feat: add official Codex skill and harden task execution

Install and update artemis-use with task diagnostics and plugin guidance. Preserve cross-device file receipts, review canonical reports, guard stage transitions and reduce small history summaries. Improve exploration lifecycle, request recovery and browser live connections.

artemis/agents/operator/operator.py

@@ -33,6 +33,7 @@ from artemis.graph.state import State
 from artemis.graph.visibility import strict_state
 from artemis.mcp.action_specs import OPERATOR_SHELL_ORDER, operator_shell_tool
 from artemis.llm.usage import usage_from_message
+from artemis.llm.structured import content_to_text
 from artemis.runtime.task_control import TaskControl, has_pending_instruction
 from artemis.services.llm import acomplete, get_llm, invoke_llm_with_timeout_message
 from artemis.tools.command_tool import (
@@ -571,9 +572,9 @@ class OperatorNode:
         fallback_limit = settings.ARTEMIS_TOOL_FALLBACK_MAX_NO_PROGRESS_ATTEMPTS
         active_llm = base_llm
         using_tool_fallback = False
-        exploration_plan_before = (
-            self._read_task_plan_text() if getattr(self.ctx, "exploration_id", None) else None
-        )
+        state.execution_report = None
+        report_requested = False
+        other_tool_failed = False
 
         for iteration in range(max_iterations):
             control = getattr(self.ctx, "task_control", None)
@@ -583,7 +584,25 @@ class OperatorNode:
             ):
                 # The device may have changed while another task held its lease.
                 return None, None, None, False
-            if iteration == max_iterations - 1:
+            if (
+                not report_requested
+                and not other_tool_failed
+                and self._exploration_ready_for_report(state)
+            ):
+                current_messages.append(
+                    SystemMessage(
+                        content=(
+                            "探索计划已完成。现在交付最终答复，不要为了结束再操作设备。"
+                            "沿用本次上下文，按用户要求给出完整报告正文，而不是仅引用笔记、"
+                            "承诺稍后提供或重复计划。需要时可读取已保存报告再原样交付，"
+                            "不重复调查或重写已有完整报告。明确区分实际发现、未测范围与"
+                            "调查完成度，不能将执行完成等同于测试通过。"
+                            "最后以不含工具调用的正文回复；系统会保存并交给独立验收。"
+                        )
+                    )
+                )
+                report_requested = True
+            if iteration == max_iterations - 1 and not report_requested:
                 logger.warning(
                     "Operator has reached the maximum number of tool calls. Adding reminder."
                 )
@@ -614,13 +633,14 @@ class OperatorNode:
             if interrupted:
                 return None, None, None, False
             assert response is not None
-            if getattr(self.ctx, "exploration_id", None):
-                from artemis.exploration.runtime import publish_response
-
-                publish_response(self.ctx, response)
             if isinstance(control, TaskControl) and has_pending_instruction(control.directory):
                 # The model answered a prompt that predates the user's new direction.
                 return None, None, None, False
+            if getattr(self.ctx, "exploration_id", None):
+                from artemis.exploration.runtime import needs_exploration_turn
+
+                if needs_exploration_turn(self.ctx):
+                    return None, None, None, False
 
             usage = usage_from_message(response)
             # The ledger's compaction thresholds read the operator's own
@@ -680,12 +700,29 @@ class OperatorNode:
                 except Exception as e:
                     logger.error(f"Failed to parse function_call fallback: {e}")
 
