feat(runtime): capture step evidence in console

2026-07-15 10:12:09 +08:00
parent 8d5b02e37f
commit ccde30e378
20 changed files with 594 additions and 53 deletions
@@ -4,7 +4,6 @@ import logging
 from dataclasses import dataclass, replace

 from agents.config import CollaborationConfig, load_config
-from agents.models import Observation, VerificationVerdict
 from agents.observer import Observer
 from agents.reflector import Reflector
 from agents.verifier import Verifier
@@ -94,10 +93,21 @@ class CollaborativeTaskRunner:

            for step in steps:
                executable_step = self._step_for_device(step, task.device_id)
+                before_screenshot = self.task_runner._planning_screenshot(
+                    task.device_id
+                )
                result = self.executor.execute(executable_step, context=context)
+                after_screenshot = self.task_runner._planning_screenshot(task.device_id)
                context.add_step_result(result)
                self.task_runner._record_step_result(
-                    world_handle, context, task, scene, step, result
+                    world_handle,
+                    context,
+                    task,
+                    scene,
+                    step,
+                    result,
+                    before_screenshot=before_screenshot,
+                    after_screenshot=after_screenshot,
                )

                post_scene = self._observe_scene(task.device_id)
@@ -146,13 +156,26 @@ class CollaborativeTaskRunner:
                        description=outcome.action.description,
                        args=outcome.action.args,
                    )
+                    before_screenshot = self.task_runner._planning_screenshot(
+                        task.device_id
+                    )
                    recovery_result = self.executor.execute(
                        self._step_for_device(recovery_step, task.device_id),
                        context=context,
                    )
+                    after_screenshot = self.task_runner._planning_screenshot(
+                        task.device_id
+                    )
                    context.add_step_result(recovery_result)
                    self.task_runner._record_step_result(
-                        world_handle, context, task, post_scene, recovery_step, recovery_result
+                        world_handle,
+                        context,
+                        task,
+                        post_scene,
+                        recovery_step,
+                        recovery_result,
+                        before_screenshot=before_screenshot,
+                        after_screenshot=after_screenshot,
                    )
                    if not recovery_result.success:
                        return self._fail(