chore(release): prepare ARTEMIS 2.4.3

.env.example

@@ -6,6 +6,9 @@ OPENAI_BASE_URL=https://api-n-cd.playones.com/v1
 OPENAI_MODEL=gpt-6-luna
 # 单次模型 HTTP 请求超时（秒）
 OPENAI_TIMEOUT_SECONDS=300
+# 模型请求和模型凭据检查默认直连；设为 true 才读取 Windows/HTTP(S)_PROXY/ALL_PROXY/NO_PROXY。
+# 仅环境配置，不显示在网页中；修改后重启服务生效。TLS 校验及自定义 CA 不受影响。
+OPENAI_USE_SYSTEM_PROXY=false
 # 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=120
 # 失败后最多重试 5 次，由 Artemis 统一管理，SDK 不叠加重试。

AGENTS.md

@@ -21,7 +21,7 @@
 | 探索、示范、用例提炼与复跑 | [探索说明](docs/exploration-mode.md) |
 | 插件协议、适配或市场协同 | [插件开发规范](docs/plugin-development.md)及插件仓库自身的 AGENTS.md、DESIGN.md |
 | 远程 Python SDK | [SDK 设计](packages/artemis-client/DESIGN.md)，保持标准库薄客户端边界 |
-| 继续历史开发、确认版本或发布 | [迁入时的开发快照](docs/development-handoff.md)、[2.1.0 发行说明](docs/releases/2.1.0.md)，再核对实时 Git 状态；`docs/plans/` 保留各自阶段的状态 |
+| 继续历史开发、确认版本或发布 | [README 当前发行入口](README.md)、对应发行说明及实时 Git 状态；[开发快照](docs/development-handoff.md)与 `docs/plans/` 仅作为历史线索，不替代当前源码与发布包核验 |
 
 ## Quick Commands
 
@@ -60,7 +60,7 @@ Windows 首次安装使用 `start.bat`，国内镜像使用 `start-cn.bat`。启
 ## Conventions
 
 - Python 使用绝对导入、4 空格缩进和双引号，由 Ruff 检查；不要放宽质量基线来掩盖新增问题。
-- 新增可调参数集中进入配置层，并更新环境示例、网页/MCP 入口和必要文档；默认值同步 `config/artemis.jsonc` 与 `artemis/resources/config/artemis.jsonc`。
+- 新增可调参数集中进入配置层，按作用域更新环境示例、网页/MCP 入口和文档；明确仅供环境配置的参数不增加前端入口。JSON 默认值同步 `config/artemis.jsonc` 与 `artemis/resources/config/artemis.jsonc`。
 - MCP 工具增删时同步工具注册、CLI 安装白名单、测试、Skill 和能力文档。
 - 同步 Codex MCP/Skill 时保留已有工具白名单、禁用状态和审批策略；异常时保留原配置并告警，不生成非法 TOML 或阻断网页启动。
 - Windows PowerShell 启动脚本保持兼容 Windows PowerShell 5.1，避免编码导致解析失败。升级只做 Git 快进，保护已有配置和本地修改。
@@ -75,6 +75,16 @@ Windows 首次安装使用 `start.bat`，国内镜像使用 `start-cn.bat`。启
 - 设备验证沿用用户指定设备；多设备且未指定时先确认。编写应用交互测试前，先通过 ARTEMIS 探索实际页面和操作路径。
 - 提交前检查 `git diff --check` 和暂存范围，只暂存本次具体路径；报告实际执行的验证及未完成项，不将未运行的检查写成通过。
 
+## Release Gates
+
+- 主程序、SDK、插件和第三方依赖独立版本化。主程序升版只修改 `pyproject.toml` 的项目版本、`uv.lock` 的 artemis 条目及前端应用的根版本字段，发行文档另行更新。禁止对仓库或整个锁文件全局替换版本字符串。
+- 单独审查锁文件差异。第三方条目的版本、下载地址、完整性校验和依赖声明必须相互匹配；主程序升版不应改变这些条目。真正升级依赖时由包管理器生成并核对上游声明；发生 EINTEGRITY 先核验来源，禁止关闭校验或只照错误提示改哈希。
+- 发布前必须在隔离目录解压最终 ZIP，使用独立空 npm 缓存完成 `npm ci` 和生产构建，覆盖本次发布的官方/国内安装路径。包内安装或构建输入变化后必须重跑；不得清空用户全局缓存或改动用户运行目录来制造干净环境。
+- 记录实际 Node/npm 版本、镜像、源码提交、ZIP SHA256 和验证范围。已有 node_modules、构建指纹、缓存命中或大量单元测试通过，均不能证明全新安装成功；某个 Node 版本通过也不能冒充其他版本实测。测试和构建命令见前端局部指南。
+- 发布顺序：固定提交并打包 → 验证最终包 → 推送标签 → 创建草稿并上传包及校验文件 → 回读校验 → 正式发布 → 无认证下载核验。标签必须指向打包提交；推送标签后检查 Release 状态，本仓库曾出现 Gitea 将已有草稿自动发布的情况。失败时修复并重新验证，不提前宣布完成。
+- 候选包与正式包目录明确区分。候选包失效后移出可分发路径并标明替代版本，不能留下同名旧 ZIP 供用户误取；对外只给已核验的正式发布链接或准确文件路径。正式版本不覆盖原标签或附件，后续修复发补丁版。
+- 安装或市场版本不符时，先核对用户实际 ZIP 的 SHA256、运行源码提交及生效市场地址；不凭界面版本号判断，也不把未经验证的缓存假设当成原因。主程序与插件版本、索引兼容性分别验证。
+
 ## Boundaries
 
 - 始终保护用户任务、历史库、环境配置和凭据。不要把个人设备序列号、绝对目录或 API Key 写入源码。

DESIGN.md

@@ -66,6 +66,10 @@ ARTEMIS 面向使用自然语言执行、探索和复跑测试的人。当前产
 
 请求重试、业务执行与最终验收分别处理。提交使用稳定标识；创建批次或探索草稿不自动执行，查询不产生设备动作。执行准入和恢复遵守现有资源锁，任务固定所用插件版本，不能通过另建队列绕开互斥。
 
+设备保活是辅助服务。保活所属锁或旧保活清理目录不可访问时记录警告，不使设备连接、恢复或监控退出；未取得保活所属锁时不发送保活动作，也不创建替代锁绕过所属权。执行资源锁、主服务注册锁和队列写锁仍须成功取得。
+
+运行时准备阶段失败记录 `initialization_failed`，批次保留详细原因并暂停未开始项，修复环境后由用户继续，已失败项不自动重跑。模型请求导致的批次暂停单独标记；模型暂停结束后恢复既定调度及失败即停止策略。用户暂停、停止全部任务和服务重启后的恢复暂停均需用户继续，不被模型恢复覆盖。Flash 与 Pro/探索 Operator 的生成失败复用统一备用模型与重试预算；不完整输出不会成为动作，已有动作不因模型切换而重放。
+
 最终验收有独立总预算，按请求超时、重试和剩余任务时间协调，保留取证结果；完整有效的结构化结论才更新正式裁定。`completed`、工具成功、探索通过、用例提炼和复跑通过各自表达自己的状态。
 
 Responses 消息交给工具、下游解析器或正式裁定前，必须具有服务端 `completed` 状态；工具参数的原始字符串必须是完整 JSON 对象，不能使用库自动补全的半截参数。流结束或库补出的 `last` 标记不能替代完成状态。缺少终止事件、明确未完成或失败的流丢弃预览，进入现有无效输出恢复策略，最多重新请求一次，配置为零次重试时不重试；恢复保留已有工具证据，不重新提交业务任务。非流式、结构化输出和串接解析器遵守同一检查。
@@ -84,6 +88,10 @@ Responses 消息交给工具、下游解析器或正式裁定前，必须具有
 
 执行平台与证据来源分别记录。报告和证据索引从执行记录汇总来源及实际 step_id/call_id/source_id；界面、接口、文件和终端各自只能支持其观察范围，业务后台名称或网址不能推断平台。最终复核明确事实、矛盾和未验证边界；来源清单不生成新结论，不覆盖 AI 原判、有效结论或人工复验。
 
+原生安卓动作在派发时记录所选设备来源。安卓截图来源也可从已保存的成功截图回执读取设备、采集时间、文件路径和校验值，并引用实际 trace_id；兼容 Flash 与 Pro 的回执封装，不从模型参数补造来源。空步骤、笔记和结束声明不计入缺失动作来源；窗口枚举等无单一目标的操作保留未关联状态，该计数不等于截图丢失。未生成独立输出正文时，报告展示当前有效判定及依据，保留人工复验优先级，不把正文缺失写成验收结论缺失。
+
+规划器的笔记工具与执行器的设备、插件工具分别绑定。规划器依据任务的实际授权插件清单制定计划，由执行器加载并验证能力；规划阶段没有绑定动作工具，不表示任务缺少这些能力，也不构成重新申请授权的依据。
+
 MCP 与单任务 HTTP 入参拒绝未知字段，校验失败不调度任务。MCP JSON 结果保留兼容文本并提供 structuredContent；任务摘要分页明确总数与 next_offset，引用实际存储编号。跨端阶段先完整初始化，再按既有阶段 id 更新状态与依据；补丁保留其他阶段、范围、资源和顺序，合并后统一校验并保存，失败不更新内存状态。
 
 Flash 的最终 AI 判定与分析独立配置，默认关闭；首页功能配置和 MCP 共用保存的全局设置。任务开始时固定设置，尚未开始的任务使用最新值；批量、精选及提炼用例的 Flash 复跑同样遵循。关闭时跳过最终 Checker，保留正常执行、步骤、截图、报告和人工复验；结果为“执行完成 · 未做 AI 判定”，不标记“AI确认”或测试通过。Pro 与主动探索的验收规则保持不变。
@@ -191,3 +199,7 @@ Flash 的最终 AI 判定与分析独立配置，默认关闭；首页功能配
 回放两侧面板默认收起、独立展开，普通浮窗和影院模式共用；插件声明期望/最小/最大宽度，宿主按视口收缩，窄屏一次展开一侧，始终保持面板位于回放的左侧或右侧。任务需求只展示本次运行最初的提示词，复用安全 Markdown 渲染。人工表单字段均可留空，不调用模型、不覆盖已有执行结论或人工复验。
 
 评审按单次任务和插件 ID 保存版本历史；运行中只读，终态可编辑或清空。停用/卸载隐藏面板与新导出字段但保留记录，任务删除时同步清理。报告只采用已安装且启用的贡献，空值保持空白；修改记录或插件状态使后续报告缓存失效。
+
+执行详情中的 Payload 默认折叠；其他超长字段也默认折叠，展开后保留完整可复制内容并限制显示高度。原始用例面板仅由启用的工作区插件声明，额外导入列不影响未启用插件的用户。评审支持所有执行模式和目标，用户修改评审后自动保存：结果选择立即保存，备注短暂防抖；切换任务前保存，失败时保留输入和当前任务。仅用户编辑触发写入，AI 不推断人工结论。
+
+模型网络代理策略仅由环境项 `OPENAI_USE_SYSTEM_PROXY` 控制，默认 false。同步、异步模型客户端和模型凭据检查统一遵循；不出现在前端配置中，不改变 TLS 验证与自定义 CA 设置。

README.md

@@ -2,7 +2,7 @@
 
 基于 [ARTEMIS](https://github.com/google/artemis) 扩展的 Android AI 自动化测试平台。用自然语言描述任务，即可通过简体中文网页或 MCP 驱动真机、模拟器执行操作并收集结果。模型统一使用 **OpenAI Responses API**。
 
-**2.3.0**：新增工作区插件接口，支持步骤回放左右侧栏、Markdown 初始需求、人工评审及报告字段扩展；配套「任务人工评审 1.0.0」从插件市场独立安装。新增 gpt-6.1-terra，探索默认 high。见 [2.3.0 发行说明](docs/releases/2.3.0.md)；上一版本见 [2.2.0](docs/releases/2.2.0.md)。
+**2.4.3**：异常模型输出耗尽重试后只失败当前任务，避免触发全局暂停；补充请求关联和有界参数摘要，便于定位流式异常。见 [2.4.3 发行说明](docs/releases/2.4.3.md)。人工评审插件保持 1.1.0；列表优化见 [2.4.2](docs/releases/2.4.2.md)，安装修复见 [2.4.1](docs/releases/2.4.1.md)。
 
 ## 主要功能
 

apps/admin_console/database/repositories/session_repository.py

@@ -15,6 +15,7 @@
 import json
 import logging
 import os
+import re
 import sqlite3
 import time
 from typing import Any
@@ -235,6 +236,47 @@ class SessionRepository:
             rows = cursor.fetchall()
             return [r[0] for r in rows if r and r[0]]
 
+    def get_recorded_model_info_map(self, session_ids: list[str]) -> dict[str, dict[str, str]]:
+        """Read each session's own requested model from its earliest diagnostics.
+
+        Prefer operator/Flash requests over auxiliary roles. Older sessions may
+        have no model diagnostics; do not replace their missing data with the
+        current global configuration.
+        """
+        result: dict[str, dict[str, str]] = {}
+        safe_payload = "CASE WHEN json_valid(t.payload) THEN t.payload ELSE '{}' END"
+        valid_model = f"json_type({safe_payload}, '$.model') = 'text'"
+        role = f"lower(json_extract({safe_payload}, '$.role'))"
+        with db_session(self.db_path) as conn:
+            for offset in range(0, len(session_ids), 500):
+                batch = session_ids[offset : offset + 500]
+                placeholders = ",".join("?" for _ in batch)
+                rows = conn.execute(
+                    "SELECT s.session_id, COALESCE("
+                    " (SELECT t.payload FROM traces t WHERE t.session_id = s.session_id"
+                    f" AND t.type = 'llm_diagnostic' AND {valid_model}"
+                    f" AND {role} IN ('operator', 'flashrunner')"
+                    " ORDER BY t.timestamp ASC LIMIT 1),"
+                    " (SELECT t.payload FROM traces t WHERE t.session_id = s.session_id"
+                    f" AND t.type = 'llm_diagnostic' AND {valid_model}"
+                    " ORDER BY t.timestamp ASC LIMIT 1)"
+                    ") AS model_payload FROM sessions s"
+                    f" WHERE s.session_id IN ({placeholders})",
+                    batch,
+                ).fetchall()
+                for row in rows:
+                    if not row[1]:
+                        continue
+                    payload = json.loads(row[1])
+                    model = payload.get("model")
+                    if isinstance(model, str) and model.strip():
+                        provider = payload.get("provider")
+                        result[str(row[0])] = {
+                            "id": model,
+                            "provider": provider if isinstance(provider, str) else "",
+                        }
+        return result
+
     def get_llm_traces_for_profiles_map(
         self, session_ids: list[str] | None = None, limit: int = 3
     ) -> dict[str, list[str]]:
@@ -349,7 +391,22 @@ class SessionRepository:
                 total += t
                 cached += _int(payload.get("cached_tokens"))
                 node = str(payload.get("node") or "").strip().lower()
-                model_name = str(payload.get("model") or "unknown")
+                model_name = payload.get("model")
+                if not model_name:
+                    # Older gateway traces carry the model in their own endpoint key.
+                    source = str(payload.get("source") or "")
+                    source_parts = source.split(":", 2)
+                    if len(source_parts) == 3 and source_parts[0] == "openai":
+                        # Model aliases can contain colons. The HTTP(S) base URL
+                        # marks the boundary; an ambiguous key stays unknown.
+                        match = re.match(r"^openai:(.+?):https?://", source)
+                        model_name = match[1] if match else None
+                    elif len(source_parts) == 3 and source_parts[:2] in (
+                        ["lens", "visual_transition"],
+                        ["lens", "step_capsule"],
+                    ):
+                        model_name = source_parts[2] if source_parts[2] != "fallback" else None
+                model_name = str(model_name or "unknown")
                 group = by_node_model.setdefault(
                     (node, model_name),
                     {

apps/admin_console/database/repositories/step_repository.py

@@ -220,6 +220,41 @@ class StepRepository:
         # recovering, waiting, completed, and terminal outcomes. Other tools
         # retain the historical compact payload to avoid sending large blobs.
         res = payload_obj.get("result")
+        if trace_type == "tool" and trace_name == "android_file":
+            # Preserve host-written file receipts, not file contents. A file's
+            # checksum is not a screenshot-store image ID.
+            if isinstance(res, str):
+                try:
+                    res = json.loads(res)
+                except ValueError:
+                    res = None
+            if isinstance(res, dict) and "outcome" in res:
+                res = res["outcome"]
+                if isinstance(res, str):
+                    try:
+                        res = json.loads(res)
+                    except ValueError:
+                        res = None
+            if isinstance(res, dict):
+                result_payload["result"] = {
+                    key: self._clean_value(res[key])
+                    for key in (
+                        "ok",
+                        "action",
+                        "path",
+                        "trace_path",
+                        "device_path",
+                        "bytes",
+                        "sha256",
+                        "verified",
+                        "width",
+                        "height",
+                        "captured_at",
+                        "device_serial",
+                    )
+                    if key in res
+                }
+            return result_payload
         is_video_analysis = str(trace_name or "").lower() in {
             "video_analysis",
             "video_analyzer",

apps/admin_console/routers/automation.py

@@ -12,7 +12,7 @@ from apps.admin_console.services.exploration_listing import EXPLORATION_RUNS_CTE
 from apps.admin_console.services.automation_store import identifier, store
 from apps.admin_console.services import automation_service as service
 from apps.admin_console.services import batch_archive as archive_service
-from apps.admin_console.services import report_export, task_import
+from apps.admin_console.services import report_export, task_extensions, task_import
 from artemis.config.settings import settings
 from apps.admin_console.services.case_review import read_reviewed_result
 
@@ -131,7 +131,9 @@ def batch_by_request(request_id: str):
 @router.get("/batches/{batch_id}")
 def batch_detail(batch_id: str):
     jobs = store.jobs(batch_id)
+    reviewed = task_extensions.reviewed_batch_sessions(batch_id, store)
     for job in jobs:
+        job["human_reviewed"] = job["session_id"] in reviewed
         job["test_result"] = read_reviewed_result(
             job["session_id"], job["status"], job.get("error") or "", storage=store
         )

apps/admin_console/routers/sessions.py

@@ -84,6 +84,9 @@ def _list_sessions_sync():
     with store.connection() as connection:
         exploration_runs = exploration_metadata(connection)
     jobs_by_id = store.jobs_for_sessions([str(row.get("session_id")) for row in rows])
+    recorded_models = session_repo.get_recorded_model_info_map(
+        [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()
@@ -217,6 +220,13 @@ def _list_sessions_sync():
             print(f"[list_sessions] Failed to update orphaned sessions: {e}")
 
     for row in result:
+        # Session history must not inherit today's global model configuration.
+        row["model_info"] = {
+            **row["model_info"],
+            "id": "",
+            "provider": "",
+            **recorded_models.get(str(row.get("session_id")), {}),
+        }
         if row.get("exploration_kind") == "validation" and row.get("exploration_case_name"):
             row["display_name"] = row["exploration_case_name"]
         model = row.pop("exploration_model", None)

apps/admin_console/routers/tasks.py

@@ -441,6 +441,24 @@ async def get_status():
             )
 
     model_info = model_service.get_active_model_info(active_profile)
+    model_sid = running_sid if is_running else latest_session_id
+    if model_info and model_sid:
+        recorded_model = session_repo.get_recorded_model_info_map([str(model_sid)]).get(
+            str(model_sid)
+        )
+        if not isinstance(recorded_model, dict):
+            matching_task = next(
+                (
+                    item
+                    for item in state.queue_items
+                    if isinstance(item, dict) and str(item.get("session_id")) == str(model_sid)
+                ),
+                None,
+            )
+            override = (matching_task or {}).get("runtime_overrides") or {}
+            model = override.get("model")
+            recorded_model = {"id": model, "provider": "openai"} if model else {}
+        model_info = {**model_info, "id": "", "provider": "", **recorded_model}
 
     # Unified Global Queue: merge web tasks and external SDK/CLI device queue tickets
     global_queued = DeviceExecutionLock.get_queued_tasks()
@@ -508,6 +526,12 @@ async def get_status():
         is_paused = state.is_paused
         conn_profile = conn_info.get("profile") or active_profile
         conn_model_info = model_service.get_active_model_info(conn_profile)
+        if conn_model_info and model_info:
+            conn_model_info = {
+                **conn_model_info,
+                "id": model_info["id"],
+                "provider": model_info["provider"],
+            }
         return {
             "status": "paused" if is_paused else "running",
             "paused_error": state.paused_error if is_paused else None,

apps/admin_console/services/automation_service.py

@@ -15,6 +15,7 @@ from artemis.runtime.task_limits import task_timeout
 
 logger = logging.getLogger(__name__)
 TERMINAL = {"completed", "failed", "cancelled", "skipped", "interrupted"}
+MODEL_PAUSE_REASON = "模型请求已暂停，请先恢复模型连接再继续批次"
 background_tasks: set[asyncio.Task] = set()
 
 
@@ -123,7 +124,9 @@ def recover_batches():
             if any(str(job["session_id"]) in live_sessions for job in store.jobs(batch["id"])):
                 continue
             batch.update(
-                status="paused", reason="服务已重启；请检查中断任务，点击继续执行未开始任务"
+                status="paused",
+                reason="服务已重启；请检查中断任务，点击继续执行未开始任务",
+                pause_source="recovery",
             )
             for job in store.jobs(batch["id"]):
                 if job["status"] in {"running", "queued", "finalizing", "task_paused", "resuming"}:
@@ -164,9 +167,29 @@ async def on_terminal(item: dict, status: str):
             }
         ):
             job["status"] = "failed"
-            job["error"] = job.get("error") or "任务执行结束，但业务检查未通过"
+            job["error"] = (
+                job.get("error")
+                or report.get("error")
+                or (report.get("test_result") or {}).get("reason")
+                or "任务未完成或验证未通过，请查看报告中的具体原因"
+            )
         elif job["status"] == "failed" and report.get("error") and not job.get("error"):
             job["error"] = report["error"]
+        if job["status"] == "failed" and report["outcome"].get("code") == "initialization_failed":
+            job["failure_code"] = "initialization_failed"
+            batch = store.get("batch", job.get("batch_id")) if job.get("batch_id") else None
+            if (
+                batch
+                and (batch["status"] == "running" or batch.get("pause_source") == "model")
+                and any(j["status"] == "pending" for j in store.jobs(batch["id"]))
+            ):
+                batch.update(
+                    status="paused",
+                    pause_source="initialization",
+                    reason="任务初始化失败；请处理环境问题后继续剩余用例："
+                    + (job.get("error") or "请查看任务报告"),
+                )
+                store.put("batch", batch["id"], batch)
         # 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"])
@@ -217,10 +240,18 @@ async def tick_batches():
         if batch["status"] not in {"running", "paused"}:
             continue
         jobs = store.jobs(batch["id"])
+        if (
+            batch["status"] == "paused"
+            and batch.get("pause_source") == "model"
+            and not state.is_paused
+        ):
+            batch.update(status="running", reason="")
+            batch.pop("pause_source", None)
+            store.put("batch", batch["id"], batch)
         active = [j for j in jobs if j["status"] in {"running", "queued", "finalizing"}]
         if active:
-            if state.is_paused:
-                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")
+            if state.is_paused and batch["status"] == "running":
+                batch.update(status="paused", reason=MODEL_PAUSE_REASON, pause_source="model")
                 store.put("batch", batch["id"], batch)
             for job in active:
                 # The queue records started_at at submission, then replaces it
@@ -284,7 +315,7 @@ async def tick_batches():
             store.put("batch", batch["id"], batch)
             continue
         if state.is_paused:
-            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")
+            batch.update(status="paused", reason=MODEL_PAUSE_REASON, pause_source="model")
             store.put("batch", batch["id"], batch)
             continue
         job = pending[0]
@@ -438,11 +469,14 @@ def batch_action(batch_id: str, action: str) -> dict:
     if action == "pause":
         if batch["status"] not in {"running", "paused"}:
             raise ValueError("只能暂停正在执行的批次")
-        batch.update(status="paused", reason="用户暂停；当前任务继续，后续任务等待")
+        batch.update(
+            status="paused", reason="用户暂停；当前任务继续，后续任务等待", pause_source="user"
+        )
     elif action == "resume":
         if batch["status"] not in {"draft", "paused"}:
             raise ValueError("只能开始草稿或继续已暂停批次")
         batch.update(status="running", reason="")
+        batch.pop("pause_source", None)
     elif action == "retry_failed":
         if batch["status"] == "running":
             raise ValueError("请先暂停批次")

apps/admin_console/services/media_service.py

@@ -149,7 +149,7 @@ class MediaService:
         return p
 
     LIVE_RECORDING_GRACE_SECONDS = 10.0
-    TRACE_STATUS_SUFFIXES = ("_PASS_", "_FAIL_", "_TESTFAIL_")
+    TRACE_STATUS_SUFFIXES = ("_PASS_", "_FAIL_", "_TESTFAIL_", "_BLOCKED_", "_UNVERIFIED_")
 
     @classmethod
     def is_live_recording(cls, p: Path) -> bool:

apps/admin_console/services/report_export.py

@@ -36,7 +36,7 @@ from artemis.runtime.case_result import RESULT_LABELS, resolve_case_result
 from apps.admin_console.services.case_review import reviewed_result
 
 EXPORT_ROOT = WORKSPACE_ROOT / "artifacts" / "reports"
-BATCH_ARCHIVE_SIGNATURE = "artemis-batch-layout-2"
+BATCH_ARCHIVE_SIGNATURE = "artemis-batch-layout-3"
 
 
 def batch_archive_signature(batch_id: str | None = None) -> str:
@@ -234,11 +234,14 @@ def session_report(session_id: str, db_path=None) -> dict:
     if status in {"failed", "interrupted"} and verification.startswith("未验证"):
         verification = "未验证（任务异常终止）"
     if not content:
-        content = (
-            "本任务未生成最终结论。请查看异常原因和已记录的执行步骤。"
-            if status in {"failed", "interrupted"}
-            else "本任务没有保存最终结论。以下内容仅来自已记录的执行状态和证据。"
-        )
+        lines = ["本任务未保存独立输出正文。", f"当前有效判定：{verification}"]
+        if test_result:
+            if test_result.get("reason"):
+                lines.append(f"判定依据：{test_result['reason']}")
+            lines.extend(f"- {item}" for item in test_result.get("evidence") or [])
+        elif error:
+            lines.append(f"异常原因：{error}")
+        content = "\n\n".join(lines)
     return {
         "id": session_id,
         **guidance_details(session_id, db_path=repo.db_path),
@@ -264,6 +267,7 @@ def session_report(session_id: str, db_path=None) -> dict:
         "category": case.get("category", ""),
         "subcategory": case.get("subcategory", ""),
         "preconditions": case.get("preconditions", ""),
+        "original_case": case.get("original_case"),
         "task_config": case.get("task_config") or {},
         "task_extensions": task_extensions.report_sections(session_id, store),
     }
@@ -330,17 +334,24 @@ def source_text(value: dict) -> str:
     for item in value.get("sources", []):
         references = ", ".join(
             " / ".join(
-                f"{key}={ref[key]}" for key in ("step_id", "call_id", "source_id") if ref.get(key)
+                f"{key}={ref[key]}"
+                for key in ("step_id", "call_id", "source_id", "trace_id")
+                if ref.get(key)
             )
             or "编号未记录"
             for ref in item.get("references", [])
         )
+        variation = "（来源标签随步骤变化，详见原始步骤）" if item.get("label_varies") else ""
         lines.append(
-            f"{labels.get(item['kind'], '其他')} · {item['label'] or item['target_id']} · {references}"
+            f"{labels.get(item['kind'], '其他')} · {item['label'] or item['target_id']}"
+            f"{variation} · {references}"
         )
     if value.get("sources_omitted"):
         lines.append(f"另 {value['sources_omitted']} 个来源见原始步骤记录。")
-    lines.append(f"来源未完整记录的步骤：{value.get('unattributed_step_count', '未知')}。")
+    lines.append(
+        f"未关联到单一来源的步骤：{value.get('unattributed_step_count', '未知')}。"
+        "窗口枚举等操作可能没有单一目标；此计数不表示截图丢失。"
+    )
     lines.append(value.get("note") or "来源清单不代表断言已验证。")
     return "\n".join(lines)
 
@@ -367,6 +378,15 @@ def metadata(report: dict) -> list[tuple]:
         ("检测项目", report.get("category") or "—"),
         ("测试子项", report.get("subcategory") or "—"),
         ("前置约束提取", report.get("preconditions") or "—"),
+        *(
+            [
+                ("原始用例 · 预置条件", report["original_case"].get("preconditions") or "未填写"),
+                ("原始用例 · 操作步骤", report["original_case"].get("steps") or "未填写"),
+                ("原始用例 · 预期结果", report["original_case"].get("expected") or "未填写"),
+            ]
+            if report.get("original_case") is not None
+            else []
+        ),
         ("任务配置", config_text(report.get("task_config"))),
         ("任务目标", report["goal"]),
         ("预期结果", report["expected"] or "未指定"),
@@ -949,8 +969,7 @@ def session_videos(report: dict) -> list[tuple[Path, str]]:
         return []
     source = Path(str(candidate)).resolve()
     trace_root = TRACES_PATH.resolve()
-    # Workers save recordings in their finalized web_<time>_<id>_PASS/FAIL
-    # folder. The recording row already ties that path to this session.
+    # The recording row already ties the finalized trace folder to this session.
     if not source.is_relative_to(trace_root):
         return []
     # A resumed recording lives under resume_NNNN; the initial recording is

apps/admin_console/services/task_extensions.py

@@ -9,6 +9,7 @@ from apps.admin_console.services.automation_store import AutomationStore, identi
 from apps.admin_console.database.repositories.session_repository import SessionRepository
 from artemis.plugins.models import PluginManifest
 from artemis.plugins.store import PluginStore
+from apps.admin_console.services.task_import import case_title
 
 TERMINAL = {"completed", "success", "failed", "cancelled", "interrupted", "skipped"}
 
@@ -35,16 +36,58 @@ def installation_signature() -> str:
     )
 
 
+def reviewed_batch_sessions(batch_id: str, store: AutomationStore) -> set[str]:
+    """Read current human review values once per batch, without loading history."""
+    manifest = next((item for item in active_manifests() if item.id == "task-review"), None)
+    if manifest is None or manifest.workspace is None:
+        return set()
+    with store.connection() as conn:
+        rows = conn.execute(
+            """SELECT j.session_id, json_extract(r.payload, '$."task-review".values') AS review_values
+               FROM automation_jobs j JOIN automation_records r
+                 ON r.kind='task_extensions' AND r.id=j.session_id
+               WHERE j.batch_id=?""",
+            (batch_id,),
+        ).fetchall()
+    reviewed = set()
+    for row in rows:
+        values = json.loads(row["review_values"] or "{}")
+        if any(
+            isinstance(value := values.get(field.id), str)
+            and value.strip()
+            and (field.kind == "text" or value in field.options)
+            for field in manifest.workspace.fields
+        ):
+            reviewed.add(row["session_id"])
+    return reviewed
+
+
 def task_context(session_id: str, store: AutomationStore) -> dict:
     identifier(session_id)
     session = SessionRepository(store.path).get_session_by_id(session_id) or {}
     job = store.job(session_id) or {}
     if not session and not job:
         raise ValueError("任务记录不存在")
+    case = job.get("case") or {}
+    navigation = None
+    if batch_id := job.get("batch_id"):
+        jobs = [item for item in store.jobs(batch_id) if item.get("status") in TERMINAL]
+        ids = [item["session_id"] for item in jobs]
+        index = ids.index(session_id) if session_id in ids else -1
+        navigation = {
+            "scope": "batch",
+            "position": index + 1,
+            "total": len(ids),
+            "previous": ids[index - 1] if index > 0 else None,
+            "next": ids[index + 1] if 0 <= index < len(ids) - 1 else None,
+        }
     return {
         "session_id": session_id,
         "initial_prompt": session.get("initial_goal") or (job.get("case") or {}).get("goal", ""),
         "editable": (job.get("status") or session.get("status")) in TERMINAL,
+        "case_title": case_title(case),
+        "original_case": case.get("original_case"),
+        "navigation": navigation,
     }
 
