life-echo/api/app/features/evaluation/schemas.py

"""HTTP / OpenAPI 模型。"""

from __future__ import annotations

from datetime import datetime
from typing import Any

from pydantic import BaseModel, ConfigDict, Field


class RegressionSetCreate(BaseModel):
    name: str
    description: str | None = None


class RegressionSetOut(BaseModel):
    model_config = ConfigDict(from_attributes=True)

    id: str
    name: str
    description: str | None
    created_at: datetime


class CaseCreate(BaseModel):
    title: str | None = None
    user_utterances: list[str]
    source_conversation_id: str | None = None
    source_user_id: str | None = None
    reference_memoir_markdown: str | None = None
    is_protected: bool = False
    meta: dict[str, Any] | None = None


class CaseOut(BaseModel):
    model_config = ConfigDict(from_attributes=True)

    id: str
    regression_set_id: str
    source_conversation_id: str | None
    source_user_id: str | None
    title: str | None
    user_utterances: list[Any]
    is_protected: bool
    created_at: datetime


class VersionCreate(BaseModel):
    name: str
    runner_kind: str = "llm_chat_v1"
    config_json: dict[str, Any] | None = None


class VersionOut(BaseModel):
    model_config = ConfigDict(from_attributes=True)

    id: str
    name: str
    runner_kind: str
    config_json: dict[str, Any] | None
    created_at: datetime


class ExperimentCreate(BaseModel):
    name: str
    regression_set_id: str
    baseline_version_id: str
    candidate_version_id: str
    rubric_pack: str = "conversation_v1+memoir_v1"
    composite_weights_json: dict[str, Any] | None = Field(
        default=None,
        description='默认 {"conversation":0.5,"memoir":0.5}',
    )


class ExperimentOut(BaseModel):
    model_config = ConfigDict(from_attributes=True)

    id: str
    name: str
    regression_set_id: str
    baseline_version_id: str
    candidate_version_id: str
    rubric_pack: str
    status: str
    error_message: str | None
    created_at: datetime
    completed_at: datetime | None


class SessionDialogueMessageOut(BaseModel):
    model_config = ConfigDict(from_attributes=True)

    role: str
    content: str
    created_at: datetime | None = None


class SessionDialogueOut(BaseModel):
    conversation_id: str
    messages: list[SessionDialogueMessageOut]


class SessionListItem(BaseModel):
    id: str
    user_id: str
    user_phone: str | None = Field(default=None, description="users.phone，列表展示用")
    started_at: datetime | None
    last_message_at: datetime | None = None
    conversation_stage: str | None
    current_topic: str | None
    status: str | None


class SessionListResponse(BaseModel):
    items: list[SessionListItem]
    total: int


class SessionTranscriptOut(BaseModel):
    conversation_id: str
    user_id: str
    user_utterances_from_segments: list[str]
    user_utterances_from_messages: list[str]


class UserExportFixtureTurnOut(BaseModel):
    user: str
    ai: str


class UserExportFixtureListOut(BaseModel):
    items: list[str]


class MemoirSectionBaselineOut(BaseModel):
    title: str
    body: str


class UserExportFixtureDetailOut(BaseModel):
    filename: str
    turns: list[UserExportFixtureTurnOut]
    source_user_id: str | None = None
    memoir_sections: list[MemoirSectionBaselineOut] = Field(default_factory=list)


class ReplayBootstrapBody(BaseModel):
    user_id: str


class ReplayBootstrapOut(BaseModel):
    conversation_id: str


class EvalSandboxOut(BaseModel):
    """内部评测专用：一次性临时账号 + 空白会话，不落真实手机号业务。"""

    user_id: str
    conversation_id: str
    phone: str
    nickname: str


class ReplayConversationBody(BaseModel):
    conversation_id: str
    fixture_filename: str | None = None
    user_utterances: list[str] | None = None
    flush_memoir_after: bool = True
    skip_tts: bool = True


class ReplayConversationOut(BaseModel):
    conversation_id: str
    turns_replayed: int
    utterances_echo: list[str] = Field(default_factory=list)


class ManualJudgeConversationBody(BaseModel):
    conversation_id: str
    """与当前评测台选中的 MD 一致，供基准 transcript / 整体打分。"""
    fixture_filename: str | None = None


class ManualJudgeConversationStreamBody(BaseModel):
    conversation_id: str
    fixture_filename: str | None = None
    include_turn_judges: bool = False
    """对当前会话逐轮调用评审 LLM（在整体分之后）。"""
    include_baseline_turn_judges: bool = False
    """对导出基线逐轮调用评审 LLM（需 fixture + 整体基线分成功）。"""


class ManualJudgeConversationOut(BaseModel):
    conversation_id: str
    fixture_filename: str | None = None
    baseline_transcript: str = ""
    replay_transcript: str
    baseline_judge: dict[str, Any] | None = None
    replay_judge: dict[str, Any] | None = None
    errors: list[str] = Field(default_factory=list)


class ManualJudgeMemoirBody(BaseModel):
    user_id: str
    baseline_sections: list[MemoirSectionBaselineOut] | None = None


class ManualJudgeMemoirOut(BaseModel):
    user_id: str
    chapter_results: list[dict[str, Any]] = Field(default_factory=list)
    story_results: list[dict[str, Any]] = Field(default_factory=list)


class MemoirChapterSnapOut(BaseModel):
    id: str
    title: str
    category: str | None = None
    order_index: int | None = None
    canonical_markdown: str | None = None


class MemoirStorySnapOut(BaseModel):
    id: str
    title: str
    stage: str | None = None
    canonical_markdown: str | None = None


class UserMemoirSnapshotOut(BaseModel):
    user_id: str
    chapters: list[MemoirChapterSnapOut]
    stories: list[MemoirStorySnapOut]


class SnapshotFromConversationBody(BaseModel):
    title: str | None = None
    use_messages: bool = False
    is_protected: bool = False


class ImportMarkdownBody(BaseModel):
    markdown: str
    title: str | None = None
    is_protected: bool = False


class ImportJsonCaseBody(BaseModel):
    regression_set_id: str
    utterances: list[str] | None = None
    raw_json: dict[str, Any] | list[Any] | None = Field(
        default=None,
        description="与 utterances 二选一：对象含 utterances 键或根数组",
    )
    title: str | None = None
    is_protected: bool = False


class RunTurnOut(BaseModel):
    model_config = ConfigDict(from_attributes=True)

    id: str
    turn_index: int
    user_utterance: str
    assistant_reply: str | None
    duration_ms: int | None
    judge_scores_json: dict[str, Any] | None
    judge_rationale: str | None


class EvalRunOut(BaseModel):
    model_config = ConfigDict(from_attributes=True)

    id: str
    experiment_id: str
    case_id: str
    side: str
    status: str
    error_message: str | None
    memoir_markdown: str | None
    conversation_score_total: float | None
    memoir_score_total: float | None
    composite_score: float | None
    judge_bundle_json: dict[str, Any] | None = None
    turns: list[RunTurnOut] = []


class SessionEvalRunItem(BaseModel):
    experiment_name: str
    run: EvalRunOut


class SessionEvalRunsOut(BaseModel):
    conversation_id: str
    items: list[SessionEvalRunItem]


class GateVerdictOut(BaseModel):
    model_config = ConfigDict(from_attributes=True)

    passed: bool
    mean_composite_delta: float | None
    protected_regressions_json: list[dict[str, Any]] | None
    details_json: dict[str, Any] | None
    computed_at: datetime


class ExperimentDetailOut(BaseModel):
    experiment: ExperimentOut
    runs: list[EvalRunOut]
    gate: GateVerdictOut | None