feat: 回忆录证据血缘与内部评测可追溯，顺带对齐本地评测台与 CI
数据库与模型：新增多版迁移（章节证据快照、对话血缘、记忆事实/时间线 lineage 等），把「成稿 ↔ 对话/记忆」的溯源信息落到表结构里。 业务链路：会话与 WS、回忆录/故事流水线、记忆写入与 enrichment 等跟着接上线索与快照；新增章节证据快照与评测侧 EvalTraceService 等模块，方便组评审用的证据包。 内部评测：自动化 run 与手工 memoir 评审共用可追溯证据；rubric/ judge 相关脚本与文档有配套调整。 app-eval-web：Memoir/实验详情里能展开看证据摘要与 evidence_trace（含对话轮次 id）；Vite 代理与 development.sh 注入的 API 端口与当前默认内部评测端口一致，避免改端口后页面连错服务。 工程杂项：GitHub Actions / 仓库说明有更新；各适配器与支付/配额/plan 等多处为小改动或跟随主改动的收尾；新增/扩充了?
This commit is contained in:
Kevin
182
api/app/features/conversation/lineage_schemas.py
Normal file
182
api/app/features/conversation/lineage_schemas.py
Normal file
@@ -0,0 +1,182 @@
|
||||
"""Canonical dialogue lineage (message-grade provenance) for memory, story, chapter, eval."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Sequence
|
||||
|
||||
from pydantic import BaseModel, Field, field_validator
|
||||
|
||||
LINEAGE_SCHEMA_VERSION = 1
|
||||
|
||||
|
||||
class DialogueTurnRef(BaseModel):
|
||||
"""One interview beat: user message paired with assistant reply (if any)."""
|
||||
|
||||
user_message_id: str
|
||||
assistant_message_id: str | None = None
|
||||
|
||||
|
||||
class DialogueLineage(BaseModel):
|
||||
"""
|
||||
Multi-turn provenance. `turns` order is chronological within the contributing slice.
|
||||
"""
|
||||
|
||||
schema_version: int = Field(default=LINEAGE_SCHEMA_VERSION, ge=1)
|
||||
conversation_id: str
|
||||
turns: list[DialogueTurnRef] = Field(default_factory=list)
|
||||
primary_user_message_id: str | None = None
|
||||
segment_ids: list[str] = Field(default_factory=list)
|
||||
|
||||
@field_validator("turns")
|
||||
@classmethod
|
||||
def _non_empty_user_ids(cls, v: list[DialogueTurnRef]) -> list[DialogueTurnRef]:
|
||||
for t in v:
|
||||
if not (t.user_message_id or "").strip():
|
||||
raise ValueError("turn.user_message_id must be non-empty")
|
||||
return v
|
||||
|
||||
def model_dump_json_safe(self) -> dict[str, Any]:
|
||||
return self.model_dump(mode="json")
|
||||
|
||||
@classmethod
|
||||
def for_single_turn(
|
||||
cls,
|
||||
*,
|
||||
conversation_id: str,
|
||||
user_message_id: str,
|
||||
assistant_message_id: str | None,
|
||||
segment_ids: list[str] | None = None,
|
||||
) -> DialogueLineage:
|
||||
return cls(
|
||||
conversation_id=conversation_id,
|
||||
turns=[
|
||||
DialogueTurnRef(
|
||||
user_message_id=user_message_id,
|
||||
assistant_message_id=assistant_message_id,
|
||||
)
|
||||
],
|
||||
primary_user_message_id=user_message_id,
|
||||
segment_ids=list(segment_ids or []),
|
||||
)
|
||||
|
||||
|
||||
def parse_dialogue_lineage(raw: Any) -> DialogueLineage | None:
|
||||
if raw is None:
|
||||
return None
|
||||
if isinstance(raw, DialogueLineage):
|
||||
return raw
|
||||
if not isinstance(raw, dict):
|
||||
return None
|
||||
try:
|
||||
return DialogueLineage.model_validate(raw)
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
|
||||
def primary_user_message_id_from_lineage(raw: Any) -> str | None:
|
||||
ln = parse_dialogue_lineage(raw)
|
||||
if ln is None:
|
||||
return None
|
||||
if ln.primary_user_message_id:
|
||||
return ln.primary_user_message_id
|
||||
if ln.turns:
|
||||
return ln.turns[0].user_message_id
|
||||
return None
|
||||
|
||||
|
||||
def merge_dialogue_lineages(
|
||||
lineages: Sequence[DialogueLineage | dict | None],
|
||||
*,
|
||||
conversation_id: str,
|
||||
segment_ids_ordered: list[str] | None = None,
|
||||
) -> DialogueLineage | None:
|
||||
"""Ordered union of turns; dedupe by user_message_id (first occurrence wins)."""
