feat(llm): провайдер за протоколом — OpenAI-совместимый API и mock, фабрика по конфигу

- LLMProvider: complete(messages, schema) -> LLMResult (текст, разобранный JSON, токены)
- openai_compat: /chat/completions, structured output через response_format json_schema,
  JSON из ```-обёртки тоже разбирается; ретраи на 429/5xx и сетевые ошибки, 4xx — сразу ошибка
- mock: детерминированные правила для тестов и демо без сети
- LLMSettings (LLM_PROVIDER/BASE_URL/MODEL/API_KEY…), CLI python -m app.llm.cli

Refs #17

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

app/llm/provider.py

@@ -0,0 +1,45 @@
+"""LLM provider contract (ADR-008): the rest of the bot depends on this, never on a vendor SDK."""
+
+from dataclasses import dataclass, field
+from typing import Any, Literal, Protocol
+
+Role = Literal["system", "user", "assistant"]
+
+
+@dataclass(frozen=True)
+class ChatMessage:
+    role: Role
+    content: str
+
+
+@dataclass(frozen=True)
+class JsonSchema:
+    """Ask the model for a JSON object of this shape (structured output)."""
+
+    name: str
+    schema: dict[str, Any]
+
+
+@dataclass(frozen=True)
+class LLMResult:
+    text: str
+    # Parsed object when a JSON schema was requested and the reply was valid JSON; None otherwise.
+    # The caller still validates it — a model can return well-formed JSON of the wrong shape.
+    data: dict[str, Any] | None = None
+    prompt_tokens: int = 0
+    completion_tokens: int = 0
+    raw: dict[str, Any] = field(default_factory=dict, repr=False)
+
+    @property
+    def tokens(self) -> int:
+        return self.prompt_tokens + self.completion_tokens
+
+
+class LLMError(Exception):
+    pass
+
+
+class LLMProvider(Protocol):
+    async def complete(self, messages: list[ChatMessage], schema: JsonSchema | None = None) -> LLMResult: ...
+
+    async def aclose(self) -> None: ...