 

apps/admin_console/services/task_import.py

@@ -21,6 +21,7 @@ HEADERS = (
     "Artemis提示词",
     "任务配置(JSON)",
 )
+CASE_HEADERS = ("预置条件", "操作步骤", "预期结果")
 MAX_ROWS = int(os.getenv("ARTEMIS_IMPORT_MAX_ROWS", "1000"))
 MAX_BYTES = int(os.getenv("ARTEMIS_IMPORT_MAX_BYTES", "10485760"))
 
@@ -61,6 +62,15 @@ class TaskOptions(BaseModel):
         return value.model_dump(exclude_unset=True)
 
 
+class OriginalCase(BaseModel):
+    """Imported review material, never appended to the execution prompt."""
+
+    model_config = ConfigDict(extra="forbid")
+    preconditions: str = Field(default="", max_length=10000)
+    steps: str = Field(default="", max_length=10000)
+    expected: str = Field(default="", max_length=10000)
+
+
 class TaskCase(BaseModel):
     model_config = ConfigDict(extra="forbid")
     case_id: str = Field(default="", max_length=200)
@@ -70,16 +80,29 @@ class TaskCase(BaseModel):
     preconditions: str = Field(default="", max_length=10000)
     goal: str = Field(min_length=1, max_length=10000)
     task_config: TaskOptions = Field(default_factory=TaskOptions)
+    original_case: OriginalCase | None = None
+
+
+def original_case_enabled() -> bool:
+    from apps.admin_console.services.task_extensions import active_manifests
+
+    return any(
+        panel.kind == "original_case"
+        for manifest in active_manifests()
+        if manifest.workspace is not None
+        for panel in manifest.workspace.panels
+    )
 
 
 def template() -> bytes:
+    headers = (*HEADERS, *CASE_HEADERS) if original_case_enabled() else HEADERS
     wb = Workbook()
     ws = wb.active
     assert ws is not None
     ws.title = "任务"
-    ws.append(HEADERS)
+    ws.append(headers)
     ws.freeze_panes = "A2"
-    ws.auto_filter.ref = "A1:G1"
+    ws.auto_filter.ref = f"A1:{get_column_letter(len(headers))}1"
     for cell in ws[1]:
         cell.font = Font(bold=True, color="FFFFFF")
         cell.fill = PatternFill("solid", fgColor="245C78")
@@ -93,7 +116,7 @@ def template() -> bytes:
     help_sheet.append(["前置约束提取及其他描述列仅作查看、搜索和报告元数据，不追加到提示词。"])
     help_sheet.append(["任务配置(JSON)可留空，空字段继承批次或全局配置；禁止密钥与未知字段。"])
     help_sheet.append(["示例仅供参考，不会导入执行。请在“任务”页填写自己的用例。"])
-    help_sheet.append(HEADERS)
+    help_sheet.append(headers)
     help_sheet.append(
         [
             "示例-001",
@@ -130,7 +153,18 @@ def template() -> bytes:
             json.dumps({"profile": "flash", "execution_target": "computer"}, ensure_ascii=False),
         ]
     )
-    for column in range(1, 8):
+    if len(headers) > len(HEADERS):
+        help_sheet.append(
+            [
+                "人工评审插件附加列：预置条件、操作步骤、预期结果。仅保存原始用例，均不追加到 AI 提示词。"
+            ]
+        )
+        for row_number in (6, 7):
+            for column, value in enumerate(
+                ("填写原始用例的预置条件", "填写原始用例的操作步骤", "填写原始用例的预期结果"), 8
+            ):
+                help_sheet.cell(row_number, column, value)
+    for column in range(1, len(headers) + 1):
         help_sheet.column_dimensions[get_column_letter(column)].width = 70 if column > 5 else 26
     for row in help_sheet:
         for cell in row:
@@ -164,7 +198,10 @@ def parse_workbook(data: bytes) -> dict:
             raise ValueError("缺少“任务”工作表，请使用下载的模板")
         rows = iter(wb["任务"].iter_rows())
         headers = [str(cell.value or "").strip() for cell in next(rows, [])]
-        if headers != list(HEADERS):
+        supported_headers = [list(HEADERS)]
+        if original_case_enabled():
+            supported_headers.append([*HEADERS, *CASE_HEADERS])
+        if headers not in supported_headers:
             raise ValueError("列名或顺序与新版模板不一致，请重新下载模板")
         tasks, errors = [], []
         for number, row in enumerate(rows, 2):
@@ -190,9 +227,29 @@ def parse_workbook(data: bytes) -> dict:
                         "preconditions": values[4],
                         "goal": values[5],
                         "task_config": config,
+                        "original_case": (
+                            dict(
+                                zip(
+                                    ("preconditions", "steps", "expected"),
+                                    (
+                                        str(cell.value if cell.value is not None else "").strip()
+                                        for cell in row[7:10]
+                                    ),
+                                )
+                            )
+                            if len(headers) == 10
+                            else None
+                        ),
+                    }
+                )
+                tasks.append(
+                    {
+                        "row": number,
+                        **case.model_dump(
+                            exclude={"original_case"} if case.original_case is None else None
+                        ),
                     }
                 )
-                tasks.append({"row": number, **case.model_dump()})
             except (ValueError, TypeError) as exc:
                 errors.append({"row": number, "message": str(exc)[:500]})
         if not tasks and not errors:

apps/admin_console/services/task_queue_service.py

@@ -1522,8 +1522,10 @@ class TaskQueueService:
         from artemis.plugins.store import PluginStore
 
         for batch in store.records("batch"):
-            if batch["status"] == "running":
-                batch.update(status="paused", reason="已停止全部任务，等待手动继续")
+            if batch["status"] in {"running", "paused"}:
+                batch.update(
+                    status="paused", reason="已停止全部任务，等待手动继续", pause_source="user"
+                )
                 store.put("batch", batch["id"], batch)
         # 1. Cancel local queue reservations
         for item in state.queue_items:

apps/showcase_ui/AGENTS.md

@@ -30,6 +30,9 @@ npm run build
 
 ## Local Conventions
 
+- 发版遵守根指南的 Release Gates。前端应用版本只改 package.json 顶层 `version` 和 package-lock.json 顶层及 `packages[""].version`；禁止把相同数字的第三方依赖一并替换。
+- Node 支持范围以锁定的 Angular CLI/构建依赖实际 `engines` 为准，核对启动脚本的主、次、补丁版本边界和提示；不要只判断“Node 22/24/26”。
+- 安装或依赖变更需在隔离目录、独立空 npm 缓存下运行 `npm ci`，再运行上述测试和构建；国内入口同时核验镜像安装。不得以关闭完整性校验、强制安装或删除锁文件掩盖不一致，也不得用已装依赖的构建结果宣称全新安装通过。
 - 页面组件在 src/app/components，服务在 src/app/services；先复用已有组件、样式及 API 服务。
 - 保持现有简体中文文案、颜色、间距和控件样式，菜单、弹窗和表单必须清晰可读。
 - 修改任务或配置交互时覆盖加载、保存、失败和空状态；不要将执行中误标成录屏中或把完成误标成验证通过。

apps/showcase_ui/package.json

@@ -1,6 +1,6 @@
 {
   "name": "artemis-showcase-ui",
-  "version": "2.3.0",
+  "version": "2.4.3",
   "scripts": {
     "ng": "ng",
     "start": "ng serve --proxy-config proxy.conf.json",
@@ -9,24 +9,29 @@
     "test": "ng test"
   },
   "private": true,
+  "overrides": {
+    "@angular/build": {
+      "vite": "8.3.5"
+    }
+  },
   "dependencies": {
-    "@angular/cdk": "^22.1.5",
-    "@angular/common": "^22.1.4",
-    "@angular/compiler": "^22.1.4",
-    "@angular/core": "^22.1.4",
-    "@angular/forms": "^22.1.4",
-    "@angular/platform-browser": "^22.1.4",
-    "@angular/platform-browser-dynamic": "^22.1.4",
-    "@angular/router": "^22.1.4",
+    "@angular/cdk": "^22.2.4",
+    "@angular/common": "^22.2.3",
+    "@angular/compiler": "^22.2.3",
+    "@angular/core": "^22.2.3",
+    "@angular/forms": "^22.2.3",
+    "@angular/platform-browser": "^22.2.3",
+    "@angular/platform-browser-dynamic": "^22.2.3",
+    "@angular/router": "^22.2.3",
     "marked": "18.1.1",
     "rxjs": "~7.8.0",
     "tslib": "^2.3.0",
     "zone.js": "~0.15.0"
   },
   "devDependencies": {
-    "@angular/build": "^22.1.6",
-    "@angular/cli": "^22.1.6",
-    "@angular/compiler-cli": "^22.1.4",
+    "@angular/build": "^22.2.4",
+    "@angular/cli": "^22.2.4",
+    "@angular/compiler-cli": "^22.2.3",
     "@types/jasmine": "~5.1.0",
     "istanbul-lib-instrument": "^6.0.3",
     "jasmine-core": "~5.6.0",

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

@@ -695,13 +695,13 @@ limitations under the License.
                                       @if (getActionTargetText(item.data)) {
                                         <div class="action-detail-row">
                                           <span class="detail-label">目标：</span>
-                                          <span class="detail-value">"{{ getActionTargetText(item.data) }}"</span>
+                                          <app-expandable-value class="detail-value" label="目标" [value]="getActionTargetText(item.data)" />
                                         </div>
                                       }
                                       @if (getActionInputText(item.data)) {
                                         <div class="action-detail-row">
                                           <span class="detail-label">{{ getActionInputLabel(item.data) }}:</span>
-                                          <span class="detail-value">"{{ getActionInputText(item.data) }}"</span>
+                                          <app-expandable-value class="detail-value" label="输入" [value]="getActionInputText(item.data)" />
                                         </div>
                                       }
                                       @if (getActionCoords(item.data)) {
@@ -719,13 +719,13 @@ limitations under the License.
                                         @if (getActionTargetText(item.data)) {
                                           <div class="grid-item">
                                             <span class="grid-label">目标</span>
-                                            <span class="grid-value">"{{ getActionTargetText(item.data) }}"</span>
+                                            <app-expandable-value label="目标" [value]="getActionTargetText(item.data)" />
                                           </div>
                                         }
                                         @if (getActionInputText(item.data)) {
                                           <div class="grid-item">
                                             <span class="grid-label">{{ getActionInputLabel(item.data) }}</span>
-                                            <span class="grid-value">"{{ getActionInputText(item.data) }}"</span>
+                                            <app-expandable-value label="输入" [value]="getActionInputText(item.data)" />
                                           </div>
                                         }
                                         @if (getActionCoords(item.data)) {
@@ -749,19 +749,7 @@ limitations under the License.
                                         @for (param of getActionExtraParams(item.data); track trackParam($index, param)) {
                                           <div class="grid-item" [class.full-width]="param.key === 'Result'">
                                             <span class="grid-label">{{ param.key }}</span>
-                                            @if (param.key === 'Result') {
-                                              <div class="action-result-preview">{{ param.value | slice:0:180 }}{{ param.value.length > 180 ? '…' : '' }}</div>
-                                              <details class="action-result-detail">
-                                                <summary>
-                                                  <span class="result-expand-label">展开完整结果</span>
-                                                  <span class="result-collapse-label">收起结果</span>
-                                                  <span class="result-length">{{ param.value.length }} 字符</span>
-                                                </summary>
-                                                <pre tabindex="0" aria-label="完整操作结果，可选择复制">{{ param.value }}</pre>
-                                              </details>
-                                            } @else {
-                                              <span class="grid-value code-pill">{{ param.value }}</span>
-                                            }
+                                            <app-expandable-value [label]="param.key" [value]="param.value" />
                                           </div>
                                         }
                                         <!-- Fallback item if all detail fields are empty -->
@@ -1008,7 +996,7 @@ limitations under the License.
                                           @if (getAdbCommandLine(item.data)) {
                                             <div class="action-detail-row">
                                               <span class="detail-label">命令：</span>
-                                              <span class="detail-value command-value"><code>{{ getAdbCommandLine(item.data) }}</code></span>
+                                              <app-expandable-value class="detail-value" label="命令" [value]="getAdbCommandLine(item.data)" />
                                             </div>
                                           }
                                           @if (getAdbCwd(item.data)) {
@@ -1029,13 +1017,13 @@ limitations under the License.
                                           @if (getToolTargetText(item.data)) {
                                             <div class="action-detail-row">
                                               <span class="detail-label">目标：</span>
-                                              <span class="detail-value">"{{ getToolTargetText(item.data) }}"</span>
+                                              <app-expandable-value class="detail-value" label="目标" [value]="getToolTargetText(item.data)" />
                                             </div>
                                           }
                                           @if (getToolInputText(item.data)) {
                                             <div class="action-detail-row">
                                               <span class="detail-label">{{ getToolInputLabel(item.data) }}:</span>
-                                              <span class="detail-value">"{{ getToolInputText(item.data) }}"</span>
+                                              <app-expandable-value class="detail-value" label="输入" [value]="getToolInputText(item.data)" />
                                             </div>
                                           }
                                           @if (getToolCoords(item.data)) {
@@ -1047,13 +1035,13 @@ limitations under the License.
                                           @if (getToolAnalysisText(item.data)) {
                                             <div class="action-detail-row">
                                               <span class="detail-label">分析：</span>
-                                              <span class="detail-value">"{{ getToolAnalysisText(item.data) }}"</span>
+                                              <app-expandable-value class="detail-value" label="分析" [value]="getToolAnalysisText(item.data)" />
                                             </div>
                                           }
                                           @if (getToolGenericDetails(item.data)) {
                                             <div class="action-detail-row">
                                               <span class="detail-label">详情：</span>
-                                              <span class="detail-value">"{{ getToolGenericDetails(item.data) }}"</span>
+                                              <app-expandable-value class="detail-value" label="详情" [value]="getToolGenericDetails(item.data)" />
                                             </div>
                                           }
                                         }
@@ -1067,7 +1055,7 @@ limitations under the License.
                                             @if (getAdbCommandLine(item.data)) {
                                               <div class="grid-item full-width">
                                                 <span class="grid-label">命令</span>
-                                                <span class="grid-value command-value"><code>{{ getAdbCommandLine(item.data) }}</code></span>
+                                                <app-expandable-value label="命令" [value]="getAdbCommandLine(item.data)" />
                                               </div>
                                             }
                                             @if (getAdbCwd(item.data)) {
@@ -1087,7 +1075,7 @@ limitations under the License.
                                             @for (param of plugin.args; track param.key) {
                                               <div class="grid-item">
                                                 <span class="grid-label">{{ param.key }}</span>
-                                                <span class="grid-value code-pill">{{ param.value }}</span>
+                                                <app-expandable-value [label]="param.key" [value]="param.value" />
                                               </div>
                                             }
                                             @if (plugin.result || plugin.rawResult || plugin.facts.length) {
@@ -1101,13 +1089,13 @@ limitations under the License.
                                             @if (getToolTargetText(item.data)) {
                                               <div class="grid-item">
                                                 <span class="grid-label">目标</span>
-                                                <span class="grid-value">"{{ getToolTargetText(item.data) }}"</span>
+                                                <app-expandable-value label="目标" [value]="getToolTargetText(item.data)" />
                                               </div>
                                             }
                                             @if (getToolInputText(item.data)) {
                                               <div class="grid-item">
                                                 <span class="grid-label">{{ getToolInputLabel(item.data) }}</span>
-                                                <span class="grid-value">"{{ getToolInputText(item.data) }}"</span>
+                                                <app-expandable-value label="输入" [value]="getToolInputText(item.data)" />
                                               </div>
                                             }
                                             @if (getToolCoords(item.data)) {
@@ -1119,19 +1107,19 @@ limitations under the License.
                                             @if (getToolAnalysisText(item.data)) {
                                               <div class="grid-item">
                                                 <span class="grid-label">分析</span>
-                                                <span class="grid-value">"{{ getToolAnalysisText(item.data) }}"</span>
+                                                <app-expandable-value label="分析" [value]="getToolAnalysisText(item.data)" />
                                               </div>
                                             }
                                             @if (getToolGenericDetails(item.data)) {
                                               <div class="grid-item">
                                                 <span class="grid-label">详情</span>
-                                                <span class="grid-value">"{{ getToolGenericDetails(item.data) }}"</span>
+                                                <app-expandable-value label="详情" [value]="getToolGenericDetails(item.data)" />
                                               </div>
                                             }
                                             @for (param of getToolExtraParams(item.data); track trackParam($index, param)) {
                                               <div class="grid-item">
                                                 <span class="grid-label">{{ param.key }}</span>
-                                                <span class="grid-value code-pill">{{ param.value }}</span>
+                                                <app-expandable-value [label]="param.key" [value]="param.value" />
                                               </div>
                                             }
                                           }

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

@@ -6,6 +6,7 @@ import { LlmRequestStatusComponent } from '../llm-request-status/llm-request-sta
 import { TaskLifecycleComponent } from '../task-lifecycle/task-lifecycle.component';
 import { ReportMarkdownComponent } from '../report-markdown/report-markdown.component';
 import { PluginToolResultComponent } from '../plugin-tool-result/plugin-tool-result.component';
+import { ExpandableValueComponent } from '../expandable-value/expandable-value.component';
 import { AutomationPanelComponent } from '../automation-panel/automation-panel.component';
 import { UiLabelPipe } from '../../utils/ui-label.pipe';
 /**
@@ -250,7 +251,7 @@ export type { MarkdownSegment, MarkdownLine, NoteMilestone, ParsedNote, StreamRe
 @Component({
   selector: 'app-agent-stream',
   standalone: true,
-  imports: [PluginToolResultComponent, ReportMarkdownComponent, LlmRequestStatusComponent, TaskLifecycleComponent, TaskIdCopyComponent, UiLabelPipe, CommonModule, FormsModule, OverlayModule, TaskHistoryComponent, AutomationPanelComponent, TestResultBadgeComponent, TestResultCardComponent, TaskBatchFilterComponent],
+  imports: [ExpandableValueComponent, PluginToolResultComponent, ReportMarkdownComponent, LlmRequestStatusComponent, TaskLifecycleComponent, TaskIdCopyComponent, UiLabelPipe, CommonModule, FormsModule, OverlayModule, TaskHistoryComponent, AutomationPanelComponent, TestResultBadgeComponent, TestResultCardComponent, TaskBatchFilterComponent],
   templateUrl: './agent-stream.component.html',
   styleUrl: './agent-stream.component.scss',
   changeDetection: ChangeDetectionStrategy.OnPush

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

@@ -108,6 +108,19 @@
        </div>
      }
     @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" [class.selected]="agent.currentSessionId() === j.session_id"><app-favorite-button [sourceId]="j.session_id" /><button (click)="openBatchTask(j.session_id)" [title]="j.case.goal" [attr.aria-pressed]="agent.currentSessionId() === j.session_id">{{j.case.case_id ? j.case.case_id + ' ' : ''}}{{j.case.name}}@if(j.repeat_count > 1){ · 第 {{j.iteration}} / {{j.repeat_count}} 轮}</button><span>{{label(j.status)}}</span><app-test-result-badge [result]="j.test_result" [executionStatus]="j.status" [compact]="true" />@if(j.error){<small>{{j.error}}</small>}</div>}
+      @for(j of b.jobs; track j.session_id){
+        <div class="job" [class.selected]="agent.currentSessionId() === j.session_id">
+          <div class="job-heading">
+            <app-favorite-button [sourceId]="j.session_id" />
+            <button (click)="openBatchTask(j.session_id)" [title]="j.case.goal" [attr.aria-pressed]="agent.currentSessionId() === j.session_id">{{j.case.case_id ? j.case.case_id + ' ' : ''}}{{j.case.name}}@if(j.repeat_count > 1){ · 第 {{j.iteration}} / {{j.repeat_count}} 轮}</button>
+          </div>
+          <div class="job-statuses">
+            <span>{{label(j.status)}}</span>
+            <app-test-result-badge [result]="j.test_result" [executionStatus]="j.status" [compact]="true" />
+            @if(j.human_reviewed){<span class="human-review-badge" title="人工评审已有保存内容，不代表测试通过">人工已审</span>}
+          </div>
+          @if(j.error){<small>{{j.error}}</small>}
+        </div>
+      }
   </section>}
 }

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

@@ -37,7 +37,15 @@ input[type=checkbox]{width:15px;height:15px;accent-color:var(--app-primary-text,
 @keyframes archive-spin{to{transform:rotate(360deg);}}
 .code{font-family:Consolas,monospace;font-size:12px;line-height:1.6;resize:vertical;background:var(--app-surface-soft, #f8fafc);}.table-wrap{max-height:260px;overflow:auto;border:1px solid var(--app-border, #e2e8f0);border-radius:8px;margin-bottom:14px;}table{width:100%;border-collapse:collapse;}th,td{padding:9px 10px;border-bottom:1px solid var(--app-border, #e2e8f0);text-align:left;overflow-wrap:anywhere;}th{background:var(--app-surface-soft, #f8fafc);color:var(--app-text-secondary, #475569);font-weight:500;}
 .preview{white-space:pre-wrap;max-height:400px;overflow:auto;font:inherit;color:var(--app-text-control, #334155);background:var(--app-surface-soft, #f8fafc);border-radius:8px;padding:12px;border:1px solid var(--app-border, #e2e8f0);}
-.job{display:flex;flex-wrap:wrap;gap:8px;align-items:center;padding:10px 0;border-bottom:1px solid var(--app-border, #f1f5f9);}.job:last-child{border-bottom:0;}.job button{flex:1;justify-content:flex-start;text-align:left;min-width:150px;}.job span{font-size:12px;background:var(--app-surface-soft, #f1f5f9);color:var(--app-text-secondary, #475569);border-radius:5px;padding:3px 7px;}.job small{width:100%;}details{margin:14px 0;}summary{color:var(--app-text-secondary, #475569);cursor:pointer;padding:8px 0;}
+.job{display:flex;flex-direction:column;gap:8px;padding:12px 0;border-bottom:1px solid var(--app-border, #f1f5f9);}
+.job:last-child{border-bottom:0;}
+.job-heading{position:relative;min-width:0;}
+.job-heading>app-favorite-button{position:absolute;left:6px;top:4px;z-index:1;}
+.job-heading>button{box-sizing:border-box;width:100%;min-width:0;padding-left:40px;justify-content:flex-start;text-align:left;overflow-wrap:anywhere;}
+.job-statuses{display:flex;flex-wrap:wrap;align-items:center;gap:8px;}
+.job-statuses>span{display:inline-flex;align-items:center;box-sizing:border-box;height:20px;padding:0 6px;border:1px solid transparent;border-radius:5px;font-size:11px;line-height:14px;background:var(--app-surface-soft, #f1f5f9);color:var(--app-text-secondary, #475569);white-space:nowrap;}
+.job small{overflow-wrap:anywhere;}
+details{margin:14px 0;}summary{color:var(--app-text-secondary, #475569);cursor:pointer;padding:8px 0;}
 .task-guidance{margin-top:16px;padding:14px;border:1px solid var(--app-primary-border, #bfdbfe);border-radius:10px;background:var(--app-primary-soft, #f8fbff);}
 .task-guidance label{margin:8px 0 4px;}
 .report-overview{padding:14px;border:1px solid var(--app-primary-border, #dbeafe);border-radius:10px;background:var(--app-primary-soft, #f8fbff);}
@@ -58,3 +66,5 @@ input[type=checkbox]{width:15px;height:15px;accent-color:var(--app-primary-text,
   table{width:100%;border-collapse:collapse;font-size:12px;}th,td{padding:7px 9px;border:1px solid var(--app-border, #e2e8f0);vertical-align:top;}th{background:var(--app-primary-soft, #eff6ff);color:var(--app-primary-text, #1e3a8a);}
   .md-para-gap{height:8px;}
 }
+
+.job .human-review-badge{white-space:nowrap;border:1px solid var(--app-primary-border, #bfdbfe);background:var(--app-primary-soft, #eff6ff);color:var(--app-primary-text, #1d4ed8);font-weight:500;}

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

@@ -90,6 +90,30 @@ describe('AutomationPanelComponent batch deletion', () => {
     expect(http.post).not.toHaveBeenCalled();
   });
 
+  it('shows only saved human review badges and removes them on a batch refresh', async () => {
+    const fixture = TestBed.createComponent(AutomationPanelComponent);
+    const component = fixture.componentInstance;
+    await new Promise<void>(resolve => setTimeout(resolve, 0));
+    component.tab.set('batches');
+    const batch = { id: 'review-batch', name: '评审批次', status: 'completed', jobs: [
+      { session_id: 'reviewed', status: 'completed', human_reviewed: true, case: { name: '已评用例' } },
+      { session_id: 'empty', status: 'completed', human_reviewed: false, case: { name: '空白用例' } },
+      { session_id: 'legacy', status: 'completed', case: { name: '旧版任务' } }
+    ] };
+    component.batch.set(batch);
+    fixture.detectChanges();
+    const rows = fixture.nativeElement.querySelectorAll('.job');
+    expect(rows[0].querySelector('.human-review-badge').textContent).toBe('人工已审');
+    expect(rows[1].querySelector('.human-review-badge')).toBeNull();
+    expect(rows[2].querySelector('.human-review-badge')).toBeNull();
+    expect(fixture.nativeElement.textContent).not.toContain('人工未审');
+    (http.get.and as any).callFake((url: string) => of(url.endsWith('/review-batch')
+      ? { ...batch, jobs: batch.jobs.map(job => ({ ...job, human_reviewed: false })) } : []));
+    await component.refresh();
+    fixture.detectChanges();
+    expect(fixture.nativeElement.querySelector('.human-review-badge')).toBeNull();
+  });
+
   it('confirms deletion and removes the batch from the visible list', async () => {
     const fixture = TestBed.createComponent(AutomationPanelComponent);
     fixture.componentInstance.tab.set('batches');
@@ -129,7 +153,7 @@ describe('AutomationPanelComponent batch deletion', () => {
       {session_id:'task-b',status:'completed',case:{name:'用例 B',goal:'观察主页'}}
     ]});
     fixture.detectChanges();
-    const jobs: HTMLButtonElement[] = [...fixture.nativeElement.querySelectorAll('.job > button')];
+    const jobs: HTMLButtonElement[] = [...fixture.nativeElement.querySelectorAll('.job-heading > button')];
     jobs[0].click(); jobs[1].click();
     expect(agent.selectSession.calls.allArgs()).toEqual([['task-a',true],['task-b',true]]);
     expect(component.tab()).toBe('batches');

apps/showcase_ui/src/app/components/expandable-value/expandable-value.component.spec.ts

@@ -0,0 +1,26 @@
+import { TestBed } from '@angular/core/testing';
+import { ExpandableValueComponent } from './expandable-value.component';
+
+describe('执行字段折叠', () => {
+  for (const [label, value] of [['Payload', '{"x":1}'], ['输入', '完整内容'.repeat(100)], ['输出', '行\n'.repeat(6)]]) {
+    it(`默认折叠 ${label} 并保留完整内容`, () => {
+      const fixture = TestBed.createComponent(ExpandableValueComponent);
+      fixture.componentRef.setInput('label', label);
+      fixture.componentRef.setInput('value', value);
+      fixture.detectChanges();
+      const details: HTMLDetailsElement = fixture.nativeElement.querySelector('details');
+      expect(details.open).toBeFalse();
+      details.querySelector('summary')!.click();
+      expect(details.open).toBeTrue();
+      expect(details.querySelector('pre')!.textContent).toBe(value);
+      fixture.detectChanges();
+      expect(details.open).toBeTrue();
+    });
+  }
+  it('直接显示普通短字段', () => {
+    const fixture = TestBed.createComponent(ExpandableValueComponent);
+    fixture.componentRef.setInput('value', '点击设置'); fixture.detectChanges();
+    expect(fixture.nativeElement.querySelector('details')).toBeNull();
+    expect(fixture.nativeElement.textContent).toContain('点击设置');
+  });
+});

apps/showcase_ui/src/app/components/expandable-value/expandable-value.component.ts

@@ -0,0 +1,31 @@
+import { ChangeDetectionStrategy, Component, computed, input } from '@angular/core';
+
+/** Visual folding only: the full receipt remains selectable and unchanged. */
+@Component({
+  selector: 'app-expandable-value', standalone: true,
+  changeDetection: ChangeDetectionStrategy.OnPush,
+  template: `
+    @if (foldable()) {
+      <details>
+        <summary><span>{{ label() }} · {{ value().length }} 字符</span><span class="hint">展开查看</span></summary>
+        <pre tabindex="0" [attr.aria-label]="label() + '完整内容，可选择复制'">{{ value() }}</pre>
+      </details>
+    } @else { <span class="short-value">{{ value() }}</span> }
+  `,
+  styles: [`
+    :host { display:block; min-width:0; max-width:100%; }
+    details { border:1px solid var(--app-border, #e2e8f0); border-radius:8px; background:var(--app-surface-soft, #f8fafc); }
+    summary { cursor:pointer; padding:7px 10px; font-size:12px; color:var(--app-text-secondary, #475569); overflow-wrap:anywhere; }
+    .hint { margin-left:8px; color:var(--app-primary-text, #1a73e8); }
+    details[open] .hint { display:none; }
+    pre { margin:0; padding:10px; max-height:24rem; overflow:auto; white-space:pre-wrap; overflow-wrap:anywhere; font-size:12px; user-select:text; }
+    .short-value { white-space:pre-wrap; overflow-wrap:anywhere; }
+    summary:focus-visible, pre:focus-visible { outline:2px solid var(--app-focus, #a5b4fc); outline-offset:2px; }
+  `]
+})
+export class ExpandableValueComponent {
+  value = input('');
+  label = input('详情');
+  foldable = computed(() => /payload|原始|^result$/i.test(this.label())
+    || this.value().length > 240 || this.value().split('\n').length > 4);
+}

apps/showcase_ui/src/app/components/floating-video-player/floating-video-player.component.html

@@ -122,7 +122,8 @@ limitations under the License.
     }
     <!-- Video Main Content Area -->
     @if (!agentService.isVideoMinimized()) {
-      <app-task-extension-panels [sessionId]="agentService.currentSessionId()" [enabled]="agentService.playerMode() === 'steps'"
+      <app-task-extension-panels [sessionId]="agentService.currentSessionId()" [enabled]="true"
+        [sessionIds]="reviewSessionIds()" (navigate)="agentService.selectSession($event, true)"
         [taskStatus]="agentService.currentSession()?.status || ''" (expandedWidth)="extensionWidth.set($event)">
       <div class="video-body">
         <!-- 1. LIVE SCREEN STREAM (AUTOMATICALLY ACTIVE DURING RUNNING TEST) -->

apps/showcase_ui/src/app/components/floating-video-player/floating-video-player.component.spec.ts

@@ -1,5 +1,5 @@
 import { provideHttpClient } from '@angular/common/http';
-import { provideHttpClientTesting } from '@angular/common/http/testing';
+import { HttpTestingController, provideHttpClientTesting } from '@angular/common/http/testing';
 import { ComponentFixture, TestBed } from '@angular/core/testing';
 import { signal } from '@angular/core';
 import { AgentService, RecordingSource, VideoSegment } from '../../services/agent.service';
@@ -41,6 +41,8 @@ describe('FloatingVideoPlayerComponent video markers', () => {
       currentSessionStepFrames: signal([frame]),
       currentSession: signal({ session_id: 'test', start_time: start }),
       currentSessionId: signal('test'),
+      sessions: signal([{ session_id: 'test', status: 'completed' }]),
+      selectSession: jasmine.createSpy('selectSession'),
       videoSeekRequest: signal<{ seconds: number; requestId: number; sourceId?: string } | null>(null),
       stepSeekRequest: signal(null),
       consumeVideoAutoplay: jasmine.createSpy('consumeVideoAutoplay').and.returnValue(false)
@@ -66,6 +68,9 @@ describe('FloatingVideoPlayerComponent video markers', () => {
 
     fixture = TestBed.createComponent(FloatingVideoPlayerComponent);
     fixture.detectChanges();
+    TestBed.inject(HttpTestingController).expectOne('/api/task-extensions/test').flush({
+      session_id: 'test', initial_prompt: '', editable: true, plugins: []
+    });
     component = fixture.componentInstance;
     video = component.videoRef!.nativeElement;
     paused = true;
@@ -100,6 +105,23 @@ describe('FloatingVideoPlayerComponent video markers', () => {
     fixture.detectChanges();
   }
 
