feat: 报告结构支持检索方向/来源与智能新增,并修复协助卡停轮与宿主跳转

为深度研究报告结构增加检索方向与技能来源、对话式智能新增页与详情排版;澄清中间件在 after_model 可靠结束本轮,避免弱模型出卡后继续生成;任务按钮补充 host 跳转与相关深链能力。

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
董宏凯andCursor committed 2026-08-22 17:46:06 +08:00
1 parent a5a9c952e8
commit 51afebb394
67 files changed
+4511 -699

No files matched your search

@@ -0,0 +1,49 @@
"""Add structure_mode to report_structures.
Per-structure 结构约束: ``fixed`` (固定大纲) vs ``adaptive`` (弹性大纲).
Existing rows stay ``adaptive`` so current writing behaviour is unchanged.
``create_all`` adds the column for brand-new DBs; the startup
``_ensure_orm_columns_sync`` sweep adds it to already-existing tables.
Revision ID: 20260821_01
Revises: 20260819_02
Create Date: 2026-08-21
"""
from __future__ import annotations
import sqlalchemy as sa
from alembic import op
from sqlalchemy import inspect
revision = "20260821_01"
down_revision = "20260819_02"
branch_labels = None
depends_on = None
def _has_table(table_name: str) -> bool:
inspector = inspect(op.get_bind())
return table_name in inspector.get_table_names()
def _has_column(table_name: str, column_name: str) -> bool:
if not _has_table(table_name):
return False
inspector = inspect(op.get_bind())
return any(col["name"] == column_name for col in inspector.get_columns(table_name))
def upgrade() -> None:
if _has_table("report_structures") and not _has_column("report_structures", "structure_mode"):
op.add_column(
"report_structures",
sa.Column("structure_mode", sa.String(length=16), nullable=False, server_default="adaptive"),
)
def downgrade() -> None:
if _has_column("report_structures", "structure_mode"):
op.drop_column("report_structures", "structure_mode")
@@ -0,0 +1,52 @@
"""Add retrieval_directions to report_structures.
Optional 检索方向 list on each 报告结构. Empty / NULL keeps today's
collector query-planning; a non-empty list tells material collection to
search along those facets.
ORM: ``ReportStructureRow.retrieval_directions = PortableJSON()``
(SQLite/PG native JSON, MySQL TEXT). ``create_all`` adds the column on
brand-new DBs; existing tables are patched by startup
``_ensure_orm_columns_sync`` (nullable, no server_default required).
Revision ID: 20260822_01
Revises: 20260821_01
Create Date: 2026-08-22
"""
from __future__ import annotations
import sqlalchemy as sa
from alembic import op
from sqlalchemy import inspect
revision = "20260822_01"
down_revision = "20260821_01"
branch_labels = None
depends_on = None
def _has_table(table_name: str) -> bool:
inspector = inspect(op.get_bind())
return table_name in inspector.get_table_names()
def _has_column(table_name: str, column_name: str) -> bool:
if not _has_table(table_name):
return False
inspector = inspect(op.get_bind())
return any(col["name"] == column_name for col in inspector.get_columns(table_name))
def upgrade() -> None:
if _has_table("report_structures") and not _has_column("report_structures", "retrieval_directions"):
op.add_column(
"report_structures",
sa.Column("retrieval_directions", sa.Text(), nullable=True),
)
def downgrade() -> None:
if _has_column("report_structures", "retrieval_directions"):
op.drop_column("report_structures", "retrieval_directions")
@@ -0,0 +1,52 @@
"""Add retrieval_skills to report_structures.
Optional 检索来源 list of skill names on each 报告结构. Empty / NULL keeps
today's collector tools; a non-empty list tells material collection to
call those skills.
ORM: ``ReportStructureRow.retrieval_skills = PortableJSON()``
(SQLite/PG native JSON, MySQL TEXT). ``create_all`` adds the column on
brand-new DBs; existing tables are patched by startup
``_ensure_orm_columns_sync`` (nullable, no server_default required).
