fix: preserve cross-device evidence and render recorded reports

artemis/agents/flash/flash_runner.md

@@ -59,3 +59,7 @@ Keep in mind that the mobile device is an asynchronous, constantly evolving envi
 - **Completion (`status="completed"`)**: ONLY call `report_task_status(status="completed", ...)` after the latest screenshot and UI elements support the claimed result. If those sources disagree during a transition, wait and observe again before concluding. Tie each claimed page title or value to an observed screenshot or UI element; mark any missing evidence as unverified.
 - **Deliver the requested output**: Completing device actions does not complete a requested report. Before finishing, check the original goal and user guidance for required deliverables. Put the actual report/answer in the explanation field, covering the requested sections with observed findings, source-specific evidence and untested or blocked scope. Do not replace it with "completed" or a promise to provide it later. The short-paragraph rule above applies to turn commentary, not to this final deliverable. Use the existing record; retrieve only missing evidence instead of repeating the whole test. Do not invent findings or treat finding a product defect as execution failure when the goal is to investigate and report it.
 - **Failure (`status="failed"`)**: If the task is genuinely impossible due to paywalls, unrecoverable crashes, or hitting an absolute dead end after sensible fallbacks, call `report_task_status(status="failed", ...)` with the exact blocking reason.
+
+
+## 收尾与跨端验收
+切换到另一端之前，核对当前端的必需验收动作是否已完成并留下证据。提交 report_task_status 前逐项对照用户要求，缺少必要且仍可安全取得的观察时只补该步骤，不重跑已完成部分；无法补齐时明确列出缺项。看到页脚不自动等于滚动已到底，若用户要求验证位置不变，需追加滚动并比较本端前后画面。截图来源、步骤和实际内容共同支持结论，执行成功回执本身不证明验收通过。

artemis/agents/flash/runner.py

@@ -63,6 +63,7 @@ from artemis.agents.validator.tool_declarations import (
     LIST_NOTES_TOOL,
     READ_NOTE_TOOL,
     REPORT_TASK_STATUS_TOOL,
+    ToolExecutionResult,
     VALIDATOR_TOOLS_DECLARATION,
     capture_screenshot_and_parse_ui,
     prune_intermediate_screenshots,
@@ -1014,7 +1015,8 @@ class FlashRunner:
         return (
             "当前使用插件观察；实际画面和控件见对应工具返回，不是安卓画面。"
             "安卓旧截图、元素编号和坐标已失效。连续操作电脑无需重复观察手机；"
-            "切回安卓时先单独调用 wait_for_delay(time_in_ms=0) 读取最新手机画面，"
+            "等待电脑加载可用正时长 wait_for_delay，等待本身不会刷新画面，之后调用插件观察工具；"
+            "只有切回安卓时才单独调用 wait_for_delay(time_in_ms=0) 读取最新手机画面，"
             "收到后再决定手机动作。不要将电脑控件编号用于手机。"
         )
 
@@ -1027,14 +1029,17 @@ class FlashRunner:
         return image, elements
 
     @staticmethod
-    def _defer_tool_calls(messages: list[BaseMessage], tool_calls: list) -> None:
+    def _defer_tool_calls(
+        messages: list[BaseMessage], tool_calls: list, *, reason: str | None = None
+    ) -> None:
         """Close every pending call without executing decisions made on stale evidence."""
         for tc in tool_calls:
             messages.append(
                 ToolMessage(
                     tool_call_id=tc.get("id") or str(uuid.uuid4()),
                     name=tc["name"],
-                    content="未执行此调用：已切回安卓并重新观察。请先读取最新手机画面和控件，再重新决定动作或结论。",
+                    content=reason
+                    or "未执行此调用：已切回安卓并重新观察。请先读取最新手机画面和控件，再重新决定动作或结论。",
                     status="error",
                 )
             )
@@ -1104,6 +1109,52 @@ class FlashRunner:
             args = tc.get("args") or {}
             tc_id = tc.get("id") or str(uuid.uuid4())
 