+  for (const mode of ['video', 'steps']) {
+    it(`shows review controls in ${mode} mode even without a recording`, () => {
+      agentService.playerMode.set(mode);
+      agentService.recordingPlaybackStatus.set('unavailable');
+      component.extensionPanels()!.refresh(); fixture.detectChanges();
+      TestBed.inject(HttpTestingController).expectOne('/api/task-extensions/test').flush({
+        session_id: 'test', initial_prompt: '', editable: true, plugins: [{
+          plugin_id: 'review', name: '原始用例', version: '1.1.0', revision: 0, values: {}, history: [],
+          workspace: { fields: [], panels: [{ id: 'case', title: '原始用例', side: 'left', kind: 'original_case', width: {minimum: 240, preferred: 340, maximum: 480} }] }
+        }]
+      }); fixture.detectChanges();
+      const button: HTMLButtonElement = fixture.nativeElement.querySelector('button[aria-label="展开原始用例"]');
+      expect(button).not.toBeNull(); button.click(); fixture.detectChanges();
+      expect(fixture.nativeElement.querySelector('aside').textContent).toContain('未记录原始用例');
+    });
+  }
+
   it('removes the live image while hidden and reconnects it on return', () => {
     const hidden = spyOnProperty(document, 'hidden', 'get').and.returnValue(false);
     agentService.recordingPlaybackStatus.set('live');

apps/showcase_ui/src/app/components/floating-video-player/floating-video-player.component.ts

@@ -51,6 +51,9 @@ import { buildVideoStepMarkers, VideoStepMarker } from '../../utils/video-step-m
 export class FloatingVideoPlayerComponent implements OnDestroy {
   public agentService = inject(AgentService);
   public extensionWidth = signal(0);
+  public reviewSessionIds = computed(() => this.agentService.sessions()
+    .filter(session => ['completed', 'success', 'failed', 'cancelled', 'interrupted', 'skipped'].includes(session.status || ''))
+    .map(session => session.session_id));
   public extensionPanels = viewChild(TaskExtensionPanelsComponent);
   public windowLeft(): number {
     const width = this.agentService.isVideoMinimized() ? 280 : 400 + this.extensionWidth();

apps/showcase_ui/src/app/components/plugin-tool-result/plugin-tool-result.component.ts

@@ -1,15 +1,17 @@
 import { Component, computed, input } from '@angular/core';
 import { PluginToolView } from '../../utils/plugin-tool-view.util';
+import { ExpandableValueComponent } from '../expandable-value/expandable-value.component';
 
 /** Readable presentation only: the full receipt and model context stay intact. */
 @Component({
   selector: 'app-plugin-tool-result',
   standalone: true,
+  imports: [ExpandableValueComponent],
   template: `
     @if (view().facts.length) {
       <dl class="receipt-facts">
         @for (fact of view().facts; track fact.key) {
-          <div><dt>{{ fact.key }}</dt><dd>{{ fact.value }}</dd></div>
+          <div><dt>{{ fact.key }}</dt><dd><app-expandable-value [label]="fact.key" [value]="fact.value" /></dd></div>
         }
       </dl>
     }

apps/showcase_ui/src/app/components/task-extension-panels/task-extension-panels.component.html

@@ -44,14 +44,21 @@
 
 <ng-template #panelContent let-plugin="plugin" let-panel="panel">
   <section [id]="'extension-' + key(plugin, panel)" [attr.aria-label]="panel.title">
-    <header><h3>{{ panel.title }}</h3><span class="panel-kind">{{ panel.kind === 'initial_prompt' ? '原始提示词' : '人工填写 · 选填' }}</span></header>
-    @if (panel.kind === 'initial_prompt') {
+    <header><h3>{{ panel.kind === 'original_case' ? (data()?.case_title || panel.title) : panel.title }}</h3><span class="panel-kind">{{ panel.kind === 'original_case' ? '原始用例' : panel.kind === 'initial_prompt' ? '原始提示词' : '人工填写 · 选填' }}</span></header>
+    @if (panel.kind === 'original_case') {
+      @if (!data()?.original_case) {
+        <p class="muted">此任务未记录原始用例内容；旧任务不会从 AI 提示词推测补写。</p>
+      }
+      <div class="case-section"><h4>预置条件</h4><app-report-markdown [content]="data()?.original_case?.preconditions || '未填写'" /></div>
+      <div class="case-section"><h4>操作步骤</h4><app-report-markdown [content]="data()?.original_case?.steps || '未填写'" /></div>
+      <div class="case-section"><h4>预期结果</h4><app-report-markdown [content]="data()?.original_case?.expected || '未填写'" /></div>
+    } @else if (panel.kind === 'initial_prompt') {
       @if (data()?.initial_prompt) {
         <app-report-markdown [content]="data()!.initial_prompt" />
       } @else { <p class="muted">该任务未记录初始需求提示词。</p> }
     } @else {
       @if (!data()?.editable) { <p class="muted">任务结束后可填写评审。</p> }
-      <fieldset [disabled]="!data()?.editable || !!saving()">
+      <fieldset [disabled]="!data()?.editable">
         @for (field of plugin.workspace.fields; track field.id) {
           <div class="field" [class.choice-field]="field.kind === 'choice'" [class.note-field]="field.kind === 'text'">
             <span class="field-label">{{ field.label }}</span>
@@ -73,17 +80,26 @@
                 }
               </div>
             } @else {
-              <textarea rows="2" [attr.aria-label]="field.label" [maxLength]="field.max_length" placeholder="添加备注（选填）"
+              <textarea rows="1" [attr.aria-label]="field.label" [maxLength]="field.max_length" placeholder="添加备注（选填）"
                 [ngModel]="drafts[plugin.plugin_id].values[field.id] || ''" (ngModelChange)="edit(plugin.plugin_id, field.id, $event)"></textarea>
             }
           </div>
         }
         <div class="form-actions">
-          <button type="button" class="save" (click)="save(plugin)">{{ saving() === plugin.plugin_id ? '正在保存…' : '保存评审' }}</button>
+          <button type="button" class="save" [disabled]="!!saving()" (click)="save(plugin)">{{ saving() === plugin.plugin_id ? '正在保存…' : '保存评审' }}</button>
           <button type="button" class="reload" [disabled]="!!saving()" (click)="reload(plugin)" title="放弃未保存内容，读取最新记录">重新加载</button>
-          @if (drafts[plugin.plugin_id].dirty) { <span class="muted unsaved">有未保存内容</span> }
+          <span class="muted unsaved">{{ saving() === plugin.plugin_id ? '正在保存…' : drafts[plugin.plugin_id].dirty ? '等待自动保存…' : '修改后自动保存' }}</span>
         </div>
       </fieldset>
+      <nav class="review-navigation" aria-label="切换评审任务">
+        <div class="navigation-buttons">
+          <button type="button" [disabled]="!navigation().previous || !!saving() || moving()" (click)="move('previous')"><span aria-hidden="true">‹</span>上一条</button>
+          <span class="review-position">{{ navigation().position }} / {{ navigation().total }}</span>
+          <button type="button" [disabled]="!navigation().next || !!saving() || moving()" (click)="move('next')">下一条<span aria-hidden="true">›</span></button>
+        </div>
+        <span class="muted">{{ navigation().scope === 'batch' ? '同批次已结束任务 · 按执行顺序' : '当前历史列表' }}</span>
+        @if (drafts[plugin.plugin_id].dirty) { <span class="muted">有待保存的修改，切换前会先保存。</span> }
+      </nav>
       @if (notice()) { <p class="notice" role="status">{{ notice() }}</p> }
       @if (plugin.history.length) {
         <details class="history"><summary>修改记录（{{ plugin.history.length }}）</summary>

apps/showcase_ui/src/app/components/task-extension-panels/task-extension-panels.component.scss

@@ -19,13 +19,19 @@ button:focus-visible, textarea:focus-visible { outline: 2px solid var(--app-prim
 .left-column { border-right: 1px solid var(--app-border, #e2e8f0); }
 .right-column { border-left: 1px solid var(--app-border, #e2e8f0); }
 section + section { border-top: 1px solid var(--app-border, #e2e8f0); padding-top: 12px; margin-top: 12px; }
-header { display: flex; justify-content: space-between; align-items: center; gap: 8px; margin-bottom: 20px; }
+header { display: flex; justify-content: space-between; align-items: flex-start; gap: 8px; margin-bottom: 14px; overflow-wrap: anywhere; }
 h3 { margin: 0; font-size: 14px; color: var(--app-text-strong, #0f172a); }
-.panel-kind { font-size: 11px; color: var(--app-text-muted, #64748b); }
+.panel-kind { flex-shrink: 0; font-size: 11px; color: var(--app-text-muted, #64748b); }
+.case-section { margin: 18px 0; }
+.case-section h4 { margin: 0 0 8px; font-size: 13px; color: var(--app-text-strong, #0f172a); }
+.review-navigation { margin: 12px 0 0; padding: 12px 0 0; background: var(--app-surface, #fff); border-top: 1px solid var(--app-border, #e2e8f0); }
+.navigation-buttons { display: flex; align-items: center; justify-content: space-between; gap: 4px; margin-bottom: 4px; }
+.navigation-buttons button { white-space: nowrap; }
+.review-position { font-size: 11px; color: var(--app-text-muted, #64748b); white-space: nowrap; }
 .muted { display: block; font-size: 12px; color: var(--app-text-secondary, #64748b); line-height: 1.6; }
 fieldset { border: 0; margin: 0; padding: 0; min-width: 0; }
 .field { display: grid; gap: 8px; margin: 0 0 14px; }
-.choice-field:not(:first-child) { border-top: 1px solid var(--app-border, #e2e8f0); padding-top: 22px; margin-top: 22px; }
+.choice-field:not(:first-child) { border-top: 1px solid var(--app-border, #e2e8f0); padding-top: 14px; margin-top: 14px; }
 .field-label { font-size: 13px; font-weight: 600; }
 .note-field .field-label { font-size: 11px; font-weight: 400; color: var(--app-text-muted, #64748b); }
 .choice-group { display: flex; flex-wrap: wrap; gap: 4px; padding: 4px; margin-top: 4px; border: 1px solid var(--app-border, #e2e8f0); border-radius: 10px; background: var(--app-surface-soft, #f8fafc); }
@@ -36,7 +42,7 @@ fieldset { border: 0; margin: 0; padding: 0; min-width: 0; }
 .choice-button.selected { border-color: var(--app-primary-border, #93c5fd); background: var(--app-primary-soft, #eff6ff); color: var(--app-primary-text, #1a73e8); font-weight: 600; }
 .choice-button.pass.selected { border-color: var(--app-success-border, #a7f3d0); background: var(--app-success-soft, #ecfdf5); color: var(--app-success-text, #047857); }
 .choice-button.failed.selected { border-color: var(--app-error-border, #fecdd3); background: var(--app-error-soft, #fff1f2); color: var(--app-error-text, #be123c); }
-textarea { box-sizing: border-box; width: 100%; min-width: 0; padding: 10px 12px; font: inherit; font-size: 12px; line-height: 1.6; color: inherit; border: 1px solid var(--app-border, #e2e8f0); border-radius: 8px; background: var(--app-surface-soft, #f8fafc); resize: vertical; min-height: 66px; max-height: 200px; }
+textarea { box-sizing: border-box; width: 100%; min-width: 0; padding: 6px 10px; font: inherit; font-size: 12px; line-height: 1.6; color: inherit; border: 1px solid var(--app-border, #e2e8f0); border-radius: 8px; background: var(--app-surface-soft, #f8fafc); resize: vertical; min-height: 34px; max-height: 200px; }
 textarea::placeholder { color: var(--app-text-muted, #94a3b8); }
 .form-actions { display: grid; grid-template-columns: auto auto; justify-content: start; align-items: center; gap: 8px; margin-top: 22px; padding-top: 18px; border-top: 1px solid var(--app-border, #e2e8f0); }
 .form-actions button { height: 36px; padding: 0 16px; white-space: nowrap; }

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

@@ -1,4 +1,4 @@
-import { TestBed, ComponentFixture } from '@angular/core/testing';
+import { TestBed, ComponentFixture, fakeAsync, flushMicrotasks, tick } from '@angular/core/testing';
 import { provideHttpClient } from '@angular/common/http';
 import { HttpTestingController, provideHttpClientTesting } from '@angular/common/http/testing';
 import { TaskExtensionPanelsComponent } from './task-extension-panels.component';
@@ -50,7 +50,7 @@ describe('步骤回放工作区扩展', () => {
     fixture.detectChanges();
   }
 
-  it('does not request extensions in video mode and shows no controls without a plugin', () => {
+  it('does not request disabled extensions and shows no controls without a plugin', () => {
     fixture.componentRef.setInput('sessionId', 'task-one');
     fixture.detectChanges();
     http.expectNone('/api/task-extensions/task-one');
@@ -87,87 +87,92 @@ describe('步骤回放工作区扩展', () => {
     }
   });
 
-  it('allows partial manual selection and keeps unfilled outcomes blank', () => {
+  it('automatically saves choices and clears while keeping unfilled outcomes blank', fakeAsync(() => {
     open(); toggle('right');
-    expect(fixture.nativeElement.querySelector('select')).toBeNull();
-    const groups: NodeListOf<HTMLElement> = fixture.nativeElement.querySelectorAll('.choice-group');
-    expect(fixture.nativeElement.querySelector('[aria-pressed="true"]')).toBeNull();
-    const pass = groups[0].querySelector<HTMLButtonElement>('.pass')!;
-    const failed = groups[0].querySelector<HTMLButtonElement>('.failed')!;
+    const pass: HTMLButtonElement = fixture.nativeElement.querySelector('.choice-button.pass');
     pass.click(); fixture.detectChanges();
-    expect(pass.getAttribute('aria-pressed')).toBe('true');
-    pass.click(); fixture.detectChanges();
-    expect(component.drafts['review'].values['accuracy']).toBe('');
-    failed.click(); pass.click(); fixture.detectChanges();
-    expect(failed.getAttribute('aria-pressed')).toBe('false');
-    expect(groups[1].querySelector('[aria-pressed="true"]')).toBeNull();
-    const note: HTMLTextAreaElement = fixture.nativeElement.querySelector('textarea');
-    note.value = '人工核对'; note.dispatchEvent(new Event('input'));
-    fixture.detectChanges();
-    fixture.nativeElement.querySelector('button.save').click();
-    const request = http.expectOne('/api/task-extensions/task-one/review');
+    expect(saved().values).toEqual({ accuracy: 'Pass', note: '', correctness: '' });
+    pass.click(); fixture.detectChanges(); expect(saved(2).values.accuracy).toBe('');
+    expect(fixture.nativeElement.textContent).toContain('人工评审已自动保存');
+  }));
+
+  function saved(revision = 1, id = 'task-one') {
+    const request = http.expectOne(`/api/task-extensions/${id}/review`);
     expect(request.request.method).toBe('PUT');
-    expect(request.request.body.values).toEqual({ accuracy: 'Pass', note: '人工核对', correctness: '' });
-    expect(request.request.body.expected_revision).toBe(0);
-    const data = snapshot(); data.plugins[0].revision = 1; data.plugins[0].values = request.request.body.values;
-    request.flush(data); fixture.detectChanges();
-    expect(fixture.nativeElement.textContent).toContain('人工评审已保存');
-  });
+    const body = request.request.body, data = snapshot(id);
+    data.plugins[0].revision = revision; data.plugins[0].values = body.values;
+    request.flush(data); flushMicrotasks(); fixture.detectChanges(); return body;
+  }
 
-  it('preserves draft and request receipt after a failed save, and permits clearing a result', () => {
-    open(); toggle('right');
-    const plugin = component.data()!.plugins[0];
-    component.edit('review', 'accuracy', 'Failed'); component.save(plugin);
-    const first = http.expectOne('/api/task-extensions/task-one/review');
-    const requestId = first.request.body.request_id;
-    first.flush({}, { status: 503, statusText: 'Unavailable' });
-    component.save(plugin);
-    const retry = http.expectOne('/api/task-extensions/task-one/review');
-    expect(retry.request.body.request_id).toBe(requestId);
-    retry.flush({}, { status: 409, statusText: 'Conflict' });
+  it('debounces notes and never posts just from opening a task', fakeAsync(() => {
+    open(); toggle('right'); tick(700); http.expectNone('/api/task-extensions/task-one/review');
+    component.edit('review', 'note', '第一段'); tick(400);
+    component.edit('review', 'note', '完整备注'); tick(599);
+    http.expectNone('/api/task-extensions/task-one/review'); tick(1);
+    expect(saved().values.note).toBe('完整备注');
+  }));
+
+  it('does not overwrite an automatic save with an older read response', fakeAsync(() => {
+    open(); component.edit('review', 'note', '已保存的新内容'); tick(600); saved(2);
+    component.refresh(); fixture.detectChanges();
+    http.expectOne('/api/task-extensions/task-one').flush(snapshot()); fixture.detectChanges();
+    expect(component.drafts['review'].values['note']).toBe('已保存的新内容');
+    expect(component.drafts['review'].revision).toBe(2);
+  }));
+
+  it('flushes a pending note when the review panel is closed', fakeAsync(() => {
+    open(); component.edit('review', 'note', '关闭前保存'); fixture.destroy();
+    const request = http.expectOne('/api/task-extensions/task-one/review');
+    expect(request.request.body.values.note).toBe('关闭前保存');
+    const response = snapshot(); response.plugins[0].revision = 1; response.plugins[0].values = request.request.body.values;
+    request.flush(response); flushMicrotasks();
+  }));
+
+  it('preserves draft and request receipt on failure, and retries only when requested', fakeAsync(() => {
+    open(); toggle('right'); const plugin = component.data()!.plugins[0];
+    component.edit('review', 'accuracy', 'Failed'); void component.save(plugin);
+    const first = http.expectOne('/api/task-extensions/task-one/review'), requestId = first.request.body.request_id;
+    first.flush({}, { status: 503, statusText: 'Unavailable' }); flushMicrotasks(); tick(700);
+    http.expectNone('/api/task-extensions/task-one/review'); void component.save(plugin);
+    const retry = http.expectOne('/api/task-extensions/task-one/review'); expect(retry.request.body.request_id).toBe(requestId);
+    retry.flush({}, { status: 409, statusText: 'Conflict' }); flushMicrotasks();
     expect(component.drafts['review'].values['accuracy']).toBe('Failed');
-    component.edit('review', 'accuracy', ''); component.save(plugin);
-    const clear = http.expectOne('/api/task-extensions/task-one/review');
-    expect(clear.request.body.values.accuracy).toBe('');
-    expect(clear.request.body.request_id).not.toBe(requestId);
-    clear.flush(snapshot());
-  });
+    component.edit('review', 'accuracy', ''); void component.save(plugin);
+    const clear = saved(); expect(clear.values.accuracy).toBe(''); expect(clear.request_id).not.toBe(requestId);
+  }));
 
-  it('renders Chinese outcomes as mutually exclusive buttons and saves their declared values', () => {
-    const data = snapshot(); data.plugins[0].workspace.fields[0].options = ['通过', '失败'];
-    open(data); toggle('right');
+  it('serializes rapid edits and saves the latest choice using the returned revision', fakeAsync(() => {
+    const data = snapshot(); data.plugins[0].workspace.fields[0].options = ['通过', '失败']; open(data); toggle('right');
     const pass: HTMLButtonElement = fixture.nativeElement.querySelector('.choice-button.pass');
     const failed: HTMLButtonElement = fixture.nativeElement.querySelector('.choice-button.failed');
-    expect(pass.textContent).toContain('通过'); expect(failed.textContent).toContain('失败');
     pass.click(); failed.click(); fixture.detectChanges();
-    expect(component.drafts['review'].values['accuracy']).toBe('失败');
-    expect(pass.getAttribute('aria-pressed')).toBe('false');
-    expect(failed.getAttribute('aria-pressed')).toBe('true');
-  });
+    expect(component.drafts['review'].values['accuracy']).toBe('失败'); expect(saved().values.accuracy).toBe('通过');
+    const second = saved(2); expect(second.values.accuracy).toBe('失败'); expect(second.expected_revision).toBe(1);
+    expect(component.drafts['review'].dirty).toBeFalse();
+  }));
 
-  it('does not apply a delayed save response to the task now displayed', () => {
-    open(); toggle('right');
-    component.edit('review', 'note', '只属于第一个任务'); component.save(component.data()!.plugins[0]);
+  it('does not apply a delayed save response to the task now displayed', fakeAsync(() => {
+    open(); toggle('right'); component.edit('review', 'note', '只属于第一个任务'); void component.save(component.data()!.plugins[0]);
     const oldSave = http.expectOne('/api/task-extensions/task-one/review');
     fixture.componentRef.setInput('sessionId', 'task-two'); fixture.detectChanges();
     http.expectOne('/api/task-extensions/task-two').flush(snapshot('task-two')); fixture.detectChanges();
-    oldSave.flush(snapshot('task-one')); fixture.detectChanges();
-    expect(component.data()!.session_id).toBe('task-two');
-    expect(component.drafts['review'].values['note']).toBe('');
-  });
+    oldSave.flush(snapshot('task-one')); flushMicrotasks(); fixture.detectChanges();
+    expect(component.data()!.session_id).toBe('task-two'); expect(component.drafts['review'].values['note']).toBe('');
+  }));
 
-  it('keeps unsaved drafts across task switches and removes panels on plugin disable', () => {
-    open(); toggle('right'); component.edit('review', 'note', '保留草稿');
+  it('flushes a pending note on direct task switches and hides disabled plugins', fakeAsync(() => {
+    open(); toggle('right'); component.edit('review', 'note', '自动保存草稿');
     fixture.componentRef.setInput('sessionId', 'task-two'); fixture.detectChanges();
     http.expectOne('/api/task-extensions/task-two').flush(snapshot('task-two'));
+    const body = saved(1, 'task-one'); expect(body.values.note).toBe('自动保存草稿');
     fixture.componentRef.setInput('sessionId', 'task-one'); fixture.detectChanges();
-    http.expectOne('/api/task-extensions/task-one').flush(snapshot()); fixture.detectChanges();
-    expect(component.drafts['review'].values['note']).toBe('保留草稿');
+    const first = snapshot(); first.plugins[0].revision = 1; first.plugins[0].values = body.values;
+    http.expectOne('/api/task-extensions/task-one').flush(first); fixture.detectChanges();
+    expect(component.drafts['review'].values['note']).toBe('自动保存草稿');
     window.dispatchEvent(new Event('artemis-plugin-change')); fixture.detectChanges();
-    http.expectOne('/api/task-extensions/task-one').flush({ ...snapshot(), plugins: [] }); fixture.detectChanges();
-    expect(fixture.nativeElement.querySelector('nav')).toBeNull();
+    http.expectOne('/api/task-extensions/task-one').flush({ ...first, plugins: [] }); fixture.detectChanges();
     expect(fixture.nativeElement.querySelector('aside')).toBeNull();
-  });
+  }));
 
   it('keeps running tasks read-only then enables editing when the task finishes', () => {
     open({ ...snapshot(), editable: false }); toggle('right');
@@ -187,4 +192,30 @@ describe('步骤回放工作区扩展', () => {
       expect(component.panels('right').length).toBe(1);
     } finally { Object.defineProperty(window, 'innerWidth', original); }
   });
+
+  it('shows original case sections in order without substituting the AI prompt', () => {
+    const data = snapshot();
+    data.plugins[0].workspace.panels[0].kind = 'original_case';
+    data.case_title = 'CASE-001 检查设置';
+    data.original_case = { preconditions: '已登录', steps: '1. 打开设置\n2. 核对版本', expected: '版本可见' };
+    open(data); toggle('left');
+    const text = fixture.nativeElement.textContent;
+    expect(text).toContain('CASE-001 检查设置');
+    expect(text).toMatch(/预置条件[\s\S]*已登录[\s\S]*操作步骤[\s\S]*核对版本[\s\S]*预期结果[\s\S]*版本可见/);
+    expect(text).not.toContain('原始需求');
+  });
+
+  it('saves before navigation and keeps the current task on save failure', fakeAsync(() => {
+    const first = snapshot(); first.navigation = { scope: 'batch', position: 1, total: 2, previous: null, next: 'task-two' };
+    open(first); toggle('right'); const emitted = jasmine.createSpy('navigate'); component.navigate.subscribe(emitted);
+    const saveButton = fixture.nativeElement.querySelector('button.save'), navigation = fixture.nativeElement.querySelector('.review-navigation');
+    expect(saveButton.compareDocumentPosition(navigation) & Node.DOCUMENT_POSITION_FOLLOWING).toBeTruthy();
+    component.edit('review', 'note', '切换前保存'); void component.move('next'); expect(emitted).not.toHaveBeenCalled();
+    http.expectOne('/api/task-extensions/task-one/review').flush({}, {status: 409, statusText: 'Conflict'});
+    flushMicrotasks(); expect(emitted).not.toHaveBeenCalled(); expect(component.drafts['review'].dirty).toBeTrue();
+    void component.move('next'); saved(); flushMicrotasks(); expect(emitted).toHaveBeenCalledOnceWith('task-two');
+    fixture.componentRef.setInput('sessionId', 'task-two'); fixture.detectChanges();
+    http.expectOne('/api/task-extensions/task-two').flush(snapshot('task-two')); fixture.detectChanges();
+    expect(component.panels('right').length).toBe(1);
+  }));
 });

apps/showcase_ui/src/app/components/task-extension-panels/task-extension-panels.component.ts

@@ -1,6 +1,7 @@
-import { Component, ChangeDetectionStrategy, HostListener, TemplateRef, effect, inject, input, output, signal, viewChild } from '@angular/core';
+import { Component, ChangeDetectionStrategy, HostListener, TemplateRef, DestroyRef, computed, effect, inject, input, output, signal, viewChild } from '@angular/core';
 import { DatePipe, NgTemplateOutlet } from '@angular/common';
 import { FormsModule } from '@angular/forms';
+import { firstValueFrom } from 'rxjs';
 import { ReportMarkdownComponent } from '../report-markdown/report-markdown.component';
 import { ExtensionDraft, ExtensionPanel, TaskExtension, TaskExtensions, TaskExtensionsService } from '../../services/task-extensions.service';
 
@@ -16,11 +17,25 @@ export class TaskExtensionPanelsComponent {
   sessionId = input<string | null>(null);
   enabled = input(false);
   taskStatus = input('');
+  sessionIds = input<string[]>([]);
+  navigate = output<string>();
+  navigation = computed(() => {
+    if (this.data()?.navigation) return this.data()!.navigation!;
+    const ids = this.sessionIds(), index = ids.indexOf(this.sessionId() || '');
+    return { scope: 'history', position: index + 1, total: ids.length,
+      previous: index > 0 ? ids[index - 1] : null,
+      next: index >= 0 && index < ids.length - 1 ? ids[index + 1] : null };
+  });
   expandedWidth = output<number>();
   headerControls = viewChild<TemplateRef<unknown>>('headerControls');
   data = signal<TaskExtensions | null>(null);
   error = signal('');
-  saving = signal<string | null>(null);
+  private destroyRef = inject(DestroyRef);
+  private savingKeys = signal<string[]>([]);
+  saving = computed(() => this.savingKeys().find(key => key.startsWith(`${this.sessionId()}/`))?.split('/')[1] || null);
+  moving = signal(false);
+  private scheduled = new Map<string, { timer: ReturnType<typeof setTimeout>; run: () => Promise<boolean> }>();
+  private inFlight = new Map<string, Promise<boolean>>();
   notice = signal('');
   opened = signal<Record<string, boolean>>({});
   private refreshToken = signal(0);
@@ -29,6 +44,7 @@ export class TaskExtensionPanelsComponent {
   drafts: Record<string, ExtensionDraft> = {};
 
   constructor() {
+    this.destroyRef.onDestroy(() => this.flushScheduled());
     effect(onCleanup => {
       const id = this.sessionId();
       const enabled = this.enabled();
@@ -37,14 +53,14 @@ export class TaskExtensionPanelsComponent {
       this.generation++;
       const identity = enabled ? id || '' : '';
       if (identity !== this.identity) {
+        this.flushScheduled();
         this.identity = identity;
         this.data.set(null);
-        this.opened.set({});
+        if (!identity) this.opened.set({});
         this.expandedWidth.emit(0);
       }
       this.error.set('');
       this.notice.set('');
-      this.saving.set(null);
       if (!id || !enabled) return;
       const subscription = this.service.read(id).subscribe({
         next: data => {
@@ -61,6 +77,27 @@ export class TaskExtensionPanelsComponent {
   @HostListener('window:artemis-plugin-change')
   refresh(): void { this.refreshToken.update(value => value + 1); }
 
