sessions" / first["session_id"]
+    report_dir.mkdir(parents=True)
+    (report_dir / "任务报告.docx").write_bytes(b"report")
+    batch_dir = reports.EXPORT_ROOT / "batches" / created["id"]
+    batch_dir.mkdir(parents=True)
+    (batch_dir / "批次报告.zip").write_bytes(b"zip")
+    mcp_task_dir = reports.EXPORT_ROOT.parent / "mcp_exports" / "sessions" / first["session_id"]
+    mcp_task_dir.mkdir(parents=True)
+    (mcp_task_dir / "报告.docx").write_bytes(b"report")
+    mcp_batch_dir = reports.EXPORT_ROOT.parent / "mcp_exports" / "batches" / created["id"]
+    mcp_batch_dir.mkdir(parents=True)
+    (mcp_batch_dir / "批次.zip").write_bytes(b"zip")
+    unrelated = reports.TRACES_PATH / "unrelated-task"
+    unrelated.mkdir()
+    (unrelated / "keep.txt").write_text("keep", encoding="utf-8")
 
     response = client.delete(f"/api/automation/batches/{created['id']}")
     assert response.status_code == 200
     assert client.get(f"/api/automation/batches/{created['id']}").status_code == 404
-    assert isolated.job(first["session_id"])["case"]["name"] == "用例甲"
+    assert isolated.job(first["session_id"]) is None
     assert isolated.job(second["session_id"]) is None
-    assert reports.session_report(first["session_id"])["name"] == "用例甲"
+    assert not trace_dir.exists()
+    assert not report_dir.exists()
+    assert not batch_dir.exists()
+    assert not mcp_task_dir.exists()
+    assert not mcp_batch_dir.exists()
+    assert (unrelated / "keep.txt").read_text(encoding="utf-8") == "keep"
+    with pytest.raises(ValueError, match="不存在"):
+        reports.session_report(first["session_id"])
     assert (
         client.post(
             "/api/automation/batches", json=payload(request_id="delete-example")
@@ -158,6 +185,49 @@ def test_batch_delete_rejects_active_jobs(client, isolated, status):
     assert len(isolated.jobs(batch["id"])) == 2
 
 
+def test_batch_deletion_reservation_blocks_new_dispatch(isolated):
+    batch = service.create_batch(payload())
+    job = isolated.jobs(batch["id"])[0]
+
+    isolated.begin_delete_batch(batch["id"])
+
+    with pytest.raises(ValueError, match="正在删除"):
+        isolated.save_job({**job, "status": "queued"})
+    with pytest.raises(ValueError, match="正在删除"):
+        isolated.put("batch", batch["id"], {**batch, "status": "running"})
+    assert isolated.jobs_for_sessions([job["session_id"]])[job["session_id"]]["status"] == "pending"
+
+
+def test_batch_deletion_preserves_shared_screenshot_until_last_task(client, isolated):
+    first_batch = service.create_batch(payload())
+    second_batch = service.create_batch(payload(name="另一批次"))
+    first = isolated.jobs(first_batch["id"])[0]
+    other = isolated.jobs(second_batch["id"])[0]
+    shared_hash = "a" * 64
+    storage = StorageManager(isolated.path, reports.TRACES_PATH)
+    image_file = reports.TRACES_PATH / "images" / f"{shared_hash}.jpg"
+    image_file.parent.mkdir(parents=True)
+    image_file.write_bytes(b"shared image")
+    with sqlite3.connect(isolated.path) as conn:
+        conn.execute("INSERT INTO images(image_name) VALUES (?)", (shared_hash,))
+        for job in (first, other):
+            conn.execute(
+                "INSERT INTO sessions(session_id,initial_goal,start_time,status,device_info) "
+                "VALUES (?,?,?,?,?)",
+                (job["session_id"], "观察设置", 1.0, "completed", "{}"),
+            )
+            conn.execute(
+                "INSERT INTO steps(step_id,session_id,pre_image_name) VALUES (?,?,?)",
+                (job["session_id"], job["session_id"], shared_hash),
+            )
+
+    assert client.delete(f"/api/automation/batches/{first_batch['id']}").status_code == 200
+    assert image_file.read_bytes() == b"shared image"
+    assert storage.get_session(UUID(other["session_id"])) is not None
+    assert client.delete(f"/api/automation/batches/{second_batch['id']}").status_code == 200
+    assert not image_file.exists()
+
+
 def test_restart_never_repeats_started_work(isolated):
     batch = service.create_batch(payload())
     service.batch_action(batch["id"], "resume")
@@ -260,6 +330,123 @@ async def test_report_failure_does_not_strand_job(isolated, monkeypatch):
     assert "disk full" in saved["report_error"]
 