|
||||
turns_out: list[DialogueTurnRef] = []
|
||||
seen_user: set[str] = set()
|
||||
segments_accum: list[str] = []
|
||||
|
||||
for raw in lineages:
|
||||
ln = parse_dialogue_lineage(raw)
|
||||
if ln is None:
|
||||
continue
|
||||
for sid in ln.segment_ids:
|
||||
if sid and sid not in segments_accum:
|
||||
segments_accum.append(sid)
|
||||
for t in ln.turns:
|
||||
uid = t.user_message_id.strip()
|
||||
if not uid or uid in seen_user:
|
||||
continue
|
||||
seen_user.add(uid)
|
||||
turns_out.append(
|
||||
DialogueTurnRef(
|
||||
user_message_id=uid,
|
||||
assistant_message_id=t.assistant_message_id,
|
||||
)
|
||||
)
|
||||
|
||||
if segment_ids_ordered:
|
||||
for sid in segment_ids_ordered:
|
||||
if sid and sid not in segments_accum:
|
||||
segments_accum.append(sid)
|
||||
|
||||
if not turns_out:
|
||||
return None
|
||||
|
||||
return DialogueLineage(
|
||||
conversation_id=conversation_id,
|
||||
turns=turns_out,
|
||||
primary_user_message_id=turns_out[0].user_message_id,
|
||||
segment_ids=segments_accum,
|
||||
)
|
||||
|
||||
|
||||
def aggregate_lineage_from_segments(
|
||||
segments: Sequence[Any],
|
||||
*,
|
||||
conversation_id_fallback: str | None = None,
|
||||
) -> dict[str, Any] | None:
|
||||
"""
|
||||
Build merged lineage dict from ORM segments (expects .id, .conversation_id,
|
||||
.lineage_json, optional .user_message_id).
|
||||
"""
|
||||
if not segments:
|
||||
return None
|
||||
conv0 = conversation_id_fallback or getattr(
|
||||
segments[0], "conversation_id", None
|
||||
) or ""
|
||||
if not conv0:
|
||||
lj0 = getattr(segments[0], "lineage_json", None)
|
||||
if isinstance(lj0, dict) and lj0.get("conversation_id"):
|
||||
conv0 = str(lj0["conversation_id"])
|
||||
if not conv0:
|
||||
return None
|
||||
|
||||
lineages: list[DialogueLineage | dict | None] = []
|
||||
seg_ids_order: list[str] = []
|
||||
for seg in segments:
|
||||
sid = str(getattr(seg, "id", "") or "")
|
||||
if sid:
|
||||
seg_ids_order.append(sid)
|
||||
lj = getattr(seg, "lineage_json", None)
|
||||
if lj:
|
||||
lineages.append(lj)
|
||||
else:
|
||||
um = getattr(seg, "user_message_id", None)
|
||||
if um:
|
||||
lineages.append(
|
||||
DialogueLineage.for_single_turn(
|
||||
conversation_id=str(
|
||||
getattr(seg, "conversation_id", None) or conv0
|
||||
),
|
||||
user_message_id=str(um),
|
||||
assistant_message_id=None,
|
||||
segment_ids=[sid] if sid else None,
|
||||
)
|
||||
)
|
||||
|
||||
merged = merge_dialogue_lineages(
|
||||
lineages, conversation_id=str(conv0), segment_ids_ordered=seg_ids_order
|
||||
)
|
||||
if merged is None:
|
||||
return None
|
||||
return merged.model_dump_json_safe()
|
||||
Reference in New Issue
Block a user