+  async move(direction: 'previous' | 'next'): Promise<void> {
+    const destination = this.navigation()[direction], id = this.sessionId();
+    if (!destination || !id || !this.data() || this.moving()) return;
+    this.moving.set(true);
+    try {
+      for (const plugin of this.data()!.plugins) {
+        if (this.drafts[plugin.plugin_id]?.dirty && !await this.save(plugin)) return;
+      }
+      if (id === this.sessionId() && !this.destroyRef.destroyed) this.navigate.emit(destination);
+    } finally { this.moving.set(false); }
+  }
+
+  private cancelScheduled(key: string): void {
+    const pending = this.scheduled.get(key);
+    if (pending) clearTimeout(pending.timer);
+    this.scheduled.delete(key);
+  }
+  private flushScheduled(): void {
+    for (const pending of [...this.scheduled.values()]) void pending.run();
+  }
+
   key(plugin: TaskExtension, panel: ExtensionPanel): string { return `${plugin.plugin_id}/${panel.id}`; }
   panels(side: 'left' | 'right') {
     return (this.data()?.plugins || []).flatMap(plugin => plugin.workspace.panels
@@ -94,41 +131,71 @@ export class TaskExtensionPanelsComponent {
     }
   }
   edit(pluginId: string, field: string, value: string): void {
-    const draft = this.drafts[pluginId];
+    const id = this.sessionId(), draft = this.drafts[pluginId];
+    if (!id || !draft || !this.data()?.editable || draft.values[field] === value) return;
     draft.values[field] = value;
     draft.dirty = true;
     draft.requestId = undefined;
     this.notice.set('');
+    const key = `${id}/${pluginId}`;
+    this.cancelScheduled(key);
+    const run = () => this.saveFor(id, pluginId, draft);
+    this.scheduled.set(key, { run, timer: setTimeout(() => void run(), 600) });
   }
   choose(pluginId: string, field: string, value: string): void {
     this.edit(pluginId, field, this.drafts[pluginId].values[field] === value ? '' : value);
+    const plugin = this.data()?.plugins.find(item => item.plugin_id === pluginId);
+    if (plugin) void this.save(plugin);
   }
   reload(plugin: TaskExtension): void {
     const id = this.sessionId();
     if (!id) return;
+    this.cancelScheduled(`${id}/${plugin.plugin_id}`);
     this.service.discard(id, plugin.plugin_id);
     this.refresh();
   }
-  save(plugin: TaskExtension): void {
+  save(plugin: TaskExtension): Promise<boolean> {
     const id = this.sessionId();
-    if (!id || !this.data()?.editable || this.saving()) return;
-    this.saving.set(plugin.plugin_id);
-    const generation = this.generation;
-    this.notice.set('');
-    this.service.save(id, plugin.plugin_id, this.drafts[plugin.plugin_id]).subscribe({
-      next: data => {
-        this.service.discard(id, plugin.plugin_id);
-        if (id !== this.sessionId() || generation !== this.generation) return;
-        for (const item of data.plugins) this.drafts[item.plugin_id] = this.service.draft(id, item);
+    if (!id || !this.data()?.editable) return Promise.resolve(false);
+    return this.saveFor(id, plugin.plugin_id, this.drafts[plugin.plugin_id]);
+  }
+
+  private async saveFor(id: string, pluginId: string, draft: ExtensionDraft): Promise<boolean> {
+    const key = `${id}/${pluginId}`;
+    this.cancelScheduled(key);
+    const pending = this.inFlight.get(key);
+    if (pending) {
+      if (!await pending) return false;
+      return draft.dirty ? this.saveFor(id, pluginId, draft) : true;
+    }
+    if (!draft.dirty) return true;
+    const submitted = { ...draft.values }, generation = this.generation;
+    const visible = () => !this.destroyRef.destroyed && id === this.sessionId() && generation === this.generation;
+    this.savingKeys.update(keys => [...keys, key]);
+    const request = firstValueFrom(this.service.save(id, pluginId, draft)).then(data => {
+      const saved = data.plugins.find(plugin => plugin.plugin_id === pluginId);
+      if (!saved) throw new Error('未收到保存回执');
+      draft.revision = saved.revision;
+      draft.dirty = JSON.stringify(draft.values) !== JSON.stringify(submitted);
+      draft.requestId = undefined;
+      if (!draft.dirty) draft.values = { ...saved.values };
+      if (visible()) {
         this.data.set(data);
-        this.saving.set(null);
-        this.notice.set('人工评审已保存，下次导出将包含最新内容');
-      },
-      error: error => {
-        if (id !== this.sessionId() || generation !== this.generation) return;
-        this.saving.set(null);
-        this.notice.set(typeof error.error?.detail === 'string' ? error.error.detail : '保存失败，已保留输入，请重试');
+        this.notice.set(draft.dirty ? '正在保存后续修改…' : '人工评审已自动保存');
       }
+      return true;
+    }).catch(error => {
+      this.cancelScheduled(key);
+      if (visible()) this.notice.set(typeof error.error?.detail === 'string'
+        ? `保存失败：${error.error.detail}；输入已保留`
+        : '保存失败，输入已保留，请点击保存评审重试');
+      return false;
+    }).finally(() => {
+      this.inFlight.delete(key);
+      this.savingKeys.update(keys => keys.filter(item => item !== key));
     });
+    this.inFlight.set(key, request);
+    const succeeded = await request;
+    return succeeded && draft.dirty ? this.saveFor(id, pluginId, draft) : succeeded;
   }
 }

apps/showcase_ui/src/app/services/task-extensions.service.ts

@@ -6,7 +6,7 @@ export interface ExtensionField {
   options: string[]; max_length: number; report: boolean;
 }
 export interface ExtensionPanel {
-  id: string; title: string; side: 'left' | 'right'; kind: 'initial_prompt' | 'form';
+  id: string; title: string; side: 'left' | 'right'; kind: 'initial_prompt' | 'original_case' | 'form';
   width: { preferred: number; minimum: number; maximum: number };
 }
 export interface TaskExtension {
@@ -17,6 +17,9 @@ export interface TaskExtension {
 }
 export interface TaskExtensions {
   session_id: string; initial_prompt: string; editable: boolean; plugins: TaskExtension[];
+  case_title?: string;
+  original_case?: { preconditions: string; steps: string; expected: string } | null;
+  navigation?: { scope: 'batch'; position: number; total: number; previous: string | null; next: string | null } | null;
 }
 export interface ExtensionDraft {
   values: Record<string, string>; revision: number; dirty: boolean; requestId?: string;
@@ -32,7 +35,7 @@ export class TaskExtensionsService {
   draft(sessionId: string, plugin: TaskExtension): ExtensionDraft {
     const key = `${sessionId}/${plugin.plugin_id}`;
     let draft = this.drafts.get(key);
-    if (!draft?.dirty) {
+    if (!draft || (!draft.dirty && plugin.revision >= draft.revision)) {
       draft = { values: { ...plugin.values }, revision: plugin.revision, dirty: false };
       this.drafts.set(key, draft);
     }

artemis/agents/flash/runner.py

@@ -96,6 +96,7 @@ from artemis.services.llm import (
     get_openai_llm,
     get_llm,
     invoke_llm_with_timeout_message,
+    with_fallback,
 )
 from artemis.tools.history import history_tool_declarations
 from artemis.tools.android_files import android_file
@@ -780,7 +781,7 @@ class FlashRunner:
             action_dict["normalized_start_coordinates"] = norm_start
             action_dict["normalized_end_coordinates"] = norm_end
         action_dict.update(metadata.get("target_semantics") or {})
-        for key in ("input_verification", "execution", "side_effect"):
+        for key in ("input_verification", "execution", "side_effect", "source"):
             if key in metadata:
                 action_dict[key] = metadata[key]
         if metadata.get("plugin_id"):
@@ -1506,20 +1507,32 @@ class FlashRunner:
             turn_base = len(messages) - 1
             current_tools = report_only_tools if is_final else self._get_tools()
 
+            async def invoke_turn():
+                if using_tool_fallback:
+                    return await self._invoke_model(fallback_llm, current_tools, messages)
+
+                async def invoke_fallback():
+                    nonlocal fallback_llm
+                    if fallback_llm is None:
+                        fallback_llm = get_llm(self.ctx, name="operator", use_fallback=True)
+                    return await self._invoke_model(fallback_llm, current_tools, messages)
+
+                return await with_fallback(
+                    lambda: self._invoke_model(llm, current_tools, messages),
+                    invoke_fallback,
+                    none_should_fallback=False,
+                )
+
             if isinstance(control, TaskControl):
                 interrupted, response = await control.run_interruptibly(
-                    self._invoke_model(
-                        fallback_llm if using_tool_fallback else llm, current_tools, messages
-                    ),
+                    invoke_turn(),
                     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(
-                        fallback_llm if using_tool_fallback else llm, current_tools, messages
-                    ),
+                    await invoke_turn(),
                 )
 
             if interrupted or (

artemis/agents/flash/summarizer.py

@@ -412,6 +412,7 @@ class VisualStepSummarizer(StepMemoryService):
             engine,
             response,
             source=f"lens:visual_transition:{self._model_name}",
+            model=self._model_name,
             update_last_prompt=False,
         )
 

artemis/agents/operator/operator.py

@@ -35,7 +35,7 @@ from artemis.mcp.action_specs import OPERATOR_SHELL_ORDER, operator_shell_tool
 from artemis.llm.usage import usage_from_message
 from artemis.llm.structured import content_to_text
 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.services.llm import acomplete, get_llm, invoke_llm_with_timeout_message, with_fallback
 from artemis.tools.command_tool import (
     analyze_task_output_wrapper,
     get_adb_task_registry,
@@ -638,9 +638,19 @@ class OperatorNode:
                     and t.name not in {"plugin_load", "plugin_read_file", "plugin_read_result"}
                 ]
                 traced_tools.extend(plugins.langchain_tools())
-            bound_llm = active_llm.bind_tools(tools=traced_tools)
+
+            async def invoke(model):
+                bound = model.bind_tools(tools=traced_tools)
+                return await invoke_llm_with_timeout_message(acomplete(bound, current_messages))
+
             interrupted, response = await self._await_or_pause(
-                invoke_llm_with_timeout_message(acomplete(bound_llm, current_messages))
+                invoke(active_llm)
+                if using_tool_fallback
+                else with_fallback(
+                    lambda: invoke(base_llm),
+                    lambda: invoke(get_llm(ctx=self.ctx, name="operator", use_fallback=True)),
+                    none_should_fallback=False,
+                )
             )
             if interrupted:
                 return None, None, None, False

artemis/agents/planner/planner.py

@@ -303,8 +303,19 @@ class PlannerNode:
             screen = await UnifiedMobileController(self.ctx).get_screen_data()
             human_message_content.append({"type": "text", "text": screen.observation_text})
         plugins = getattr(self.ctx, "plugins", None)
-        if plugins:
-            human_message_content.append({"type": "text", "text": plugins.prompt()})
+        plugin_catalog = plugins.prompt() if plugins else ""
+        if plugin_catalog:
+            human_message_content.append(
+                {
+                    "type": "text",
+                    "text": "规划与执行的工具分工：规划器只使用本阶段绑定的笔记工具制定计划；"
+                    "下列插件清单描述执行器获授权的能力。执行器可以调用 plugin_load 加载插件。"
+                    "规划器当前工具列表里没有 plugin_load 或设备动作，不表示执行器缺少这些能力。"
+                    "将需要的插件、待观察的目标和验收条件写入计划，由执行器根据实际加载与操作回执"
+                    "确认可用性；未取得回执时保留待确认，不预先记录为插件不可用或要求用户补授权。",
+                }
+            )
+            human_message_content.append({"type": "text", "text": plugin_catalog})
         if screenshot_b64:
             human_message_content.append(
                 {

artemis/agents/validator/action_execution.py

@@ -92,6 +92,11 @@ async def exec_action(
         return False, str(e)
 
     try:
+        from artemis.data_engine.evidence_sources import android_action_source
+
+        source = android_action_source(getattr(getattr(ctx, "device", None), "device_id", None))
+        if source:
+            action_item["source"] = source
         res = await session.call(tool_name, wire_args)
     except Exception as e:
         action_item.update(execution="unknown", side_effect="possible")

artemis/config/settings.py

@@ -87,7 +87,7 @@ class Settings(BaseSettings):
     """Centralized ARTEMIS runtime settings loaded from environment and .env files."""
 
     ARTEMIS_PLUGIN_MARKETPLACE_URL: str = (
-        "https://git.playones.com/chenmingxuan/Artemis-Plugins/raw/branch/main/catalog-v3.json"
+        "https://git.playones.com/chenmingxuan/Artemis-Plugins/raw/branch/main/catalog-v4.json"
     )
     ARTEMIS_PLUGIN_START_TIMEOUT_SECONDS: float = Field(default=30, gt=0, le=300)
     ARTEMIS_PLUGIN_TOOL_TIMEOUT_SECONDS: float = Field(default=60, gt=0, le=3600)
@@ -109,6 +109,8 @@ class Settings(BaseSettings):
     OPENAI_BASE_URL: str | None = "https://api-n-cd.playones.com/v1"
     OPENAI_MODEL: str = Field(default=DEFAULT_MODEL, min_length=1)
     OPENAI_TIMEOUT_SECONDS: float = Field(default=300.0, gt=0)
+    # Environment only; deliberately absent from the saved UI/task configuration.
+    OPENAI_USE_SYSTEM_PROXY: bool = False
     OPENAI_MAX_RETRIES: int = Field(default=5, ge=0, le=10)
     OPENAI_RETRY_INTERVAL_SECONDS: float = Field(default=10.0, ge=0, le=300)
     OPENAI_RATE_LIMIT_RETRY_SECONDS: float = Field(default=60.0, ge=0, le=3600)

artemis/data_engine/evidence_sources.py

@@ -8,6 +8,58 @@ import json
 SOURCE_KINDS = {"android", "computer", "terminal", "api", "file", "other"}
 
 
+def android_action_source(device_id: object) -> dict | None:
+    """Stamp a native action at dispatch, using its actual selected device."""
+    if not isinstance(device_id, str) or not device_id or device_id == "computer:local":
+        return None
+    return {"kind": "android", "target_id": device_id, "label": "安卓屏幕"}
+
+
+def _android_screenshot_records(step: dict) -> list[dict]:
+    """Project explicit capture receipts; never infer provenance from tool args."""
+    records = []
+    seen = set()
+    for tool in step.get("generic_tools") or []:
+        if not isinstance(tool, dict) or (
+            tool.get("type"),
+            tool.get("name"),
+            tool.get("status"),
+        ) != ("tool", "android_file", "success"):
+            continue
+        payload = tool.get("payload")
+        receipt = payload.get("result") if isinstance(payload, dict) else None
+        if not isinstance(receipt, dict) or (
+            receipt.get("ok") is not True
+            or receipt.get("verified") is not True
+            or receipt.get("action") != "screenshot"
+        ):
+            continue
+        serial, path, digest = (
+            receipt.get("device_serial"),
+            receipt.get("trace_path"),
+            receipt.get("sha256"),
+        )
+        if not all(isinstance(value, str) and value for value in (serial, path, digest)):
+            continue
+        captured_at = receipt.get("captured_at")
+        captured_at = captured_at if isinstance(captured_at, str) else None
+        key = (serial, path, digest, captured_at)
+        if key in seen:
+            # Nested tool decorators can record the same completed capture twice.
+            continue
+        seen.add(key)
+        records.append(
+            {
+                "source": {"kind": "android", "target_id": serial, "label": "安卓屏幕"},
+                "trace_id": tool.get("trace_id"),
+                "artifact_path": path,
+                "sha256": digest,
+                "captured_at": captured_at,
+            }
+        )
+    return records
+
+
 def _step_reference(step: dict) -> dict:
     value = step.get("step_id")
     return {
@@ -16,6 +68,19 @@ def _step_reference(step: dict) -> dict:
     }
 
 
+def _represented_capture(action: dict, captures: list[dict]) -> bool:
+    if action.get("action") != "android_file":
+        return False
+    args = action.get("args") or {}
+    if not isinstance(args, dict) or args.get("action") != "screenshot":
+        return False
+    filename = args.get("filename")
+    return any(
+        capture["artifact_path"].replace("\\", "/").rsplit("/", 1)[-1] == filename
+        for capture in captures
+    )
+
+
 def recorded_sources(steps: list[dict], *, limit: int = 100) -> dict:
     sources = {}
     unattributed = []
@@ -23,7 +88,23 @@ def recorded_sources(steps: list[dict], *, limit: int = 100) -> dict:
         result = step.get("last_execution_result")
         execution = result.get("execution") if isinstance(result, dict) else None
         records = execution if isinstance(execution, list) else step.get("action_taken")
-        records = records if isinstance(records, list) else [records]
+        records = records if isinstance(records, list) else [records] if records else []
+        captures = _android_screenshot_records(step)
+        records = [
+            record
+            for record in records
+            if not isinstance(record, dict)
+            or (
+                record.get("action")
+                not in {"save_note", "read_note", "list_notes", "report_task_status"}
+                and not _represented_capture(record, captures)
+            )
+        ]
+        records = [*records, *captures]
+        if not records:
+            # A planning or completion turn with no recorded action is not a
+            # missing action source. Screenshots alone do not supply provenance.
+            continue
         found = False
         missing = False
         for record in records:
@@ -39,6 +120,7 @@ def recorded_sources(steps: list[dict], *, limit: int = 100) -> dict:
                 continue
             found = True
             plugin = str(record.get("plugin_id") or "")[:100]
+            label = str(source.get("label") or "")[:500]
             key = (plugin, kind, target[:256])
             if key not in sources:
                 sources[key] = {
@@ -46,18 +128,30 @@ def recorded_sources(steps: list[dict], *, limit: int = 100) -> dict:
                     "kind": kind,
                     "plugin_id": plugin,
                     "target_id": target[:256],
-                    "label": str(source.get("label") or "")[:500],
+                    "label": label,
                     "category": "interface" if kind in {"android", "computer"} else "auxiliary",
                     "references": [],
                     "reference_count": 0,
                 }
             reference = _step_reference(step)
-            for field in ("call_id", "source_id"):
+            for field in (
+                "call_id",
+                "source_id",
+                "trace_id",
+                "artifact_path",
+                "sha256",
+                "captured_at",
+            ):
                 if isinstance(record.get(field), str) and record[field]:
-                    reference[field] = record[field][:256]
+                    reference[field] = record[field][: 2048 if field == "artifact_path" else 256]
             if isinstance(record.get("read_only"), bool):
                 reference["read_only"] = record["read_only"]
             entry = sources[key]
+            if not entry.get("label_varies") and entry["label"] != label:
+                # The same window can navigate between tabs/pages. Its first
+                # title is not a valid label for all later evidence.
+                entry["label"] = ""
+                entry["label_varies"] = True
             entry["reference_count"] += 1
             if len(entry["references"]) < 8:
                 entry["references"].append(reference)

artemis/interfaces/cli/commands/run.py

@@ -164,6 +164,7 @@ async def execute_task(
         config.with_graph_config_callbacks(graph_config_callbacks)
 
     agent: Agent | None = None
+    task_started = False
     try:
         agent = Agent(config=config.build(), session_id=effective_sid)
         await agent.init(
@@ -196,7 +197,14 @@ async def execute_task(
             request.plugins = plugins
         elif plugin_choices is not None:
             request.plugins = TypeAdapter(list[PluginSelection]).validate_json(plugin_choices)
+        task_started = True
         await agent.run_task(request=request)
+    except Exception as exc:
+        if not task_started and effective_sid:
+            from artemis.runtime.task_result import save_failure_result
+
+            save_failure_result(str(effective_sid), str(exc), code="initialization_failed")
+        raise
     finally:
         if agent is not None:
             await agent.clean()

artemis/llm/argument_fingerprint.py

@@ -0,0 +1,53 @@
+"""Bounded fingerprints of received argument deltas, without retaining text."""
+
+import hashlib
+
+
+PREFIX_BYTES = 4096
+MAX_PREFIXES = 16
+MAX_TRACKED_TOOLS = 64
+
+
+class ArgumentFingerprint:
+    def __init__(self):
+        self.characters = 0
+        self.bytes = 0
+        self.deltas = 0
+        self.encoding_valid = True
+        self.digest = hashlib.sha256()
+        self.prefixes: list[dict] = []
+
+    def observe(self, arguments: str) -> None:
+        self.characters += len(arguments)
+        if not arguments:
+            return
+        self.deltas += 1
+        if not self.encoding_valid:
+            return
+        try:
+            encoded = arguments.encode("utf-8")
+        except UnicodeEncodeError:
+            # Diagnostics must not repair, reject or otherwise alter the stream.
+            self.encoding_valid = False
+            return
+        offset = 0
+        while offset < len(encoded) and len(self.prefixes) < MAX_PREFIXES:
+            size = min(PREFIX_BYTES - self.bytes % PREFIX_BYTES, len(encoded) - offset)
+            self.digest.update(encoded[offset : offset + size])
+            self.bytes += size
+            offset += size
+            if self.bytes % PREFIX_BYTES == 0:
+                self.prefixes.append({"bytes": self.bytes, "sha256": self.digest.hexdigest()})
+        if offset < len(encoded):
+            self.digest.update(encoded[offset:])
+            self.bytes += len(encoded) - offset
+
+    def snapshot(self) -> dict:
+        return {
+            "argument_chars": self.characters,
+            "argument_bytes": self.bytes if self.encoding_valid else None,
+            "argument_sha256": self.digest.hexdigest() if self.encoding_valid else None,
+            "argument_deltas": self.deltas,
+            "argument_prefixes": [dict(prefix) for prefix in self.prefixes],
+            "argument_encoding_valid": self.encoding_valid,
+        }

artemis/llm/diagnostics.py

@@ -13,6 +13,7 @@ from uuid import uuid4
 from PIL import Image
 
 from artemis.data_engine.context_vars import CURRENT_NODE_NAME, CURRENT_TRACE_ID
+from artemis.llm.argument_fingerprint import ArgumentFingerprint, MAX_TRACKED_TOOLS
 from artemis.llm.final_review import ACTIVE_FINAL_REVIEW, FinalReviewBudgetExceeded
 from artemis.llm.reliability import LLMExhaustedError
 from artemis.llm.usage import usage_from_message
@@ -107,6 +108,7 @@ class RequestAttempt:
         self.clock = time.monotonic()
         self.last_publish = self.clock
         self.tools: dict[int | str, dict] = {}
+        self.tool_fingerprints: dict[int | str, ArgumentFingerprint] = {}
         self.review = ACTIVE_FINAL_REVIEW.get()
         if self.review:
             self.review.request_started(request_id, attempt)
@@ -126,6 +128,9 @@ class RequestAttempt:
             "usage": None,
             "output_chunks": 0,
             "tool_argument_chars": 0,
+            "tool_observation_layer": "langchain_tool_call_chunks",
+            "argument_fingerprint_version": 1,
+            "tool_stats_truncated": False,
             "tools": [],
             "step_id": str(self.step_id) if self.step_id else None,
             "parent_trace_id": str(self.parent_id) if self.parent_id else None,
@@ -167,9 +172,10 @@ class RequestAttempt:
         self.data.update(
             headers_at=time.time(),
             http_status=response.status_code,
-            server_request_id=_identifier(
-                response.headers.get("x-request-id") or response.headers.get("request-id")
-            ),
+            server_request_id=_identifier(response.headers.get("x-oneapi-request-id"))
+            or _identifier(response.headers.get("x-request-id"))
+            or _identifier(response.headers.get("request-id")),
+            response_x_request_id=_identifier(response.headers.get("x-request-id")),
             server_trace_id=_identifier(response.headers.get("x-trace-id")),
             phase="waiting_output",
         )
@@ -196,18 +202,31 @@ class RequestAttempt:
             self.data["usage"] = usage
         tool_chunks = getattr(chunk, "tool_call_chunks", None) or []
         # Responses exposes the same argument delta in content and tool_call_chunks.
-        # Count only the latter; retain lengths/names, never argument bodies.
+        # Count only the latter; retain bounded fingerprints, never argument bodies.
         for tool in tool_chunks:
+            arguments = tool.get("args")
+            if isinstance(arguments, str):
+                self.data["tool_argument_chars"] += len(arguments)
             index = tool.get("index")
-            key = index if index is not None else tool.get("id") or "unknown"
-            stats = self.tools.setdefault(key, {"name": None, "argument_chars": 0})
+            call_id = _identifier(tool.get("id"))
+            key = index if index is not None else call_id or "unknown"
+            if key not in self.tools and len(self.tools) >= MAX_TRACKED_TOOLS:
+                self.data["tool_stats_truncated"] = True
+                continue
+            stats = self.tools.setdefault(key, {"name": None})
+            if call_id:
+                stats["call_id"] = call_id
+            if index is not None:
+                stats["chunk_index"] = index
             name = tool.get("name")
             if isinstance(name, str) and re.fullmatch(r"[\w.:-]{1,128}", name):
                 stats["name"] = name
-            arguments = tool.get("args")
+            fingerprint = self.tool_fingerprints.get(key)
+            if fingerprint is None:
+                fingerprint = self.tool_fingerprints[key] = ArgumentFingerprint()
             if isinstance(arguments, str):
-                stats["argument_chars"] += len(arguments)
-                self.data["tool_argument_chars"] += len(arguments)
+                fingerprint.observe(arguments)
+            stats.update(fingerprint.snapshot())
         self.data["tools"] = list(self.tools.values())
         content = getattr(chunk, "content", None)
         substantive = isinstance(content, str) and bool(content)
@@ -252,6 +271,8 @@ class RequestAttempt:
             if isinstance(status, int):
                 self.data["http_status"] = status
             if request_id := _identifier(getattr(error, "request_id", None)):
+                self.data["error_request_id"] = request_id
+                if not self.data.get("server_request_id"):
                     self.data["server_request_id"] = request_id
             if category == "timeout":
                 self.data.setdefault("timeout_scope", "transport")
@@ -301,6 +322,7 @@ async def observe_request_headers(request):
     if attempt is None:
         return
     request.headers.setdefault("X-Client-Request-Id", attempt.data["request_id"])
+    request.headers.setdefault("X-Client-Attempt-Id", attempt.data["attempt_id"])
     routing = {}
     for name in ("thread-id", "thread_id", "session-id", "session_id"):
         value = request.headers.get(name)
@@ -309,9 +331,12 @@ async def observe_request_headers(request):
     attempt.data.update(
         request_sent_at=time.time(),
         client_request_id=_identifier(request.headers.get("X-Client-Request-Id")),
+        client_attempt_id=_identifier(request.headers.get("X-Client-Attempt-Id")),
         routing_header_fingerprints=routing,
         client_request_id_matches=request.headers.get("X-Client-Request-Id")
         == attempt.data["request_id"],
+        client_attempt_id_matches=request.headers.get("X-Client-Attempt-Id")
+        == attempt.data["attempt_id"],
     )
     attempt.publish()
 

artemis/llm/http.py

@@ -0,0 +1,15 @@
+"""Environment-only network policy shared by model calls and credential checks."""
+
+from typing import Any
+
+import httpx
+
+from artemis.config.settings import settings
+
+
+def model_http_options() -> dict[str, Any]:
+    return {
+        "trust_env": settings.OPENAI_USE_SYSTEM_PROXY,
+        # Proxy opt-out must not disable configured CA certificates or TLS checks.
+        "verify": httpx.create_ssl_context(trust_env=True),
+    }

artemis/llm/reliability.py

@@ -30,6 +30,7 @@ from __future__ import annotations
 from dataclasses import dataclass
 from enum import StrEnum
 import random
+import re
 from functools import lru_cache
 import threading
 import time
@@ -124,6 +125,11 @@ def classify_failure(error: BaseException) -> Failure:
         # Programmer/request errors: retrying is useless and falling back only
         # hides the bug inside a different model's output.
         return Failure(FailureCategory.BAD_REQUEST, False, False)
+    # langchain-openai 1.7 raises this ValueError for a response.failed event
+    # without provider error details, before our completion guard sees it.
+    # Preserve the bounded invalid-output retry policy for these failed streams.
+    if isinstance(error, ValueError) and re.fullmatch(r"Response \S+ failed\.", str(error)):
+        return Failure(FailureCategory.INVALID_OUTPUT, True, True)
     return Failure(FailureCategory.UNKNOWN, True, True)
 
 
@@ -147,7 +153,7 @@ class LLMPermanentError(LLMCallError):
 
 
 class LLMExhaustedError(LLMCallError):
-    """Retryable failures exhausted every attempt and the pause deadline."""
+    """Retryable failures exhausted attempts and any applicable pause deadline."""
 
 
 # ---------------------------------------------------------------------------

artemis/llm/router.py

@@ -62,6 +62,7 @@ class ModelEndpoint(BaseModel):
             self.reasoning_effort,
             self.enable_grounding,
             self.api_base or settings.OPENAI_BASE_URL,
+            settings.OPENAI_USE_SYSTEM_PROXY,
             hashlib.sha256(key.encode()).hexdigest(),
         )
 
@@ -87,9 +88,10 @@ class ModelFactory:
             )
 
         from langchain_openai import ChatOpenAI
-        from openai import DefaultAsyncHttpxClient
+        from openai import DefaultAsyncHttpxClient, DefaultHttpxClient
 
         from artemis.llm.diagnostics import observe_request_headers, observe_response_headers
+        from artemis.llm.http import model_http_options
 
         api_key = endpoint.api_key or (
             settings.OPENAI_API_KEY.get_secret_value() if settings.OPENAI_API_KEY else None
@@ -112,8 +114,14 @@ class ModelFactory:
             "use_responses_api": True,
             "output_version": "responses/v1",
             "store": False,
+            # The explicit clients own proxy policy, including the synchronous path.
+            "openai_proxy": "",
+            "http_client": DefaultHttpxClient(
+                timeout=endpoint.timeout_seconds, **model_http_options()
+            ),
             "http_async_client": DefaultAsyncHttpxClient(
                 timeout=endpoint.timeout_seconds,
+                **model_http_options(),
                 event_hooks={
                     "request": [observe_request_headers],
                     "response": [observe_response_headers],

artemis/llm/stream_guard.py

@@ -23,7 +23,7 @@ class ToolArgumentOverflow(ValueError):
             "limit_chars": SMALL_ACTION_ARGUMENT_LIMIT,
         }
         super().__init__(
-            f"模型生成的 {name} 参数异常膨胀（{characters} 字符，"
+            f"收到的 {name} 参数流超出安全限制（{characters} 字符，"
             f"保护上限 {SMALL_ACTION_ARGUMENT_LIMIT}）；已关闭输出流，未执行本次动作。"
         )
 

artemis/mcp/action_executor.py

@@ -280,6 +280,11 @@ class McpActionExecutor:
     ) -> ToolExecutionResult:
         span = TraceSpan(name=raw_name, trace_type="action", ctx=self.ctx)
         span.payload = {"args": args}
+        from artemis.data_engine.evidence_sources import android_action_source
+
+        source = android_action_source(
+            getattr(getattr(self.ctx, "device", None), "device_id", None)
+        )
 
         message = ""
         res: ActionResult | None = None
@@ -291,6 +296,7 @@ class McpActionExecutor:
         observation_settled: bool | None = None
         input_verification: str | None = None
         expected_input: str | None = None
+        dispatched = False
         with span:
             try:
                 session = await self._session_or_start()
@@ -315,6 +321,7 @@ class McpActionExecutor:
                         or observation_anchor(state, index_elements)
                     )
                 extension = raw_name not in (REQUIRED_ACTIONS | OPTIONAL_ACTIONS)
+                dispatched = True
                 if extension:
                     raw_result = await session.call_raw(wire_name, wire_args)
                     message = next(
@@ -386,6 +393,7 @@ class McpActionExecutor:
                 "post_image_name": post_image_name,
                 "has_xml": bool(xml_list),
                 "status": status,
+                **({"source": source} if source and dispatched else {}),
             }
             if status == "error":
                 span.status = "failed"
@@ -400,6 +408,7 @@ class McpActionExecutor:
             screenshot_path=shot_path,
             ui_elements_text=xml_list,
             metadata={
+                **({"source": source} if source and dispatched else {}),
                 "code": res.code.value,
                 "normalized_coordinates": res.normalized_coordinates,
                 "target_semantics": target_semantics,

artemis/memory/chunking.py

@@ -532,6 +532,7 @@ class StepCapsuleLens(StepLens):
                     engine,
                     response,
                     source=f"lens:step_capsule:{model_label}",
+                    model=model_label if model_label != "fallback" else None,
                     update_last_prompt=False,
                 )
         except Exception as exc:

artemis/plugins/installer.py

@@ -44,10 +44,11 @@ def download(url: str, progress: Callable[[str, int], None]) -> bytes:
 
 def load_catalog() -> PluginCatalog:
     url = settings.ARTEMIS_PLUGIN_MARKETPLACE_URL
-    # Older hosts reject schema-v3 entries before checking version constraints.
-    # Keep their index intact, and route only the exact former official URL.
-    if url == "https://git.playones.com/chenmingxuan/Artemis-Plugins/raw/branch/main/catalog.json":
-        url = url.removesuffix("catalog.json") + "catalog-v3.json"
+    # Strict older hosts cannot parse newer panel kinds, even if incompatible.
+    # Preserve their indexes; upgrade only the exact official saved addresses.
+    official = "https://git.playones.com/chenmingxuan/Artemis-Plugins/raw/branch/main/"
+    if url in {official + "catalog.json", official + "catalog-v3.json"}:
+        url = official + "catalog-v4.json"
     data = download(url, lambda *_: None)
     if len(data) > 2 * 1024 * 1024:
         raise ValueError("市场索引过大")

artemis/plugins/workspace.py

@@ -47,7 +47,7 @@ class WorkspacePanel(WorkspaceModel):
     id: str = Field(pattern=r"^[a-z][a-z0-9_]{0,47}$")
     title: str = Field(min_length=1, max_length=100)
     side: Literal["left", "right"]
-    kind: Literal["initial_prompt", "form"]
+    kind: Literal["initial_prompt", "original_case", "form"]
     width: PanelWidth = Field(default_factory=PanelWidth)
 
 

artemis/runtime/awake_service.py

@@ -101,7 +101,10 @@ def _configure_usb_stay_awake(device_id: str) -> str | None:
     # Migration cleanup belongs to the long-lived host. A queued task worker
     # must not wait on another process's optional legacy wake-lock cleanup.
     if os.environ.get("ARTEMIS_TASK_WORKER") != "1":
+        try:
             ScreenAwakeLease(device_id).cleanup_unowned_references()
+        except OSError as exc:
+            logger.warning(f"Could not prepare optional legacy awake cleanup on {device_id}: {exc}")
 
     commands = (
         (
@@ -209,6 +212,7 @@ class ScreenAwakeService:
         self._monitor_thread: threading.Thread | None = None
         self._shutdown_requested = False
         self._owners: dict[str, FileLock] = {}
+        self._ownership_warnings: set[str] = set()
 
     def start(self, device_ids: Iterable[str] | None = None) -> dict[str, str | None]:
         if self._shutdown_requested:
@@ -241,13 +245,24 @@ class ScreenAwakeService:
             existing = self._strategies.get(device_id)
             if existing is not None:
                 return existing
-            owner = _owner_lock(device_id)
             try:
+                owner = _owner_lock(device_id)
                 owner.acquire(timeout=0)
             except Timeout:
                 # Do not cache a follower as owner: discovery can take over if
                 # the process holding the OS lock exits or releases the device.
                 return None
+            except OSError as exc:
+                # Awake is optional. Never bypass ownership or let an ACL / I/O
+                # failure abort device connection, resume, or the host monitor.
+                if device_id not in self._ownership_warnings:
+                    logger.warning(
+                        f"Could not acquire awake ownership on {device_id}; skipping optional "
+                        f"stay-awake policy: {exc}"
+                    )
+                    self._ownership_warnings.add(device_id)
+                return None
+            self._ownership_warnings.discard(device_id)
             try:
                 strategy = _configure_usb_stay_awake(device_id)
             except BaseException:

artemis/runtime/helper_manager.py

@@ -77,6 +77,8 @@ from typing import Any
 import urllib.error
 import urllib.request
 