 
+@pytest.mark.asyncio
+async def test_batch_timeout_stays_visible_in_job_report_and_history(client, isolated):
+    job = isolated.jobs(service.create_batch(payload())["id"])[0]
+    isolated.save_job(
+        {**job, "status": "running", "timed_out": True, "error": "任务执行超时（30 秒）"}
+    )
+    await service.on_terminal({"session_id": job["session_id"]}, "cancelled")
+    saved = isolated.job(job["session_id"])
+    assert saved["status"] == "failed"
+    assert "超时" in saved["error"]
+    assert "超时" in reports.session_report(job["session_id"])["error"]
+    history = client.get("/api/automation/history").json()["items"]
+    assert any(
+        item["session_id"] == job["session_id"] and "超时" in item["error"] for item in history
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("stop_on_failure", [False, True])
+async def test_timed_out_case_releases_next_batch_case(isolated, monkeypatch, stop_on_failure):
+    from apps.admin_console import server
+    from artemis.runtime.device_pool import DeviceStatus
+
+    batch = service.create_batch(payload(timeout_seconds=1, stop_on_failure=stop_on_failure))
+    service.batch_action(batch["id"], "resume")
+    first = isolated.jobs(batch["id"])[0]
+    isolated.save_job({**first, "status": "running", "started_at": time.time() - 2})
+    monkeypatch.setattr(
+        service, "state", type("State", (), {"is_paused": False, "active_runs": {}})()
+    )
+    stop = Mock(return_value=True)
+    enqueue = AsyncMock(return_value={"tasks": [{"device_serial": "test-device"}]})
+    monkeypatch.setattr(server.task_queue_service, "stop_tasks", stop)
+    monkeypatch.setattr(server.task_queue_service, "enqueue_tasks", enqueue)
+    monkeypatch.setattr(
+        "artemis.runtime.device_pool.try_list_devices_async",
+        AsyncMock(return_value=[DeviceStatus(serial="test-device", state="device")]),
+    )
+    monkeypatch.setattr(reports, "export_batch", Mock())
+
+    await service.tick_batches()
+    assert isolated.get("batch", batch["id"])["status"] == "running"
+    assert "超时" in isolated.job(first["session_id"])["error"]
+    stop.assert_called_once_with(session_id=first["session_id"])
+    await service.tick_batches()
+    stop.assert_called_once()
+
+    await service.on_terminal({"session_id": first["session_id"]}, "cancelled")
+    await service.tick_batches()
+    statuses = [job["status"] for job in isolated.jobs(batch["id"])]
+    assert statuses == (["failed", "skipped"] if stop_on_failure else ["failed", "queued"])
+    assert enqueue.await_count == (0 if stop_on_failure else 1)
+
+
+@pytest.mark.asyncio
+async def test_queued_case_does_not_consume_execution_timeout(isolated, monkeypatch):
+    from apps.admin_console import server
+
+    batch = service.create_batch(payload(timeout_seconds=1))
+    service.batch_action(batch["id"], "resume")
+    first = isolated.jobs(batch["id"])[0]
+    isolated.save_job({**first, "status": "queued", "started_at": time.time() - 30})
+    monkeypatch.setattr(service, "state", type("State", (), {"is_paused": False})())
+    stop = Mock()
+    monkeypatch.setattr(server.task_queue_service, "stop_tasks", stop)
+
+    await service.tick_batches()
+    stop.assert_not_called()
+    assert isolated.job(first["session_id"])["status"] == "queued"
+    assert isolated.get("batch", batch["id"])["status"] == "running"
+
+
+@pytest.mark.asyncio
+async def test_model_timeout_from_runner_log_reaches_failed_task_and_report(isolated):
+    job = isolated.jobs(service.create_batch(payload())["id"])[0]
+    folder = reports.TRACES_PATH / job["session_id"]
+    folder.mkdir(parents=True)
+    (folder / "stderr.log").write_text(
+        "TimeoutError: model request timed out after 300 seconds\n", encoding="utf-8"
+    )
+
+    await service.on_terminal({"session_id": job["session_id"]}, "failed")
+
+    saved = isolated.job(job["session_id"])
+    assert saved["status"] == "failed"
+    assert "超时" in saved["error"]
+    assert reports.session_report(job["session_id"])["status"] == "failed"
+    assert "超时" in reports.session_report(job["session_id"])["error"]
+
+
+def test_optional_timeout_warnings_are_not_reported_as_task_failure(tmp_path):
+    (tmp_path / "stdout.log").write_text(
+        "⚠ Could not clean unowned screen wake locks on emulator-5554: "
+        "Timed out acquiring the Artemis awake-lease mutex.\n"
+        "⚠ VisualStepSummarizer: Error generating summary for step 3: \n"
+        "ℹ StepMemoryService: Retrying Step 3 (attempt 4) after 1.0s\n",
+        encoding="utf-8",
+    )
+    assert reports.failure_reason(tmp_path, "failed", None) == (
+        "任务未完成，运行日志中没有可提取的具体异常；请查看执行步骤。"
+    )
+
+    (tmp_path / "stderr.log").write_text(
+        "TimeoutError: model request timed out after 300 seconds\n", encoding="utf-8"
+    )
+    reason = reports.failure_reason(tmp_path, "failed", None)
+    assert "model request timed out" in reason
+    assert "awake-lease" not in reason
+
+    (tmp_path / "stderr.log").write_text(
+        "DeviceBusyError: device queue reservation was cancelled\n", encoding="utf-8"
+    )
+    assert reports.failure_reason(tmp_path, "failed", None) == (
+        "DeviceBusyError: device queue reservation was cancelled"
+    )
+
+
 def test_reports_do_not_execute_formulas_or_invent_pass(isolated):
     batch = service.create_batch(payload())
     job = isolated.jobs(batch["id"])[0]
@@ -296,6 +483,7 @@ def test_failed_report_exposes_logged_reason_and_formats_chinese_markdown(isolat
     assert "abc123secret" not in reports.failure_reason(
         folder, "failed", "认证失败 OPENAI_API_KEY=abc123secret Authorization: Bearer abc123secret"
     )
+    assert "超时" not in reports.failure_reason(folder, "failed", "LLMExhaustedError: 额度不足")
     paths = reports.export_session(job["session_id"])
     doc = Document(next(path for path in paths if path.suffix == ".docx"))
     assert doc.styles["Normal"].font.name == "Microsoft YaHei"
@@ -325,6 +513,7 @@ def test_task_material_zip_contains_ordered_evidence_and_reports(
     client, isolated, tmp_path, monkeypatch
 ):
     job = isolated.jobs(service.create_batch(payload())["id"])[0]
+    isolated.save_job({**job, "case": {**job["case"], "case_id": "1.1"}})
     evidence = tmp_path / "evidence"
     evidence.mkdir()
     first = evidence / "first.png"
@@ -343,14 +532,16 @@ def test_task_material_zip_contains_ordered_evidence_and_reports(
     assert response.status_code == 200
     with zipfile.ZipFile(BytesIO(response.content)) as archive:
         files = archive.namelist()
+        assert all(name.startswith("1.1/") for name in files)
         assert any(name.endswith(".docx") for name in files)
         assert any(name.endswith(".xlsx") for name in files)
-        assert files.index("步骤截图/0001_步骤0001_操作前.png") < files.index(
+        assert files.index("1.1/步骤截图/0001_步骤0001_操作前.png") < files.index(
-            "步骤截图/0002_步骤0002_操作后.png"
+            "1.1/步骤截图/0002_步骤0002_操作后.png"
         )
-        assert archive.read("任务录屏/0001_recording.mp4") == b"recording.mp4"
+        assert archive.read("1.1/任务录屏/0001_recording.mp4") == b"recording.mp4"
-        manifest = json.loads(archive.read("文件清单.json"))
+        manifest = json.loads(archive.read("1.1/文件清单.json"))
         assert manifest["session_id"] == job["session_id"]
+    assert "1.1-all.zip" in response.headers["content-disposition"]
 
