feat: release 2.4.0 with original cases and automatic human review

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: