fix: allow AI to use type clarify when asking questions to avoid Pydantic validation error

Author: yash-pouranik

apps/python-service/routers/ai.py

@@ -57,7 +57,7 @@ class CollectionCreatorRequest(BaseModel):
     encrypted_byok: EncryptedByok | None = None
 
 class CollectionCreatorResponse(BaseModel):
-    type: Literal["schema", "complete"]
+    type: Literal["clarify", "schema", "complete"]
     message: str
     schema_: list[CollectionSchema] | None = Field(default=None, alias="schema")
 
@@ -166,7 +166,7 @@ async def collection_creator(request: CollectionCreatorRequest, req: Request):
         system_prompt = """You are a MongoDB schema designer for urBackend, a Backend-as-a-Service platform.
 
 Rules:
-1. If the description is vague, ask 2-3 specific clarifying questions. NEVER ask more than 3 at once.
+1. If the description is vague, ask 2-3 specific clarifying questions and set type: "clarify". NEVER ask more than 3 at once.
 2. Once you have enough context, propose a schema and set type: "schema".
 3. Only use these field types: String, Number, Boolean, Date, Object, Array, Ref.
 4. ALWAYS include "createdAt" (type: Date, required: true) in EVERY collection.