Revision ID: 20260822_02
Revises: 20260822_01
Create Date: 2026-08-22
"""
from __future__ import annotations
import sqlalchemy as sa
from alembic import op
from sqlalchemy import inspect
revision = "20260822_02"
down_revision = "20260822_01"
branch_labels = None
depends_on = None
def _has_table(table_name: str) -> bool:
inspector = inspect(op.get_bind())
return table_name in inspector.get_table_names()
def _has_column(table_name: str, column_name: str) -> bool:
if not _has_table(table_name):
return False
inspector = inspect(op.get_bind())
return any(col["name"] == column_name for col in inspector.get_columns(table_name))
def upgrade() -> None:
if _has_table("report_structures") and not _has_column("report_structures", "retrieval_skills"):
op.add_column(
"report_structures",
sa.Column("retrieval_skills", sa.Text(), nullable=True),
)
def downgrade() -> None:
if _has_column("report_structures", "retrieval_skills"):
op.drop_column("report_structures", "retrieval_skills")
@@ -63,6 +63,7 @@ from deerflow.persistence.position_roundtable.model import (
)
from deerflow.persistence.positions.model import PositionRow, PositionTagBindingRow
from deerflow.persistence.recommended_questions.model import RecommendedQuestionRow
from deerflow.persistence.report_structures.model import ReportStructureRow
from deerflow.persistence.research_templates.model import ResearchTemplateRow
from deerflow.persistence.roundtable_artifact_submissions.model import RoundtableArtifactSubmissionRow
from deerflow.persistence.roundtable_chains.model import RoundtableChainRow
@@ -135,6 +136,7 @@ __all__ = [
"PositionRow",
"PositionTagBindingRow",
"RecommendedQuestionRow",
"ReportStructureRow",
"ResearchTemplateRow",
"RoundtableChainRow",
"RoundtableArtifactSubmissionRow",
@@ -5,14 +5,44 @@ from __future__ import annotations
from deerflow.persistence.report_structures.base import ReportStructureStore
from deerflow.persistence.report_structures.memory import MemoryReportStructureStore
from deerflow.persistence.report_structures.model import ReportStructureRow
from deerflow.persistence.report_structures.directions import (
MAX_DIRECTION_CHARS,
MAX_RETRIEVAL_DIRECTIONS,
normalize_retrieval_directions,
)
from deerflow.persistence.report_structures.skills import (
MAX_RETRIEVAL_SKILLS,
MAX_SKILL_NAME_CHARS,
normalize_retrieval_skills,
)
from deerflow.persistence.report_structures.modes import (
DEFAULT_STRUCTURE_MODE,
STRUCTURE_MODE_ADAPTIVE,
STRUCTURE_MODE_FIXED,
STRUCTURE_MODES,
StructureMode,
normalize_structure_mode,
)
from deerflow.persistence.report_structures.sql import ReportStructureRepository
__all__ = [
"DEFAULT_STRUCTURE_MODE",
"MemoryReportStructureStore",
"ReportStructureRepository",
"ReportStructureRow",
"ReportStructureStore",
"STRUCTURE_MODE_ADAPTIVE",
"STRUCTURE_MODE_FIXED",
"STRUCTURE_MODES",
"StructureMode",
"MAX_DIRECTION_CHARS",
"MAX_RETRIEVAL_DIRECTIONS",
"MAX_RETRIEVAL_SKILLS",
"MAX_SKILL_NAME_CHARS",
"make_report_structure_store",
"normalize_retrieval_directions",
"normalize_retrieval_skills",
"normalize_structure_mode",
]
@@ -31,12 +31,12 @@ class ReportStructureStore(ABC):
@abstractmethod
async def create_structure(self, data: dict[str, Any]) -> dict[str, Any]:
"""Insert ``{id, title, name, content, created_by}`` (enabled forced True)."""