+            if not response.tool_calls and not getattr(response, "invalid_tool_calls", None):
+                report_text = content_to_text(response.content).strip()
+                if report_requested and report_text and self._exploration_ready_for_report(state):
+                    state.execution_report = report_text
+                    current_messages.append(response)
+                    logger.info("Exploration final report prepared; returning for final review.")
+                    break
+
+            if getattr(self.ctx, "exploration_id", None):
+                from artemis.exploration.runtime import publish_response
+
+                publish_response(self.ctx, response)
+
             if not response.tool_calls:
                 no_progress_attempts += 1
                 if no_progress_attempts >= (
                     fallback_limit if using_tool_fallback else no_progress_limit
                 ):
                     if using_tool_fallback:
+                        if report_requested:
+                            raise OperatorNoProgressError(
+                                "模型未生成可用的最终报告正文，已停止空转。"
+                            )
                         raise OperatorNoProgressError(
                             f"首选模型连续 {no_progress_limit} 次、兜底模型连续 "
                             f"{no_progress_attempts} 次未提供可执行的工具调用；"
@@ -697,16 +734,23 @@ class OperatorNode:
                     logger.warning("Operator 首选模型未调用工具，当前步骤切换到兜底模型")
                     current_messages.append(
                         SystemMessage(
-                            content="本步骤已切换兜底模型。请使用工具完成操作或明确报告阻碍。"
+                            content=(
+                                "已切换兜底模型。请直接交付完整报告正文，不要再次操作设备。"
+                                if report_requested
+                                else "本步骤已切换兜底模型。请使用工具完成操作或明确报告阻碍。"
+                            )
                         )
                     )
                     continue
-                logger.warning("LLM returned no tool call; requesting a concrete tool call.")
+                logger.warning("LLM returned no usable result; requesting bounded recovery.")
                 current_messages.append(response)
                 current_messages.append(
                     SystemMessage(
                         content=(
-                            "No tool call was returned, so no device action occurred. "
+                            "尚未收到可用的最终报告正文。请用文字交付实际结果；"
+                            "缺少证据时如实说明，不要为了结束再操作设备。"
+                            if report_requested
+                            else "No tool call was returned, so no device action occurred. "
                             "Use the available tool interface now, not a prose promise or JSON "
                             "inside text. Use an index from the current element list or "
                             "normalized coordinates with target_description. If blocked, "
@@ -1040,32 +1084,6 @@ class OperatorNode:
             for tm in tool_outputs:
                 current_messages.append(tm)
 
-            if (
-                getattr(self.ctx, "exploration_id", None)
-                and other_calls
-                and not has_terminal_calls
-                and not other_tool_failed
-            ):
-                from artemis.exploration.runtime import needs_exploration_turn
-
-                plan_after = self._read_task_plan_text()
-                snapshot = parse_plan(plan_after or "")
-                if (
-                    plan_after != exploration_plan_before
-                    and snapshot.has_top_level
-                    and snapshot.all_top_level_done
-                    and (
-                        not snapshot.continuous_top_level
-                        or getattr(state, "user_stop_requested", False)
-                    )
-                    and not needs_exploration_turn(self.ctx)
-                ):
-                    # Completing the plan is useful progress. Return to the
-                    # convergence gate and final review instead of demanding
-                    # another device action just to end the operator turn.
-                    logger.info("Exploration plan completed; returning for final review.")
-                    break
-
             if action_calls and not validation_errors:
                 break
 
@@ -1244,6 +1262,7 @@ class OperatorNode:
 
         return {
             "structured_decisions": structured_decisions,
+            "execution_report": state.execution_report,
             "operator_raw_thinking": raw_thinking,
             "operator_native_thinking": native_thinking,
             "indexed_points": state.indexed_points,
@@ -1253,6 +1272,19 @@ class OperatorNode:
             "operator_tool_limit_exceeded": tool_limit_exceeded,
         }
 
+    def _exploration_ready_for_report(self, state: State) -> bool:
+        if not getattr(self.ctx, "exploration_id", None):
+            return False
+        from artemis.exploration.runtime import needs_exploration_turn
+
+        snapshot = parse_plan(self._read_task_plan_text() or "")
+        return bool(
+            snapshot.has_top_level
+            and snapshot.all_top_level_done
+            and (not snapshot.continuous_top_level or getattr(state, "user_stop_requested", False))
+            and not needs_exploration_turn(self.ctx)
+        )
+
     def _plan_ledger_gate_enabled(self) -> bool:
         try:
             from artemis.config import load_agent_config