feat: 新增报告协作页,并强化 Deep Research 运行诊断与报告兜底
支持浏览器侧素材快照撰写、拒绝报告读时修复、Mermaid PNG 导出与 Word 导出加固。 Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
1 parent
65d6b61d5d
commit
f109a95535
65 files changed
+10342
-245
No files matched your search
+67
-4
@@ -13,8 +13,11 @@ don't carry those ids around.
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
from collections.abc import Awaitable, Callable
|
||||
from datetime import date, datetime
|
||||
from enum import Enum
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
from deerflow.agents.deep_research.events import (
|
||||
@@ -29,6 +32,26 @@ if TYPE_CHECKING:
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _json_default(value: Any) -> Any:
|
||||
if isinstance(value, (datetime, date)):
|
||||
return value.isoformat()
|
||||
if isinstance(value, Enum):
|
||||
return value.value
|
||||
if hasattr(value, "model_dump"):
|
||||
return value.model_dump(mode="json")
|
||||
return str(value)
|
||||
|
||||
|
||||
def _json_safe_payload(payload: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Normalize event payloads before they reach any event repository.
|
||||
|
||||
This protects deployments that still use a strict ``json.dumps`` inside
|
||||
the SQL repository and keeps native datetime values in source metadata
|
||||
from degrading every ``source_added`` event.
|
||||
"""
|
||||
return json.loads(json.dumps(payload, ensure_ascii=False, default=_json_default))
|
||||
|
||||
|
||||
class PersistingEventSink:
|
||||
"""EventSink implementation backed by the deep-research event repository.
|
||||
|
||||
@@ -48,6 +71,7 @@ class PersistingEventSink:
|
||||
self._session_id = session_id
|
||||
self._job_id = job_id
|
||||
self._on_event = on_event
|
||||
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
|
||||
# numbers for the live-only path so clients can render every milestone
|
||||
@@ -61,7 +85,8 @@ class PersistingEventSink:
|
||||
phase: ResearchPhase = "initializing",
|
||||
payload: dict | None = None,
|
||||
) -> DeepResearchEvent:
|
||||
event_payload = payload or {}
|
||||
event_payload = _json_safe_payload(payload or {})
|
||||
persistence_error: Exception | None = None
|
||||
try:
|
||||
row = await self._repo.append(
|
||||
session_id=self._session_id,
|
||||
@@ -79,17 +104,29 @@ class PersistingEventSink:
|
||||
phase=row.get("phase", phase),
|
||||
payload=row.get("payload") or event_payload,
|
||||
)
|
||||
except Exception: # noqa: BLE001
|
||||
except Exception as exc: # noqa: BLE001
|
||||
# Progress persistence must not turn a recoverable database blip
|
||||
# into a failed report. The job/status stores still record terminal
|
||||
# state; this live-only frame lets an attached UI stay responsive
|
||||
# until durable replay becomes available again after reconnect.
|
||||
self._fallback_seq -= 1
|
||||
logger.exception(
|
||||
"deep-research event persistence failed; continuing job with a live-only event (job=%s, type=%s, phase=%s)",
|
||||
persistence_error = exc
|
||||
self.diagnostics.append(
|
||||
{
|
||||
"code": "event_persistence_degraded",
|
||||
"stage": phase,
|
||||
"eventType": type,
|
||||
"errorType": exc.__class__.__name__,
|
||||
"detail": str(exc).split("[SQL:", 1)[0].strip()[:600] or exc.__class__.__name__,
|
||||
}
|
||||
)
|
||||
logger.warning(
|
||||
"deep-research event persistence degraded; continuing job with a live-only event "
|
||||
"(job=%s, type=%s, phase=%s, error=%s)",
|
||||
self._job_id,
|
||||
type,
|
||||
phase,
|
||||
persistence_error.__class__.__name__,
|
||||
)
|
||||
event = DeepResearchEvent(
|
||||
seq=self._fallback_seq,
|
||||
@@ -100,6 +137,32 @@ class PersistingEventSink:
|
||||
payload={**event_payload, "eventPersistenceDegraded": True},
|
||||
)
|
||||
await self._publish_event(event)
|
||||
if persistence_error is not None:
