feat(engine): 添加运行时上下文支持并重构工具迭代限制

添加 RuntimeContext 类用于捕获模型运行时的日期时间信息，
包括UTC时间、本地时间和时区信息，并在系统提示中显示这些信息。

同时增加最大上下文消息数和工具迭代次数的配置选项，
将验证服务从引擎加载器中移除，并更新相关的数据结构和接口。

BREAKING CHANGE: 移除了验证服务，相关字段被替换为证据状态和接受状态。

- 添加 RuntimeContext 类和相关渲染方法
- 增加 max_context_messages 和 max_tool_iterations 配置
- 移除 ValidationService 相关代码
- 更新消息记录中的验证状态字段
- 添加原始工具调用检测和回退处理

app-instance/backend/beaver/skills/learning/service.py

@@ -69,15 +69,24 @@ class SkillLearningService:
                 existing_ids.add(candidate.candidate_id)
         return candidates
 
-    def build_learning_candidates_for_task(self, task_id: str, *, trigger_run_id: str) -> list[SkillLearningCandidate]:
-        """Build candidates scoped to a single validated and satisfied Task run."""
+    def build_learning_candidates_for_task(
+        self,
+        task_id: str,
+        *,
+        final_accepted_run_id: str | None = None,
+        trigger_run_id: str | None = None,
+    ) -> list[SkillLearningCandidate]:
+        """Build candidates from a user-accepted Task and all of its runs."""
 
+        final_accepted_run_id = final_accepted_run_id or trigger_run_id
+        if not final_accepted_run_id:
+            return []
         runs = [record for record in self.run_store.list_runs() if record.task_id == task_id]
-        trigger_run = next((record for record in runs if record.run_id == trigger_run_id), None)
-        if trigger_run is None or not self._is_confirmed_positive_run(trigger_run):
+        final_run = next((record for record in runs if record.run_id == final_accepted_run_id), None)
+        if final_run is None or not self._is_task_accepted_run(final_run):
             return []
 
-        source_runs = [record for record in runs if self._is_confirmed_positive_run(record)]
+        source_runs = sorted(runs, key=lambda item: (item.started_at, item.run_id))
         if not source_runs:
             return []
 
@@ -100,11 +109,16 @@ class SkillLearningService:
                     source_session_ids=source_session_ids,
                     related_skill_names=[],
                     reason=f"Task {task_id} completed successfully without a published skill; consider extracting reusable guidance.",
-                    evidence={"task_id": task_id, "trigger_run_id": trigger_run_id, "theme": self._task_theme(trigger_run.task_text)},
+                    evidence={
+                        "task_id": task_id,
+                        "final_accepted_run_id": final_accepted_run_id,
+                        "source_run_ids": source_run_ids,
+                        "theme": self._task_theme(final_run.task_text),
+                    },
                     status="open",
                     priority=1,
                     confidence=0.8,
-                    trigger_reason="validation_accepted_and_user_satisfied",
+                    trigger_reason="task_accepted",
                 )
             )
         else:
@@ -137,13 +151,14 @@ class SkillLearningService:
                         ),
                         evidence={
                             "task_id": task_id,
-                            "trigger_run_id": trigger_run_id,
+                            "final_accepted_run_id": final_accepted_run_id,
+                            "source_run_ids": source_run_ids,
                             "skill_version": receipt.skill_version,
                         },
                         status="open",
                         priority=1,
                         confidence=0.7,
-                        trigger_reason="validation_accepted_and_user_satisfied",
+                        trigger_reason="task_accepted",
                     )
                 )
 
@@ -269,7 +284,7 @@ class SkillLearningService:
             groups.setdefault(key, []).append(record)
         candidates: list[SkillLearningCandidate] = []
         for theme, runs in groups.items():
-            successful = [record for record in runs if self._is_confirmed_positive_run(record)]
+            successful = [record for record in runs if self._is_task_accepted_run(record)]
             if len(successful) < 2:
                 continue
             if any(record.activated_skills for record in successful):
@@ -290,7 +305,7 @@ class SkillLearningService:
     def _build_merge_candidates(self) -> list[SkillLearningCandidate]:
         pair_counts: dict[tuple[str, str], list[RunRecord]] = {}
         for record in self.run_store.list_runs():
-            if not self._is_confirmed_positive_run(record):
+            if not self._is_task_accepted_run(record):
                 continue
             unique = sorted({receipt.skill_name for receipt in record.activated_skills})
             for pair in combinations(unique, 2):
@@ -351,14 +366,15 @@ class SkillLearningService:
         return effects
 
     @staticmethod
-    def _is_confirmed_positive_run(record: RunRecord) -> bool:
-        validation = record.validation_result or {}
+    def _is_task_accepted_run(record: RunRecord) -> bool:
         feedback = record.feedback or {}
+        acceptance_type = feedback.get("acceptance_type")
+        if acceptance_type is None and feedback.get("feedback_type") == "satisfied":
+            acceptance_type = "accept"
         return (
             bool(record.success)
             and bool(record.task_id)
-            and validation.get("accepted") is True
-            and feedback.get("feedback_type") == "satisfied"
+            and acceptance_type == "accept"
         )
 
     @staticmethod