147 lines
5.9 KiB
Python
147 lines
5.9 KiB
Python
"""统一意图分类出口，业务 Agent 不得自行解析模型分类结果。
|
||
|
||
运行期可选的配置来源是 `agent_intent_config` 中 `status='active'` 的行：装载后只用于
|
||
**增强分类提示与置信度阈值**，不改变任何既有契约——仍然是严格 JSON 输出、格式违约与
|
||
未声明意图一律失败关闭、意图必须落在 `AgentDefinition.supported_intents` 内、
|
||
`needs_clarification = confidence < 阈值`。
|
||
"""
|
||
|
||
import json
|
||
from collections.abc import Awaitable, Callable
|
||
from typing import Any, Protocol
|
||
|
||
from pydantic import BaseModel, ConfigDict, Field, ValidationError
|
||
|
||
from app.core.contracts import IntentResult
|
||
from app.core.errors import RecoverableAgentError, ValidationAgentError
|
||
from app.service.model_gateway import ModelGenerationService
|
||
|
||
|
||
class IntentEndpointResolver(Protocol):
|
||
async def resolve(self, *, agent_type: str, task_type: str) -> list[Any]: ...
|
||
|
||
|
||
class IntentConfigEntry(BaseModel):
|
||
"""`agent_intent_config` 生效行在分类链路上的投影（只带分类用得到的字段）。"""
|
||
|
||
model_config = ConfigDict(frozen=True)
|
||
|
||
intent_code: str = Field(min_length=1, max_length=64)
|
||
intent_name: str = Field(default="", max_length=128)
|
||
description: str | None = Field(default=None, max_length=500)
|
||
examples: tuple[str, ...] = ()
|
||
classifier_instruction: str | None = None
|
||
confidence_threshold: float = Field(default=0.6, ge=0, le=1)
|
||
|
||
|
||
# 装载器按 `agent_type` 读取当前生效的意图配置；无配置时返回空元组。
|
||
IntentConfigLoader = Callable[[str], Awaitable[tuple[IntentConfigEntry, ...]]]
|
||
|
||
|
||
class _IntentPayload(BaseModel):
|
||
model_config = ConfigDict(extra="forbid")
|
||
|
||
intent: str = Field(min_length=1, max_length=64)
|
||
confidence: float = Field(ge=0, le=1)
|
||
|
||
|
||
class IntentClassifier:
|
||
"""使用已路由模型输出严格 JSON，并绑定 Agent 声明的意图集合。"""
|
||
|
||
def __init__(
|
||
self,
|
||
model_service: ModelGenerationService,
|
||
*,
|
||
threshold: float = 0.65,
|
||
config_loader: IntentConfigLoader | None = None,
|
||
) -> None:
|
||
if not 0 <= threshold <= 1:
|
||
raise ValueError("intent threshold must be between 0 and 1")
|
||
self.model_service = model_service
|
||
self.threshold = threshold
|
||
self._config_loader = config_loader
|
||
|
||
@property
|
||
def config_loader(self) -> IntentConfigLoader | None:
|
||
"""暴露装载器便于装配自检（生产装配必须注入，测试可缺省）。"""
|
||
return self._config_loader
|
||
|
||
async def classify(
|
||
self,
|
||
*,
|
||
message: str,
|
||
supported_intents: tuple[str, ...],
|
||
endpoints: list[Any],
|
||
agent_type: str | None = None,
|
||
) -> IntentResult:
|
||
if not message.strip():
|
||
raise ValidationAgentError("待分类消息不能为空")
|
||
if not supported_intents:
|
||
raise ValidationAgentError("Agent 未声明支持的意图")
|
||
# 只认 AgentDefinition 声明过的意图：配置里多出来的意图既不进提示，也不放宽校验。
|
||
loaded = await self._load(agent_type)
|
||
configured = tuple(
|
||
entry for entry in loaded if entry.intent_code in supported_intents
|
||
)
|
||
prompt = self._build_prompt(message, supported_intents, configured)
|
||
execution = await self.model_service.generate(endpoints, prompt)
|
||
payload = self._parse(execution.text)
|
||
if payload.intent not in supported_intents:
|
||
raise ValidationAgentError("模型返回了未声明的意图")
|
||
return IntentResult(
|
||
intent=payload.intent,
|
||
confidence=payload.confidence,
|
||
needs_clarification=payload.confidence
|
||
< self._threshold_for(payload.intent, configured),
|
||
)
|
||
|
||
async def _load(self, agent_type: str | None) -> tuple[IntentConfigEntry, ...]:
|
||
if self._config_loader is None or agent_type is None:
|
||
return ()
|
||
return await self._config_loader(agent_type)
|
||
|
||
def _threshold_for(self, intent: str, configured: tuple[IntentConfigEntry, ...]) -> float:
|
||
"""阈值语义不变（confidence < 阈值 → 需澄清），阈值取值优先生效配置。"""
|
||
for entry in configured:
|
||
if entry.intent_code == intent:
|
||
return entry.confidence_threshold
|
||
return self.threshold
|
||
|
||
@staticmethod
|
||
def _build_prompt(
|
||
message: str,
|
||
supported_intents: tuple[str, ...],
|
||
configured: tuple[IntentConfigEntry, ...],
|
||
) -> str:
|
||
lines = [
|
||
"请仅输出 JSON，不要 Markdown。字段必须为 intent 和 confidence。",
|
||
f"intent 只能从 {list(supported_intents)!r} 中选择，confidence 为 0 到 1 的数字。",
|
||
]
|
||
if configured:
|
||
lines.append("平台配置的意图说明：")
|
||
for entry in configured:
|
||
detail = f"- {entry.intent_code}"
|
||
if entry.intent_name:
|
||
detail += f"（{entry.intent_name}）"
|
||
if entry.description:
|
||
detail += f"：{entry.description}"
|
||
if entry.examples:
|
||
detail += f"；示例：{' / '.join(entry.examples)}"
|
||
lines.append(detail)
|
||
if entry.classifier_instruction:
|
||
lines.append(f" 分类要求：{entry.classifier_instruction}")
|
||
lines.append(f"用户消息：{message}")
|
||
return "\n".join(lines)
|
||
|
||
@staticmethod
|
||
def _parse(text: str) -> _IntentPayload:
|
||
candidate = text.strip()
|
||
if candidate.startswith("```"):
|
||
candidate = candidate.removeprefix("```")
|
||
candidate = candidate.removeprefix("json").removesuffix("```").strip()
|
||
try:
|
||
value = json.loads(candidate)
|
||
return _IntentPayload.model_validate(value)
|
||
except (json.JSONDecodeError, ValidationError, TypeError) as exc:
|
||
raise RecoverableAgentError("模型意图输出不是有效 JSON") from exc
|