feat(deep-research): 强化任务链路可靠性并接入 agentfx 报告助手种子

功能说明:\n- 重构 Deep Research 调度与执行链,补齐 dispatcher、executor、live hub 与依赖注入入口,提升任务下发、执行、回调的稳定性\n- 增强运行时持久化与恢复能力,接入业务映射、任务来源与任务事件日志模型,覆盖持久化与执行可靠性关键路径测试\n- 新增 agentfx 报告助手 seed 与任务报告导入脚本配置,支持离线环境快速初始化与任务流模板回填\n- 完善 deep-research 与 thread_runs 路由参数编排,兼容不同业务映射与运行入口的前后端联动\n- 补充前端 agentfx deep-link 解析,保证 deep-research 场景下的登录跳转与任务上下文一致
This commit is contained in:
董宏凯 committed 2026-09-04 23:18:52 +08:00
1 parent 438772f0b7
commit 5c75e1af16
36 files changed
+3163 -312

No files matched your search

@@ -16,8 +16,10 @@ from __future__ import annotations
import json
import logging
from collections.abc import Awaitable, Callable
from contextlib import suppress
from datetime import date, datetime
from enum import Enum
from time import monotonic
from typing import TYPE_CHECKING, Any
from deerflow.agents.deep_research.events import (
@@ -42,6 +44,20 @@ def _json_default(value: Any) -> Any:
return str(value)
# Live-only frame types that have no durable counterpart at all. Report and
# summary text are already checkpointed (``report_chunk`` / ``summary_completed``),
# so only the reasoning channel needs a cross-worker mirror.
_MIRRORED_LIVE_TYPES = frozenset({"report_thinking", "plan_reasoning", "summary_thinking"})
# Coalescing bounds for that mirror: one bounded row per ~600 characters or
# ~1.5 seconds, never one row per provider token.
_MIRROR_MIN_CHARS = 600
_MIRROR_MAX_DELAY_S = 1.5
# Floor for the time-based flush: a slowly trickling reasoning stream must not
# degrade into one durable row per token. Anything shorter is carried until the
# next durable milestone flushes it.
_MIRROR_MIN_FLUSH_CHARS = 40
def _json_safe_payload(payload: dict[str, Any]) -> dict[str, Any]:
"""Normalize event payloads before they reach any event repository.
@@ -66,11 +82,18 @@ class PersistingEventSink:
session_id: str,
job_id: str,
on_event: Callable[[dict[str, Any]], Awaitable[None]] | None = None,
live_subscriber_probe: Callable[[str], bool] | None = None,
) -> None:
self._repo = repo
self._session_id = session_id
self._job_id = job_id
self._on_event = on_event
# Reports whether this worker holds an SSE connection for the job.
# Absent probe → assume the live path reaches the viewer (single-worker
# deployments and tests keep today's zero-extra-write behaviour).
self._live_subscriber_probe = live_subscriber_probe
self._mirror_buffers: dict[str, dict[str, Any]] = {}
self._mirroring = False
self.diagnostics: list[dict[str, Any]] = []
# A durable event row normally owns the sequence. When the event
# database is temporarily unavailable, use distinct negative sequence
@@ -87,6 +110,10 @@ class PersistingEventSink:
) -> DeepResearchEvent:
event_payload = _json_safe_payload(payload or {})
persistence_error: Exception | None = None
if not self._mirroring:
# Order any coalesced reasoning tail before the next milestone
# instead of leaving it buffered until the job ends.
await self._flush_live_mirrors()
try:
row = await self._repo.append(
session_id=self._session_id,
@@ -211,6 +238,87 @@ class PersistingEventSink:
type,
exc_info=True,
)
with suppress(Exception):
await self._mirror_live_frame(type, phase=phase, payload=payload or {})
# ── cross-worker mirror for live-only reasoning frames ──────────────────
async def _mirror_live_frame(
self,
type: str, # noqa: A002
*,
phase: ResearchPhase,
payload: dict[str, Any],
) -> None:
"""Buffer a live-only reasoning delta when no local viewer can see it.
The live hub is in-process. A job runs on the worker that won its
durable lease, while the SSE connection is served by whichever worker
accepted it, so on a multi-worker deployment the model's thinking is
usually published into a hub with no subscribers and is then lost —
there is no durable row to replay it from. When that is the case, the
reasoning is coalesced here and persisted as a bounded durable event
so the polling stream on the other worker still renders it.
"""
if type not in _MIRRORED_LIVE_TYPES or self._live_subscriber_probe is None:
return
delta = payload.get("delta")
if not isinstance(delta, str) or not delta:
return
if self._live_subscriber_probe(self._job_id):
# A viewer is attached here and has already received every frame
# live. Drop the buffer rather than flushing it, so that viewer
# does not also receive the same text as a durable replay.
self._mirror_buffers.pop(self._mirror_key(type, payload), None)
return
key = self._mirror_key(type, payload)
buffered = self._mirror_buffers.get(key)
if buffered is None:
buffered = {
"type": type,
"phase": phase,
"target": payload.get("target"),
"reportVersion": payload.get("reportVersion"),
"text": "",
"since": monotonic(),
}
self._mirror_buffers[key] = buffered
buffered["text"] += delta
buffered["phase"] = phase
buffered_chars = len(buffered["text"])
aged_out = (
buffered_chars >= _MIRROR_MIN_FLUSH_CHARS
