fix: align Freepik API paths with OpenAPI spec

The original implementation used guessed endpoint paths that don't match
the actual Freepik API. Key fixes based on their OpenAPI spec:

- Task polling is per-endpoint (e.g. GET /v1/ai/text-to-image/flux-dev/{task-id})
  not a generic /v1/ai/tasks/{id}. freepik_client now returns TaskResult
  with status_path, and task_tracker polls using that path.
- Fixed endpoint paths: flux-pro -> flux-pro-v1-1, upscale -> image-upscaler,
  relight -> image-relight, style-transfer -> image-style-transfer,
  expand -> image-expand/flux-pro, inpaint -> ideogram-image-edit,
  remove-background -> beta/remove-background, classifier -> classifier/image,
  audio-isolate -> audio-isolation, icon -> text-to-icon
- Fixed video paths: kling -> kling-o1-pro with kling-o1 status path,
  minimax -> minimax-hailuo-02-1080p, seedance -> seedance-pro-1080p
- Fixed request schemas to match actual API params (e.g. scale_factor
  not scale, reference_image not style_reference, image_url for bg removal)
- Fixed response parsing: status is uppercase (COMPLETED not completed),
  results in data.generated[] array, classifier returns [{class_name, probability}]

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

app/schemas/image_generation.py

@@ -5,31 +5,30 @@ from pydantic import BaseModel, Field
 
 class MysticRequest(BaseModel):
     prompt: str = Field(..., min_length=1, max_length=4000)
-    negative_prompt: Optional[str] = None
-    resolution: Optional[str] = None
+    resolution: Optional[str] = Field(None, description='1k, 2k, or 4k')
+    aspect_ratio: Optional[str] = Field(None, description='e.g. square_1_1, widescreen_16_9')
+    model: Optional[str] = Field(None, description='realism, fluid, zen, flexible, super_real, editorial_portraits')
+    seed: Optional[int] = Field(None, ge=1, le=4294967295)
     styling: Optional[dict] = None
-    seed: Optional[int] = None
-    num_images: Optional[int] = Field(None, ge=1, le=4)
+    structure_reference: Optional[str] = Field(None, description='Base64 image for structure reference')
+    style_reference: Optional[str] = Field(None, description='Base64 image for style reference')
 
 
 class FluxDevRequest(BaseModel):
     prompt: str = Field(..., min_length=1, max_length=4000)
-    image: Optional[str] = Field(None, description='Base64-encoded image for img2img')
-    guidance_scale: Optional[float] = Field(None, ge=1.0, le=20.0)
-    num_images: Optional[int] = Field(None, ge=1, le=4)
-    seed: Optional[int] = None
+    aspect_ratio: Optional[str] = Field(None, description='e.g. square_1_1, widescreen_16_9')
+    styling: Optional[dict] = None
+    seed: Optional[int] = Field(None, ge=1, le=4294967295)
 
 
 class FluxProRequest(BaseModel):
     prompt: str = Field(..., min_length=1, max_length=4000)
-    image: Optional[str] = Field(None, description='Base64-encoded image for img2img')
-    guidance_scale: Optional[float] = Field(None, ge=1.0, le=20.0)
-    seed: Optional[int] = None
+    aspect_ratio: Optional[str] = Field(None, description='e.g. square_1_1, widescreen_16_9')
+    styling: Optional[dict] = None
+    seed: Optional[int] = Field(None, ge=1, le=4294967295)
 
 
 class SeedreamRequest(BaseModel):
     prompt: str = Field(..., min_length=1, max_length=4000)
-    image: Optional[str] = Field(None, description='Base64-encoded image for img2img')
-    aspect_ratio: Optional[str] = None
-    num_images: Optional[int] = Field(None, ge=1, le=4)
-    seed: Optional[int] = None
+    aspect_ratio: Optional[str] = Field(None, description='e.g. square_1_1, widescreen_16_9')
+    seed: Optional[int] = Field(None, ge=1, le=4294967295)