+from filelock import FileLock
+
 from artemis.config.constants import ENV_ARTEMIS_HELPER_AUTO_INSTALL
 from artemis.config.paths import get_temp_dir
 from artemis.runtime.adb_endpoint import adb_command
@@ -323,7 +325,7 @@ class AccessibilityHelperManager:
             if re.fullmatch(r"[0-9a-f]{32,128}", text):
                 self._token = text
                 return text
-        except OSError:
+        except FileNotFoundError:
             pass
         token = secrets.token_hex(24)
         try:
@@ -550,6 +552,15 @@ class AccessibilityHelperManager:
         root.mkdir(parents=True, exist_ok=True)
         digest = hashlib.sha256(serial.encode("utf-8")).hexdigest()[:16]
         path = root / f"{digest}.mutex"
+        # An age-based lease alone can be stolen from a live, delayed owner.
+        # Retain the legacy lease for coexistence with older Artemis processes,
+        # but serialize current processes with a kernel lock released on exit.
+        with FileLock(path.with_suffix(".guard"), timeout=_PROVISION_MUTEX_TIMEOUT_SECONDS):
+            with self._legacy_provision_mutex(path, serial):
+                yield
+
+    @contextmanager
+    def _legacy_provision_mutex(self, path: Path, serial: str):
         started = time.monotonic()
         while True:
             try:

artemis/sdk/agent.py

@@ -209,7 +209,10 @@ class Agent:
             raise ValueError("任务目标必须是 android、computer 或 mixed")
         self._execution_target = execution_target
         if execution_target == "computer":
+            from artemis.platform import platform as pal_platform
+
             self._device_context = DeviceContext(
+                host_platform=pal_platform.os_type.name,
                 device_id="computer:local",
                 mobile_platform=DevicePlatform.COMPUTER,
                 device_width=0,
@@ -584,6 +587,7 @@ class Agent:
                 or getattr(getattr(task, "request", None), "task_name", None)
             )
             device_lock = None
+            execution_started = False
             try:
                 # Construct the runtime only inside the task's cleanup boundary. A
                 # cancelled queue wait or setup failure must not leave version pins.
@@ -761,6 +765,7 @@ class Agent:
                     publish_startup_progress(
                         "environment_ready", "Device environment is ready", session_id=str(sess_id)
                     )
+                    execution_started = True
                     try:
                         if request.profile and request.profile.lower() == "flash":
                             logger.info(f"[{task_name}] Invoking FlashRunner reactive loop...")
@@ -792,7 +797,7 @@ class Agent:
 
                             status = flash_result.get("status")
                             if status == "completed":
-                                logger.info(f"✅ Automation '{task_name}' is success ✅")
+                                logger.info(f"Automation '{task_name}' execution completed.")
                                 await task.finalize(content=output, state=last_state_snapshot)
                                 if context.data_engine:
                                     context.data_engine.end_session("completed")
@@ -907,7 +912,7 @@ class Agent:
                                     " see the test summary."
                                 )
                             else:
-                                logger.info(f"✅ Automation '{task_name}' is success ✅")
+                                logger.info(f"Automation '{task_name}' execution completed.")
                             await task.finalize(content=output, state=last_state_snapshot)
                             if context.data_engine:
                                 context.data_engine.end_session("completed")
@@ -972,7 +977,11 @@ class Agent:
                 from artemis.runtime.task_result import save_failure_result
 
                 if sess_id:
-                    save_failure_result(str(sess_id), err)
+                    save_failure_result(
+                        str(sess_id),
+                        err,
+                        code="execution_failed" if execution_started else "initialization_failed",
+                    )
                 if context.data_engine:
                     context.data_engine.end_session("failed")
 
@@ -1681,13 +1690,15 @@ def attach_test_summary(output, run_outcome: dict | None):
 
 
 def resolve_trace_suffix(task_status: str, run_outcome: dict | None) -> str:
-    """Trace naming: assertion failures must be distinguishable from _PASS."""
+    """Keep execution and the independently verified test verdict distinct."""
     if task_status != "completed":
         return "_FAIL"
     tests = (run_outcome or {}).get("tests") or {}
-    if (
-        int(tests.get("failed", 0)) > 0
-        or ((run_outcome or {}).get("test_result") or {}).get("status") == "failed"
-    ):
+    verdict = ((run_outcome or {}).get("test_result") or {}).get("status")
+    if verdict == "blocked":
+        return "_BLOCKED"
+    if verdict == "inconclusive":
+        return "_UNVERIFIED"
+    if verdict == "failed" or int(tests.get("failed", 0)) > 0:
         return "_TESTFAIL"
-    return "_PASS"
+    return "_PASS" if verdict == "passed" else "_UNVERIFIED"

artemis/services/llm.py

@@ -317,12 +317,32 @@ async def _wait_for_resume(pause_file: Path) -> bool:
     """Wait for the pause file to be cleared. Returns False on deadline."""
     deadline = float(getattr(settings, "LLM_PAUSE_TIMEOUT_SECONDS", 0.0) or 0.0)
     waited = 0.0
+    try:
+        owned = pause_file.stat()
+    except FileNotFoundError:
+        return True
+    try:
         while pause_file.exists():
             if deadline > 0 and waited >= deadline:
                 return False
             await asyncio.sleep(1)
             waited += 1
         return True
+    finally:
+        # Cancellation (stop, guidance, outer deadline) also ends this wait.
+        # Do not leave a global pause behind or remove a newer request's pause.
+        try:
+            current = pause_file.stat()
+            if (current.st_ino, current.st_mtime_ns, current.st_size) == (
+                owned.st_ino,
+                owned.st_mtime_ns,
+                owned.st_size,
+            ):
+                pause_file.unlink(missing_ok=True)
+        except FileNotFoundError:
+            pass
+        except OSError as exc:
+            llm_logger.warning("Could not clear finished LLM pause: %s", exc)
 
 
 async def _wait_for_breaker(key: str) -> None:
@@ -361,7 +381,7 @@ async def _run_with_recovery[T](
       immediately: retrying cannot help and pausing would hang the task.
     - When retryable attempts are exhausted: if a fallback model is waiting
       (with_fallback), raise LLMExhaustedError so it takes over immediately;
-      final acceptance also raises instead of pausing an already-finished task.
+      final acceptance and invalid output also raise instead of globally pausing.
       Other calls pause (bounded by settings.LLM_PAUSE_TIMEOUT_SECONDS) and
       retry the same request on resume.
     """
@@ -450,7 +470,7 @@ async def _run_with_recovery[T](
                     )
                     if failure.category is FailureCategory.INVALID_OUTPUT:
                         # One fresh response can recover a generation loop. Repeated
-                        # runaway output must reach the existing fallback/pause path,
+                        # runaway output must reach fallback or fail this request,
                         # even when ordinary network retries are configured higher.
                         max_attempts = min(
                             max_attempts, total_attempts + max(0, policy.max_attempts - attempt)
@@ -485,7 +505,11 @@ async def _run_with_recovery[T](
                     ACTIVE_ATTEMPT.reset(observation_token)
 
             # Retryable attempts exhausted.
-            if _FALLBACK_AVAILABLE.get() or ACTIVE_FINAL_REVIEW.get() is not None:
+            if (
+                _FALLBACK_AVAILABLE.get()
+                or ACTIVE_FINAL_REVIEW.get() is not None
+                or last_failure.category is FailureCategory.INVALID_OUTPUT
+            ):
                 if failed_endpoints is not None and endpoint_key:
                     failed_endpoints[endpoint_key] = last_error
                 _record_llm_event(
@@ -494,7 +518,11 @@ async def _run_with_recovery[T](
                         "error": str(last_error)[:1000],
                         "category": last_failure.category.value,
                         "retryable": True,
-                        "handover": "fallback" if _FALLBACK_AVAILABLE.get() else "final_review_end",
+                        "handover": "fallback"
+                        if _FALLBACK_AVAILABLE.get()
+                        else "final_review_end"
+                        if ACTIVE_FINAL_REVIEW.get() is not None
+                        else "task_failed",
                     },
                     status="failed",
                 )
@@ -510,10 +538,6 @@ async def _run_with_recovery[T](
                 "LLM pause deadline"
                 f" ({settings.LLM_PAUSE_TIMEOUT_SECONDS:.0f}s) exceeded; giving up."
             )
-            try:
-                pause_file.unlink(missing_ok=True)
-            except OSError:
-                pass
             raise LLMExhaustedError(
                 str(last_error), failure=last_failure, cause=last_error
             ) from last_error
@@ -670,7 +694,12 @@ class RobustChatModelWrapper:
         engine = self.ctx.data_engine if self.ctx else None
         if engine is None:
             engine = _get_current_data_engine()
-        record_llm_usage(engine, response, source=self._endpoint_key())
+        record_llm_usage(
+            engine,
+            response,
+            source=self._endpoint_key(),
+            model=self.endpoint.model_name if self.endpoint else None,
+        )
 
     def _diagnostics(self, args, kwargs):
         prefix = None
@@ -1232,7 +1261,7 @@ async def _with_fallback[T](
         )
 
     # The contextvar must be reset BEFORE fallback_call runs: the fallback has
-    # no further fallback behind it, so its own exhaustion should pause.
+    # no further fallback behind it, so apply its category's terminal policy.
     fallback_token = _FALLBACK_AVAILABLE.set(True)
     try:
         result = await main_call()

artemis/services/token_meter.py

@@ -224,6 +224,7 @@ def record_llm_usage(
     response: Any,
     *,
     source: str | None = None,
+    model: str | None = None,
     update_last_prompt: bool = True,
 ) -> dict | None:
     """Meters one LLM response and records an ``llm_usage`` trace, best-effort.
@@ -251,6 +252,8 @@ def record_llm_usage(
         }
         if source:
             payload["source"] = source
+        if model:
+            payload["model"] = model
         node = CURRENT_NODE_NAME.get()
         if node:
             payload["node"] = str(node)

artemis/utils/credentials_validator.py

@@ -17,6 +17,7 @@
 import httpx
 
 from artemis.config.settings import settings
+from artemis.llm.http import model_http_options
 
 from artemis.utils.logger import get_logger
 
@@ -91,7 +92,8 @@ async def validate_api_key(
 
     try:
         async with httpx.AsyncClient(
-            timeout=timeout if timeout is not None else settings.ARTEMIS_CREDENTIAL_TIMEOUT_SECONDS
+            timeout=timeout if timeout is not None else settings.ARTEMIS_CREDENTIAL_TIMEOUT_SECONDS,
+            **(model_http_options() if clean_provider == "openai" else {}),
         ) as client:
             if clean_provider in ("ocr", "vision", "google_vision"):
                 # Test Google Cloud Vision OCR API

docs/automation-workspace.md

@@ -112,3 +112,5 @@ Flash 跨端任务由模型通过内部 `update_task_progress` 记录短阶段
 批次保留原顺序、循环次数和失败停止策略，默认保留各项配置，也可明确选择统一模型和思考强度。探索用例固定收藏版本，首次无复跑配置时默认 Flash；“收藏为重新探索”会创建新的探索会话并沿用原探索配置。
 
 单任务下载全部资料时，未变化的终态报告和资料包会复用；人工复验、结果和资料变化会重新生成。批次沿用已生成的报告包，人工复验后重新打包；旧目录格式的包首次下载时更新。运行中的下载是当前快照。录像分为“安卓”“电脑”“人工示范”目录，索引路径与实际文件一致。打包优先速度，对已压缩的图片、视频和 Office 文件直接存储，保持原画质。
+
+安装并启用任务人工评审 1.1.0 后，批量模板在原七列之后增加“预置条件、操作步骤、预期结果”。三列独立保存原始用例，不追加到 Artemis 提示词；左侧按用例编号和标题展示，右侧可用上一条/下一条评审同批次已结束任务。未启用该插件时仍提供并校验原七列模板。

docs/development-handoff.md

@@ -1,5 +1,11 @@
 # 开发交接：2026-10-19
 
+2026-10-28 发布主线整理为 **ARTEMIS 2.4.0**，配套人工评审插件 **1.1.0**。本轮改动、配置和验证边界见 [2.4.0 发行说明](releases/2.4.0.md)；下方记录为各阶段历史快照。
+
+2026-10-28 配套升级 OpenAI/LangChain 与安全依赖，审计范围、版本、验证及容器构建限制见[依赖安全更新记录](plans/2026-10-28-dependency-security.md)。
+
+2026-10-28 会话已接续至 **ARTEMIS 2.3.0**，最新提交、插件发布状态、产品约定和待验证范围见[本次交接记录](plans/2026-10-28-session-handoff.md)及[2.3.0 发行说明](releases/2.3.0.md)。以下各日期内容保留为历史快照，不代表当前待办。
+
 2026-10-27 发布主线已整理为 **ARTEMIS 2.2.0**，配套插件为 **Cua 0.38.0+artemis.1**，Helper 为 **1.2.3**。最新升级内容、验证与未测范围以[2.2.0 发行说明](releases/2.2.0.md)为准；下方“尚未发布”、分叉计数和候选版本均属于对应日期快照。插件从独立工作树发布，原插件主目录的 OCU 开发现场保留。
 
 2026-10-26 已再次接续开发会话，当前基线为主程序本地提交 `fac4ccb`（2.2.0）。两个仓库现场、已撤回机制与后续验收范围见[本次接续记录](plans/2026-10-26-session-handoff.md)。以下继续保留原始交接快照。

docs/llm-stream-diagnostics.md

@@ -0,0 +1,39 @@
+# 模型流式参数诊断
+
+小型内置动作的参数流仍受 16384 字符保护。超限时关闭输出流、丢弃不完整参数，不执行该次动作；一次新响应重试和可用备用端点耗尽后，只结束当前任务，不进入共享的模型暂停。批次仍遵循“失败即停止”、人工暂停和取消设置。网络故障、认证错误和最终验收保留各自的恢复规则。
+
+## 请求关联
+
+每个模型请求尝试沿用现有 `llm_diagnostic` 记录，不另建日志数据库。
+
+| 字段 / 请求头 | 含义 |
+| --- | --- |
+| `request_id` / `X-Client-Request-Id` | 同一次恢复循环内保持稳定的逻辑请求编号；切换备用调用或恢复暂停后可能建立新的逻辑请求 |
+| `attempt_id` / `X-Client-Attempt-Id` | 本次客户端尝试编号；重试时变化，`previous_attempt_id` 关联前次尝试 |
+| `client_*_id_matches` | 实际发送的请求头是否与本地编号一致；调用方已指定的头保留原值 |
+| `server_request_id` | 首个有效的 `X-Oneapi-Request-Id`、`X-Request-Id` 或 `Request-Id`，按此前后顺序选择 |
+| `response_x_request_id` | 响应中的原始 `X-Request-Id`，不推定它来自模型上游 |
+| `error_request_id` | SDK 异常带回的编号，不覆盖已经从响应头读取的编号 |
+| `response_id` | SDK 实际返回的 Responses 响应编号 |
+
+编号只接收有长度限制的可打印白名单字符。请求头不控制会话亲和性，不替换 `thread-id` / `session-id`。网关自身的重试应使用独立编号或序号，不能假装是一次新的客户端尝试。
+
+## 参数指纹 v1
+
+`tool_observation_layer=langchain_tool_call_chunks` 明确表示客户端观测的是 SDK 转换后的参数片段，不是原始 SSE 帧。每工具记录实际可得的 `call_id`、`chunk_index`、工具名，以及：
+
+- `argument_chars`：参数片段的 Unicode 字符数之和。
+- `argument_bytes` / `argument_sha256`：按原顺序连接片段后，其 UTF-8 字节长度和 SHA256；不解析、重排参数 JSON，也不规范化空白或 Unicode。
+- `argument_deltas`：非空参数片段数，不能直接与网关原始事件数比较。
+- `argument_prefixes`：每 4096 字节的累计 SHA256，最多保留前 16 个。可以在分片大小不同、上游预读或中途取消时比较相同字节位置。
+- `argument_encoding_valid`：遇到不能编码为 UTF-8 的片段时为 false，当前总字节数和总哈希留空，避免伪造可比结果；诊断本身不改变执行流程。
+
+最多记录 64 个工具；超过时设置 `tool_stats_truncated=true`，总参数字符计数仍继续。诊断不保留参数正文。哈希仅证明已收到的字节前缀，不能证明输出完整或动作成功；完整性仍由响应终止状态和解析校验决定。
+
+跨三端优先使用 `response_id + call_id` 关联。LangChain 的 `chunk_index` 可能因文本或推理子块不同于原始 `output_index`，缺失编号时不能按数组位置猜测。正常的 `arguments.done`、`output_item.done`、`response.completed` 快照不重复计入参数；自定义工具转换、非空初始参数或协议异常需要先核对 SDK 映射，不能仅凭跨层哈希不同认定某一端重复发送。
+
+历史日志没有保存的原始帧无法由新增诊断恢复。HTTP 200 只说明响应头已到达；客户端保护后出现的 499 或 Broken pipe 也不能证明最初原因。网关写入本机下游 writer 成功不等于客户端已消费或执行。
+
+## 离线验证
+
+`tests/unit/test_llm_stream_guard.py` 验证保护、有限重试、相同/不同备用端点，以及不会创建或清除其他请求的全局暂停。`tests/unit/test_request_diagnostics.py` 验证请求编号、超时重试、响应头及单次参数计数。`tests/unit/test_argument_fingerprint.py` 验证不同分片、中文和 emoji、固定字节前缀、有界统计与异常编码。这些测试不调用真实模型或设备。

docs/plans/2026-10-28-dependency-security.md

@@ -0,0 +1,87 @@
+# 2026-10-28 依赖安全更新与兼容性验证
+
+## 审计结果
+
+范围为主仓库声明的 Python、前端 npm、后台原型依赖及可识别的构建依赖。使用当日 PyPI/pip-audit、npm audit、OSV 和上游安全公告；没有忽略漏洞或降低检查级别。
+
+| 范围 | 更新前 | 更新后 |
+| --- | --- | --- |
+| `uv.lock` 中全部 169 个 registry 包，含开发依赖及非 Windows 平台包 | 11 个包命中，97 条公告记录 | 0 条，未跳过包 |
+| 前端 npm 锁文件 | 17 个受影响包：3 critical、11 high、3 moderate | 0 个受影响包 |
+| `playground/backend_manager/requirements.txt` 当日解析结果 | 54 个包，2 个包命中、3 条记录 | 52 个包，0 条，未跳过包 |
+| Python 构建工具的当日解析结果 | — | setuptools 84.2.1、Cython 3.3.0，0 条 |
+| Android Gradle Plugin 8.5.0 | — | OSV 直接包查询未检出公告；未解析完整 Gradle 构建工具传递依赖 |
+
+公告可能含重复 ID 或别名，97 条不代表 97 个独立 CVE；npm 受影响包数也包含依赖链上的父包。零结果仅表示本次数据库未检出已知漏洞，不代表没有未知风险或业务安全问题。
+
+远程 Python SDK 不含第三方运行时依赖；Android Helper 使用系统 API，不含第三方运行时库。独立 `Artemis-Plugins` 仓库、用户安装的插件、系统软件包和完整容器镜像不在上述零漏洞结论内。
+
+## 版本调整
+
+| 包 | 原版本 | 更新后 |
+| --- | --- | --- |
+| openai | 3.3.0 | 3.40.0，沿用同日 SDK 更新 |
+| langchain / langchain-core | 1.3.15 / 1.5.6 | 1.4.7 / 1.7.0 |
+| langchain-openai | 1.5.2 | 1.7.3 |
+| langgraph / langgraph-sdk | 1.2.11 / 0.4.2 | 1.2.18 / 0.4.10 |
+| httpx | 0.28.1 | 保持 0.28.1，当日最新版 |
+| httpx2 / httpcore2 | 2.12.0 | 2.16.0 |
+| mcp | 1.29.0 | 1.30.0 |
+| aiohttp | 3.14.3 | 3.14.5 |
+| certifi | 2026.7.22 | 2026.10.23 |
+| filelock | 3.32.3 | 4.2.4 |
+| multidict | 6.7.1 | 7.2.1 |
+| pillow | 12.3.0 | 13.0.0 |
+| pyjwt | 2.13.0 | 2.15.1 |
+| tornado | 6.5.8 | 6.6 |
+| urllib3 | 2.7.0 | 2.8.0 |
+| virtualenv | 21.7.4 | 21.15.1 |
+| Angular framework / compiler-cli | 22.1.4 | 22.2.3 |
+| Angular CLI / build | 22.1.6 | 22.2.4 |
+| Angular CDK | 22.1.5 | 22.2.4 |
+| Vite | 8.1.5 | 8.3.5 |
+| Piscina | 5.2.0 | 5.3.2 |
+| 原型 Nginx 基础镜像 | 1.27-alpine | 1.30.6-alpine |
+
+`langchain-community 0.4.2` 和 `langchain-mcp-adapters 0.3.2` 保持不变。后者要求 MCP `<2`，因此主项目声明 `mcp>=1.30.0,<2.0.0`，使用兼容的 1.x 安全修复版本。其余联动升级见 `uv.lock`。
+
+Angular build 22.2.4 仍精确依赖存在漏洞的 Vite 8.3.0，通过限定在 `@angular/build` 下的 npm override 使用 8.3.5，未使用 `--force` 或 `--legacy-peer-deps`。以后上游采用安全版本时可移除 override，重新审计并验证构建。
+
+后台原型的 `python-jose 3.5.0` 和间接 `ecdsa 0.19.2` 没有可用修复版，改为 `PyJWT[crypto]>=2.15.1,<3.0.0`，保持算法白名单与 HTTP 401 错误处理。原型仍按 requirements 动态解析；该扫描结果不是所有旧镜像或旧安装环境的审计证明。
+
+## 必要的适配
+
+- `langchain-openai 1.7.x` 对没有错误详情的 `response.failed` 抛出 `ValueError("Response <id> failed.")`。补充精确分类，保留 `INVALID_OUTPUT` 的有限重试；未把所有 ValueError 当成无效模型输出。
+- 补充失败流重试回归，验证不完整输出不会成为正式结论或工具动作，重试保留已有工具证据。
+- Responses 模拟传输改用 OpenAI 默认使用的 httpx2，并修正测试夹具中 `request` 同名遮蔽，确保超过 1 MiB 的中文工具参数确实经过分块 SSE/UTF-8 传输。
+- 原型 JWT 回归覆盖签发、声明、当前用户、过期、错误签名、算法不匹配、无签名、畸形 token 和缺失 subject。
+- MCP 的 audience 漏洞需要服务端配置配合，单纯升级不自动开启校验。本仓库没有配置 `AuthSettings`/`token_verifier`，当前不使用该 bearer-auth 路径；未来接入时必须同时设置 `validate_token_resource` 并提供正确的 token resource。
+
+## 验证
+
+- 隔离环境完整默认 Python 测试：3207 通过、6 跳过、8 排除；102 条现有 Pillow `getdata()` 弃用警告，该接口计划在 Pillow 14 移除。
+- 随后改用 httpx2 的模型流、失败分类和 JWT 专项测试：41 通过；同步原 `.venv` 后同一组 41 项再次通过。
+- Ruff 格式/静态检查、质量基线、核心 Pyright 类型检查通过；Pyright 额外显式使用了升级后的解释器。
+- 锁文件校验、升级环境 `uv pip check`、`git diff --check` 通过。
+- 前端 ChromeHeadless：336 通过；生产构建通过，生成产物不纳入提交。
+- 主 Python、原型 Python、Python 构建工具及前端更新后复扫无已知漏洞。
+- Nginx 1.30.6 为当日官方稳定修复版本，Docker Hub 标签存在且 active。已尝试构建原型镜像，但 Docker Hub registry/auth 连接超时，尚未完成容器构建和运行验证，也未扫描完整镜像内的 OS 包。
+- 未调用付费模型、执行设备业务测试、发布提交或修改用户任务配置。
+
+原始审计 JSON、解析清单和测试日志保存在本地被 Git 忽略的 `artifacts/dependency-audit-20261028/`。
+
+## 生效
+
+初次同步受到运行中服务占用 Pillow DLL 的阻止，已恢复旧环境并通过依赖一致性检查。用户随后明确表示已停止服务，原 `.venv` 已成功执行 `uv sync --dev --locked` 并再次通过版本核对与兼容性测试。
+
+随后通过 `artemis restart --no-open` 恢复后台服务；`/api/system/server-status` 返回 running，首页 HTTP 200 且引用本次新前端构建。原环境全部 165 个已安装 distribution 的版本均与锁文件匹配。
+
+本次沿用 ARTEMIS 2.3.0，按用户要求提交源码和锁文件，不发布。用户已明确无需构建 Docker，本次不再继续容器构建；修改 Dockerfile 不会更新已有容器。
+
+## 上游依据
+
+- [Pillow 13.0.0 安全修复](https://pillow.readthedocs.io/en/stable/releasenotes/13.0.0.html)
+- [MCP bearer token audience 公告](https://github.com/modelcontextprotocol/python-sdk/security/advisories/GHSA-w4fh-qvv9-3v23)
+- [Vite/launch-editor Windows 命令执行公告](https://github.com/advisories/GHSA-587h-7wmj-h5pm)
+- [Vite 8.3.5 发布说明](https://github.com/vitejs/vite/releases/tag/v8.3.5)
+- [Nginx 安全公告](https://nginx.org/en/security_advisories.html)及[当前稳定版本](https://nginx.org/en/download.html)

docs/plans/2026-10-28-openai-sdk-3.40.md

@@ -0,0 +1,35 @@
+# OpenAI Python SDK 3.40.0 适配
+
+本文保留 SDK 单独升级阶段的结果。同日后续的 LangChain、HTTPX2 与安全依赖升级，以及最终验证与生效状态，见[依赖安全更新记录](2026-10-28-dependency-security.md)。
+
+## 范围
+
+- `pyproject.toml` 显式声明 `openai>=3.40.0,<4.0.0`；项目直接使用 SDK 的 HTTP 客户端，不再仅依赖 `langchain-openai` 间接带入。
+- `uv.lock` 将 SDK 从 3.3.0 升至 3.40.0，保留既有 `langchain-openai 1.5.2`、`httpx2 2.12.0` 及其他包版本。锁文件记录发行包和 SHA-256。
+- 继续使用 Responses API、`store=False` 与 ARTEMIS 的重试预算；SDK `max_retries=0`，不叠加 SDK 重试。
+- 没有修改模型默认值、已有用户配置、设备调度或插件协议，主程序版本仍为 2.3.0。
+
+## 兼容性核对
+
+从 3.3.0 到 3.40.0 的更新涉及 SSE 解码、异步流关闭、传输异常归一化、重试验证、Responses 类型及缓存元数据。现有 Responses 调用与已锁定的 LangChain 适配层在专项回归中兼容，无需新增业务兼容分支。
+
+3.40.0 增加显式缓存断点 TTL 类型。此次只升级 SDK，不自动启用显式缓存断点或改变 TTL；以后接入产品配置时，需要同时处理服务端与模型支持、参数入口和用量展示，不能将 SDK 类型支持当作当前端点支持。
+
+新增回归覆盖超过 1 MiB 的中文工具参数，在 SSE 帧和 UTF-8 字符跨网络块时完整还原；即使参数完整，缺少 `response.completed` 仍拒绝输出正式结论。
+
+## 本次验证
+
+- 在 OpenAI SDK 3.40.0 下，模型调用专项回归 97 项通过；完整默认回归 3198 项通过、6 项跳过、8 项排除，保留 102 条已有 Pillow 弃用警告。
+- Ruff 格式与静态检查、质量基线、核心 Pyright 类型检查、`uv pip check`、`uv lock --check` 通过。
+- 本次未改前端，未运行前端测试或构建；未执行真实模型或设备业务验收。
+
+## 生效与边界
+
+开发环境已通过 `uv sync --dev --locked` 同步。已有长驻服务需正常重启后完整加载新 SDK，本次不主动重启。验证使用本地模拟传输，不调用付费模型或真实设备。
+
+## 来源
+
+- [OpenAI Python SDK 3.40.0 发布说明](https://github.com/openai/openai-python/releases/tag/v3.40.0)
+- [SDK 变更记录](https://github.com/openai/openai-python/blob/v3.40.0/CHANGELOG.md)
+- [官方 Python SDK 文档](https://developers.openai.com/api/reference/python)
+- [官方提示词缓存说明](https://developers.openai.com/api/docs/guides/prompt-caching)

docs/plans/2026-10-28-runtime-recovery.md

@@ -0,0 +1,33 @@
+# 2026-10-28 运行时故障与批次恢复修复
+
+## 已确认问题
+
+- awake 所属锁的目录创建和获取只处理正常争用，`PermissionError` 可从 UIAutomator、无障碍连接、设备恢复和主程序监控的共享入口传播。
+- 旧唤醒租约清理虽然处理了清理过程异常，构造时创建临时目录仍可能失败。
+- Flash、Pro/探索 Operator 的工具无进展恢复有备用模型，但模型生成异常未进入该入口。
+- 批次模型暂停与用户暂停未区分；模型等待超时后文件已清除，批次仍维持暂停。
+- 模型等待被取消时可能残留暂停文件；终态报告的通用失败说明可能遮蔽真实初始化/模型错误。
+
+## 修复范围
+
+- 保活权限/I/O 异常降级为警告。未取得所属锁时不执行保活动作；后续可重新获取，不缓存为成功。同一设备持续获取失败只警告一次，成功后重置。
+- 工作进程早期 Agent 准备及 SDK 运行时准备失败记录 `initialization_failed`。批次在报告导出前保存失败原因并暂停剩余项；导出失败不改变这一分类。
+- Flash 和 Operator 接入现有 `with_fallback`。取消、永久请求错误和同端点重试预算仍遵守统一网关规则，不修改用户模型配置，不放宽工具参数/完整响应保护。
+- 区分模型、初始化、用户、服务恢复暂停。模型恢复后按既定失败策略继续；停止全部任务覆盖自动恢复标记。重启后没有存活任务时仍要求人工继续。
+- 模型等待结束或被取消时清理本次暂停；文件已被新请求改写时保留。
+
+## 边界
+
+- 不删除或改 ACL，不更换锁目录绕过互斥。设备执行锁、主程序注册锁和队列 I/O 锁保留失败即阻止执行的行为。
+- 未重跑原批次、修改历史裁定或调用真实设备/付费模型；未构建 Docker。
+- 原 Windows 锁文件的 ACL、占用者及异常发生时依赖版本尚无本机证据；本修复处理应用传播和恢复缺口，不宣称证明了操作系统拒绝访问的具体来源。
+- 旧批次不自动迁移暂停原因，需用户显式继续；不会从历史零步骤数量推断并改写失败分类。
+
+## 验证
+
+针对性测试覆盖锁目录/文件权限拒绝后恢复、监控继续处理其他设备、旧保活清理、Flash/Operator 生成失败切换、暂停取消/超时、初始化错误保留与批次暂停、手动继续不重跑失败项、用户暂停与停止全部、服务重启恢复。
+
+- 默认测试：3225 通过、6 跳过、8 按默认标记排除。102 条既有 Pillow `getdata()` 弃用警告。
+- Ruff 格式检查与静态检查通过，质量基线通过，核心 Pyright 检查 0 错误、0 警告。
+- 第一轮完整测试暴露新增 CLI 测试的环境变量隔离遗漏，影响两项录像测试；修正测试隔离后第二轮完整测试全部通过，未为此改变产品行为或放宽断言。
+- 本次仅修改 Python 与文档，未运行前端构建、真实设备或付费模型测试。

