feat(backend): 完善 Workflow 与 DeepResearch 的运行链路与持久化能力
功能说明:\n- 重构并增强工作流网关执行链路,支持更完整的 proposal 与 run 调度参数透传\n- 增加 DeepResearch/workflow 运行事件持久化能力并补齐建表 SQL 与查询/保存接口适配\n- 优化 lead agent 与 deep research runner 的中间态处理,增强线程收集与执行链并发控制\n- 调整工作流执行器与任务路由,提升兼容性并完善错误与回放行为\n- 补充回归测试:deep_research 持久化、workflow 并发、定义加载、引擎执行、run 流程等覆盖
This commit is contained in:
1 parent
f5bf7897b9
commit
6d326a21cd
28 files changed
+836
-135
No files matched your search
+39
-2
@@ -45,6 +45,10 @@ logger = logging.getLogger(__name__)
|
||||
# Upper bound on harvested materials so a chatty collector thread cannot blow
|
||||
# up the report context; the curating/compressing stages trim further anyway.
|
||||
MAX_HARVESTED_MATERIALS = 80
|
||||
# A collector model may time out after tool calls were checkpointed but before
|
||||
# its final assistant response advanced the thread head. Keep the scan bounded
|
||||
# while retaining the richest checkpoint from that short history.
|
||||
MAX_CHECKPOINT_HISTORY = 32
|
||||
|
||||
# Tool-name → ResearchMaterial.source_type. Everything unknown maps to
|
||||
# ``other``; ``bash`` is treated as ``skill`` because skill scripts emit there.
|
||||
@@ -72,11 +76,43 @@ async def harvest_thread_materials(
|
||||
visible text (its collection小结) and doubles as a fallback material when
|
||||
the thread produced no harvestable tool results.
|
||||
"""
|
||||
checkpoint_tuple = await checkpointer.aget_tuple({"configurable": {"thread_id": runtime_thread_id, "checkpoint_ns": ""}})
|
||||
config = {"configurable": {"thread_id": runtime_thread_id, "checkpoint_ns": ""}}
|
||||
checkpoint_tuple = await checkpointer.aget_tuple(config)
|
||||
if checkpoint_tuple is None:
|
||||
logger.warning("deep-research harvest: no checkpoint for thread %s", runtime_thread_id)
|
||||
return [], ""
|
||||
values = checkpoint_tuple.checkpoint.get("channel_values", {}) or {}
|
||||
|
||||
best_materials, best_summary = _harvest_checkpoint_tuple(checkpoint_tuple, query=query)
|
||||
|
||||
# ``aget_tuple`` normally returns the latest state. When a streamed lead
|
||||
# agent call fails, however, some checkpointers leave that head at the
|
||||
# final input checkpoint even though an earlier checkpoint already holds
|
||||
# the successful web-search tool results. Prefer the richest available
|
||||
# material pool rather than treating that transient head as an empty run.
|
||||
checkpoint_history = getattr(checkpointer, "alist", None)
|
||||
if callable(checkpoint_history):
|
||||
try:
|
||||
history = checkpoint_history(config, limit=MAX_CHECKPOINT_HISTORY)
|
||||
if hasattr(history, "__aiter__"):
|
||||
async for candidate in history:
|
||||
materials, summary = _harvest_checkpoint_tuple(candidate, query=query)
|
||||
if len(materials) > len(best_materials):
|
||||
best_materials, best_summary = materials, summary
|
||||
else:
|
||||
for candidate in history:
|
||||
materials, summary = _harvest_checkpoint_tuple(candidate, query=query)
|
||||
if len(materials) > len(best_materials):
|
||||
best_materials, best_summary = materials, summary
|
||||
except Exception: # noqa: BLE001 - newest checkpoint remains a safe fallback
|
||||
logger.debug("deep-research harvest: checkpoint history unavailable for %s", runtime_thread_id, exc_info=True)
|
||||
return best_materials, best_summary
|
||||
|
||||
|
||||
def _harvest_checkpoint_tuple(checkpoint_tuple: Any, *, query: str) -> tuple[list[ResearchMaterial], str]:
|
||||
checkpoint = getattr(checkpoint_tuple, "checkpoint", None)
|
||||
if not isinstance(checkpoint, dict):
|
||||
return [], ""
|
||||
values = checkpoint.get("channel_values", {}) or {}
|
||||
messages = values.get("messages") or []
|
||||
return harvest_messages_materials(messages, query=query)
|
||||
|
||||
@@ -259,6 +295,7 @@ class StaticHarvestMaterialProvider:
|
||||
|
||||
|
||||
__all__ = [
|
||||
"MAX_CHECKPOINT_HISTORY",
|
||||
"MAX_HARVESTED_MATERIALS",
|
||||
"StaticHarvestMaterialProvider",
|
||||
"harvest_messages_materials",
|
||||
|
||||
Reference in new issue
Block a user