+            # A positive wait on the PC means elapsed time, not a phone refresh.
+            if (
+                getattr(self, "_android_observation_stale", False)
+                and name == "wait_for_delay"
+                and isinstance(args.get("time_in_ms"), (int, float))
+                and 0 < args["time_in_ms"] < float("inf")
+            ):
+                operation = asyncio.sleep(args["time_in_ms"] / 1000)
+                if isinstance(control, TaskControl):
+                    interrupted, _ = await control.run_interruptibly(
+                        operation,
+                        on_pause=getattr(self.ctx, "on_task_pause", None),
+                        on_resume=getattr(self.ctx, "on_task_resume", None),
+                    )
+                    if interrupted:
+                        self._defer_tool_calls(
+                            messages,
+                            tool_calls[call_index:],
+                            reason="等待被用户打断，请重新观察当前目标再继续。",
+                        )
+                        return None, pre_screenshot_bytes, xml_list, action_sequence
+                else:
+                    await operation
+                message = f"已等待 {args['time_in_ms']} 毫秒，保持当前插件操作端；未采集新画面，请用插件观察工具核对加载结果。"
+                result = ToolExecutionResult(
+                    tool_name=name, tool_call_id=tc_id, status="success", text_summary=message
+                )
+                step_id = None
+                if self.ctx.data_engine:
+                    step_id = self._record_action_step(
+                        name,
+                        args,
+                        result,
+                        raw_text,
+                        step_token_usage,
+                        None,
+                        "",
+                        None,
+                        injected=injected,
+                        native_text=native_text,
+                    )
+                turn.step_keys.append(str(step_id or tc_id))
+                turn.actions.append((name, "success", message))
+                messages.append(ToolMessage(tool_call_id=tc_id, name=name, content=message))
+                continue
+
             returning_to_android = (
                 getattr(self, "_android_observation_stale", False) and name in android_tools
             )

artemis/agents/flash/summarizer.py

@@ -276,15 +276,18 @@ class VisualStepSummarizer(StepMemoryService):
             "post_ui_elements_text": post_ui_elements_text,
             "observation_settled": observation_settled,
         }
-        if receipt_only:
+        unchanged = bool(pre_img_bytes and post_img_bytes and pre_img_bytes == post_img_bytes)
+        if receipt_only or unchanged:
             from artemis.config.constants import PLUGIN_SUMMARY_TEXT_CHARS
             from artemis.plugins.prompt_budget import bounded_result_text
 
             summary = (
-                f"步骤 {step_number}：只读观察 {action_name}；未执行写操作。"
+                f"步骤 {step_number}：{action_name}；重新采集的动作后截图与动作前截图完全相同。"
+                "只能确认本次画面未变化，不能单凭此判定动作生效、已到页底或测试通过。\n"
+                if unchanged
+                else f"步骤 {step_number}：只读观察 {action_name}；未执行写操作。"
                 "以下为工具返回摘录，截图仍在本步骤证据中；不代表视觉验收通过。\n"
-                + bounded_result_text(exec_outcome, limit=PLUGIN_SUMMARY_TEXT_CHARS)
-            )
+            ) + bounded_result_text(exec_outcome, limit=PLUGIN_SUMMARY_TEXT_CHARS)
             # Evidence has already been persisted by the caller. As with a
             # completed visual summary, do not retain every frame in memory.
             payload.update(pre_img_bytes=None, post_img_bytes=None, focus=None)
@@ -295,7 +298,10 @@ class VisualStepSummarizer(StepMemoryService):
             if data_engine_step_id is not None and self.ctx.data_engine:
                 try:
                     self.ctx.data_engine.update_step_summary(
-                        data_engine_step_id, summary, status="ready", source="tool_receipt"
+                        data_engine_step_id,
+                        summary,
+                        status="ready",
+                        source="unchanged_capture" if unchanged else "tool_receipt",
                     )
                 except (OSError, ValueError, sqlite3.Error) as de_err:
                     logger.debug(f"DataEngine receipt summary update skipped: {de_err}")
@@ -442,7 +448,8 @@ class VisualStepSummarizer(StepMemoryService):
             # ACTION section and forbids synthesizing a transition.
             dual = bool(pre_bytes) and bool(post_bytes)
             template = self._prompt_template if dual else self._single_prompt_template
-            rendered_prompt = Template(template).render(step_number=step_number)
+            # The ordinal belongs to the dynamic input, not the cacheable rules.
+            rendered_prompt = Template(template).render(step_number="N")
             phrase = self._action_phrase(action_name, action_args)
             lead_lines = [f"Step {step_number} Physical Action: {phrase}"]
             # The verbatim arguments are worth a line only when the phrase
@@ -455,7 +462,8 @@ class VisualStepSummarizer(StepMemoryService):
                 lead_lines.append(
                     "Observation status: screen still changing; page state is not confirmed."
                 )
-            focus = input_data.get("focus")
+            focus = dict(input_data.get("focus") or {})
+            goal = focus.pop("goal", "")
             if isinstance(focus, dict) and focus:
                 lead_lines.extend(["", render_focus_block(focus, dual=dual)])
             content_blocks: list[dict[str, Any]] = [{"type": "text", "text": "\n".join(lead_lines)}]
@@ -513,7 +521,10 @@ class VisualStepSummarizer(StepMemoryService):
                 )
 
             messages: list[BaseMessage] = [
-                SystemMessage(content=rendered_prompt),
+                SystemMessage(
+                    content=rendered_prompt
+                    + f"\n\nTask goal (attention context, not observed evidence):\n{goal}"
+                ),
                 HumanMessage(content=content_blocks),
             ]