 
 def test_history_filters_all_persisted_rows_and_escapes_like(client, isolated):

tests/unit/admin_console/test_model_settings.py

@@ -59,6 +59,17 @@ def test_save_reload_and_blank_key_preserves_secret(isolated_settings):
     assert dotenv_values(isolated_settings)["OPENAI_API_KEY"] == "new-test-secret"
 
 
+def test_new_install_uses_playones_endpoint_without_overriding_saved_url(monkeypatch):
+    monkeypatch.delenv("OPENAI_BASE_URL", raising=False)
+    expected = "https://api-n-cd.playones.com/v1"
+    assert Settings(_env_file=None).OPENAI_BASE_URL == expected
+    assert service.ModelSettingsUpdate(model="test").base_url == expected
+    monkeypatch.setattr(settings, "OPENAI_BASE_URL", None)
+    assert service.get_model_settings()["base_url"] == expected
+    monkeypatch.setattr(settings, "OPENAI_BASE_URL", "https://saved.example/v1")
+    assert service.get_model_settings()["base_url"] == "https://saved.example/v1"
+
+
 @pytest.mark.parametrize(
     "url",
     [

tests/unit/admin_console/test_session_list_batching.py

@@ -5,6 +5,14 @@ import pytest
 from apps.admin_console.routers import sessions as sessions_router
 
 
+@pytest.fixture(autouse=True)
+def isolate_jobs(monkeypatch):
+    mocked = MagicMock()
+    mocked.jobs_for_sessions.return_value = {}
+    monkeypatch.setattr(sessions_router, "store", mocked)
+    return mocked
+
+
 @pytest.mark.asyncio
 async def test_list_sessions_uses_batched_history_metadata(monkeypatch):
     repo = MagicMock()
@@ -96,3 +104,42 @@ async def test_list_sessions_extracts_device_serial(monkeypatch):
     assert result[0]["device_id"] == "63191FDKX00062"
     assert result[1]["device_serial"] == "emulator-5554"
     assert result[1]["device_id"] == "emulator-5554"
+
+
+@pytest.mark.asyncio
+async def test_list_sessions_uses_batch_title_and_timeout_error(monkeypatch, isolate_jobs):
+    repo = MagicMock()
+    repo.get_all_sessions.return_value = [
+        {
+            "session_id": "session-case",
+            "status": "completed",
+            "start_time": 1.0,
+            "initial_goal": "打开设置并检查页面",
+            "device_info": '{"profile":"flash"}',
+        }
+    ]
+    repo.get_video_recordings_map.return_value = {}
+    repo.get_latest_video_recordings_map.return_value = {}
+    repo.get_agent_trace_names_map.return_value = {}
+    monkeypatch.setattr(sessions_router, "session_repo", repo)
+    monkeypatch.setattr(
+        sessions_router.media_service, "build_video_index", MagicMock(return_value={})
+    )
+    isolate_jobs.jobs_for_sessions.return_value = {
+        "session-case": {
+            "session_id": "session-case",
+            "status": "failed",
+            "ended_at": 65.0,
+            "error": "任务执行超时（60 秒）",
+            "case": {"case_id": "1.1", "name": "打开并核对设置", "goal": "打开设置并检查页面"},
+        }
+    }
+
+    result = await sessions_router.list_sessions()
+
+    isolate_jobs.jobs_for_sessions.assert_called_once_with(["session-case"])
+    assert result[0]["display_name"] == "1.1 打开并核对设置"
+    assert result[0]["initial_goal"] == "打开设置并检查页面"
+    assert result[0]["status"] == "failed"
+    assert result[0]["end_time"] == 65.0
+    assert "超时" in result[0]["error"]

tests/unit/agents/test_flash_runner_ledger.py

@@ -636,6 +636,32 @@ async def test_run_no_tool_call_turn_is_nudged_not_terminated(mock_context):
         and any(EXECUTION_RESULT_MARKER in b.get("text", "") for b in m.content)
         for m in turn2_messages
     )
+    assert not any(
+        isinstance(m, AIMessage) and m.content == "thinking only" for m in turn2_messages
+    )
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("attempts", [1, 3])
+async def test_flash_stops_repeated_no_tool_responses(mock_context, monkeypatch, attempts):
+    from artemis.config.settings import settings
+
+    monkeypatch.setattr(settings, "ARTEMIS_FLASH_MAX_NO_PROGRESS_ATTEMPTS", attempts)
+    responses = [AIMessage(content="I will click now.", tool_calls=[]) for _ in range(attempts)]
+    with (
+        patch("artemis.controllers.unified_controller.get_driver"),
+        patch(
+            "artemis.agents.flash.runner.capture_screenshot_and_parse_ui",
+            AsyncMock(return_value=_INITIAL_OBSERVATION),
+        ),
+    ):
+        runner = _make_runner(mock_context, responses, max_turns=0)
+        result = await runner.run(State(initial_goal="Open Settings"))
+
+    assert result["status"] == "failed"
+    assert f"连续 {attempts} 次未调用工具" in result["explanation"]
+    assert runner._invoke_model.await_count == attempts
+    runner.executor.execute.assert_not_awaited()
 
 
 # ---------------------------------------------------------------------------

tests/unit/agents/test_flash_step_summarizer.py

@@ -14,6 +14,7 @@
 
 """Unit tests for VisualStepSummarizer and Context Compressor in Flash profile."""
 
+import asyncio
 from unittest.mock import ANY, AsyncMock, Mock, call
 from uuid import uuid4
 import pytest
@@ -106,6 +107,29 @@ async def test_summarizer_retries_independently(mock_context):
     assert attempt_count == 2
 
 
+@pytest.mark.asyncio
+async def test_visual_summary_uses_its_own_configured_timeout(mock_context):
+    summarizer = VisualStepSummarizer(mock_context, retry_limit=0, timeout_seconds=0.01)
+
+    async def slow_response(_messages):
+        await asyncio.sleep(1)
+
+    summarizer._llm = Mock()
+    summarizer._llm.ainvoke = AsyncMock(side_effect=slow_response)
+    summarizer.dispatch(
+        step_number=1,
+        action_name="click",
+        action_args={"target": [100, 100]},
+        pre_img_bytes=b"pre",
+        post_img_bytes=b"post",
+        exec_outcome="Clicked",
+    )
+
+    await summarizer.flush()
+    assert summarizer.has_failed(1)
+    assert summarizer._llm.ainvoke.await_count == 1
+
+
 @pytest.mark.asyncio
 async def test_summarizer_bounded_retry_marks_failed(mock_context):
     """Persistent failures exit after 1 + retry_limit attempts with an explicit failed state."""

tests/unit/mcp/test_automation_tools.py

@@ -80,13 +80,19 @@ async def test_download_writes_actual_binary_atomically(monkeypatch, tmp_path):
     monkeypatch.setattr(
         tools.httpx, "AsyncClient", lambda **kw: client_type(transport=transport, **kw)
     )
-    result = await tools._download("/api/automation/reports/test/docx", "test.docx")
+    result = await tools._download(
+        "/api/automation/reports/test/docx",
+        "test.docx",
+        owner_kind="sessions",
+        owner_id="test",
+    )
     from pathlib import Path
 
     assert Path(result["path"]).read_bytes() == b"PK\x03\x04report-bytes"
     assert Path(result["path"]).is_absolute()
+    assert Path(result["path"]).parent == tmp_path / "sessions" / "test"
     assert result["download_url"] == "http://test/api/automation/reports/test/docx"
-    assert not list(tmp_path.glob("*.part"))
+    assert not list(tmp_path.rglob("*.part"))
 
 
 @pytest.mark.asyncio

tests/unit/mcp/test_mcp_tools.py

@@ -373,7 +373,7 @@ def test_mobile_manage_task_inject_instruction(temp_trace_env):
     ok_res = mobile_manage_task(
         action="inject_instruction", trace_id=trace_id, instruction="Scroll down slowly"
     )
-    assert "Successfully injected" in ok_res["message"]
+    assert "current model step interrupted" in ok_res["message"]
 
 
 @pytest.mark.asyncio

tests/unit/runtime/test_awake_lease.py

@@ -13,6 +13,8 @@
 # limitations under the License.
 
