fix: preserve cross-device evidence and render recorded reports

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),
             ]