and monotonic() - float(buffered["since"]) >= _MIRROR_MAX_DELAY_S
)
if buffered_chars >= _MIRROR_MIN_CHARS or aged_out:
await self._emit_mirror(key)
@staticmethod
def _mirror_key(type: str, payload: dict[str, Any]) -> str: # noqa: A002
return f"{type}::{payload.get('target') or 'report'}"
async def _flush_live_mirrors(self) -> None:
for key in tuple(self._mirror_buffers):
with suppress(Exception):
await self._emit_mirror(key)
async def _emit_mirror(self, key: str) -> None:
buffered = self._mirror_buffers.pop(key, None)
if buffered is None or not buffered["text"]:
return
payload: dict[str, Any] = {
"delta": buffered["text"],
"liveMirror": True,
}
if buffered["target"] is not None:
payload["target"] = buffered["target"]
if buffered["reportVersion"] is not None:
payload["reportVersion"] = buffered["reportVersion"]
self._mirroring = True
try:
await self.emit(buffered["type"], phase=buffered["phase"], payload=payload)
finally:
self._mirroring = False
class NullEventSink:
@@ -33,7 +33,7 @@ from deerflow.agents.deep_research.cancellation import CancellationToken
from deerflow.agents.deep_research.config import DeepResearchConfig, ModelRole
from deerflow.agents.deep_research.events import EventSink
from deerflow.agents.deep_research.types import CompletionResult
from deerflow.utils.stream_text import InlineThinkTagFilter
from deerflow.utils.stream_text import InlineThinkTagFilter, strip_inline_think_tags
if TYPE_CHECKING:
from langchain.chat_models import BaseChatModel
@@ -388,31 +388,57 @@ class DeerFlowCompletionBackend:
# Custom ``report_delta`` events remain the only live preview channel.
isolated_config = _parent_isolated_run_config(f"deep_research:{operation}")
reset_parent_config = _clear_inherited_runnable_config(isolated_config)
attempts = 2 if operation.startswith("write_report") else 1
last_error: Exception | None = None
try:
async for chunk in model.astream(
to_langchain_messages(messages),
config=isolated_config,
**kwargs,
):
if self._cancel is not None:
self._cancel.raise_if_cancelled()
reasoning = _reasoning_delta(chunk)
if reasoning and on_reasoning is not None:
await on_reasoning(reasoning)
# A few OpenAI-compatible models put their reasoning in the
# ordinary content channel instead of ``reasoning_content``.
# Split it from Markdown even when tags span tokens: callers may
# display a live thought trace, but it never joins ``text``.
delta, inline_reasoning = inline_think_filter.push_parts(_content_to_text(chunk))
if inline_reasoning and on_reasoning is not None:
await on_reasoning(inline_reasoning)
if delta:
text_parts.append(delta)
if on_delta is not None:
await on_delta(delta)
chunk_usage = _extract_usage(chunk)
if any(chunk_usage.values()):
usage = chunk_usage
for attempt in range(attempts):
text_parts.clear()
inline_think_filter = InlineThinkTagFilter()
try:
async for chunk in model.astream(
to_langchain_messages(messages),
config=isolated_config,
**kwargs,
):
if self._cancel is not None:
self._cancel.raise_if_cancelled()
reasoning = _reasoning_delta(chunk)
if reasoning and on_reasoning is not None:
await on_reasoning(reasoning)
# A few OpenAI-compatible models put their reasoning in the
# ordinary content channel instead of ``reasoning_content``.
# Split it from Markdown even when tags span tokens: callers may
# display a live thought trace, but it never joins ``text``.
delta, inline_reasoning = inline_think_filter.push_parts(_content_to_text(chunk))
if inline_reasoning and on_reasoning is not None:
await on_reasoning(inline_reasoning)
if delta:
text_parts.append(delta)
if on_delta is not None:
await on_delta(delta)
chunk_usage = _extract_usage(chunk)
if any(chunk_usage.values()):
usage = chunk_usage
last_error = None
break
except Exception as exc: # noqa: BLE001 - report writing waits like ordinary chat
from deerflow.agents.deep_research.cancellation import ResearchCancelled
if isinstance(exc, (ResearchCancelled, asyncio.CancelledError)):
raise
last_error = exc
# Only replay a clean connection; a half-written stream is
# reset by the runner, not by appending a second attempt.
if text_parts or attempt + 1 >= attempts:
raise
logger.warning(
"deep_research llm: %s stream interrupted before the first token (%s); retrying once",
operation,
type(exc).__name__,
)
await asyncio.sleep(1.5)
if last_error is not None:
raise last_error
finally:
reset_parent_config()
@@ -470,7 +496,10 @@ class DeerFlowCompletionBackend:
if self._cancel is not None:
self._cancel.raise_if_cancelled()
text = _content_to_text(response)
# ``ainvoke`` returns raw content, including the inline ``<think>``
# block some OpenAI-compatible deployments write there. The streamed
# path filters it out, so this retry path must not reintroduce it.
text = strip_inline_think_tags(_content_to_text(response))
usage = _extract_usage(response)
await self._record_usage(model_name, operation, usage)
return CompletionResult(text=text, model=model_name, usage=usage)