 import json
+from pathlib import Path
+import time
 
 import pytest
 
@@ -126,3 +128,30 @@ def test_migration_cleanup_never_drains_a_live_legacy_owner(monkeypatch):
     cleanup._drain_references = lambda: pytest.fail("must not drain a live owner")
 
     assert cleanup.cleanup_unowned_references() is False
+
+
+def test_optional_cleanup_skips_a_busy_mutex_without_delaying_task_start(monkeypatch):
+    owner = ScreenAwakeLease("device-123")
+    owner.mutex_path.write_text(json.dumps(owner._payload()), encoding="utf-8")
+    cleanup = ScreenAwakeLease("device-123")
+    monkeypatch.setattr(cleanup, "_drain_references", lambda: pytest.fail("must not drain"))
+
+    started_at = time.monotonic()
+    assert cleanup.cleanup_unowned_references() is False
+    assert time.monotonic() - started_at < 2.0
+
+
+def test_unremovable_stale_mutex_still_obeys_deadline(monkeypatch):
+    lease = ScreenAwakeLease("device-123")
+    lease.mutex_path.write_text(json.dumps({"pid": 999999}), encoding="utf-8")
+    original_unlink = Path.unlink
+
+    def refuse_mutex_unlink(path, *args, **kwargs):
+        if path == lease.mutex_path:
+            raise PermissionError("file is in use")
+        return original_unlink(path, *args, **kwargs)
+
+    monkeypatch.setattr(Path, "unlink", refuse_mutex_unlink)
+    with pytest.raises(TimeoutError, match="awake-lease mutex"):
+        with lease._mutex(wait_timeout_seconds=0.1):
+            pytest.fail("stale mutex must not be acquired")

tests/unit/runtime/test_awake_service.py

@@ -1,3 +1,4 @@
+import os
 from unittest.mock import MagicMock, patch
 
 from artemis.runtime.awake_service import (
@@ -37,6 +38,22 @@ def test_usb_policy_is_primary_when_android_reports_it_active(mock_run, lease_ty
     assert not any("KEYCODE_UNKNOWN" in command for command in commands)
 
 
+@patch.dict(os.environ, {"ARTEMIS_TASK_WORKER": "1"})
+@patch("artemis.runtime.awake_service.ScreenAwakeLease")
+@patch("artemis.runtime.awake_service.subprocess.run")
+def test_queued_worker_does_not_run_optional_legacy_cleanup(mock_run, lease_type):
+    mock_run.side_effect = [
+        completed(),
+        completed(),
+        completed(),
+        completed("2\n"),
+        completed("  mStayOn=true\n"),
+    ]
+
+    assert _configure_usb_stay_awake("device-123") == AWAKE_STRATEGY_USB
+    lease_type.assert_not_called()
+
+
 @patch("artemis.runtime.awake_service.ScreenAwakeLease")
 @patch("artemis.runtime.awake_service.subprocess.run")
 def test_inactive_usb_policy_falls_back_to_effective_host_heartbeat(mock_run, _lease_type):

tests/unit/runtime/test_task_control.py

@@ -116,6 +116,35 @@ async def test_interruptible_call_returns_normal_result_without_pause(tmp_path,
     assert await control.run_interruptibly(model_call()) == (False, "current result")
 
 
+@pytest.mark.asyncio
+async def test_new_guidance_cancels_stale_model_without_releasing_device(tmp_path, monkeypatch):
+    monkeypatch.setattr(task_control, "TRACES_PATH", tmp_path)
+    released = []
+
+    class Lock:
+        def release(self):
+            released.append(True)
+
+    control = task_control.TaskControl("task-123", Lock())
+    started = asyncio.Event()
+    cancelled = asyncio.Event()
+
+    async def stale_model():
+        started.set()
+        try:
+            await asyncio.Event().wait()
+        finally:
+            cancelled.set()
+
+    call = asyncio.create_task(control.run_interruptibly(stale_model()))
+    await asyncio.wait_for(started.wait(), 1)
+    task_control.add_instruction("task-123", "改为检查当前页面", source="mcp")
+    assert await asyncio.wait_for(call, 1) == (True, None)
+    assert cancelled.is_set()
+    assert released == []
+    assert task_control.consume_instructions(control.directory)["instruction"] == "改为检查当前页面"
+
+
 def test_guidance_history_distinguishes_submission_from_runner_consumption(tmp_path, monkeypatch):
     monkeypatch.setattr(task_control, "TRACES_PATH", tmp_path)
     first = task_control.add_instruction("task-123", "从快捷设置进入", source="web")

tests/unit/test_bootstrap_scripts_encoding.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-"""Keep bootstrap scripts ASCII for Windows PowerShell 5.1 compatibility.
+"""Require ASCII or UTF-8 with BOM for Windows PowerShell 5.1 scripts.
 
 BOM-less scripts are decoded using the system ANSI code page. UTF-8 symbols
 can become quote delimiters under cp1252 and cause parse errors.
@@ -31,18 +31,11 @@ def test_powershell_scripts_are_discovered():
 
 
 @pytest.mark.parametrize("script", POWERSHELL_SCRIPTS, ids=lambda p: p.name)
-def test_powershell_script_is_pure_ascii(script):
+def test_powershell_script_has_windows_compatible_encoding(script):
     raw = script.read_bytes()
-    offending = []
+    if any(byte > 0x7F for byte in raw):
-    line_no = 1
+        assert raw.startswith(b"\xef\xbb\xbf"), (
-    for index, byte in enumerate(raw):
+            f"{script.name} contains non-ASCII bytes without a UTF-8 BOM; "
-        if byte == 0x0A:
+            "Windows PowerShell 5.1 would use the system ANSI code page."
-            line_no += 1
-        elif byte > 0x7F:
-            offending.append((line_no, index, hex(byte)))
-
-    assert not offending, (
-        f"{script.name} contains non-ASCII bytes at (line, offset, byte) "
-        f"{offending[:10]}; Windows PowerShell 5.1 decodes BOM-less .ps1 files "
-        "with the system ANSI code page. Use ASCII status labels."
         )
+        raw.decode("utf-8-sig")

tests/unit/test_installation_update.py

@@ -120,7 +120,7 @@ command = "leave-alone"
     assert path.with_name(path.name + ".artemis-update.bak").read_text(encoding="utf-8") == original
 
