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/flash/runner.py

@@ -56,6 +56,7 @@ from langchain_core.messages import (
 )
 
 from artemis.agents.flash.summarizer import VisualStepSummarizer, build_focus_context
+from artemis.agents.flash.progress import PROGRESS_TOOL, TaskProgress
 from artemis.agents.operator.prompts import REASONING_REMINDER, UserGuidance, render_user_guidance
 from artemis.agents.validator.tool_declarations import (
     ASK_EXPLORER_TOOL,
@@ -207,8 +208,7 @@ class FlashRunner:
         return getattr(setup, "video_recording_tools_enabled", False) is True
 
     def _get_tools(self) -> list:
-        # Flash has no tool that writes notes and its prompt never teaches
-        # them, so the Validator set's note readers are left out here.
+        # Task-local deliverables use the same notes and history as Pro.
         tools = [
             t
             for t in VALIDATOR_TOOLS_DECLARATION
@@ -216,6 +216,24 @@ class FlashRunner:
         ]
         tools.insert(1, CLICK_SEQUENCE_TOOL)
         tools.append(ASK_EXPLORER_TOOL)
+        if self.ctx.data_engine is not None:
+            from artemis.core.tool_declaration import ToolDeclaration
+            from artemis.tools.scratchpad import SaveNoteArgs
+
+            tools.extend([READ_NOTE_TOOL, LIST_NOTES_TOOL])
+            tools.append(
+                ToolDeclaration(
+                    "save_note",
+                    "Save a requested text deliverable to this task's trace/notes/<key>.md. "
+                    "Use a plain key such as report or reusable_case, never an absolute path. "
+                    "Returns the actual path, size, SHA-256 and read-back verification. Existing "
+                    "notes with this key are overwritten. The output key is reserved for the "
+                    "automatically saved final response. Use read_note to inspect saved content. "
+                    "Do not save/rewrite a plan every turn; only persist requested deliverables "
+                    "or important findings not already retained in history.",
+                    SaveNoteArgs.model_json_schema(),
+                )
+            )
         # Helper tools shared with the Pro operator: the history tools are
         # declared from the very same args schemas the LangChain tools bind
         # (same availability gates: a DataEngine session, recall config).
@@ -246,6 +264,7 @@ class FlashRunner:
             tools = filter_declarations(tools, actuator, "flash")
         if getattr(self.ctx, "plugins", None):
             tools.extend(self.ctx.plugins.declarations())
+            tools.append(PROGRESS_TOOL)
         return tools
 
     def _prune_intermediate_screenshots(self, messages: list[BaseMessage]) -> None:
@@ -594,9 +613,31 @@ class FlashRunner:
         xml_list,
         messages: list[BaseMessage],
         native_text: str | None = None,
-    ) -> dict:
+    ) -> dict | None:
         """Records the final step, acknowledges the tool call, and flushes."""
-        final_report = args
+        final_report = dict(args)
+        if args.get("report_note_key"):
+            from artemis.utils.notes import read_note_content
+
+            try:
+                key = args["report_note_key"]
+                if not isinstance(key, str) or not re.fullmatch(r"[\w-]{1,128}", key):
+                    raise ValueError("report_note_key 必须是已保存报告的普通笔记名称")
+                body = read_note_content(self.ctx.data_engine.base_dir, key)
+                if not body.strip():
+                    raise ValueError("报告正文为空")
+                final_report["explanation"] = body
+            except (OSError, ValueError, AttributeError) as exc:
+                messages.append(
+                    ToolMessage(
+                        tool_call_id=tc_id,
+                        name=name,
+                        status="error",
+                        content=f"最终报告未提交：{exc}。修正报告名称或直接提供完整 explanation。",
+                    )
+                )
+                return None
+        args = final_report
         self.final_report_received = True
         if self.ctx.data_engine:
             try:
@@ -645,7 +686,7 @@ class FlashRunner:
             return post_img_bytes
         # File operations have their own verified receipts. Do not add a UI
         # observation/visual summary that could obscure that non-visual evidence.
-        if post_img_bytes or name not in action_names or name == "android_file":
+        if post_img_bytes or name not in action_names or name in {"android_file", "save_note"}:
             return post_img_bytes
         if state is not None:
             state.indexed_points = []
@@ -764,7 +805,7 @@ class FlashRunner:
             )
             action_dict.pop("coordinates", None)
             action_dict.pop(COORDINATE_SPACE_KEY, None)
-        if name == "android_file":
+        if name in {"android_file", "save_note"}:
             action_dict.pop("coordinates", None)
             action_dict.pop(COORDINATE_SPACE_KEY, None)
         return action_dict
@@ -863,7 +904,7 @@ class FlashRunner:
         # extension tools, so extension steps are recorded like actions.
         # File helpers perform real work too. Persist their receipts as steps,
         # otherwise helper-only turns vanish from the final checker's evidence.
-        action_names = self.executor.action_tool_names | {"android_file"}
+        action_names = self.executor.action_tool_names | {"android_file", "save_note"}
         plugin_action = False
         try:
             operation = self.executor.execute(
@@ -929,8 +970,8 @@ class FlashRunner:
                     exec_result,
                     raw_text,
                     step_token_usage,
-                    pre_screenshot_bytes,
-                    xml_list,
+                    None if name == "save_note" else pre_screenshot_bytes,
+                    "" if name == "save_note" else xml_list,
                     post_img_bytes,
                     injected=injected,
                     native_text=native_text,
@@ -1104,6 +1145,8 @@ class FlashRunner:
         from artemis.plugins.runtime import get_plugin_runtime
 