docs/plans/2026-10-28-session-handoff.md

@@ -0,0 +1,47 @@
+# ARTEMIS 开发主线交接：2026-10-28
+
+本次依据用户提供的《ARTEMIS开发主线-1027》完整会话记录、仓库发行说明与本地 Git 状态接续开发。agentmemory 未返回匹配本项目目录的会话，因此不采用其他项目的记忆。此次未联网刷新远端、重跑测试、重启服务或操作设备；发布和实测结论来自上一会话记录，不能视为本次重新验证。
+
+## 当前基线
+
+| 范围 | 本次本地核对结果 |
+| --- | --- |
+| 主程序 | `main` 与本地 `eapil/main` 位于 `bb873ec`，版本 2.3.0；迁入前已跟踪文件无修改，只有未跟踪的 `.angular/` 缓存 |
+| 人工评审插件工作树 | 插件仓库 `.tmp/task-review-extension`，分离 HEAD `386f108`，工作树干净；`7bcdb2a` 增加插件，`386f108` 上架市场 |
+| Cua 工作树 | 插件仓库 `.tmp/cua-shell-observation`，分支 `codex/cua-shell-observation`，提交 `b780a60`，工作树干净 |
+| 插件原主目录 | `main` 位于 `757b829`，相对本地 `origin/main` 领先 4、落后 10；仍有 OCU、Cua 和测试脚本等既有修改与未跟踪文件，必须保留 |
+
+上一会话已完成 ARTEMIS 2.2.0、Cua `0.38.0+artemis.1`、ARTEMIS 2.3.0 和任务人工评审 1.0.0 的推送及发布；Cua 继续标注预览版。最后已核验远端提交、发行附件下载校验值，并完成线上市场隔离安装和启用验证。早期记录中的“2.2.0 尚未发布”“Cua 尚未提交”已经过时。
+
+## 已完成的开发与约定
+
+- 2.2.0 接入仅 PC 测试，网页、MCP、参数 JSON 和 Python SDK 使用 `execution_target="computer"`；PC、安卓和跨端任务统一全局串行。
+- 已修复安卓缩放截图的校验坐标、观测恢复预算、输入首次清空与空值确认、Helper 聚焦目标选择、Pro 收尾空转和重复计划、MCP 排队及运行状态、笔记截图路径和验收项展示标签匹配。Helper 升级至 1.2.3。动作卡片文字可复制，长 RESULT 默认折叠。
+- 模型选项增加 `gpt-6.1-terra`，新安装探索默认 `gpt-6.1-terra / high`；保存配置优先。
+- 2.3.0 提供 `schema_version: 3` 的声明式 `workspace` 插件接口。独立「任务人工评审」插件从市场安装启用，主程序不默认安装启用。
+- 回放标题栏控制左右侧栏，普通浮窗和影院模式均支持；单侧展开仍位于对应左右侧，窄屏一次展开一侧。
+- 左侧只展示本次运行最初提交的需求提示词，支持 Markdown，不混入模型拆解步骤或后续指导。
+- 右侧由人工填写「AI执行准确性」「测试结果正确性」，使用中文「通过 / 失败」，两项及备注均选填，可以修改或清空。结果正确性评价 ARTEMIS 判断是否准确，与业务用例是否通过区分。
+- 评审不调用 AI，不覆盖原执行结论或既有人工复验；运行中只读，结束后可编辑，保留修改历史，并防止并发覆盖和重复写入。
+- 评审绑定单次运行，复跑不继承；禁用或卸载保留数据但隐藏界面及新导出字段，重新安装启用后恢复，删除任务时清理。
+- 已启用插件的字段进入单任务 Word/Excel、批次汇总及资料包报告，空项留空。重新导出反映最新评审，已下载旧文件不变。
+- 插件 SDK、工作区接口文档及随程序分发的 Skill 已同步。2.3.0 使用 `catalog-v3.json`，旧 `catalog.json` 保持兼容 2.2.x；执行插件更新需兼顾两个索引，工作区插件只加入新版。
+- 已撤回的次数配额、内容指纹和 AI 二次动作否决不恢复；已移除的设备动作回放不恢复，历史步骤和截图回看保留。
+
+## 历史验证与仍待覆盖范围
+
+- 2.2.0 发布前记录：后端 3189 项、前端 326 项、SDK 24 项通过，构建及质量检查通过。集中回归 9/9 正式实测通过；后续对排队状态、截图路径、验收项标签另有修复和实测证据。
+- 2.3.0 发布前记录：后端默认回归 3197 项、插件针对性回归 49 项、前端 336 项通过，构建及静态检查通过；Windows 隔离示例验证主题、左右布局、中文评审保存与 Word/Excel 导出。该轮未执行真实设备业务或付费模型测试，macOS/Linux 未实测。
+- Cua 真实鼠标跟随问题按用户此前要求暂缓；原任务不足以证明具体误点根因，不能因驱动已发布就标为已解决。
+- 真实断线恢复、小时级稳定性、多显示器及多 DPI 等扩大兼容性场景仍缺完整验证。发布完成不等于这些场景全部通过。
+- 素材准备句柄、跨次任务取代关系仍只是产品候选，尚未立项。
+
+当前没有尚未完成的发布步骤或待回答的产品确认。本次仅迁移上下文；后续按用户新需求继续，修改前重新核对相关仓库和工作树，不自动恢复旧设备任务或重复发布。
+
+## 参考
+
+- [2.2.0 发行说明](../releases/2.2.0.md)
+- [2.3.0 发行说明](../releases/2.3.0.md)
+- [工作区插件接口](../workspace-plugins.md)
+- [插件开发 SDK](../plugin-development.md)
+- [上次会话接续记录](2026-10-26-session-handoff.md)

docs/releases/2.4.0.md

@@ -0,0 +1,44 @@
+# ARTEMIS 2.4.0
+
+> 全新安装的 npm 校验失败已在 [2.4.1](2.4.1.md) 修复，请使用补丁版源码包或通过更新脚本升级。
+
+本版改进批量用例人工评审与执行详情阅读，并包含 OpenAI SDK 适配、安全依赖更新、Windows 资源锁和报告证据修复。配套「任务人工评审」独立发布 **1.1.0**。
+
+## 人工评审与原始用例
+
+- 安装并启用人工评审 1.1.0 后，批量模板在原七列后增加「预置条件、操作步骤、预期结果」，仍接受七列旧模板。未启用插件时保持原有七列模板和校验；新增内容不进入 AI 提示词。
+- 左侧标题为用例编号与用例标题，下面依次展示三项原始内容；历史任务未保存的内容显示缺失，不用 AI 提示词替代。
+- 「AI执行准确性」改为「用例执行准确性」，保留字段 ID 和既有评审；备注框缩短，可自行拉高。
+- 「上一条／下一条」放在保存评审下方。同批次按已结束任务顺序切换，独立任务使用当前历史列表。
+- 选择结果立即保存，备注停止输入 600 毫秒后保存，切换前也先保存。失败时保留输入和当前用例，允许手动重试；连续修改不会被较早回执覆盖。打开任务不会自行填写或保存评审。
+- Flash、Pro、探索以及安卓、电脑、跨端任务均可显示面板，步骤与视频视图均支持。
+
+## 执行详情与报告
+
+- Payload、原始结果及超长、多行调试字段默认折叠；展开后限高滚动，全文可读，不截断保存的证据。
+- 修复正式验收通过但没有单独输出正文时出现「没有保存最终结论」的误导提示，报告按有效结论生成说明。
+- 安卓截图的真实保存回执进入结构化来源汇总，保留路径与哈希；窗口枚举没有单一目标时说明原因，不误报截图丢失。
+- 电脑任务记录真实宿主平台；来源窗口标题变化时提示查看原始步骤。结果目录区分通过、不通过、阻塞与未验证。
+- 历史模型和思考强度优先读取任务自身诊断，用量统计保留实际请求模型，减少历史条目被当前配置误标；修复步骤、队列与录屏收尾相关读取问题。
+
+## 模型、依赖与运行稳定性
+
+- OpenAI Python 更新为 3.40.0，配套 LangChain 1.4.7、langchain-core 1.7.0、langchain-openai 1.7.3；httpx 保持兼容的 0.28.1。Python 与前端安全依赖更新写入锁文件。
+- 新增仅环境配置 `OPENAI_USE_SYSTEM_PROXY=false`，模型请求默认不采用系统代理。需要代理时在 `.env` 设为 `true` 并重启；同步、异步请求和 OpenAI 连接检查一致，TLS 与自定义 CA 校验继续保留。
+- 修复 Windows 临时目录 awake 锁访问失败及所有权恢复，检查同类资源锁和运行时收尾。持久权限错误仍保留实际原因，不跳过互斥保护。
+- Helper 初始化增加操作系统互斥锁，防止仍在执行的操作仅因锁文件超龄而被抢占；已有宿主令牌无法读取时保留原文件和错误，不生成另一份令牌覆盖它。
+- 规划器明确区分规划阶段与执行器的插件能力，避免因本阶段没有动作工具而误判插件不可用；批次模型失败保留明确诊断。
+
+2.4.0 使用独立的 `catalog-v4.json` 市场索引；保留 2.3.x 与 2.2.x 的旧索引，防止旧宿主因新面板类型无法解析而导致市场加载失败。已有官方地址自动路由，自定义地址保持原样。
+
+## 验证范围
+
+发布前最终默认后端测试 **3267 通过、2 跳过、8 按标记排除**，前端 **347 项通过**；生产构建、Ruff 格式与静态检查、质量基线和核心类型检查通过。Windows 浏览器隔离夹具覆盖深浅色、宽窄布局、视频视图面板、自动保存与切换，以及长 Payload 折叠。未写入真实任务人工评审。
+
+此前用户重启后的实际复测中，5 项正式用例通过 AI 验收，另有 1 项电脑路径探索通过，覆盖安卓、电脑与跨端；该样本没有发现 awake 锁访问失败。此结果不等于重跑原 192 项业务批次，未完成大批次压力及 macOS/Linux 实测。本次发版不构建 Docker，不重启用户服务。
+
+## 升级与下载
+
+等待当前任务结束后运行 `update.bat`（国内镜像用 `update-cn.bat`），完成后运行 `start.bat` / `start-cn.bat` 并刷新网页。需要人工评审新功能时，再从插件市场升级并启用 [任务人工评审 1.1.0](https://git.playones.com/chenmingxuan/Artemis-Plugins/releases/tag/task-review-v1.1.0)。插件要求 ARTEMIS 2.4.0+；升级主程序不会自动升级或授权已安装插件。
+
+源码附件为 `artemis-2.4.0-source.zip` 和 `SHA256SUMS.txt`，保留浅层 Git 更新能力，不包含用户配置、凭据、历史任务、依赖目录或预构建网页。工作区扩展接口见 [插件文档](../workspace-plugins.md)。

docs/releases/2.4.1.md

@@ -0,0 +1,26 @@
+# ARTEMIS 2.4.1
+
+本补丁修复 2.4.0 全新安装时的 `npm ci / EINTEGRITY`，适用于 `start.bat` 和 `start-cn.bat`。人工评审插件版本保持 **1.1.0**。
+
+## 修复
+
+- 2.4.0 发版时误将锁文件中的 MCP 间接依赖版本从 2.3.1 改为 2.4.0，仍保留 2.3.1 的 SHA-512。现在恢复 Angular CLI 22.2.4 官方声明的 `@modelcontextprotocol/server@2.3.1` 及其 `core@2.3.1`，使依赖关系、下载地址和校验值一致。未关闭 npm 完整性验证，也不要求用户清空全局缓存。
+- Windows 启动脚本准确检查 Angular 支持的 Node.js 范围：22.x 至少 22.22.3，24.x 至少 24.15.0，或 26.0.0 及以上；提示文案同步修正。
+- 保留最终 2.4.0 中的独立 v4 市场索引，提供人工评审 1.1.0；旧版宿主继续使用旧索引。曾用于发版准备的早期 2.4.0 候选包仍使用 v3 索引，会显示人工评审 1.0.0，不应继续分发。
+
+## 验证
+
+- Windows、Node.js 24.22.1、npm 11.19.1，独立源码目录及空 npm 缓存，使用国内镜像执行 `npm ci`：448 个包安装成功。实际依赖树与 Angular CLI 官方声明一致。
+- 同一全新环境下，前端 ChromeHeadless 347 项通过，生产构建通过；官方 npm 审计未发现已知漏洞。
+- 默认后端回归 3268 通过、2 跳过、8 按标记排除；包含 Node 22/24/26 兼容边界与启动脚本回归。Ruff、质量基线和核心类型检查通过。
+- 未启动用户服务，未执行设备或真实业务验收；以上为安装、构建和确定性测试结果。
+
+## 升级
+
+已有安装请先等待任务结束，再运行 `update-cn.bat`（国内镜像）或 `update.bat`，随后重新启动。建议使用更新脚本保留已有配置与数据，不要直接用源码 ZIP 覆盖安装目录。
+
+如果此前已手动修改 `package-lock.json`，更新脚本可能因本地修改而停止；先备份这份文件，确认只包含该安装问题的临时修正后再处理冲突，不要对整个仓库执行重置或清理。
+
+新安装请下载本版 `artemis-2.4.1-source.zip`，按 `SHA256SUMS.txt` 校验后使用。插件仍需在市场中单独安装或更新并启用，升级主程序不会自动授权插件。
+
+本次不构建 Docker，不启动或重启用户服务，不操作真实设备或业务任务。

docs/releases/2.4.2.md

@@ -0,0 +1,24 @@
+# ARTEMIS 2.4.2
+
+本版为批次任务增加人工评审标记，并调整任务列表布局。人工评审插件保持 **1.1.0**，第三方依赖版本不变。
+
+## 更新
+
+- 安装并启用人工评审插件后，任务存在已保存的有效评审内容时，批次列表显示“人工已审”。评审结论或非空备注均计入；清空全部内容后隐藏，禁用或卸载插件后也不显示。
+- 标记仅说明已有人工评审内容，不代表测试通过，不覆盖 AI 判定或改变任务执行流程。没有安装插件的用户不显示该标记。
+- 批次任务标题与状态分行显示：收藏星标位于标题框内，执行状态、AI 判定和人工已审标签在下方等高、左对齐排列。此布局适用于所有用户。
+- 按批次一次读取当前评审内容，沿用列表自动刷新，不逐条增加网络请求；重跑任务不继承旧任务的已审标记。
+- 补充发版约束：应用与第三方依赖独立版本化，检查锁文件差异，并验证最终源码包的全新安装。
+
+## 验证
+
+- 默认 Python 回归：3269 通过，2 跳过，8 按标记排除；Ruff、质量基线和核心类型检查通过。
+- 前端 ChromeHeadless：348 项通过；生产构建通过。
+- 内置浏览器使用隔离数据检查收藏星标、两行布局及有评审/无评审标签显示。未写入真实任务评审数据。
+- 最终源码包另行执行独立目录、空 npm 缓存的官方源和国内镜像安装及生产构建，结果随发布附件提供。
+
+## 升级
+
+已有安装请等待任务结束，运行 `update-cn.bat` 或 `update.bat` 后重启。新安装下载 `artemis-2.4.2-source.zip`，按 `SHA256SUMS.txt` 校验后启动。请勿直接覆盖旧安装目录。
+
+人工评审插件仍需单独安装并启用；本次无需升级已安装的 1.1.0。发布过程不构建 Docker，不重启用户服务，不执行设备或真实业务任务。

docs/releases/2.4.3.md

@@ -0,0 +1,25 @@
+# ARTEMIS 2.4.3
+
+本版修复异常模型输出影响整个批次的问题，并增加流式参数诊断。人工评审插件保持 **1.1.0**，SDK、其他插件及第三方依赖版本不变。
+
+## 更新
+
+- 已识别的异常输出（包括工具参数溢出、响应完整性校验失败）在有限重试和可用备用端点耗尽后，只结束当前任务，不再创建全局模型暂停。批次未开启“失败即停止”时可继续下一条；人工暂停、失败即停止、网络恢复及最终验收的原有规则保留。
+- 保留 16384 字符工具参数保护，关闭异常输出流，丢弃未完成内容，不执行本次异常动作。报错改为描述“收到的参数流”，避免在证据不足时直接归责模型。
+- 增加单次尝试请求头，区分逻辑请求、客户端尝试、网关响应与 SDK 异常中的请求编号，便于跨服务核对。
+- 对收到的工具参数片段记录字符数、UTF-8 字节数及有界 SHA256 前缀摘要，默认不新增参数正文记录。最多跟踪 64 个工具，每工具最多保留 16 个固定位置前缀。SDK 的 chunk_index 与原始协议 output_index 分开命名。
+
+诊断字段及边界见 [流式参数诊断](../llm-stream-diagnostics.md)。本次主程序安装不会部署或升级 NEWAPI、CodexManager；服务端修复独立交付。
+
+## 验证
+
+- 默认 Python 回归：3284 通过，6 跳过，8 按标记排除；Ruff 格式和静态检查、质量基线、核心类型检查通过。
+- 五类合成输入经过实际 CodexManager、NEWAPI 转发函数及原 OpenAI/LangChain SDK 的离线文件串接：正常输入有效；超长、累计全文、重复及半关闭输入被拒绝；各层参数摘要一致，设备动作执行数为 0。
+- 最终源码 ZIP 的隔离解压、独立空 npm 缓存、官方源与国内镜像安装和生产构建结果随发布附件 `INSTALL-VERIFICATION.md` 提供。
+- 未重跑用户原业务批次、未做高并发压力测试或真实模型端到端验证。历史原始参数帧未保存，不能据此认定原事故参数膨胀首先发生在哪一层。
+
+## 升级
+
+已有安装请等待任务结束，运行 `update-cn.bat` 或 `update.bat` 后重启。新安装下载 `artemis-2.4.3-source.zip`，按 `SHA256SUMS.txt` 校验后启动。请勿直接覆盖旧安装目录。
+
+人工评审插件 1.1.0 无需更新。本次发布不构建 Docker，不重启用户服务，不执行设备或真实业务任务。

docs/workspace-plugins.md

@@ -1,6 +1,6 @@
 # 工作区插件：侧栏、人工字段与报告
 
-工作区扩展使用 `plugin.json` 的 `schema_version: 3` 和 `workspace` 声明。旧版 1/2 执行插件继续兼容。纯工作区插件无需 MCP、Skill、模型、设备或任务资源，不出现在任务执行插件选择器中；安装后手动启用即可在历史任务上使用。此接口从 ARTEMIS 2.3.0 起提供；插件必须声明 `artemis_version: ">=2.3.0,<3.0.0"`，2.2.x 不支持。
+工作区扩展使用 `plugin.json` 的 `schema_version: 3` 和 `workspace` 声明。旧版 1/2 执行插件继续兼容。纯工作区插件无需 MCP、Skill、模型、设备或任务资源，不出现在任务执行插件选择器中；安装后手动启用即可在历史任务上使用。此接口从 ARTEMIS 2.3.0 起提供；插件必须声明 `artemis_version: ">=2.3.0,<3.0.0"`，2.2.x 不支持。`original_case` 面板从 2.4.0 起提供，使用它的插件须声明 `>=2.4.0,<3.0.0`。
 
 ## 声明接口
 
@@ -14,31 +14,35 @@
   "id": "review-example",
   "name": "评审扩展示例",
   "version": "1.0.0",
-  "artemis_version": ">=2.3.0,<3.0.0",
+  "artemis_version": ">=2.4.0,<3.0.0",
   "platforms": ["win32", "linux", "darwin"],
   "targets": [],
   "capabilities": {"kind": "other", "tools": {}},
   "workspace": {
     "panels": [
-      {"id":"requirements","title":"任务需求","side":"left","kind":"initial_prompt","width":{"preferred":340,"minimum":240,"maximum":480}},
+      {"id":"requirements","title":"原始用例","side":"left","kind":"original_case","width":{"preferred":340,"minimum":240,"maximum":480}},
       {"id":"review","title":"人工评审","side":"right","kind":"form","width":{"preferred":360,"minimum":260,"maximum":520}}
     ],
     "fields": [
-      {"id":"execution_accuracy","label":"AI执行准确性","kind":"choice","options":["通过","失败"]},
-      {"id":"execution_note","label":"AI执行准确性备注","kind":"text","max_length":2000}
+      {"id":"execution_accuracy","label":"用例执行准确性","kind":"choice","options":["通过","失败"]},
+      {"id":"execution_note","label":"用例执行准确性备注","kind":"text","max_length":2000}
     ]
   }
 }
 ```
 
-- `panels`：最多两个，`id` 和 `kind` 各自唯一；`side` 为 left/right。`initial_prompt` 展示该次运行最初收到的任务需求提示词，复用宿主 Markdown 渲染及 HTML 清理；不展示模型拆解步骤或后续指导。`form` 渲染本插件声明的字段。
-- `width`：CSS 像素，满足 minimum ≤ preferred ≤ maximum。minimum 范围 160–800，preferred 200–1000，maximum 200–1200。宿主优先采用首选宽度，并根据播放器、窗口空间调整；窄屏可低于 minimum 防止溢出。开关位于回放标题栏，以左右方向表示展开与收起。普通浮窗、影院均支持，默认收起；宽屏左右独立展开，窄屏一次展开一侧；单侧也始终位于回放左侧或右侧，不切换为上下排列。
+- `panels`：最多两个，`id` 和 `kind` 各自唯一；`side` 为 left/right。`initial_prompt` 展示该次运行最初收到的任务需求提示词，复用宿主 Markdown 渲染及 HTML 清理；不展示模型拆解步骤或后续指导。`original_case` 以用例编号与标题为标题，依次展示导入表中的预置条件、操作步骤、预期结果；缺失时明确提示，不从提示词推测。`form` 渲染本插件声明的字段。
+- `width`：CSS 像素，满足 minimum ≤ preferred ≤ maximum。minimum 范围 160–800，preferred 200–1000，maximum 200–1200。宿主优先采用首选宽度，并根据播放器、窗口空间调整；窄屏可低于 minimum 防止溢出。开关位于回放标题栏，以左右方向表示展开与收起。Flash/Pro/探索以及安卓、电脑、跨端任务的步骤、视频或实时视图均可使用；普通浮窗、影院均支持，默认收起；宽屏左右独立展开，窄屏一次展开一侧；单侧也始终位于回放左侧或右侧，不切换为上下排列。
 - `fields`：最多 20 个，`id` 唯一；`kind` 为 choice/text。choice 声明非空、不重复的 options，显示为互斥分段按钮，再次点击已选项可清空；text 使用多行输入。description 可选。max_length 默认 2000、最高 10000；report 默认 true。所有字段均选填，空字符串表示未填写，用户可清空。
 - 两项人工评审的标签和说明由插件提供；宿主不推断结果、不调用模型、不覆盖执行状态、AI 原判或既有人工复验。
 
 ## 任务数据接口
 
-`GET /api/task-extensions/{session_id}` 返回 `session_id`、`initial_prompt`、`editable` 和已安装且启用的插件贡献列表。每项包含 plugin_id/name/version/workspace/revision/values/history。无插件时列表为空。
+`GET /api/task-extensions/{session_id}` 返回 `session_id`、`initial_prompt`、`case_title`、`original_case`、`navigation`、`editable` 和已安装且启用的插件贡献列表。每项包含 plugin_id/name/version/workspace/revision/values/history。无插件时列表为空。
+
+`original_case` 为 `{preconditions, steps, expected}` 或 null。只有安装并启用声明 `original_case` 面板的插件时，批量模板才附加“预置条件、操作步骤、预期结果”三列并接受十列表格；否则仍只提供和接受原七列。三列不进入模型提示词。启用时也兼容七列表格，历史缺失字段不补写。
+
+批次任务的 `navigation` 含 scope=batch、position、total、previous、next，按执行顺序在同批次已结束任务之间切换；独立任务使用当前历史列表。上一条/下一条位于保存评审按钮下方。用户选择结果后立即自动保存，备注停止输入 600 毫秒后保存；连续编辑按修订串行写入，旧回执不覆盖新输入。切换前先保存，失败或冲突时留在当前任务并保留输入；手动保存可重试，使用原 request_id 防止重复。切换保留面板展开状态。打开任务或读取已有记录不触发写入。
 
 `PUT /api/task-extensions/{session_id}/{plugin_id}` 接收：
 
@@ -58,7 +62,7 @@ values 是本次提交的字段；未提交的字段保持原值。保存仅允
 
 ## 独立人工评审插件
 
-插件源代码位于独立 Artemis-Plugins 仓库的 `plugins/task-review/`，包名 task-review，版本 1.0.0，可从内置插件市场安装。它声明需求提示词面板，以及「AI执行准确性」「测试结果正确性」两个 通过/失败 字段和各自可选备注。
+插件源代码位于独立 Artemis-Plugins 仓库的 `plugins/task-review/`，包名 task-review，1.1.0 要求宿主 2.4.0，可从插件市场安装，或通过高级接入导入发行 ZIP。它声明原始用例面板，以及「用例执行准确性」「测试结果正确性」两个 通过/失败 字段和各自可选备注。
 
 在已更新宿主的环境，用 `uv run python scripts/check_plugin.py <插件目录>` 检查清单，再在「插件 → 高级接入」导入目录或 ZIP。安装、启用、填写、清空、导出、禁用、卸载和重新安装均应通过确定性测试；只检查清单不代表界面和导出已验证。
 
@@ -72,6 +76,6 @@ GET 成功返回完整贡献快照；PUT 成功返回同样结构和新 revision
 
 人工结果只能由用户填写；AI 不自行调用 PUT 生成或推断评审。此接口未加入模型 MCP 工具或远程 Python SDK 的人工写入方法。插件没有设备目标时，无需为安装验证提交安卓/PC 测试任务；用隔离终态示例验证保存、清空、重装、导出与旧缓存失效即可。
 
-市场发布时保持清单、ZIP、版本标签与 catalog-v3.json 内嵌清单一致；先上传不可变 ZIP 与 SHA256SUMS.txt 并回读验证，再更新索引。仅静态清单校验通过不能宣称全部平台已实测。
+市场发布时保持清单、ZIP、版本标签与 catalog-v4.json 内嵌清单一致；先上传不可变 ZIP 与 SHA256SUMS.txt 并回读验证，再更新索引。仅静态清单校验通过不能宣称全部平台已实测。
 
-官方市场为 2.3.0+ 提供 catalog-v3.json，catalog.json 保留给 2.2.x。宿主读取原官方地址时自动选择新版索引，不改写用户配置；自定义市场地址不会被替换。
+官方市场为 2.4.0+ 提供 catalog-v4.json，catalog-v3.json 保留给 2.3.x，catalog.json 保留给 2.2.x，避免旧宿主严格解析新面板类型时导致整个市场加载失败。2.4.0 读取原官方 catalog.json 或 catalog-v3.json 地址时自动选择新版索引，不改写用户配置；自定义市场地址不会被替换。

playground/backend_manager/app/auth/jwt_handler.py

@@ -15,7 +15,8 @@
 from datetime import datetime, timedelta, timezone, UTC
 from fastapi import Depends, HTTPException, Security, status
 from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
-from jose import JWTError, jwt
+import jwt
+from jwt import InvalidTokenError
 from app.config import settings
 
 security = HTTPBearer(auto_error=False)
@@ -40,7 +41,7 @@ def decode_access_token(token: str) -> dict:
     try:
         payload = jwt.decode(token, settings.JWT_SECRET_KEY, algorithms=[settings.JWT_ALGORITHM])
         return payload
-    except JWTError as e:
+    except InvalidTokenError as e:
         raise HTTPException(
             status_code=status.HTTP_401_UNAUTHORIZED,
             detail=f"Invalid or expired credentials: {str(e)}",

playground/backend_manager/requirements.txt

@@ -2,7 +2,7 @@ fastapi>=0.115.0
 uvicorn[standard]>=0.32.0
 pydantic>=2.9.0
 pydantic-settings>=2.5.0
-python-jose[cryptography]>=3.3.0
+PyJWT[crypto]>=2.15.1,<3.0.0
 passlib[bcrypt]>=1.7.4
 docker>=7.1.0
 google-cloud-bigquery>=3.26.0

playground/nginx_container/Dockerfile

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-FROM nginx:1.27-alpine
+FROM nginx:1.30.6-alpine
 
 # Install openssl for auto-generating self-signed dev certificates and curl for healthchecks
 RUN apk add --no-cache openssl curl bash

pyproject.toml

@@ -14,7 +14,7 @@
 
 [project]
 name = "artemis"
-version = "2.3.0"
+version = "2.4.3"
 description = "Autonomous AI Assistant for Mobile Automation"
 
 authors = [
@@ -27,14 +27,15 @@ dependencies = [
     # Remote Python SDK (kept as a zero-dependency workspace package)
     "artemis-client>=0.1.0",
     # Orchestration & Framework
-    "langgraph>=1.0.2,<2.0.0",
-    "langchain>=1.0.0",
-    "langchain-core>=1.0.0",
+    "langgraph>=1.2.18,<2.0.0",
+    "langchain>=1.4.7,<2.0.0",
+    "langchain-core>=1.7.0,<2.0.0",
     "langchain-community>=0.4.1",
     "langchain-mcp-adapters>=0.2.0",
-    "mcp>=1.26.0",
+    "mcp>=1.30.0,<2.0.0",
     # LLM Providers & GenAI SDKs
-    "langchain-openai>=1.0.0",
+    "langchain-openai>=1.7.3,<2.0.0",
+    "openai>=3.40.0,<4.0.0",
     # Configuration, Models & Validation
     "pydantic>=2.7.0",
     "pydantic-settings>=2.10.1",
@@ -59,7 +60,7 @@ dependencies = [
     "websockets>=12.0",
     "sseclient-py>=1.8.0",
     # Image, Video & Multimodal Perception
-    "pillow>=10.0.0",
+    "pillow>=13.0.0",
     "opencv-python>=4.9.0.80",
     "imageio-ffmpeg>=0.5.1",
     "matplotlib>=3.8.0",
@@ -67,7 +68,7 @@ dependencies = [
     "scipy>=1.13.0",
     # System, Utilities & Telemetry
     "psutil>=5.9.0",
-    "filelock>=3.20.0",
+    "filelock>=4.2.4",
     "retry>=0.9.2",
     "posthog>=3.5.0",
     "uuid-utils>=0.9.0",

scripts/start.ps1

@@ -218,14 +218,10 @@ function Test-NodeCompatible {
         $verRaw = (& node -v 2>$null)
         if (-not $verRaw) { return $false }
         $verStr = $verRaw.ToString().Trim().TrimStart('v')
-        $parts = $verStr.Split('.')
-        if ($parts.Count -ge 2) {
-            $major = [int]$parts[0]
-            $minor = [int]$parts[1]
-            if ($major -ge 26) { return $true }
-            if ($major -eq 24 -and $minor -ge 15) { return $true }
-            if ($major -eq 22 -and $minor -ge 22) { return $true }
-        }
+        $version = [version]$verStr
+        if ($version.Major -ge 26) { return $true }
+        if ($version.Major -eq 24 -and $version -ge [version]'24.15.0') { return $true }
+        if ($version.Major -eq 22 -and $version -ge [version]'22.22.3') { return $true }
     } catch {
         return $false
     }
@@ -383,7 +379,7 @@ if ($frontendChanged -or ((-not (Test-Path $ShowcaseIndex)) -and (-not (Test-Pat
     if (-not (Test-NodeCompatible)) {
         if (Test-CommandExists "node") {
             $curVer = (& node -v 2>$null)
-            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
+            Write-Host (Get-LaunchText "   [INFO] Detected Node.js $curVer; Angular CLI requires 22.x >= 22.22.3, 24.x >= 24.15.0, or >= 26.0.0." "   [检查] 检测到 Node.js $curVer；前端需要 22.x >= 22.22.3、24.x >= 24.15.0 或 >= 26.0.0。") -ForegroundColor Yellow
         } else {
             Write-Host (Get-LaunchText "   [INFO] Node.js/npm not found (required for Showcase UI)." "   [检查] 未找到 Node.js/npm，网页构建需要安装。") -ForegroundColor Cyan
         }
@@ -401,7 +397,7 @@ if ($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 (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
+                    Write-Host (Get-LaunchText "   [INFO] Showcase UI requires Node.js 22.x >= 22.22.3, 24.x >= 24.15.0, or >= 26.0.0." "   [检查] 网页需要 Node.js 22.x >= 22.22.3、24.x >= 24.15.0 或 >= 26.0.0。") -ForegroundColor Cyan
                     $ans = Read-Host (Get-LaunchText "      Install/Upgrade Node.js via WinGet (may require Administrator)? [Y/n]" "      通过 WinGet 安装/升级 Node.js（可能需要管理员权限）？[Y/n]")
                     if ($ans -eq "" -or $ans -match "^[Yy]") {
                         $useWinGetNode = $true

skills/artemis-use/references/workspace-plugins.md

@@ -1,6 +1,6 @@
 # 工作区插件：侧栏、人工字段与报告
 
-工作区扩展使用 `plugin.json` 的 `schema_version: 3` 和 `workspace` 声明。旧版 1/2 执行插件继续兼容。纯工作区插件无需 MCP、Skill、模型、设备或任务资源，不出现在任务执行插件选择器中；安装后手动启用即可在历史任务上使用。此接口从 ARTEMIS 2.3.0 起提供；插件必须声明 `artemis_version: ">=2.3.0,<3.0.0"`，2.2.x 不支持。
+工作区扩展使用 `plugin.json` 的 `schema_version: 3` 和 `workspace` 声明。旧版 1/2 执行插件继续兼容。纯工作区插件无需 MCP、Skill、模型、设备或任务资源，不出现在任务执行插件选择器中；安装后手动启用即可在历史任务上使用。此接口从 ARTEMIS 2.3.0 起提供；插件必须声明 `artemis_version: ">=2.3.0,<3.0.0"`，2.2.x 不支持。`original_case` 面板从 2.4.0 起提供，使用它的插件须声明 `>=2.4.0,<3.0.0`。
 
 ## 声明接口
 
@@ -14,31 +14,35 @@
   "id": "review-example",
   "name": "评审扩展示例",
   "version": "1.0.0",
-  "artemis_version": ">=2.3.0,<3.0.0",
+  "artemis_version": ">=2.4.0,<3.0.0",
   "platforms": ["win32", "linux", "darwin"],
   "targets": [],
   "capabilities": {"kind": "other", "tools": {}},
   "workspace": {
     "panels": [
-      {"id":"requirements","title":"任务需求","side":"left","kind":"initial_prompt","width":{"preferred":340,"minimum":240,"maximum":480}},
+      {"id":"requirements","title":"原始用例","side":"left","kind":"original_case","width":{"preferred":340,"minimum":240,"maximum":480}},
       {"id":"review","title":"人工评审","side":"right","kind":"form","width":{"preferred":360,"minimum":260,"maximum":520}}
     ],
     "fields": [
-      {"id":"execution_accuracy","label":"AI执行准确性","kind":"choice","options":["通过","失败"]},
-      {"id":"execution_note","label":"AI执行准确性备注","kind":"text","max_length":2000}
+      {"id":"execution_accuracy","label":"用例执行准确性","kind":"choice","options":["通过","失败"]},
+      {"id":"execution_note","label":"用例执行准确性备注","kind":"text","max_length":2000}
     ]
   }
 }
 ```
 