 
-def test_json_only_updates_existing_matching_project(tmp_path):
+def test_json_migrates_existing_standard_mcp_to_current_checkout(tmp_path):
     path = tmp_path / "mcp.json"
     root = tmp_path / "project"
     config = {
@@ -132,19 +132,170 @@ def test_json_only_updates_existing_matching_project(tmp_path):
         "autoApprove": [],
     }
     path.write_text(json.dumps({"mcpServers": {"artemis": config, "other": {"command": "keep"}}}))
-    assert not update.refresh_json(
+    moved_root = tmp_path / "new release"
-        path, ("mcpServers",), tmp_path / "different", "new", ("mobile_batch",)
+    assert update.refresh_json(path, ("mcpServers",), moved_root, "new", ("mobile_batch",))
-    )
-    assert update.refresh_json(path, ("mcpServers",), root, "new", ("mobile_batch",))
     result = json.loads(path.read_text())["mcpServers"]
-    assert result["artemis"]["env"] == {"CUSTOM": "preserved"}
+    assert result["artemis"]["env"]["CUSTOM"] == "preserved"
+    assert result["artemis"]["env"]["PYTHONPATH"] == str(moved_root)
+    assert result["artemis"]["cwd"] == str(moved_root)
     assert result["artemis"]["disabled"] is True
     assert result["other"] == {"command": "keep"}
+    assert not update.refresh_json(path, ("mcpServers",), moved_root, "new", ("mobile_batch",))
     missing = tmp_path / "not-installed.json"
     assert not update.refresh_json(missing, ("mcpServers",), root, "new", ())
     assert not missing.exists()
 