         plugins = get_plugin_runtime(self.ctx)
+        if not hasattr(self, "_progress"):
+            self._progress = TaskProgress()
         android_tools = action_names | {"ask_explorer"}
         if plugins:
             android_tools -= plugins.tool_names
@@ -1116,6 +1159,63 @@ class FlashRunner:
             args = tc.get("args") or {}
             tc_id = tc.get("id") or str(uuid.uuid4())
 
+            if name == "update_task_progress":
+                try:
+                    resources = (
+                        {"android"}
+                        if getattr(self.ctx, "execution_target", None) != "computer"
+                        else set()
+                    )
+                    resources.update(plugins.packages if plugins else [])
+                    directory = getattr(self.ctx.data_engine, "base_dir", None)
+                    text = self._progress.update(args, resources=resources, directory=directory)
+                    status = "success"
+                except (ValueError, OSError) as exc:
+                    text, status = str(exc), "error"
+                messages.append(
+                    ToolMessage(tool_call_id=tc_id, name=name, status=status, content=text)
+                )
+                if self.ctx.data_engine:
+                    result = ToolExecutionResult(
+                        tool_name=name, tool_call_id=tc_id, status=status, text_summary=text
+                    )
+                    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))
+                if status == "error":
+                    self._defer_tool_calls(
+                        messages,
+                        tool_calls[call_index + 1 :],
+                        reason="进度更新失败，先修正后再执行关联动作。",
+                    )
+                    return None, pre_screenshot_bytes, xml_list, action_sequence
+                continue
+
+            resource = None
+            if plugins and name in plugins.bindings:
+                if not plugins.is_read_only(name):
+                    resource = plugins.bindings[name][0]
+            elif name in android_tools and name not in {"wait_for_delay", "ask_explorer"}:
+                if name != "android_file" or args.get("action") in {"write_text", "push"}:
+                    resource = "android"
+            blocked = self._progress.guard(
+                resource,
+                completed=name == "report_task_status" and args.get("status") == "completed",
+            )
+            if blocked:
+                self._defer_tool_calls(messages, tool_calls[call_index:], reason=blocked)
+                return None, pre_screenshot_bytes, xml_list, action_sequence
+
             # A positive wait on the PC means elapsed time, not a phone refresh.
             if (
                 getattr(self, "_android_observation_stale", False)
@@ -1204,6 +1304,8 @@ class FlashRunner:
                 native_text=native_text,
                 index_elements=index_elements,
             )
+            if resource:
+                self._progress.last_resource = resource
             if returning_to_android:
                 # wait_for_delay has no stale target and its normal post-action
                 # observation is fresh. The model must see it before any further