-- `panels`：最多两个，`id` 和 `kind` 各自唯一；`side` 为 left/right。`initial_prompt` 展示该次运行最初收到的任务需求提示词，复用宿主 Markdown 渲染及 HTML 清理；不展示模型拆解步骤或后续指导。`form` 渲染本插件声明的字段。
-- `width`：CSS 像素，满足 minimum ≤ preferred ≤ maximum。minimum 范围 160–800，preferred 200–1000，maximum 200–1200。宿主优先采用首选宽度，并根据播放器、窗口空间调整；窄屏可低于 minimum 防止溢出。开关位于回放标题栏，以左右方向表示展开与收起。普通浮窗、影院均支持，默认收起；宽屏左右独立展开，窄屏一次展开一侧；单侧也始终位于回放左侧或右侧，不切换为上下排列。
+- `panels`：最多两个，`id` 和 `kind` 各自唯一；`side` 为 left/right。`initial_prompt` 展示该次运行最初收到的任务需求提示词，复用宿主 Markdown 渲染及 HTML 清理；不展示模型拆解步骤或后续指导。`original_case` 以用例编号与标题为标题，依次展示导入表中的预置条件、操作步骤、预期结果；缺失时明确提示，不从提示词推测。`form` 渲染本插件声明的字段。
+- `width`：CSS 像素，满足 minimum ≤ preferred ≤ maximum。minimum 范围 160–800，preferred 200–1000，maximum 200–1200。宿主优先采用首选宽度，并根据播放器、窗口空间调整；窄屏可低于 minimum 防止溢出。开关位于回放标题栏，以左右方向表示展开与收起。Flash/Pro/探索以及安卓、电脑、跨端任务的步骤、视频或实时视图均可使用；普通浮窗、影院均支持，默认收起；宽屏左右独立展开，窄屏一次展开一侧；单侧也始终位于回放左侧或右侧，不切换为上下排列。
 - `fields`：最多 20 个，`id` 唯一；`kind` 为 choice/text。choice 声明非空、不重复的 options，显示为互斥分段按钮，再次点击已选项可清空；text 使用多行输入。description 可选。max_length 默认 2000、最高 10000；report 默认 true。所有字段均选填，空字符串表示未填写，用户可清空。
 - 两项人工评审的标签和说明由插件提供；宿主不推断结果、不调用模型、不覆盖执行状态、AI 原判或既有人工复验。
 
 ## 任务数据接口
 
-`GET /api/task-extensions/{session_id}` 返回 `session_id`、`initial_prompt`、`editable` 和已安装且启用的插件贡献列表。每项包含 plugin_id/name/version/workspace/revision/values/history。无插件时列表为空。
+`GET /api/task-extensions/{session_id}` 返回 `session_id`、`initial_prompt`、`case_title`、`original_case`、`navigation`、`editable` 和已安装且启用的插件贡献列表。每项包含 plugin_id/name/version/workspace/revision/values/history。无插件时列表为空。
+
+`original_case` 为 `{preconditions, steps, expected}` 或 null。只有安装并启用声明 `original_case` 面板的插件时，批量模板才附加“预置条件、操作步骤、预期结果”三列并接受十列表格；否则仍只提供和接受原七列。三列不进入模型提示词。启用时也兼容七列表格，历史缺失字段不补写。
+
+批次任务的 `navigation` 含 scope=batch、position、total、previous、next，按执行顺序在同批次已结束任务之间切换；独立任务使用当前历史列表。上一条/下一条位于保存评审按钮下方。用户选择结果后立即自动保存，备注停止输入 600 毫秒后保存；连续编辑按修订串行写入，旧回执不覆盖新输入。切换前先保存，失败或冲突时留在当前任务并保留输入；手动保存可重试，使用原 request_id 防止重复。切换保留面板展开状态。打开任务或读取已有记录不触发写入。
 
 `PUT /api/task-extensions/{session_id}/{plugin_id}` 接收：
 
@@ -58,10 +62,9 @@ values 是本次提交的字段；未提交的字段保持原值。保存仅允
 
 ## 独立人工评审插件
 
-插件源代码位于独立 Artemis-Plugins 仓库的 `plugins/task-review/`，包名 task-review，版本 1.0.0，可从内置插件市场安装。它声明需求提示词面板，以及「AI执行准确性」「测试结果正确性」两个 通过/失败 字段和各自可选备注。
-
-在已更新宿主的环境，用 `<ARTEMIS_PYTHON> <本Skill目录>/scripts/check_plugin.py <插件目录>` 检查清单，再在「插件 → 高级接入」导入目录或 ZIP。安装、启用、填写、清空、导出、禁用、卸载和重新安装均应通过确定性测试；只检查清单不代表界面和导出已验证。
+插件源代码位于独立 Artemis-Plugins 仓库的 `plugins/task-review/`，包名 task-review，1.1.0 要求宿主 2.4.0，可从插件市场安装，或通过高级接入导入发行 ZIP。它声明原始用例面板，以及「用例执行准确性」「测试结果正确性」两个 通过/失败 字段和各自可选备注。
 
+在已更新宿主的环境，用 `uv run python scripts/check_plugin.py <插件目录>` 检查清单，再在「插件 → 高级接入」导入目录或 ZIP。安装、启用、填写、清空、导出、禁用、卸载和重新安装均应通过确定性测试；只检查清单不代表界面和导出已验证。
 
 ## 开发与兼容边界
 
@@ -73,6 +76,6 @@ GET 成功返回完整贡献快照；PUT 成功返回同样结构和新 revision
 
 人工结果只能由用户填写；AI 不自行调用 PUT 生成或推断评审。此接口未加入模型 MCP 工具或远程 Python SDK 的人工写入方法。插件没有设备目标时，无需为安装验证提交安卓/PC 测试任务；用隔离终态示例验证保存、清空、重装、导出与旧缓存失效即可。
 
-市场发布时保持清单、ZIP、版本标签与 catalog-v3.json 内嵌清单一致；先上传不可变 ZIP 与 SHA256SUMS.txt 并回读验证，再更新索引。仅静态清单校验通过不能宣称全部平台已实测。
+市场发布时保持清单、ZIP、版本标签与 catalog-v4.json 内嵌清单一致；先上传不可变 ZIP 与 SHA256SUMS.txt 并回读验证，再更新索引。仅静态清单校验通过不能宣称全部平台已实测。
 
-官方市场为 2.3.0+ 提供 catalog-v3.json，catalog.json 保留给 2.2.x。宿主读取原官方地址时自动选择新版索引，不改写用户配置；自定义市场地址不会被替换。
+官方市场为 2.4.0+ 提供 catalog-v4.json，catalog-v3.json 保留给 2.3.x，catalog.json 保留给 2.2.x，避免旧宿主严格解析新面板类型时导致整个市场加载失败。2.4.0 读取原官方 catalog.json 或 catalog-v3.json 地址时自动选择新版索引，不改写用户配置；自定义市场地址不会被替换。

tests/unit/admin_console/test_automation.py

@@ -417,13 +417,21 @@ def test_batch_deletion_preserves_shared_screenshot_until_last_task(client, isol
     assert not image_file.exists()
 
 
-def test_restart_never_repeats_started_work(isolated):
+@pytest.mark.parametrize("model_paused", [False, True])
+def test_restart_never_repeats_started_work(isolated, model_paused):
     batch = service.create_batch(payload())
     service.batch_action(batch["id"], "resume")
+    if model_paused:
+        isolated.put(
+            "batch",
+            batch["id"],
+            {**isolated.get("batch", batch["id"]), "status": "paused", "pause_source": "model"},
+        )
     job = isolated.jobs(batch["id"])[0]
     isolated.save_job({**job, "status": "queued"})
     service.recover_batches()
     assert isolated.get("batch", batch["id"])["status"] == "paused"
+    assert isolated.get("batch", batch["id"])["pause_source"] == "recovery"
     assert [j["status"] for j in isolated.jobs(batch["id"])] == ["interrupted", "pending"]
     retry = service.batch_action(batch["id"], "retry_failed")
     assert retry["status"] == "draft"
@@ -603,6 +611,106 @@ async def test_device_outage_pauses_without_consuming_pending_case(isolated, mon
     assert all(job["status"] == "pending" for job in isolated.jobs(batch["id"]))
 
 
+def test_stop_all_overrides_model_auto_resume(isolated, monkeypatch):
+    from apps.admin_console.services import task_queue_service as queue
+
+    batch = service.create_batch(payload())
+    isolated.put("batch", batch["id"], {**batch, "status": "paused", "pause_source": "model"})
+    monkeypatch.setattr("apps.admin_console.services.automation_store.store", isolated)
+    monkeypatch.setattr(queue, "state", Mock(queue_items=[], active_connections={}))
+    for method in (
+        "_terminate_all_device_owners",
+        "_kill_all_local_runs",
+        "_clear_pause_file",
+        "ensure_worker_running",
+    ):
+        monkeypatch.setattr(queue.TaskQueueService, method, Mock())
+    assert queue.TaskQueueService._stop_all_tasks()
+    saved = isolated.get("batch", batch["id"])
+    assert saved["pause_source"] == "user"
+    assert "等待手动继续" in saved["reason"]
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("manual_pause", [False, True])
+@pytest.mark.parametrize("stop_on_failure", [False, True])
+async def test_model_pause_recovery_preserves_user_pause_and_failure_policy(
+    isolated, monkeypatch, manual_pause, stop_on_failure
+):
+    from apps.admin_console import server
+    from artemis.runtime.device_pool import DeviceStatus
+
+    batch = service.create_batch(payload(stop_on_failure=stop_on_failure))
+    service.batch_action(batch["id"], "resume")
+    first, second = isolated.jobs(batch["id"])
+    isolated.save_job({**first, "status": "running", "started_at": time.time()})
+    pause_state = type("State", (), {"is_paused": True, "active_runs": {}})()
+    monkeypatch.setattr(service, "state", pause_state)
+    enqueue = AsyncMock(return_value={"tasks": [{"device_serial": "test-device"}]})
+    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"])["pause_source"] == "model"
+    if manual_pause:
+        service.batch_action(batch["id"], "pause")
+        # Another paused-model tick must not overwrite the explicit user pause.
+        await service.tick_batches()
+        assert isolated.get("batch", batch["id"])["pause_source"] == "user"
+    isolated.save_job({**first, "status": "failed"})
+    pause_state.is_paused = False
+    await service.tick_batches()
+    assert isolated.job(first["session_id"])["status"] == "failed"
+    expected = "pending" if manual_pause else "skipped" if stop_on_failure else "queued"
+    assert isolated.job(second["session_id"])["status"] == expected
+    assert enqueue.await_count == (0 if manual_pause or stop_on_failure else 1)
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("code", ["initialization_failed", "execution_failed"])
+async def test_failure_reason_retained_and_only_initialization_blocks_remaining_batch(
+    isolated, monkeypatch, code
+):
+    from apps.admin_console import server
+    from artemis.runtime import task_result
+    from artemis.runtime.device_pool import DeviceStatus
+
+    batch = service.create_batch(payload())
+    service.batch_action(batch["id"], "resume")
+    first, second = isolated.jobs(batch["id"])
+    isolated.save_job({**first, "status": "running"})
+    monkeypatch.setattr(task_result, "TRACES_PATH", reports.TRACES_PATH)
+    task_result.save_failure_result(
+        first["session_id"], "PermissionError: awake lock denied", code=code
+    )
+    monkeypatch.setattr(reports, "export_session", Mock(side_effect=OSError("export unavailable")))
+    monkeypatch.setattr(service, "state", type("State", (), {"is_paused": False})())
+    enqueue = AsyncMock(return_value={"tasks": [{"device_serial": "test-device"}]})
+    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")]),
+    )
+
+    await service.on_terminal({"session_id": first["session_id"]}, "failed")
+    await service.tick_batches()
+    saved = isolated.job(first["session_id"])
+    assert saved["error"] == "PermissionError: awake lock denied"
+    assert saved["report_error"] == "export unavailable"
+    if code == "initialization_failed":
+        assert isolated.get("batch", batch["id"])["pause_source"] == "initialization"
+        assert isolated.job(second["session_id"])["status"] == "pending"
+        enqueue.assert_not_awaited()
+        service.batch_action(batch["id"], "resume")
+        await service.tick_batches()
+    assert enqueue.await_count == 1
+    assert enqueue.call_args.kwargs["session_id"] == second["session_id"]
+    assert isolated.job(first["session_id"])["status"] == "failed"
+
+
 @pytest.mark.asyncio
 async def test_fail_fast_includes_skipped_reports(isolated, monkeypatch):
     batch = service.create_batch(payload(stop_on_failure=True))
@@ -800,6 +908,85 @@ def test_reports_do_not_execute_formulas_or_invent_pass(isolated):
         assert "未验证".encode() in doc.read("word/document.xml")
 
 
+@pytest.mark.parametrize("result_status", ["passed", "failed", "blocked", "inconclusive"])
+def test_report_without_output_body_uses_effective_verdict_and_evidence(isolated, result_status):
+    job = isolated.jobs(service.create_batch(payload())["id"])[0]
+    isolated.save_job({**job, "status": "completed"})
+    folder = reports.TRACES_PATH / job["session_id"]
+    folder.mkdir(parents=True)
+    (folder / "run_outcome.json").write_text(
+        json.dumps(
+            {
+                "task_status": "completed",
+                "test_result": {
+                    "status": result_status,
+                    "reason": "实际验收依据",
+                    "evidence": ["记录中的证据"],
+                },
+            }
+        ),
+        encoding="utf-8",
+    )
+    report = reports.session_report(job["session_id"])
+    assert report["verdict"] in report["content"]
+    assert "实际验收依据" in report["content"]
+    assert "记录中的证据" in report["content"]
+    assert "未保存独立输出正文" in report["content"]
+    assert "没有保存最终结论" not in report["content"]
+    assert report["test_result"]["status"] == result_status
+
+
+def test_report_without_output_body_keeps_human_review_authoritative(isolated):
+    job = isolated.jobs(service.create_batch(payload())["id"])[0]
+    isolated.save_job({**job, "status": "completed"})
+    folder = reports.TRACES_PATH / job["session_id"]
+    folder.mkdir(parents=True)
+    (folder / "run_outcome.json").write_text(
+        json.dumps(
+            {
+                "test_result": {"status": "passed", "reason": "AI 原判通过"},
+            }
+        ),
+        encoding="utf-8",
+    )
+    isolated.save_case_review(job["session_id"], "failed", "用户确认实际结果不符合预期")
+    report = reports.session_report(job["session_id"])
+    assert "人工确认" in report["content"]
+    assert "用户确认实际结果不符合预期" in report["content"]
+    assert "AI 原判通过" not in report["content"]
+    assert report["test_result"]["status"] == "failed"
+
+
+def test_report_projects_stored_android_receipts_without_rewriting_history(isolated):
+    from tests.unit.data_engine.test_evidence_sources import android_receipt
+
+    sid = isolated.jobs(service.create_batch(payload())["id"])[0]["session_id"]
+    receipt = android_receipt()["payload"]["result"]
+    raw_payload = json.dumps({"args": {"action": "screenshot"}, "result": json.dumps(receipt)})
+    with sqlite3.connect(isolated.path) as conn:
+        conn.execute(
+            "INSERT INTO sessions(session_id,initial_goal,start_time,status) VALUES (?,?,?,?)",
+            (sid, "跨端截图", 1, "completed"),
+        )
+        conn.execute(
+            "INSERT INTO steps(step_id,session_id,step_number) VALUES (?,?,?)", ("s", sid, 1)
+        )
+        conn.execute(
+            "INSERT INTO traces(trace_id,session_id,step_id,type,name,timestamp,status,payload) VALUES (?,?,?,?,?,?,?,?)",
+            ("capture", sid, "s", "tool", "android_file", 2, "success", raw_payload),
+        )
+    report = reports.session_report(sid)
+    source = report["evidence_sources"]["sources"][0]
+    assert source["kind"] == "android"
+    assert source["references"][0]["trace_id"] == "capture"
+    assert report["evidence_sources"]["unattributed_step_count"] == 0
+    with sqlite3.connect(isolated.path) as conn:
+        assert (
+            conn.execute("SELECT payload FROM traces WHERE trace_id='capture'").fetchone()[0]
+            == raw_payload
+        )
+
+
 def test_failed_report_exposes_logged_reason_and_formats_chinese_markdown(isolated):
     job = isolated.jobs(service.create_batch(payload())["id"])[0]
     isolated.save_job({**job, "status": "failed"})

tests/unit/admin_console/test_media_recording_recovery.py

@@ -110,6 +110,8 @@ def test_strip_trace_status_suffix_handles_every_terminal_marker():
     assert MediaService.strip_trace_status_suffix("web_1_PASS_2026") == "web_1"
     assert MediaService.strip_trace_status_suffix("web_1_FAIL_2026") == "web_1"
     assert MediaService.strip_trace_status_suffix("web_1_TESTFAIL_2026") == "web_1"
+    assert MediaService.strip_trace_status_suffix("web_1_BLOCKED_2026") == "web_1"
+    assert MediaService.strip_trace_status_suffix("web_1_UNVERIFIED_2026") == "web_1"
     assert MediaService.strip_trace_status_suffix("web_1") == "web_1"
 
 

tests/unit/admin_console/test_session_list_batching.py

@@ -44,6 +44,10 @@ async def test_list_sessions_uses_batched_history_metadata(monkeypatch):
     repo.get_llm_traces_for_profiles_map.return_value = {
         "session-3": ['{"model": "gemini-3.7-pro"}']
     }
+    repo.get_recorded_model_info_map.return_value = {
+        "session-1": {"id": "gpt-6.1-terra", "provider": "openai"},
+        "session-2": {"id": "gpt-6-luna", "provider": "openai"},
+    }
     repo.get_agent_trace_names_map.return_value = {}
 
     monkeypatch.setattr(sessions_router, "session_repo", repo, raising=False)
@@ -57,6 +61,10 @@ async def test_list_sessions_uses_batched_history_metadata(monkeypatch):
     result = await sessions_router.list_sessions()
 
     assert len(result) == 3
+    assert [row["model_info"]["id"] for row in result] == ["gpt-6.1-terra", "gpt-6-luna", ""]
+    repo.get_recorded_model_info_map.assert_called_once_with(
+        ["session-1", "session-2", "session-3"]
+    )
     repo.get_latest_video_recordings_map.assert_called_once_with()
     repo.get_llm_traces_for_profiles_map.assert_called_once_with(["session-3"])
     repo.get_agent_trace_names_map.assert_called_once_with()

tests/unit/admin_console/test_session_repository_liveness.py

@@ -1,3 +1,4 @@
+import json
 from unittest.mock import patch
 
 from apps.admin_console.database.connection import db_session
@@ -37,3 +38,31 @@ def test_session_list_harvest_rechecks_worker_liveness(tmp_path):
         assert repository.harvest_orphaned_sessions(["external-live"]) == 0
 
     assert repository.get_session_status("external-live") == "running"
+
+
+def test_recorded_model_metadata_is_per_session_and_prefers_operator(tmp_path):
+    db_path = tmp_path / "sessions.db"
+    repository = SessionRepository(db_path)
+    for session_id in ("one", "two", "no-record"):
+        _insert_running_session(db_path, session_id, 1)
+    with db_session(db_path) as conn:
+        for trace_id, session_id, timestamp, payload in (
+            ("invalid", "one", 0, "{"),
+            ("planner", "one", 1, json.dumps({"role": "planner", "model": "other-model"})),
+            (
+                "operator",
+                "one",
+                2,
+                json.dumps({"role": "operator", "model": "gpt-6.1-terra", "provider": "openai"}),
+            ),
+            ("flash", "two", 1, json.dumps({"role": "FlashRunner", "model": "gpt-6-luna"})),
+        ):
+            conn.execute(
+                "INSERT INTO traces(trace_id,session_id,type,timestamp,payload) VALUES (?,?,?,?,?)",
+                (trace_id, session_id, "llm_diagnostic", timestamp, payload),
+            )
+        conn.commit()
+    assert repository.get_recorded_model_info_map(["one", "two", "no-record"]) == {
+        "one": {"id": "gpt-6.1-terra", "provider": "openai"},
+        "two": {"id": "gpt-6-luna", "provider": ""},
+    }

tests/unit/admin_console/test_session_usage_endpoint.py

@@ -99,6 +99,34 @@ def test_usage_flash_runner_counts_as_operator_and_has_no_tuning(tmp_path):
     assert usage["run_tuning"] is None
 
 
+def test_usage_uses_its_recorded_model_and_supports_legacy_endpoint_keys(tmp_path):
+    db_path = tmp_path / "sessions.db"
+    repo = SessionRepository(db_path)
+    _insert_session(db_path, "models", {"profile": "flash"})
+    _insert_usage(db_path, "models", "new", 1.0, {**_usage(100, 10), "model": "terra"})
+    _insert_usage(
+        db_path,
+        "models",
+        "legacy",
+        2.0,
+        {**_usage(200, 20), "source": "openai:terra:https://example.test:high"},
+    )
+    _insert_usage(
+        db_path, "models", "lens", 3.0, {**_usage(300, 30), "source": "lens:step_capsule:terra"}
+    )
+    _insert_usage(db_path, "models", "unknown", 4.0, {**_usage(300, 30), "source": "other"})
+    _insert_usage(
+        db_path,
+        "models",
+        "fallback",
+        5.0,
+        {**_usage(300, 30), "source": "lens:step_capsule:fallback"},
+    )
+    models = {item["model"]: item for item in repo.get_session_usage("models")["by_node_model"]}
+    assert models["terra"]["llm_calls"] == 3
+    assert models["unknown"]["llm_calls"] == 2
+
+
 def test_usage_for_unknown_or_empty_session_is_zeroed(tmp_path):
     db_path = tmp_path / "sessions.db"
     repo = SessionRepository(db_path)
@@ -112,6 +140,26 @@ def test_usage_for_unknown_or_empty_session_is_zeroed(tmp_path):
     assert usage["run_tuning"] is None
 
 
+def test_legacy_usage_preserves_model_colons_and_keeps_models_separate(tmp_path):
+    db_path = tmp_path / "sessions.db"
+    repo = SessionRepository(db_path)
+    _insert_session(db_path, "models", {"profile": "flash"})
+    sources = {
+        "team/model:stable": "openai:team/model:stable:https://example.test:8443/v1:high",
+        "team/model:preview": "openai:team/model:preview:http://[::1]:8080/v1:high",
+        "unknown": "openai:team/model:preview:unparseable:high",
+    }
+    for index, source in enumerate(sources.values()):
+        _insert_usage(
+            db_path, "models", str(index), float(index), {**_usage(100, 10), "source": source}
+        )
+
+    groups = {item["model"]: item for item in repo.get_session_usage("models")["by_node_model"]}
+    assert groups.keys() == sources.keys()
+    assert all(item["llm_calls"] == 1 for item in groups.values())
+    assert all(item["prompt_tokens"] == 100 for item in groups.values())
+
+
 def test_usage_route_is_registered():
     from apps.admin_console.routers import sessions
 

tests/unit/admin_console/test_step_repository.py

@@ -3,6 +3,30 @@ import json
 from apps.admin_console.database.repositories.step_repository import StepRepository
 
 
+def test_android_capture_receipt_survives_cleaning_without_becoming_image_store_id():
+    receipt = {
+        "ok": True,
+        "action": "screenshot",
+        "verified": True,
+        "device_serial": "device-under-test",
+        "trace_path": "artifacts/android/screen.png",
+        "sha256": "a" * 64,
+        "captured_at": "2026-10-28T00:00:00Z",
+        "content": "large file content must not be copied into the task stream",
+    }
+    cleaned = StepRepository()._clean_tool_payload(
+        {"args": {"action": "screenshot"}, "result": json.dumps(receipt)},
+        "tool",
+        "android_file",
+    )
+    assert cleaned["result"] == {key: value for key, value in receipt.items() if key != "content"}
+    assert "post_image_name" not in cleaned
+    wrapped = StepRepository()._clean_tool_payload(
+        {"result": json.dumps({"outcome": json.dumps(receipt)})}, "tool", "android_file"
+    )
+    assert wrapped["result"] == cleaned["result"]
+
+
 def test_legacy_pause_log_is_normalized_to_failed_llm_trace():
     repository = StepRepository()
     trace = {

tests/unit/admin_console/test_task_extensions.py

@@ -57,12 +57,16 @@ def manifest_payload():
     }
 
 
-def install(plugins):
+def install(plugins, original_case=False, plugin_id="review"):
     package = BytesIO()
+    manifest = manifest_payload()
+    manifest["id"] = plugin_id
+    if original_case:
+        manifest["workspace"]["panels"][0]["kind"] = "original_case"
     with zipfile.ZipFile(package, "w") as archive:
-        archive.writestr("plugin.json", json.dumps(manifest_payload()))
+        archive.writestr("plugin.json", json.dumps(manifest))
     install_archive(plugins, package.getvalue())
-    plugins.set_enabled("review", True)
+    plugins.set_enabled(plugin_id, True)
 
 
 @pytest.fixture
@@ -105,6 +109,151 @@ def save(client, values, revision=0, request_id=None):
     )
 
 
+def test_batch_review_badge_tracks_current_values_and_plugin_lifecycle(context, monkeypatch):
+    from apps.admin_console.routers import automation
+
+    store, plugins, client = context
+    monkeypatch.setattr(automation, "store", store)
+    result = {"status": "inconclusive", "source": "execution"}
+    monkeypatch.setattr(automation, "read_reviewed_result", lambda *args, **kwargs: result)
+    client.app.include_router(automation.router)
+    store.create_batch({"id": "review-batch", "status": "completed"}, [], {})
+    store.save_job(
+        {"session_id": "batch-task", "batch_id": "review-batch", "status": "completed", "case": {}}
+    )
+    store.save_job(
+        {"session_id": "new-run", "batch_id": "review-batch", "status": "completed", "case": {}}
+    )
+
+    def badge():
+        response = client.get("/api/automation/batches/review-batch")
+        assert response.status_code == 200
+        jobs = {job["session_id"]: job for job in response.json()["jobs"]}
+        assert "batch-task" in jobs, response.json()
+        assert jobs["batch-task"]["test_result"] == result
+        assert jobs["new-run"]["human_reviewed"] is False
+        return jobs["batch-task"]["human_reviewed"]
+
+    assert badge() is False
+    install(plugins)
+    assert (
+        client.put(
+            "/api/task-extensions/batch-task/review",
+            json={
+                "values": {"accuracy": "Pass"},
+                "expected_revision": 0,
+                "request_id": str(uuid4()),
+            },
+        ).status_code
+        == 200
+    )
+    assert badge() is False  # Other workspace plugins are not the human review plugin.
+    install(plugins, plugin_id="task-review")
+    assert badge() is False
+    for revision, (values, expected) in enumerate(
+        [
+            ({}, False),
+            ({"accuracy_note": "  \n"}, False),
+            ({"accuracy": "Pass"}, True),
+            ({"accuracy": "Failed"}, True),
+            ({"accuracy": "", "accuracy_note": ""}, False),
+            ({"accuracy_note": "人工核对了截图"}, True),
+        ]
+    ):
+        response = client.put(
+            "/api/task-extensions/batch-task/task-review",
+            json={"values": values, "expected_revision": revision, "request_id": str(uuid4())},
+        )
+        assert response.status_code == 200
+        assert badge() is expected
+    plugins.set_enabled("task-review", False)
+    assert badge() is False
+    plugins.set_enabled("task-review", True)
+    assert badge() is True
+    plugins.uninstall("task-review")
+    assert badge() is False
+
+
+def test_original_case_import_requires_enabled_plugin_and_keeps_execution_prompt(context):
+    from apps.admin_console.services import task_import
+
+    store, plugins, client = context
+    legacy = load_workbook(BytesIO(task_import.template()))
+    assert legacy["任务"].max_column == 7
+    legacy["任务"].append(["OLD", "", "", "旧用例", "", "原样执行", ""])
+    legacy_bytes = BytesIO()
+    legacy.save(legacy_bytes)
+    assert "original_case" not in task_import.parse_workbook(legacy_bytes.getvalue())["tasks"][0]
+
+    install(plugins, original_case=True)
+    workbook = load_workbook(BytesIO(task_import.template()))
+    assert [cell.value for cell in workbook["任务"][1]] == [
+        *task_import.HEADERS,
+        *task_import.CASE_HEADERS,
+    ]
+    workbook["任务"].append(
+        [
+            "CASE-001",
+            "检测项目",
+            "测试子项",
+            "测试标题",
+            "提取的约束",
+            "只执行此提示词",
+            "{}",
+            "原始预置条件",
+            "1. 第一步\n2. 第二步",
+            "原始预期结果",
+        ]
+    )
+    stream = BytesIO()
+    workbook.save(stream)
+    case = task_import.parse_workbook(stream.getvalue())["tasks"][0]
+    assert task_import.case_goal(case) == "只执行此提示词"
+    assert case["preconditions"] == "提取的约束"
+    assert case["original_case"] == {
+        "preconditions": "原始预置条件",
+        "steps": "1. 第一步\n2. 第二步",
+        "expected": "原始预期结果",
+    }
+    assert task_import.parse_workbook(legacy_bytes.getvalue())["valid"]
+    store.save_job({"session_id": "task-one", "status": "completed", "case": case})
+    result = client.get("/api/task-extensions/task-one").json()
+    assert "CASE-001" in result["case_title"] and "测试标题" in result["case_title"]
+    assert result["original_case"] == case["original_case"]
+    assert result["initial_prompt"] == "只执行此提示词"
+    assert report_export.session_report("task-one")["original_case"] == case["original_case"]
+
+    plugins.set_enabled("review", False)
+    assert load_workbook(BytesIO(task_import.template()))["任务"].max_column == 7
+    with pytest.raises(ValueError, match="列名或顺序"):
+        task_import.parse_workbook(stream.getvalue())
+
+
+def test_review_navigation_uses_batch_order_and_excludes_unfinished_jobs(context):
+    store, _, client = context
+    store.create_batch({"id": "review-batch", "status": "completed"}, [], {})
+    for position, status in [(3, "completed"), (1, "failed"), (2, "pending")]:
+        store.save_job(
+            {
+                "session_id": f"batch-task-{position}",
+                "batch_id": "review-batch",
+                "position": position,
+                "status": status,
+                "case": {"name": f"用例{position}", "goal": "测试"},
+            }
+        )
+    first = client.get("/api/task-extensions/batch-task-1").json()["navigation"]
+    assert first == {
+        "scope": "batch",
+        "position": 1,
+        "total": 2,
+        "previous": None,
+        "next": "batch-task-3",
+    }
+    last = client.get("/api/task-extensions/batch-task-3").json()["navigation"]
+    assert last["previous"] == "batch-task-1" and last["next"] is None
+
+
 def test_workspace_requires_v3_and_valid_bounded_declarations():
     for change in (
         {"schema_version": 2},

tests/unit/admin_console/test_task_queue_service.py

@@ -601,6 +601,45 @@ async def test_status_reports_external_global_owner_without_ipc_connection():
     assert result["goal"] == "CLI task: inspect settings"
 