"""Insert ``{id, title, name, content, structure_mode, retrieval_directions, retrieval_skills, created_by}`` (enabled forced True)."""
raise NotImplementedError
@abstractmethod
async def update_structure(self, structure_id: str, data: dict[str, Any]) -> dict[str, Any] | None:
"""Update any of ``title`` / ``name`` / ``content``. None when missing."""
"""Update any of ``title`` / ``name`` / ``content`` / ``structure_mode`` / ``retrieval_directions`` / ``retrieval_skills``. None when missing."""
raise NotImplementedError
@abstractmethod
@@ -0,0 +1,65 @@
"""Normalize the optional 检索方向 list stored on a report structure.
Kept next to the ORM column so the store / API can round-trip a JSON list
without importing the Deep Research runtime. Empty → original collection path.
"""
from __future__ import annotations
import json
from typing import Any
MAX_RETRIEVAL_DIRECTIONS = 12
MAX_DIRECTION_CHARS = 200
_EMPTY_TOKENS = frozenset({"", "[]", "{}", "null", "none", "undefined"})
def _coerce_listish(value: Any) -> list[Any]:
"""Flatten model-produced JSON strings like ``"[]"`` / ``'["a","b"]'`` into a list."""
if value is None or isinstance(value, bool):
return []
if isinstance(value, (list, tuple)):
return list(value)
if isinstance(value, str):
text = value.strip()
if text.casefold() in _EMPTY_TOKENS:
return []
if text[:1] in "[{":
try:
parsed = json.loads(text)
except (json.JSONDecodeError, TypeError, ValueError):
return [value]
if parsed is None:
return []
if isinstance(parsed, list):
return parsed
return []
return [value]
return []
def normalize_retrieval_directions(value: Any) -> list[str]:
"""Return a de-duplicated, bounded list of retrieval-direction strings.
``None`` / empty / unusable input → ``[]`` (callers keep the original
query-planning path). Newlines inside a single item are flattened so the
collector prompt and search queries stay one-line.
"""
parts = _coerce_listish(value)
seen: set[str] = set()
out: list[str] = []
for item in parts:
text = " ".join(str(item).replace("\x00", "").replace("\r", "").split()).strip()
if not text or text.casefold() in _EMPTY_TOKENS:
continue
text = text[:MAX_DIRECTION_CHARS]
key = text.casefold()
if key in seen:
continue
seen.add(key)
out.append(text)
if len(out) >= MAX_RETRIEVAL_DIRECTIONS:
break
return out
@@ -6,6 +6,9 @@ from datetime import UTC, datetime
from typing import Any
from deerflow.persistence.report_structures.base import ReportStructureStore
from deerflow.persistence.report_structures.directions import normalize_retrieval_directions
from deerflow.persistence.report_structures.skills import normalize_retrieval_skills
from deerflow.persistence.report_structures.modes import normalize_structure_mode
def _now_iso() -> str:
@@ -33,6 +36,9 @@ class MemoryReportStructureStore(ReportStructureStore):
"title": str(data.get("title") or ""),
"name": str(data.get("name") or ""),
"content": str(data.get("content") or ""),
"structure_mode": normalize_structure_mode(data.get("structure_mode")),
"retrieval_directions": normalize_retrieval_directions(data.get("retrieval_directions")),
"retrieval_skills": normalize_retrieval_skills(data.get("retrieval_skills")),
"enabled": True,
"created_by": data.get("created_by"),
"created_at": _now_iso(),
@@ -48,6 +54,12 @@ class MemoryReportStructureStore(ReportStructureStore):
for key in ("title", "name", "content"):
if key in data:
row[key] = str(data[key])
if "structure_mode" in data:
row["structure_mode"] = normalize_structure_mode(data["structure_mode"])
if "retrieval_directions" in data:
row["retrieval_directions"] = normalize_retrieval_directions(data["retrieval_directions"])
if "retrieval_skills" in data:
row["retrieval_skills"] = normalize_retrieval_skills(data["retrieval_skills"])
row["updated_at"] = _now_iso()
return dict(row)
@@ -8,6 +8,16 @@ structure the user can pick to fill ``custom_outline``:
- ``name`` — 名称, a secondary display label.
