feat: release 2.4.0 with original cases and automatic human review

.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。

DESIGN.md

@@ -88,6 +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。
@@ -195,3 +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)。
+**2.4.0**：人工评审支持原始用例、自动保存与上一条/下一条；执行详情默认折叠长字段。升级 OpenAI/LangChain 及安全依赖，修复 Windows 资源锁、报告证据与历史用量。配套「任务人工评审 1.1.0」独立安装。见 [2.4.0 发行说明](docs/releases/2.4.0.md)；上一版本见 [2.3.0](docs/releases/2.3.0.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/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/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"}
 
@@ -41,10 +42,26 @@ def task_context(session_id: str, store: AutomationStore) -> dict:
     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/showcase_ui/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "artemis-showcase-ui",
-  "version": "2.3.0",
+  "version": "2.4.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "artemis-showcase-ui",
-      "version": "2.3.0",
+      "version": "2.4.0",
       "dependencies": {
         "@angular/cdk": "^22.2.4",
         "@angular/common": "^22.2.3",
@@ -253,7 +253,7 @@
         "@angular-devkit/schematics": "22.2.4",
         "@inquirer/prompts": "8.7.2",
         "@listr2/prompt-adapter-inquirer": "4.2.7",
-        "@modelcontextprotocol/server": "2.3.1",
+        "@modelcontextprotocol/server": "2.4.0",
         "@schematics/angular": "22.2.4",
         "jsonc-parser": "3.3.1",
         "listr2": "11.1.0",
@@ -2043,8 +2043,8 @@
       ]
     },
     "node_modules/@modelcontextprotocol/core": {
-      "version": "2.3.1",
-      "resolved": "https://registry.npmjs.org/@modelcontextprotocol/core/-/core-2.3.1.tgz",
+      "version": "2.4.0",
+      "resolved": "https://registry.npmjs.org/@modelcontextprotocol/core/-/core-2.4.0.tgz",
       "integrity": "sha512-laVmIhPGpWi7rG9q+0UigblRN0Hws/Yjlb6qLFtVqryXVLkc4h+yN8z731POD2LnAGQlFe7/tXhUm7Bi0YB91g==",
       "dev": true,
       "license": "Apache-2.0",
@@ -2056,13 +2056,13 @@
       }
     },
     "node_modules/@modelcontextprotocol/server": {
-      "version": "2.3.1",
-      "resolved": "https://registry.npmjs.org/@modelcontextprotocol/server/-/server-2.3.1.tgz",
+      "version": "2.4.0",
+      "resolved": "https://registry.npmjs.org/@modelcontextprotocol/server/-/server-2.4.0.tgz",
       "integrity": "sha512-e59MfWuSssj6DoQ96JCTqdW1AXT5/XtnTl0WWd6MU1Ka434fFUGGosCLJbGNySDhHGvxQWoRWK137FXYFkYNWw==",
       "dev": true,
       "license": "Apache-2.0",
       "dependencies": {
-        "@modelcontextprotocol/core": "2.3.1",
+        "@modelcontextprotocol/core": "2.4.0",
         "zod": "^4.2.0"
       },
       "engines": {

apps/showcase_ui/package.json

@@ -1,6 +1,6 @@
 {
   "name": "artemis-showcase-ui",
-  "version": "2.3.0",
+  "version": "2.4.0",
   "scripts": {
     "ng": "ng",
     "start": "ng serve --proxy-config proxy.conf.json",

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/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);
-        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');
+    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.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

@@ -781,7 +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"):

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/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

@@ -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/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/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/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/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/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,
@@ -794,7 +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")
@@ -909,7 +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")
@@ -1687,13 +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

@@ -686,7 +686,12 @@ 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

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 +1,7 @@
 # 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。

docs/releases/2.4.0.md

@@ -0,0 +1,39 @@
+# ARTEMIS 2.4.0
+
+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。
+- 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。
+
+## 验证范围
+
+本轮开发默认后端测试 **3263 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/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。
 

pyproject.toml

@@ -14,7 +14,7 @@
 
 [project]
 name = "artemis"
-version = "2.3.0"
+version = "2.4.0"
 description = "Autonomous AI Assistant for Mobile Automation"
 
 authors = [

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
 

tests/unit/admin_console/test_automation.py

@@ -908,6 +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

@@ -57,10 +57,13 @@ def manifest_payload():
     }
 
 
-def install(plugins):
+def install(plugins, original_case=False):
     package = BytesIO()
+    manifest = manifest_payload()
+    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)
 
