refactor(server): adopt uv and modular typed FastAPI structure

s2s_client/models/requests.py

@@ -0,0 +1,34 @@
+from __future__ import annotations
+
+from pydantic import BaseModel
+
+
+class SearchRequest(BaseModel):
+    query: str
+    # Optional user-supplied key (fallback when the deploy has no server key).
+    # Used for this request only; never stored.
+    key: str | None = None
+
+
+class ReasoningRequest(BaseModel):
+    transcript: str
+    instructions: str = ""
+    language: str = ""
+    user_context: str = ""
+    # Optional phone number. When S2S_INJECT_PROFILE is true the proxy fetches
+    # the caller profile from VOCERO_USER_PHONE_AUTH_URL and:
+    #   1. prepends the serialized profile to user_context before feeding the
+    #      engine (NODE_RED or OPENAI);
+    #   2. appends the profile context to the LLM instructions prompt.
+    phoneNumber: str | None = None
+    # Optional podcast episode ID. When set the proxy fetches the episode from
+    # the Aquachile AzurianLab API and injects it as the PRIMARY context into
+    # both user_context (prepended) and LLM instructions prompt (appended first).
+    episode_id: str | None = None
+
+
+class ApipilotExecuteRequest(BaseModel):
+    """Body for the ApiPilot execute proxy endpoint. Mirrors §2.2 request shape."""
+
+    name: str
+    arguments: dict = {}