Add shared ai-service container as AI provider intermediary

All feature containers now POST messages to ai-service (port 8010) instead
of calling AI providers directly. ai-service routes to LM Studio, Ollama,
or Anthropic based on /config/ai_service_config.json. doc-service AI
providers removed; replaced by httpx ai_client.py. Backend settings
restructured to /api/settings/ai. Frontend gets dedicated AIAdminSettingsPage
and AI Service card in AppsPage.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

features/ai-service/app/schemas/chat.py

@@ -0,0 +1,30 @@
+from typing import Literal
+
+from pydantic import BaseModel, field_validator
+
+
+class ChatMessage(BaseModel):
+    role: Literal["system", "user", "assistant"]
+    content: str
+
+
+class ChatRequest(BaseModel):
+    messages: list[ChatMessage]
+    max_tokens: int = 2048
+    temperature: float = 0.0
+    response_format: Literal["json", "text"] = "text"
+
+    @field_validator("messages")
+    @classmethod
+    def messages_not_empty(cls, v: list) -> list:
+        if not v:
+            raise ValueError("messages must not be empty")
+        return v
+
+
+class ChatResponse(BaseModel):
+    content: str
+    provider: str
+    model: str
+    input_tokens: int | None = None
+    output_tokens: int | None = None