@@ -105,6 +108,86 @@ def save(client, values, revision=0, request_id=None):
     )
 
 
+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_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/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_model_proxy.py

@@ -0,0 +1,49 @@
+"""Model HTTP clients consistently opt out of ambient proxies by default."""
+
+import ssl
+
+import pytest
+
+from artemis.config.settings import Settings, settings
+from artemis.llm.router import ModelEndpoint, ModelFactory
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("use_proxy", [False, True])
+async def test_sync_and_async_clients_follow_env_only_proxy_policy(monkeypatch, use_proxy):
+    monkeypatch.setenv("HTTPS_PROXY", "http://127.0.0.1:9")
+    monkeypatch.setenv("HTTP_PROXY", "http://127.0.0.1:9")
+    monkeypatch.setenv("OPENAI_PROXY", "http://127.0.0.1:9")
+    monkeypatch.delenv("ARTEMIS_FAKE_LLM", raising=False)
+    monkeypatch.setattr(settings, "OPENAI_USE_SYSTEM_PROXY", use_proxy)
+    model = ModelFactory.create_model(
+        ModelEndpoint(api_key="test-only", api_base="https://example.invalid/v1")
+    )
+    try:
+        for client in (model.http_client, model.http_async_client):
+            assert client.trust_env is use_proxy
+            assert bool([mount for mount in client._mounts.values() if mount]) is use_proxy
+            assert client._transport._pool._ssl_context.verify_mode == ssl.CERT_REQUIRED
+        assert model.openai_proxy == ""
+    finally:
+        model.http_client.close()
+        await model.http_async_client.aclose()
+
+
+def test_proxy_setting_is_env_only_and_part_of_client_cache_identity(monkeypatch):
+    from apps.admin_console.services.model_settings_service import (
+        ModelSettingsUpdate,
+        get_model_settings,
+    )
+
+    monkeypatch.delenv("OPENAI_USE_SYSTEM_PROXY", raising=False)
+    assert Settings(_env_file=None).OPENAI_USE_SYSTEM_PROXY is False
+    monkeypatch.setenv("OPENAI_USE_SYSTEM_PROXY", "true")
+    assert Settings(_env_file=None).OPENAI_USE_SYSTEM_PROXY is True
+    endpoint = ModelEndpoint(api_key="test-only")
+    monkeypatch.setattr(settings, "OPENAI_USE_SYSTEM_PROXY", False)
+    direct = endpoint.cache_key()
+    monkeypatch.setattr(settings, "OPENAI_USE_SYSTEM_PROXY", True)
+    assert endpoint.cache_key() != direct
+    assert not any("proxy" in key.lower() for key in get_model_settings())
+    assert not any("proxy" in key.lower() for key in ModelSettingsUpdate.model_fields)

tests/unit/test_plugins.py

@@ -892,6 +892,16 @@ async def test_workspace_computer_discovery_never_queries_adb(monkeypatch):
     assert set(routes) == {"/api/status", "/api/plugins"}
 
 
+@pytest.mark.asyncio
+async def test_computer_task_uses_the_actual_host_platform():
+    from artemis.platform import platform
+    from artemis.sdk.agent import Agent
+
+    agent = Agent()
+    await agent.init(execution_target="computer")
+    assert agent._device_context.host_platform == platform.os_type.name
+
+
 @pytest.mark.asyncio
 async def test_sdk_setup_failure_releases_plugin_version_pin(store, monkeypatch):
     from artemis.sdk.agent import Agent

tests/unit/test_token_meter.py

@@ -126,6 +126,14 @@ def test_record_llm_usage_accumulates_across_calls_same_session():
     assert meter.last_prompt_tokens == 250
 
 
+def test_record_llm_usage_preserves_the_call_model():
+    engine = Mock()
+    engine.current_session_id = uuid4()
+    engine.current_step_id = None
+    payload = record_llm_usage(engine, _msg_with_usage(), model="gpt-6.1-terra")
+    assert payload["model"] == "gpt-6.1-terra"
+
+
 def test_record_llm_usage_never_raises_and_skips_gracefully():
     # No engine
     assert record_llm_usage(None, _msg_with_usage()) is None

uv.lock

@@ -248,7 +248,7 @@ wheels = [
 
 [[package]]
 name = "artemis"
-version = "2.3.0"
+version = "2.4.0"
 source = { editable = "." }
 dependencies = [
     { name = "adbutils" },