- ``content`` — 接口内容, the Markdown outline text applied to the research
config's ``custom_outline`` when the card is selected.
- ``structure_mode`` — 结构约束: ``fixed`` (固定大纲) reproduces the stored
headings and hierarchy; ``adaptive`` (弹性大纲) keeps the current
material-driven layout. Existing rows default to ``adaptive``.
- ``retrieval_directions`` — 检索方向, an optional list of search facets.
Empty / unset keeps today's collector query-planning; a non-empty list
tells material collection to **split retrievable terms along those
directions** (not to search the labels themselves).
- ``retrieval_skills`` — 检索来源, an optional list of skill names. Empty /
unset keeps today's collector tools; a non-empty list tells material
collection to call those skills.
- ``enabled`` — 启用/停用; creation always defaults to True (the caller cannot
choose it) and a dedicated toggle flips it later.
- ``created_by`` — 创建用户名 (audit-only display field).
@@ -24,7 +34,7 @@ from sqlalchemy import Boolean, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime
from deerflow.persistence.types import BeijingDateTime, PortableJSON
class ReportStructureRow(Base):
@@ -37,6 +47,13 @@ class ReportStructureRow(Base):
# ``server_default`` 必须显式声明:否则在已存在该表但缺列的旧库上,启动期
# ``_ensure_orm_columns_sync`` 会跳过「NOT NULL 且无 server_default」的列(见
# engine.py),该列永远补不上 → 查询报 Unknown column → 500。
structure_mode: Mapped[str] = mapped_column(
String(16), nullable=False, default="adaptive", server_default="adaptive"
)
# Nullable JSON so ``_ensure_orm_columns_sync`` can ADD COLUMN on existing
# tables. ``None`` / missing reads as an empty list at the store boundary.
retrieval_directions: Mapped[list | None] = mapped_column(PortableJSON(), default=list, nullable=True)
retrieval_skills: Mapped[list | None] = mapped_column(PortableJSON(), default=list, nullable=True)
enabled: Mapped[bool] = mapped_column(Boolean, nullable=False, default=True, server_default="1")
created_by: Mapped[str | None] = mapped_column(String(128), nullable=True)
created_at: Mapped[datetime] = mapped_column(BeijingDateTime(), nullable=False, default=lambda: datetime.now(UTC))
@@ -0,0 +1,25 @@
"""Report-structure writing constraint (结构约束).
``fixed`` — 固定大纲: the writer must reproduce the stored outline's headings
and hierarchy. ``adaptive`` — 弹性大纲: keep the current, material-driven
layout (sections without evidence may be merged or omitted).
"""
from __future__ import annotations
from typing import Any, Literal
StructureMode = Literal["fixed", "adaptive"]
STRUCTURE_MODE_FIXED: StructureMode = "fixed"
STRUCTURE_MODE_ADAPTIVE: StructureMode = "adaptive"
STRUCTURE_MODES: tuple[StructureMode, ...] = (STRUCTURE_MODE_FIXED, STRUCTURE_MODE_ADAPTIVE)
DEFAULT_STRUCTURE_MODE: StructureMode = STRUCTURE_MODE_ADAPTIVE
def normalize_structure_mode(value: Any) -> StructureMode:
"""Coerce unknown / legacy values to a supported mode. Default is adaptive."""
raw = str(value or "").strip().lower()
if raw in {"fixed", "canonical", "prescriptive", "rigid"}:
return STRUCTURE_MODE_FIXED
return STRUCTURE_MODE_ADAPTIVE
@@ -0,0 +1,40 @@
"""Normalize the optional 检索技能 list stored on a report structure.
Skill names (hyphen-case ids) are the retrieval *source*. Empty → original
collection path (collector web_search / default Q&A research skills).
