"""商家条件与逐来源分析合同。"""

from __future__ import annotations

from typing import Literal
from urllib.parse import urlsplit

from pydantic import BaseModel, ConfigDict, Field, field_validator

KNOWLEDGE_ID = "xiaohongshu_prospecting"
BUSINESS_ID = "prospecting"
START_URL = "https://www.xiaohongshu.com/explore"
ALLOWED_DOMAINS = ["www.xiaohongshu.com", "xiaohongshu.com"]
TARGET_QUESTION = "这次先整理多少位候选？"


class ProspectingBrief(BaseModel):
    model_config = ConfigDict(extra="forbid")

    product: str = Field(default="", max_length=300)
    target_customer: str = Field(default="", max_length=300)
    keywords: list[str] = Field(default_factory=list)
    region: str | None = Field(default=None, max_length=100)
    # None means no application-imposed quota. A positive number is an explicit
    # scope chosen by the user, not a default business/runtime budget.
    max_notes: int | None = Field(default=None, ge=1)
    max_comments_per_note: int | None = Field(default=None, ge=0)
    # Desired deliverable, counted by a source-bound person identity. This is
    # distinct from how many notes or comments may be read to find that person.
    target_candidates: int | None = Field(default=None, ge=1, strict=True)
    # Program-grounded deliverable requirements, never guessed from the model's
    # interpretation. Missing optional account/demand fields do not add a gate.
    required_result_fields: list[Literal["xiaohongshu_id", "explicit_demand", "region", "csv"]] = Field(default_factory=list)
    discovery_scope: Literal["candidate_count", "route_pass"] = "candidate_count"
    use_web_search: bool = False
    user_notes: str = Field(default="", max_length=2000)
    intent: Literal["discover", "research", "inspect", "export", "follow", "message"] = "discover"
    subject_urls: list[str] = Field(default_factory=list)
    action_scope: str = Field(default="", max_length=2000)
    message_text: str = Field(default="", max_length=2000)

    @field_validator("product", "target_customer")
    @classmethod
    def trim_text(cls, value: str) -> str:
        return value.strip()

    @field_validator("region")
    @classmethod
    def normalize_region(cls, value: str | None) -> str | None:
        return value.strip() or None if value else None

    @field_validator("keywords")
    @classmethod
    def normalize_keywords(cls, values: list[str]) -> list[str]:
        result = list(dict.fromkeys(value.strip() for value in values if value.strip()))
        if any(len(value) > 80 for value in result):
            raise ValueError("每个搜索词最多 80 字")
        return result

    @field_validator("subject_urls")
    @classmethod
    def validate_subject_urls(cls, values: list[str]) -> list[str]:
        clean = list(dict.fromkeys(value.strip() for value in values if value.strip()))
        for url in clean:
            parts = urlsplit(url)
            if parts.scheme != "https" or parts.hostname not in {"www.xiaohongshu.com", "xiaohongshu.com", "xhslink.com", "www.xhslink.com"} or parts.username or parts.password:
                raise ValueError("请提供实际小红书 HTTPS 页面或分享链接")
        return clean

    def missing(self) -> list[str]:
        if self.intent in {"follow", "message"}:
            missing = [] if self.action_scope or self.subject_urls else ["要操作的对象范围"]
            if self.intent == "message" and not self.message_text:
                missing.append("私信内容")
            return missing
        if self.intent == "export":
            return []  # Existing sources can be exported without a business profile.
        missing = [] if self.subject_urls or self.keywords or self.target_customer or self.user_notes else ["想完成的任务"]
        # An explicitly bounded read/page task already has an endpoint. Legacy
        # default note limits are removed by the orchestrator before this check.
        if (self.intent == "discover" and self.target_candidates is None
                and self.discovery_scope == "candidate_count" and self.max_notes is None
                and not self.subject_urls):
            missing.append(TARGET_QUESTION)
        return missing


class IntentPlan(BaseModel):
    """A model interpretation, never an authorization to send or follow."""

    model_config = ConfigDict(extra="forbid")
    brief: ProspectingBrief
    summary: str = Field(min_length=1, max_length=1000)
    stages: list[str] = Field(default_factory=list)
    missing: list[str] = Field(default_factory=list)
    assumptions: list[str] = Field(default_factory=list)
    reuse_existing_sources: bool = False


class SourceDecision(BaseModel):
    model_config = ConfigDict(extra="forbid")

    source_id: str
    decision: Literal["keep", "exclude", "unclear"]
    quote: str = Field(max_length=1500)
    reason: str = Field(min_length=1, max_length=1000)
    demand_stage: Literal["unknown", "planning", "in_progress", "completed"] = "unknown"
    seeking_service: Literal["yes", "no", "unknown"] = "unknown"
    region_match: Literal["yes", "no", "unknown"] = "unknown"
    region_quote: str = Field(default="", max_length=500)


class AnalysisOutput(BaseModel):
    model_config = ConfigDict(extra="forbid")

    results: list[SourceDecision]
    summary: str = Field(default="", max_length=2000)