add AI and generation routers, models, and OpenRouter service integration with tests

Co-authored-by: Copilot <copilot@github.com>

backend/app/models/ai.py

@@ -0,0 +1,92 @@
+"""Pydantic schemas for AI generation endpoints."""
+from typing import Any
+from pydantic import BaseModel
+
+
+class ChatMessage(BaseModel):
+    role: str  # "user" | "assistant" | "system"
+    content: str
+
+
+class ChatRequest(BaseModel):
+    model: str
+    messages: list[ChatMessage]
+    temperature: float = 0.7
+    max_tokens: int = 1024
+
+
+class ChatResponse(BaseModel):
+    id: str
+    model: str
+    content: str
+    usage: dict[str, Any] | None = None
+
+
+class ModelInfo(BaseModel):
+    id: str
+    name: str
+    context_length: int | None = None
+    pricing: dict[str, Any] | None = None
+
+
+# --- Text generation ---
+
+class TextRequest(BaseModel):
+    model: str
+    prompt: str
+    system_prompt: str | None = None
+    temperature: float = 0.7
+    max_tokens: int = 1024
+
+
+class TextResponse(BaseModel):
+    id: str
+    model: str
+    content: str
+    usage: dict[str, Any] | None = None
+
+
+# --- Image generation ---
+
+class ImageRequest(BaseModel):
+    model: str
+    prompt: str
+    n: int = 1
+    size: str = "1024x1024"
+
+
+class ImageResult(BaseModel):
+    url: str | None = None
+    b64_json: str | None = None
+    revised_prompt: str | None = None
+
+
+class ImageResponse(BaseModel):
+    id: str
+    model: str
+    images: list[ImageResult]
+
+
+# --- Video generation ---
+
+class VideoRequest(BaseModel):
+    model: str
+    prompt: str
+    duration_seconds: int | None = None
+    aspect_ratio: str = "16:9"
+
+
+class VideoFromImageRequest(BaseModel):
+    model: str
+    image_url: str
+    prompt: str
+    duration_seconds: int | None = None
+    aspect_ratio: str = "16:9"
+
+
+class VideoResponse(BaseModel):
+    id: str
+    model: str
+    status: str  # "queued" | "processing" | "completed"
+    video_url: str | None = None
+    metadata: dict[str, Any] | None = None