 
+@pytest.mark.asyncio
+@pytest.mark.parametrize("recorded", [True, False])
+async def test_status_uses_the_active_sessions_model(recorded):
+    owner = DeviceLockOwner(
+        pid=24680,
+        process_created_at=1234.5,
+        token="active-owner-token",
+        device_id="emulator-5554",
+        description="active task",
+        acquired_at="2026-08-24T00:00:00+00:00",
+        session_id="active",
+        ingress="web",
+    )
+    state.queue_items.append(
+        {"session_id": "active", "status": "running", "runtime_overrides": {"model": "terra"}}
+    )
+    with (
+        patch.object(TaskQueueService, "ensure_worker_running"),
+        patch(
+            "apps.admin_console.routers.tasks.DeviceExecutionLock.get_active_owner",
+            return_value=owner,
+        ),
+        patch(
+            "apps.admin_console.routers.tasks.DeviceExecutionLock.get_active_owners",
+            return_value={},
+        ),
+        patch("apps.admin_console.routers.tasks.session_repo") as repo,
+        patch("apps.admin_console.routers.tasks.model_service") as models,
+    ):
+        repo.get_latest_session.return_value = None
+        repo.get_session_by_id.return_value = None
+        repo.get_recorded_model_info_map.return_value = (
+            {"active": {"id": "terra-recorded", "provider": "openai"}} if recorded else {}
+        )
+        models.get_active_model_info.return_value = {"id": "global", "provider": "openai"}
+        result = await get_status()
+    assert result["model_info"]["id"] == ("terra-recorded" if recorded else "terra")
+
+
 @pytest.mark.asyncio
 async def test_cancel_task_triggers_next_pending_task():
     executed_goals = []

tests/unit/agents/test_flash_runner.py

@@ -379,9 +379,13 @@ def test_flash_records_the_executors_target_semantics(mock_context):
         runner,
         "click",
         click_args,
-        metadata={"target_semantics": {"target_description": "play button"}},
+        metadata={
+            "target_semantics": {"target_description": "play button"},
+            "source": {"kind": "android", "target_id": "selected-phone", "label": "安卓屏幕"},
+        },
     )
     assert click["target_description"] == "play button"
+    assert click["source"]["target_id"] == "selected-phone"
     assert "target_text" not in click
     assert format_actions_clean(click) == "Tapped 'play button' (self-described) at [320, 399]"
 

tests/unit/agents/test_flash_runner_ledger.py

@@ -429,6 +429,44 @@ def _report(status="completed", tc_id="tc-report", **extra):
 _INITIAL_OBSERVATION = ("shot0.png", b"IMG0", "[1] Settings")
 
 
+@pytest.mark.asyncio
+async def test_generation_failure_uses_fallback_without_repeating_device_actions(mock_context):
+    from artemis.llm.response_guard import ResponseIntegrityError
+    from artemis.services import llm as gateway
+
+    click = AIMessage(
+        content="tap", tool_calls=[{"name": "click", "args": {"index": 1}, "id": "click"}]
+    )
+    with patch("artemis.controllers.unified_controller.get_driver"):
+        runner = _make_runner(mock_context, [])
+    primary = runner._init_llm.return_value
+    fallback = Mock()
+    calls = []
+
+    async def invoke(model, tools, messages):
+        calls.append(model)
+        if len(calls) == 1:
+            assert gateway._FALLBACK_AVAILABLE.get()
+            raise ResponseIntegrityError("missing completed response")
+        if model is fallback:
+            assert not gateway._FALLBACK_AVAILABLE.get()
+            return click
+        return _report()
+
+    runner._invoke_model = AsyncMock(side_effect=invoke)
+    with (
+        patch(
+            "artemis.agents.flash.runner.capture_screenshot_and_parse_ui",
+            AsyncMock(return_value=_INITIAL_OBSERVATION),
+        ),
+        patch("artemis.agents.flash.runner.get_llm", return_value=fallback),
+    ):
+        result = await runner.run(State(initial_goal="Open Settings"))
+    assert result["status"] == "completed"
+    assert calls == [primary, fallback, primary]
+    assert runner.executor.execute.await_count == 1
+
+
 @pytest.mark.asyncio
 @pytest.mark.parametrize("fallback_succeeds", [True, False])
 async def test_failed_actions_have_finite_fallback_and_restore_primary(

tests/unit/agents/test_operator_recovery.py

@@ -82,6 +82,31 @@ async def run_loop(operator, monkeypatch, responses):
     return result, messages, invoke
 
 
+@pytest.mark.asyncio
+async def test_generation_failure_hands_over_before_pausing(operator, monkeypatch):
+    from artemis.llm.response_guard import ResponseIntegrityError
+    from artemis.services import llm as gateway
+
+    node, state = operator
+    primary, fallback = Mock(), Mock()
+    contexts = []
+
+    async def invoke(model, messages):
+        contexts.append(gateway._FALLBACK_AVAILABLE.get())
+        if model is primary.bind_tools.return_value:
+            raise ResponseIntegrityError("missing completed response")
+        assert model is fallback.bind_tools.return_value
+        return click()
+
+    monkeypatch.setattr("artemis.agents.operator.operator.acomplete", invoke)
+    monkeypatch.setattr("artemis.agents.operator.operator.get_llm", Mock(return_value=fallback))
+    messages = []
+    result = await node._invoke_llm_loop(primary, messages, [], [], state)
+    assert contexts == [True, False]
+    assert len(result[0]) == 1
+    assert len([m for m in messages if isinstance(m, AIMessage)]) == 1
+
+
 @pytest.mark.asyncio
 async def test_prose_retry_keeps_context_and_recovers_once(operator, monkeypatch):
     prose = AIMessage(content="I will click the model menu.")

tests/unit/agents/test_planner_node.py

@@ -124,6 +124,11 @@ async def test_planner_knows_computer_plugins_with_mobile_primary_screen(mock_co
     content = llm.astream.call_args.args[0][1].content
     text = "\n".join(part["text"] for part in content if part["type"] == "text")
     assert text.count("电脑插件：cua-driver") == 1
+    assert "规划器只使用本阶段绑定的笔记工具" in text
+    assert "不表示执行器缺少这些能力" in text
+    assert "实际加载与操作回执" in text
+    bound_names = {tool.name for tool in llm.bind_tools.call_args.args[0]}
+    assert "plugin_load" not in bound_names
     assert f"当前主设备截图（{'电脑' if target == 'computer' else '安卓'}）" in text
     assert "不决定其他步骤的执行平台" in text
 

tests/unit/agents/test_validator.py

@@ -122,6 +122,7 @@ def mock_mcp():
 async def test_validator_success(mock_mcp, mock_context, temp_screenshot):
     """Test that ValidatorNode executes actions successfully."""
     decisions = json.dumps([{"action": "tap", "coordinates": [105, 205]}])
+    mock_context.device.device_id = "selected-phone"
     state = DummyState(structured_decisions=decisions, latest_screenshot=temp_screenshot)
     state.initial_goal = "在真实审批表单上 Approve once，不要普通聊天代答或重复提交。"
 
@@ -142,6 +143,11 @@ async def test_validator_success(mock_mcp, mock_context, temp_screenshot):
     assert len(report["execution"]) == 1
     assert report["execution"][0]["action"] == "tap"
     assert "attempts" not in report["execution"][0]
+    assert report["execution"][0]["source"] == {
+        "kind": "android",
+        "target_id": "selected-phone",
+        "label": "安卓屏幕",
+    }
     # The Operator's tap verb was translated to the canonical click tool.
     assert len(mock_mcp.calls_for("click")) == 1
 

tests/unit/data_engine/test_evidence_sources.py

@@ -1,5 +1,7 @@
 from copy import deepcopy
 
+import pytest
+
 from artemis.data_engine.evidence_sources import recorded_sources
 
 
@@ -59,6 +61,21 @@ def test_sources_remain_separate_and_references_use_host_ids():
     assert value["sources"][1]["category"] == "interface"
 
 
+def test_window_label_change_does_not_attribute_all_steps_to_the_first_title():
+    first = record("computer", "window", call_id="c1")
+    second = record("computer", "window", call_id="c2")
+    first["source"]["label"] = "first page"
+    second["source"]["label"] = "second page"
+    result = recorded_sources(
+        [{"step_id": "s1", "action_taken": first}, {"step_id": "s2", "action_taken": second}]
+    )
+    source = result["sources"][0]
+    assert result["total_sources"] == 1
+    assert source["reference_count"] == 2
+    assert source["label"] == ""
+    assert source["label_varies"] is True
+
+
 def test_model_arguments_and_unsourced_images_do_not_fabricate_source_metadata():
     value = recorded_sources(
         [
@@ -103,3 +120,98 @@ def test_partial_source_metadata_does_not_hide_unknown_actions_in_the_same_step(
     )
     assert value["total_sources"] == 1
     assert value["unattributed_step_count"] == 1
+
+
+def android_receipt():
+    return {
+        "trace_id": "capture-trace",
+        "type": "tool",
+        "name": "android_file",
+        "status": "success",
+        "payload": {
+            "result": {
+                "ok": True,
+                "action": "screenshot",
+                "verified": True,
+                "device_serial": "test-phone",
+                "trace_path": "artifacts/android/home.png",
+                "sha256": "a" * 64,
+                "captured_at": "2026-10-28T00:00:00Z",
+            }
+        },
+    }
+
+
+def test_android_receipts_join_computer_sources_and_deduplicate_nested_tool_traces():
+    tool = android_receipt()
+    duplicate = {**deepcopy(tool), "trace_id": "outer-wrapper"}
+    steps = [
+        {
+            "step_id": "mixed",
+            "action_taken": record("computer", "window"),
+            "generic_tools": [tool, duplicate],
+        },
+        {"step_id": "final", "generic_tools": [tool]},
+        {"step_id": "empty", "action_taken": None, "generic_tools": []},
+    ]
+    before = deepcopy(steps)
+    result = recorded_sources(steps)
+    sources = {source["kind"]: source for source in result["sources"]}
+    assert set(sources) == {"android", "computer"}
+    assert sources["android"]["target_id"] == "test-phone"
+    assert sources["android"]["reference_count"] == 2
+    assert sources["android"]["references"][0]["trace_id"] == "capture-trace"
+    assert sources["android"]["references"][0]["artifact_path"] == "artifacts/android/home.png"
+    assert result["unattributed_step_count"] == 0
+    assert steps == before
+
+
+@pytest.mark.parametrize("invalid", ["failed", "unverified", "different_tool", "arguments_only"])
+def test_only_successful_android_capture_receipts_supply_provenance(invalid):
+    tool = android_receipt()
+    if invalid == "failed":
+        tool["status"] = "failed"
+    elif invalid == "unverified":
+        tool["payload"]["result"]["verified"] = False
+    elif invalid == "different_tool":
+        tool["name"] = "read_note"
+    else:
+        tool["payload"] = {"args": tool["payload"]["result"]}
+    value = recorded_sources(
+        [{"step_id": "s", "action_taken": {"action": "tap"}, "generic_tools": [tool]}]
+    )
+    assert value["sources"] == []
+    assert value["unattributed_step_count"] == 1
+
+
+def test_capture_receipt_does_not_cover_an_unattributed_action_in_the_same_step():
+    value = recorded_sources(
+        [{"step_id": "s", "action_taken": {"action": "tap"}, "generic_tools": [android_receipt()]}]
+    )
+    assert value["sources"][0]["kind"] == "android"
+    assert value["unattributed_step_count"] == 1
+
+
+def test_flash_capture_receipt_replaces_only_its_matching_action_record():
+    tool = android_receipt()
+    action = {"action": "android_file", "args": {"action": "screenshot", "filename": "home.png"}}
+    value = recorded_sources([{"step_id": "s", "action_taken": action, "generic_tools": [tool]}])
+    assert value["sources"][0]["reference_count"] == 1
+    assert value["unattributed_step_count"] == 0
+    action["args"]["filename"] = "missing.png"
+    value = recorded_sources([{"step_id": "s", "action_taken": action, "generic_tools": [tool]}])
+    assert value["unattributed_step_count"] == 1
+
+
+def test_note_and_final_report_actions_do_not_claim_device_evidence_or_missing_sources():
+    value = recorded_sources(
+        [
+            {
+                "step_id": "note",
+                "action_taken": {"action": "save_note", "args": {"content": "device claim"}},
+            },
+            {"step_id": "final", "action_taken": {"action": "report_task_status"}},
+        ]
+    )
+    assert value["sources"] == []
+    assert value["unattributed_step_count"] == 0

tests/unit/graph/test_exit_settlement.py

@@ -532,7 +532,7 @@ async def test_assert_failure_yields_failed_tests_but_completed_status(tmp_path)
 
     # SDK wrap-up: trace suffix distinguishes assertion failures from _PASS
     assert resolve_trace_suffix("completed", outcome) == "_TESTFAIL"
-    assert resolve_trace_suffix("completed", {"tests": {"failed": 0}}) == "_PASS"
+    assert resolve_trace_suffix("completed", {"tests": {"failed": 0}}) == "_UNVERIFIED"
     assert resolve_trace_suffix("failed", outcome) == "_FAIL"
 
     # And the return structure surfaces the machine-readable summary

tests/unit/mcp/test_action_executor_semantics.py

@@ -22,14 +22,40 @@ sequence must be described too. Nothing is inferred, the description never
 reaches the wire, and the wire only ever sees coordinates.
 """
 
-from unittest.mock import Mock
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, Mock
 
 import pytest
 
 from artemis.mcp.action_executor import McpActionExecutor, _ArgError
+from artemis.mcp.action_types import ActionCode, ActionResult, ObserveResult
 from artemis.utils.action_target import observation_anchor
 
 
+@pytest.mark.asyncio
+@pytest.mark.parametrize("valid", [True, False])
+async def test_native_action_source_is_stamped_only_after_dispatch(valid):
+    ctx = SimpleNamespace(
+        device=SimpleNamespace(device_id="selected-phone", device_width=1080, device_height=2400),
+        data_engine=None,
+    )
+    executor = McpActionExecutor(ctx, actuator=Mock())
+    session = Mock()
+    session.call = AsyncMock(
+        return_value=ActionResult(ok=True, code=ActionCode.OK, action="click", message="clicked")
+    )
+    executor._session_or_start = AsyncMock(return_value=session)
+    executor._observe_after_action = AsyncMock(return_value=(ObserveResult(ok=False), None))
+    args = {"target": [100, 200], "target_description": "button"} if valid else {}
+    result = await executor._execute_device_action("click", "click", args, "call", _state())
+    if valid:
+        assert result.metadata["source"]["target_id"] == "selected-phone"
+        session.call.assert_awaited_once()
+    else:
+        assert "source" not in result.metadata
+        session.call.assert_not_awaited()
+
+
 def _make_executor(width=1080, height=2400):
     ctx = Mock()
     ctx.device.device_width = width

tests/unit/runtime/test_awake_service.py

@@ -24,6 +24,66 @@ def completed(stdout="", returncode=0, stderr=""):
     return MagicMock(returncode=returncode, stdout=stdout, stderr=stderr)
 
 
+@pytest.mark.parametrize("stage", ["directory", "acquire"])
+def test_inaccessible_awake_lock_skips_actions_and_can_recover(stage, monkeypatch, tmp_path):
+    owner = FileLock(tmp_path / "recovered.lock", thread_local=False)
+    denied_owner = MagicMock()
+    denied_owner.acquire.side_effect = PermissionError("awake lock access denied")
+    factory = MagicMock(
+        side_effect=[
+            PermissionError("awake directory denied") if stage == "directory" else denied_owner,
+            owner,
+        ]
+    )
+    configure = MagicMock(return_value=AWAKE_STRATEGY_USB)
+    monkeypatch.setattr("artemis.runtime.awake_service._owner_lock", factory)
+    monkeypatch.setattr("artemis.runtime.awake_service._configure_usb_stay_awake", configure)
+    service = ScreenAwakeService()
+    try:
+        assert service.ensure_device("device") is None
+        configure.assert_not_called()
+        assert service.device_ids == ()
+        assert service.ensure_device("device") == AWAKE_STRATEGY_USB
+        configure.assert_called_once_with("device")
+    finally:
+        service.shutdown()
+
+
+def test_awake_monitor_continues_to_other_devices_after_access_denied(monkeypatch, tmp_path):
+    def owner(device):
+        if device == "denied":
+            raise PermissionError("denied")
+        return FileLock(tmp_path / f"{device}.lock", thread_local=False)
+
+    monkeypatch.setattr("artemis.runtime.awake_service._owner_lock", owner)
+    configure = MagicMock(return_value=AWAKE_STRATEGY_USB)
+    monkeypatch.setattr("artemis.runtime.awake_service._configure_usb_stay_awake", configure)
+    service = ScreenAwakeService()
+    try:
+        service._reconcile_connected_devices({"denied", "healthy"})
+        service._reconcile_connected_devices({"denied", "healthy"})
+        assert service.device_ids == ("healthy",)
+        configure.assert_called_once_with("healthy")
+    finally:
+        service.shutdown()
+
+
+@patch(
+    "artemis.runtime.awake_service.ScreenAwakeLease",
+    side_effect=PermissionError("legacy directory denied"),
+)
+@patch("artemis.runtime.awake_service.subprocess.run")
+def test_optional_legacy_directory_failure_does_not_abort_usb_policy(mock_run, _lease):
+    mock_run.side_effect = [
+        completed(),
+        completed(),
+        completed(),
+        completed("2"),
+        completed("mStayOn=true"),
+    ]
+    assert _configure_usb_stay_awake("device") == AWAKE_STRATEGY_USB
+
+
 @patch(
     "artemis.runtime.awake_service._configure_usb_stay_awake", return_value=AWAKE_STRATEGY_HEARTBEAT
 )

tests/unit/runtime/test_helper_manager.py

@@ -214,6 +214,54 @@ def test_concurrent_managers_share_the_first_host_token(tmp_path, monkeypatch):
     assert token_path.read_text() == tokens[0]
 
 
+def test_unreadable_host_token_is_not_replaced(tmp_path, monkeypatch):
+    monkeypatch.setattr(hm, "get_temp_dir", lambda _name: tmp_path / "mutex")
+    token_path = tmp_path / "session.token"
+    token_path.write_text("a" * 48)
+    original_read = Path.read_text
+
+    def denied(path, *args, **kwargs):
+        if path == token_path:
+            raise PermissionError("token temporarily inaccessible")
+        return original_read(path, *args, **kwargs)
+
+    monkeypatch.setattr(Path, "read_text", denied)
+    manager = AccessibilityHelperManager(token_path=token_path)
+    with pytest.raises(PermissionError, match="temporarily inaccessible"):
+        manager.host_token()
+    assert original_read(token_path) == "a" * 48
+    monkeypatch.setattr(Path, "read_text", original_read)
+    assert manager.host_token() == "a" * 48
+
+
+def test_live_provision_mutex_cannot_be_stolen_after_lease_ages(tmp_path, monkeypatch):
+    import hashlib
+    import os
+    import threading
+    import time
+
+    monkeypatch.setattr(hm, "get_temp_dir", lambda _name: tmp_path)
+    first = AccessibilityHelperManager()
+    second = AccessibilityHelperManager()
+    entered = threading.Event()
+
+    def contender():
+        with second._provision_mutex(SERIAL):
+            entered.set()
+
+    with ThreadPoolExecutor(max_workers=1) as executor:
+        with first._provision_mutex(SERIAL):
+            digest = hashlib.sha256(SERIAL.encode()).hexdigest()[:16]
+            path = tmp_path / f"{digest}.mutex"
+            old = time.time() - hm._PROVISION_MUTEX_STALE_SECONDS - 10
+            os.utime(path, (old, old))
+            future = executor.submit(contender)
+            stolen = entered.wait(0.2)
+        future.result(timeout=5)
+    assert not stolen
+    assert entered.is_set()
+
+
 # --------------------------------------------------------------------------- #
 # Provision
 # --------------------------------------------------------------------------- #

tests/unit/sdk/test_agent_trace_finalization.py

@@ -64,7 +64,10 @@ async def test_device_context_uses_adb_size_without_starting_ui_client():
 
 
 @pytest.mark.asyncio
-async def test_task_that_never_acquires_queue_does_not_create_trace_session():
+async def test_task_that_never_acquires_queue_does_not_create_trace_session(tmp_path, monkeypatch):
+    from artemis.runtime import task_result
+
+    monkeypatch.setattr(task_result, "TRACES_PATH", tmp_path)
     agent = Agent()
     agent._initialized = True
     agent._device_context = DeviceContext(
@@ -86,6 +89,13 @@ async def test_task_that_never_acquires_queue_does_not_create_trace_session():
             await agent.run_task(goal="queued task", profile="flash")
 
     agent._prepare_tracing.assert_not_called()
+    outcomes = list(tmp_path.glob("*/run_outcome.json"))
+    assert len(outcomes) == 1
+    import json
+
+    outcome = json.loads(outcomes[0].read_text(encoding="utf-8"))
+    assert outcome["code"] == "initialization_failed"
+    assert "queue cancelled" in outcome["error"]
 
 
 @pytest.mark.asyncio

tests/unit/test_argument_fingerprint.py

@@ -0,0 +1,59 @@
+import hashlib
+import json
+
+import pytest
+from langchain_core.messages import AIMessageChunk
+
+from artemis.llm.argument_fingerprint import ArgumentFingerprint, MAX_PREFIXES, PREFIX_BYTES
+from artemis.llm.diagnostics import RequestAttempt
+
+
+@pytest.mark.parametrize("fragment_size", [1, 37, 4096, 100000])
+def test_fingerprints_match_at_byte_offsets_despite_unicode_and_different_fragmentation(
+    fragment_size,
+):
+    arguments = '{"target":"' + "私人内容🙂" * 8000 + '"}'
+    expected = arguments.encode("utf-8")
+    fingerprint = ArgumentFingerprint()
+    for offset in range(0, len(arguments), fragment_size):
+        fingerprint.observe(arguments[offset : offset + fragment_size])
+    result = fingerprint.snapshot()
+    assert result["argument_chars"] == len(arguments)
+    assert result["argument_bytes"] == len(expected)
+    assert result["argument_sha256"] == hashlib.sha256(expected).hexdigest()
+    assert result["argument_encoding_valid"] is True
+    assert result["argument_prefixes"] == [
+        {"bytes": size, "sha256": hashlib.sha256(expected[:size]).hexdigest()}
+        for size in range(PREFIX_BYTES, PREFIX_BYTES * MAX_PREFIXES + 1, PREFIX_BYTES)
+    ]
+    assert "私人" not in json.dumps(result, ensure_ascii=False)
+
+
+def test_invalid_utf8_is_marked_without_failing_or_forging_a_digest():
+    fingerprint = ArgumentFingerprint()
+    for value in ["safe", "\ud800", "later"]:
+        fingerprint.observe(value)
+    assert fingerprint.snapshot() == {
+        "argument_chars": 10,
+        "argument_bytes": None,
+        "argument_sha256": None,
+        "argument_deltas": 3,
+        "argument_prefixes": [],
+        "argument_encoding_valid": False,
+    }
+
+
+def test_tool_tracking_is_bounded_but_total_count_keeps_all_received_arguments():
+    attempt = RequestAttempt(
+        None, request_id="bounded", attempt=1, timeout=300, max_retries=0, metadata={}
+    )
+    for index in range(65):
+        attempt.chunk(
+            AIMessageChunk(
+                content=[],
+                tool_call_chunks=[{"name": "click", "args": "{}", "index": index}],
+            )
+        )
+    assert len(attempt.data["tools"]) == len(attempt.tool_fingerprints) == 64
+    assert attempt.data["tool_stats_truncated"] is True
+    assert attempt.data["tool_argument_chars"] == 130

tests/unit/test_backend_manager_jwt.py

@@ -0,0 +1,75 @@
+"""Regression coverage for the prototype's python-jose to PyJWT migration."""
+
+from datetime import UTC, datetime, timedelta
+import importlib.util
+from pathlib import Path
+import sys
+from types import ModuleType, SimpleNamespace
+
+from fastapi import HTTPException
+from fastapi.security import HTTPAuthorizationCredentials
+import jwt
+import pytest
+
+
+@pytest.fixture
+def auth(monkeypatch):
+    # Load only the authentication module, without Docker, GCP or real settings.
+    config = ModuleType("app.config")
+    config.settings = SimpleNamespace(
+        JWT_SECRET_KEY="test-only-signing-key-with-at-least-32-bytes",
+        JWT_ALGORITHM="HS256",
+        JWT_ACCESS_TOKEN_EXPIRE_MINUTES=60,
+    )
+    monkeypatch.setitem(sys.modules, "app.config", config)
+    path = (
+        Path(__file__).resolve().parents[2] / "playground/backend_manager/app/auth/jwt_handler.py"
+    )
+    spec = importlib.util.spec_from_file_location("backend_manager_jwt_test", path)
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+@pytest.mark.asyncio
+async def test_signed_token_preserves_claims_and_authenticated_user(auth):
+    token = auth.create_access_token("user@example.com", {"role": "tester"})
+    claims = auth.decode_access_token(token)
+    assert claims["sub"] == "user@example.com"
+    assert claims["role"] == "tester"
+    assert claims["iss"] == "artemis-backend-manager"
+    assert claims["exp"] > claims["iat"]
+    credentials = HTTPAuthorizationCredentials(scheme="Bearer", credentials=token)
+    assert await auth.get_current_user(credentials) == "user@example.com"
+
+
+@pytest.mark.parametrize("invalid", ["expired", "signature", "algorithm", "unsigned", "malformed"])
+def test_invalid_tokens_remain_unauthorized(auth, invalid):
+    claims = {"sub": "user", "exp": datetime.now(UTC) + timedelta(minutes=5)}
+    key = auth.settings.JWT_SECRET_KEY
+    algorithm = "HS256"
+    if invalid == "expired":
+        claims["exp"] = datetime.now(UTC) - timedelta(minutes=5)
+    elif invalid == "signature":
+        key = "different-test-only-signing-key-with-32-bytes"
+    elif invalid == "algorithm":
+        algorithm = "HS384"
+        key = "another-test-only-key-long-enough-for-hs384-signatures"
+    elif invalid == "unsigned":
+        algorithm, key = "none", None
+    token = jwt.encode(claims, key, algorithm=algorithm)
+    if invalid == "malformed":
+        token = "not-a-jwt"
+    with pytest.raises(HTTPException) as error:
+        auth.decode_access_token(token)
+    assert error.value.status_code == 401
+    assert error.value.headers == {"WWW-Authenticate": "Bearer"}
+
+
+@pytest.mark.asyncio
+async def test_missing_subject_is_rejected(auth):
+    token = jwt.encode({}, auth.settings.JWT_SECRET_KEY, algorithm="HS256")
+    credentials = HTTPAuthorizationCredentials(scheme="Bearer", credentials=token)
+    with pytest.raises(HTTPException) as error:
+        await auth.get_current_user(credentials)
+    assert error.value.status_code == 401

tests/unit/test_case_result.py

@@ -44,6 +44,20 @@ def test_completed_execution_and_failed_test_are_independent():
     assert resolve_trace_suffix("completed", outcome("failed")) == "_TESTFAIL"
 
 
+@pytest.mark.parametrize(
+    ("status", "suffix"),
+    [
+        ("passed", "_PASS"),
+        ("failed", "_TESTFAIL"),
+        ("blocked", "_BLOCKED"),
+        ("inconclusive", "_UNVERIFIED"),
+    ],
+)
+def test_completed_execution_trace_names_use_the_formal_verdict(status, suffix):
+    assert resolve_trace_suffix("completed", outcome(status)) == suffix
+    assert resolve_trace_suffix("completed", None) == "_UNVERIFIED"
+
+
 def test_skipped_review_metadata_survives_reload_without_changing_model_schema(tmp_path):
     result = CaseTestResult(
         status="inconclusive", reason="执行完成 · 未做 AI 判定", verification_skipped=True

tests/unit/test_cli.py

@@ -163,6 +163,35 @@ def test_cli_trace_help():
     assert "view" in result.output
 
 
+@pytest.mark.asyncio
+async def test_worker_initialization_failure_is_persisted_and_cleaned(monkeypatch):
+    from unittest.mock import AsyncMock, MagicMock
+    import artemis.interfaces.cli.commands.run as run_module
+    from artemis.runtime import task_result
+
+    monkeypatch.setenv("ARTEMIS_SESSION_ID", "test-session")
+    monkeypatch.setenv("ARTEMIS_TASK_INGRESS", "test")
+    fake_agent = MagicMock()
+    fake_agent.init = AsyncMock(side_effect=PermissionError("device initialization denied"))
+    fake_agent.clean = AsyncMock()
+    fake_agent.run_task = AsyncMock()
+    monkeypatch.setattr(run_module, "initialize_llm_config", MagicMock())
+    monkeypatch.setattr(run_module, "AgentProfile", MagicMock())
+    monkeypatch.setattr(run_module, "Builders", MagicMock())
+    monkeypatch.setattr(run_module, "Agent", MagicMock(return_value=fake_agent))
+    save = MagicMock()
+    monkeypatch.setattr(task_result, "save_failure_result", save)
+    with pytest.raises(PermissionError, match="initialization denied"):
+        await run_module.execute_task(
+            "inspect", execution_target="computer", session_id="test-session"
+        )
+    save.assert_called_once_with(
+        "test-session", "device initialization denied", code="initialization_failed"
+    )
+    fake_agent.clean.assert_awaited_once()
+    fake_agent.run_task.assert_not_awaited()
+
+
 def test_cli_mcp_help():
     """Verify 'artemis mcp --help' lists server options."""
     result = runner.invoke(app, ["mcp", "--help"])

tests/unit/test_download_mirrors.py

@@ -75,6 +75,34 @@ if ($env:npm_config_registry) { throw 'Official mode selected a China registry'
     assert result.returncode == 0, result.stdout + result.stderr
 
 
+def test_node_compatibility_matches_angular_supported_release_lines(tmp_path):
+    result = powershell(
+        tmp_path,
+        """
+$tokens = $null; $errors = $null
+$ast = [System.Management.Automation.Language.Parser]::ParseFile($env:LAUNCH_SCRIPT, [ref]$tokens, [ref]$errors)
+if ($errors) { throw 'Launcher parse error' }
+$checker = $ast.Find({ param($node) $node -is [System.Management.Automation.Language.FunctionDefinitionAst] -and $node.Name -eq 'Test-NodeCompatible' }, $true)
+. ([scriptblock]::Create($checker.Extent.Text))
+function Test-CommandExists { return $true }
+function node { return $script:nodeVersion }
+$cases = @{
+    'v20.19.0' = $false; 'v22.22.0' = $false; 'v22.22.2' = $false
+    'v22.22.3' = $true; 'v22.23.2' = $true; 'v23.0.0' = $false
+    'v24.14.0' = $false; 'v24.15.0' = $true; 'v24.22.1' = $true
+    'v24.15.0-rc.1' = $false; 'v25.0.0' = $false; 'v26.0.0' = $true
+    'not-a-version' = $false
+}
+foreach ($case in $cases.GetEnumerator()) {
+    $script:nodeVersion = $case.Key
+    if ((Test-NodeCompatible) -ne $case.Value) { throw "Wrong compatibility for $($case.Key)" }
+}
+""",
+        LAUNCH_SCRIPT=str(ROOT / "scripts/start.ps1"),
+    )
+    assert result.returncode == 0, result.stdout + result.stderr
+
+
 @pytest.mark.parametrize("first_failure", ["http", "timeout", "hash", "all"])
 def test_scrcpy_source_failover_checks_hash_before_installing(tmp_path, first_failure):
     archive = tmp_path / "fixture.zip"