 
+def test_mcp_sync_installs_detected_clients_and_migrates_codex(tmp_path, monkeypatch):
+    from artemis.interfaces.cli.commands import mcp as mcp_command
+
+    home = tmp_path / "home"
+    home.mkdir()
+    codex_home = home / ".codex"
+    codex_home.mkdir()
+    codex_config = codex_home / "config.toml"
+    codex_config.write_text(
+        'model = "my-model"\n'
+        "[mcp_servers.artemis]\n"
+        'command = "old-python"\n'
+        'args = ["-m", "mcp_server.server"]\n'
+        'cwd = "C:/old-release"\n'
+        'enabled_tools = ["mobile_run_task", "retired_tool"]\n'
+        "enabled = false\n"
+        "[mcp_servers.artemis.env]\n"
+        'PYTHONPATH = "C:/old-release"\n'
+        'OPENAI_API_KEY = "keep-secret"\n',
+        encoding="utf-8",
+    )
+    cursor_home = home / ".cursor"
+    cursor_home.mkdir()
+    (cursor_home / "mcp.json").write_text('{"mcpServers":{"other":{"command":"keep"}}}')
+    monkeypatch.setattr("pathlib.Path.home", lambda: home)
+    monkeypatch.setattr(mcp_command, "_get_vscode_user_dir", lambda: home / "vscode-user")
+    monkeypatch.setenv("CODEX_HOME", str(codex_home))
+    monkeypatch.setenv("APPDATA", str(home / "AppData"))
+    root = tmp_path / "new release"
+    assert update.refresh_mcp(root) == 0
+    codex = tomllib.loads(codex_config.read_text(encoding="utf-8"))
+    entry = codex["mcp_servers"]["artemis"]
+    assert codex["model"] == "my-model"
+    assert entry["command"] == update.sys.executable
+    assert entry["cwd"] == str(root)
+    assert entry["args"] == ["-m", "mcp_server"]
+    assert entry["enabled"] is False
+    assert entry["env"]["OPENAI_API_KEY"] == "keep-secret"
+    assert entry["env"]["PYTHONPATH"] == str(root)
+    assert entry["enabled_tools"] == list(mcp_command.ARTEMIS_MCP_TOOLS)
+    cursor = json.loads((cursor_home / "mcp.json").read_text(encoding="utf-8"))
+    assert cursor["mcpServers"]["artemis"]["env"]["PYTHONPATH"] == str(root)
+    assert cursor["mcpServers"]["other"] == {"command": "keep"}
+    first = codex_config.read_text(encoding="utf-8")
+    assert update.refresh_mcp(root) == 0
+    assert codex_config.read_text(encoding="utf-8") == first
+
+
+def test_mcp_sync_fails_on_invalid_detected_config_without_overwriting(tmp_path, monkeypatch):
+    from artemis.interfaces.cli.commands import mcp as mcp_command
+
+    home = tmp_path / "home"
+    cursor_home = home / ".cursor"
+    cursor_home.mkdir(parents=True)
+    config = cursor_home / "mcp.json"
+    config.write_text("{invalid json", encoding="utf-8")
+    monkeypatch.setattr("pathlib.Path.home", lambda: home)
+    monkeypatch.setattr(mcp_command, "_get_vscode_user_dir", lambda: home / "vscode-user")
+    monkeypatch.delenv("CODEX_HOME", raising=False)
+    assert update.refresh_mcp(tmp_path / "project") == 1
+    assert config.read_text(encoding="utf-8") == "{invalid json"
+
+
+def test_mcp_sync_installs_codex_when_client_directory_exists(tmp_path, monkeypatch):
+    from artemis.interfaces.cli.commands import mcp as mcp_command
+
+    home = tmp_path / "home"
+    codex_home = home / ".codex"
+    codex_home.mkdir(parents=True)
+    monkeypatch.setattr("pathlib.Path.home", lambda: home)
+    monkeypatch.setattr(mcp_command, "_get_vscode_user_dir", lambda: home / "vscode-user")
+    monkeypatch.setenv("CODEX_HOME", str(codex_home))
+    root = tmp_path / "project"
+    assert update.refresh_mcp(root) == 0
+    config = tomllib.loads((codex_home / "config.toml").read_text(encoding="utf-8"))
+    assert config["mcp_servers"]["artemis"]["cwd"] == str(root)
+    assert config["mcp_servers"]["artemis"]["enabled_tools"] == list(mcp_command.ARTEMIS_MCP_TOOLS)
+
+
+def test_codex_install_preserves_existing_user_tables(tmp_path):
+    path = tmp_path / "config.toml"
+    path.write_text(
+        'model = "keep"\n[mcp_servers.other]\ncommand = "other-tool"\n', encoding="utf-8"
+    )
+    template = {
+        "command": "new-python",
+        "args": ["-m", "mcp_server"],
+        "cwd": str(tmp_path),
+        "env": {"PYTHONPATH": str(tmp_path)},
+        "enabled_tools": ["mobile_run_task"],
+    }
+    assert update.refresh_codex(
+        path,
+        tmp_path,
+        "new-python",
+        ("mobile_run_task",),
+        template=template,
+        install_missing=True,
+    )
+    data = tomllib.loads(path.read_text(encoding="utf-8"))
+    assert data["model"] == "keep"
+    assert data["mcp_servers"]["other"]["command"] == "other-tool"
+    assert data["mcp_servers"]["artemis"]["env"]["PYTHONPATH"] == str(tmp_path)
+
+
+def test_codex_inline_environment_sync_is_idempotent(tmp_path):
+    path = tmp_path / "config.toml"
+    path.write_text(
+        '[mcp_servers.artemis]\ncommand = "old-python"\n'
+        'args = ["-m", "mcp_server"]\n'
+        'env = { PYTHONPATH = "C:/old", OPENAI_API_KEY = "keep-secret" }\n',
+        encoding="utf-8",
+    )
+    template = {
+        "command": "new-python",
+        "args": ["-m", "mcp_server"],
+        "cwd": str(tmp_path),
+        "env": {"PYTHONPATH": str(tmp_path)},
+        "enabled_tools": ["mobile_run_task"],
+    }
+    assert update.refresh_codex(
+        path, tmp_path, "new-python", ("mobile_run_task",), template=template
+    )
+    data = tomllib.loads(path.read_text(encoding="utf-8"))["mcp_servers"]["artemis"]
+    assert data["env"]["OPENAI_API_KEY"] == "keep-secret"
+    assert data["env"]["PYTHONPATH"] == str(tmp_path)
+    assert not update.refresh_codex(
+        path, tmp_path, "new-python", ("mobile_run_task",), template=template
+    )
+
+
+def test_custom_mcp_wrapper_is_left_unchanged(tmp_path):
+    path = tmp_path / "mcp.json"
+    original = '{"mcpServers":{"artemis":{"command":"uv","args":["run","custom"]}}}'
+    path.write_text(original, encoding="utf-8")
+    assert (
+        update.refresh_json(
+            path,
+            ("mcpServers",),
+            tmp_path,
+            "new-python",
+            ("mobile_run_task",),
+            install_missing=True,
+            template={"command": "new-python", "args": ["-m", "mcp_server"], "env": {}},
+        )
+        is None
+    )
+    assert path.read_text(encoding="utf-8") == original
+
+
 def test_frontend_fingerprint_detects_lock_source_and_deleted_assets(tmp_path):
     ui = tmp_path / "apps/showcase_ui"
     (ui / "src").mkdir(parents=True)

tests/unit/test_source_archive.py

@@ -1,36 +1,134 @@
 import importlib.util
 from pathlib import Path
+import shutil
+import subprocess
 import zipfile
 