|
||||
# Keep the original source/progress event live, and additionally
|
||||
# expose one copyable diagnostic frame. This never re-enters the
|
||||
# failing repository and therefore cannot interrupt the job.
|
||||
self._fallback_seq -= 1
|
||||
detail = str(persistence_error).split("[SQL:", 1)[0].strip()[:600]
|
||||
await self._publish_event(
|
||||
DeepResearchEvent(
|
||||
seq=self._fallback_seq,
|
||||
session_id=self._session_id,
|
||||
job_id=self._job_id,
|
||||
type="warning",
|
||||
phase=phase,
|
||||
payload={
|
||||
"code": "event_persistence_degraded",
|
||||
"message": "研究过程事件暂未写入数据库,报告任务已继续运行",
|
||||
"recoverable": True,
|
||||
"diagnostic": {
|
||||
"stage": phase,
|
||||
"eventType": type,
|
||||
"errorType": persistence_error.__class__.__name__,
|
||||
"detail": detail or persistence_error.__class__.__name__,
|
||||
},
|
||||
},
|
||||
)
|
||||
)
|
||||
return event
|
||||
|
||||
async def _publish_event(self, event: DeepResearchEvent) -> None:
|
||||
|
||||
+48
@@ -427,6 +427,54 @@ class DeerFlowCompletionBackend:
|
||||
await self._record_usage(model_name, operation, usage)
|
||||
return CompletionResult(text="".join(text_parts), model=model_name, usage=usage)
|
||||
|
||||
async def complete_prose(
|
||||
self,
|
||||
*,
|
||||
model_role: ModelRole = "smart",
|
||||
messages: list[dict[str, str]],
|
||||
temperature: float | None = None,
|
||||
max_tokens: int | None = None,
|
||||
operation: str = "unknown",
|
||||
) -> CompletionResult:
|
||||
"""Generate long prose without the provider's inter-chunk timeout.
|
||||
|
||||
This is the report retry path. Some reasoning models pause for longer
|
||||
than the streaming client's 120-second chunk deadline after already
|
||||
producing several chunks. A normal complete response can still finish
|
||||
successfully, so the retry deliberately waits for that full response.
|
||||
"""
|
||||
if self._cancel is not None:
|
||||
self._cancel.raise_if_cancelled()
|
||||
|
||||
model = self._get_model(model_role)
|
||||
model_name = self._resolve_model_name(model_role) or "default"
|
||||
kwargs: dict[str, Any] = {}
|
||||
if temperature is not None:
|
||||
kwargs["temperature"] = temperature
|
||||
if max_tokens is not None:
|
||||
from deerflow.models.openai_codex_provider import CodexChatModel
|
||||
|
||||
if not isinstance(model, CodexChatModel):
|
||||
kwargs["max_tokens"] = max_tokens
|
||||
|
||||
isolated_config = _parent_isolated_run_config(f"deep_research:{operation}")
|
||||
reset_parent_config = _clear_inherited_runnable_config(isolated_config)
|
||||
try:
|
||||
response = await model.ainvoke(
|
||||
to_langchain_messages(messages),
|
||||
config=isolated_config,
|
||||
**kwargs,
|
||||
)
|
||||
finally:
|
||||
reset_parent_config()
|
||||
|
||||
if self._cancel is not None:
|
||||
self._cancel.raise_if_cancelled()
|
||||
text = _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)
|
||||
|
||||
# ── usage accounting ────────────────────────────────────────────────────
|
||||
|
||||
async def _record_usage(self, model_name: str, operation: str, usage: dict[str, Any]) -> None:
|
||||
|
||||
Reference in new issue
Block a user