"""
from __future__ import annotations
from typing import Any
from deerflow.persistence.report_structures.directions import _EMPTY_TOKENS, _coerce_listish
MAX_RETRIEVAL_SKILLS = 8
MAX_SKILL_NAME_CHARS = 64
def normalize_retrieval_skills(value: Any) -> list[str]:
"""Return a de-duplicated, bounded list of skill names.
``None`` / empty / unusable input → ``[]`` (callers keep the original
collection path). Whitespace inside a name is rejected so the collector
allowlist and ``skill_view`` lookups stay exact folder ids.
"""
parts = _coerce_listish(value)
seen: set[str] = set()
out: list[str] = []
for item in parts:
text = str(item).replace("\x00", "").replace("\r", "").replace("\n", "").strip()
if not text or text.casefold() in _EMPTY_TOKENS or any(ch.isspace() for ch in text):
continue
text = text[:MAX_SKILL_NAME_CHARS]
key = text.casefold()
if key in seen:
continue
seen.add(key)
out.append(text)
if len(out) >= MAX_RETRIEVAL_SKILLS:
break
return out
@@ -11,7 +11,10 @@ from sqlalchemy.exc import IntegrityError
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker
from deerflow.persistence.report_structures.base import ReportStructureStore
from deerflow.persistence.report_structures.directions import normalize_retrieval_directions
from deerflow.persistence.report_structures.skills import normalize_retrieval_skills
from deerflow.persistence.report_structures.model import ReportStructureRow
from deerflow.persistence.report_structures.modes import normalize_structure_mode
logger = logging.getLogger(__name__)
@@ -22,6 +25,8 @@ def _to_dict(row: ReportStructureRow) -> dict[str, Any]:
value = data.get(key)
if isinstance(value, datetime):
data[key] = value.isoformat()
data["retrieval_directions"] = normalize_retrieval_directions(data.get("retrieval_directions"))
data["retrieval_skills"] = normalize_retrieval_skills(data.get("retrieval_skills"))
return data
@@ -49,6 +54,9 @@ class ReportStructureRepository(ReportStructureStore):
title=str(data.get("title") or ""),
name=str(data.get("name") or ""),
content=str(data.get("content") or ""),
structure_mode=normalize_structure_mode(data.get("structure_mode")),
retrieval_directions=normalize_retrieval_directions(data.get("retrieval_directions")),
retrieval_skills=normalize_retrieval_skills(data.get("retrieval_skills")),
# 创建永远默认启用(前端不提供该项填写)。
enabled=True,
created_by=data.get("created_by"),
@@ -69,6 +77,12 @@ class ReportStructureRepository(ReportStructureStore):
for key in ("title", "name", "content"):
if key in data:
setattr(row, key, str(data[key]))
if "structure_mode" in data:
row.structure_mode = normalize_structure_mode(data["structure_mode"])
if "retrieval_directions" in data:
row.retrieval_directions = normalize_retrieval_directions(data["retrieval_directions"])
if "retrieval_skills" in data:
row.retrieval_skills = normalize_retrieval_skills(data["retrieval_skills"])
row.updated_at = datetime.now(UTC)
await session.commit()
await session.refresh(row)
@@ -8,8 +8,10 @@ left task panel. Each row is one button:
- ``business`` — which workspace the button belongs to (``rwfx`` / ``3qfx`` /
``xdfx``).
- ``label`` — display name.
- ``link_type`` — ``url`` (external, opened in a new tab) or ``business``
(internal switch to another deep-link business).
- ``link_type`` — ``url`` (external / in-app route), ``business``
(internal switch to another deep-link business), ``purpose`` (task-purpose
dialog), or ``host`` (iframe ``postMessage`` ``HOST_NAVIGATE`` to the
embedding host).
- ``target`` — the full URL (``url``) or the target business code (``business``).
- ``append_task_id`` — for ``url`` buttons, whether to append ``?id={taskId}``.
- ``enabled`` — 停用 parks a button without deleting it.