+import pytest
 
-def test_archive_keeps_source_and_excludes_local_builds_and_secrets(tmp_path):
+
-    script = Path(__file__).resolve().parents[2] / "scripts/package_source.py"
+SCRIPT = Path(__file__).resolve().parents[2] / "scripts/package_source.py"
-    spec = importlib.util.spec_from_file_location("package_source", script)
+spec = importlib.util.spec_from_file_location("package_source", SCRIPT)
 module = importlib.util.module_from_spec(spec)
 spec.loader.exec_module(module)
+
+
+def git(root, *args):
+    result = subprocess.run(
+        ["git", "-C", str(root), *args], capture_output=True, text=True, timeout=30
+    )
+    assert result.returncode == 0, result.stderr
+    return result.stdout.strip()
+
+
+@pytest.fixture
+def repository(tmp_path):
+    if not shutil.which("git"):
+        pytest.skip("Git required")
+    root = tmp_path / "source"
+    root.mkdir()
+    git(root, "init", "-b", "main")
+    git(root, "config", "user.name", "Fixture")
+    git(root, "config", "user.email", "fixture@example.test")
     keep = ["start.bat", ".env.example", "uv.lock", "apps/showcase_ui/src/main.ts"]
+    tracked_builds = [
+        "artemis/resources/showcase_ui/main.js",
+        "packages/artemis-accessibility-helper/ArtemisAccessibilityHelper.apk",
+        "packages/artemis-accessibility-helper/debug.keystore",
+    ]
     omit = [
         ".env",
         ".env.local",
         ".venv/pyvenv.cfg",
         "nested/node_modules/foo.js",
         "apps/showcase_ui/dist/main.js",
-        "artemis/resources/showcase_ui/main.js",
         "__pycache__/a.pyc",
         "traces/data.db",
-        "helper.apk",
-        "debug.keystore",
-        ".git/config",
         ".roo/mcp.json",
     ]
-    for name in keep + omit:
+    for name in keep + tracked_builds + omit:
-        target = tmp_path / name
+        target = root / name
         target.parent.mkdir(parents=True, exist_ok=True)
         target.write_text("fixture")
+    (root / ".gitignore").write_text(
+        ".env*\n!.env.example\n.venv/\nnode_modules/\ndist/\ntraces/\n.roo/\n__pycache__/\n"
+    )
+    git(root, "add", "--", ".gitignore", *keep, *tracked_builds)
+    git(root, "commit", "-m", "initial")
+    git(root, "remote", "add", "eapil", "https://git.example.invalid/team/project.git")
+    git(root, "config", "branch.main.remote", "eapil")
+    git(root, "config", "branch.main.merge", "refs/heads/main")
+    return root, keep, tracked_builds, omit
+
+
+def test_archive_is_updatable_clean_checkout_without_local_data(repository, tmp_path):
+    root, keep, tracked_builds, omit = repository
     output = tmp_path / "artifacts/source.zip"
-    count, digest = module.package_source(tmp_path, output)
+    count, digest = module.package_source(root, output)
-    assert count == len(keep)
+    assert count > len(keep)
     assert len(digest) == 64
     with zipfile.ZipFile(output) as archive:
         assert archive.testzip() is None
-        assert set(archive.namelist()) == {f"artemis/{name}" for name in keep}
+        names = set(archive.namelist())
+        assert {f"artemis/{name}" for name in keep}.issubset(names)
+        assert not {f"artemis/{name}" for name in tracked_builds + omit} & names
+        assert "artemis/.git/config" in names
+        assert "artemis/.git/index" in names
+        assert not any(name.startswith("artemis/.git/logs/") for name in names)
+        assert not any(name.startswith("artemis/.git/hooks/") for name in names)
+        archive.extractall(tmp_path / "unpacked")
+    extracted = tmp_path / "unpacked/artemis"
+    assert git(extracted, "symbolic-ref", "--short", "HEAD") == "main"
+    assert git(extracted, "rev-parse", "HEAD") == git(root, "rev-parse", "HEAD")
+    assert git(extracted, "status", "--porcelain") == ""
+    assert git(extracted, "remote", "get-url", "origin") == (
+        "https://git.example.invalid/team/project.git"
+    )
+    assert git(extracted, "config", "--get", "branch.main.remote") == "origin"
+    (extracted / tracked_builds[0]).parent.mkdir(parents=True)
+    (extracted / tracked_builds[0]).write_text("new bundle")
+    assert git(extracted, "status", "--porcelain") == ""
+
+
+def test_unpacked_archive_fast_forwards(repository, tmp_path):
+    root, _, tracked_builds, _ = repository
+    bare = tmp_path / "upstream.git"
+    bare.mkdir()
+    git(bare, "init", "--bare")
+    git(root, "remote", "add", "test-upstream", str(bare))
+    git(root, "push", "test-upstream", "main")
+    archive = tmp_path / "source.zip"
+    module.package_source(root, archive)
+    with zipfile.ZipFile(archive) as contents:
+        contents.extractall(tmp_path / "unpacked")
+    extracted = tmp_path / "unpacked/artemis"
+    git(extracted, "remote", "set-url", "origin", str(bare))
+    built_asset = extracted / tracked_builds[0]
+    built_asset.parent.mkdir(parents=True)
+    built_asset.write_text("generated after setup")
+    (root / "start.bat").write_text("updated")
+    git(root, "add", "--", "start.bat")
+    git(root, "commit", "-m", "update launcher")
+    git(root, "push", "test-upstream", "main")
+    from scripts.update_installation import update_source
+
+    assert update_source(extracted, port=1) == 10
+    assert (extracted / "start.bat").read_text() == "updated"
+    assert git(extracted, "status", "--porcelain") == ""
+
+
+def test_packaging_rejects_uncommitted_changes_and_credentials(repository, tmp_path):
+    root, _, _, _ = repository
+    (root / "start.bat").write_text("local change")
+    with pytest.raises(ValueError, match="Commit tracked changes"):
+        module.package_source(root, tmp_path / "source.zip")
+    (root / "start.bat").write_text("fixture")
+    git(
+        root,
+        "remote",
+        "set-url",
+        "eapil",
+        "https://user:secret@git.example.invalid/team/project.git",
+    )
+    with pytest.raises(ValueError, match="credential-free HTTPS"):
+        module.package_source(root, tmp_path / "source.zip")

uv.lock

@@ -206,7 +206,7 @@ wheels = [
 
 [[package]]
 name = "artemis"
-version = "1.1.0"
+version = "1.2.2"
 source = { editable = "." }
 dependencies = [
     { name = "adbutils" },