Add a reasoning-off setting (-1 reasoning budget)

Models like DeepSeek V4 Flash reason by default, and the reasoning budget
setting could only ever add thinking tokens - there was no value that turned
thinking off. A negative budget now sends `reasoning: {effort: "none"}`.

Uses effort:none rather than exclude:true deliberately - exclude still thinks
and still bills, it only hides the trace.

Zero keeps its old meaning (send no `reasoning` field at all) so endpoints that
reject unknown fields, like the default Ollama one, are unaffected. Reusing the
existing int column this way avoids a migration.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UeQVy5bEjLhfgWNc27Efet

backend/app/schemas.py

@@ -375,7 +375,8 @@ class SettingsUpdate(BaseModel):
     api_mode: Annotated[str, Field(max_length=20)] | None = None
     temperature: Annotated[float, Field(ge=0, le=5)] | None = None
     max_output_tokens: Annotated[int, Field(ge=1, le=100_000)] | None = None
-    reasoning_max_tokens: Annotated[int, Field(ge=0, le=100_000)] | None = None
+    # -1 = explicitly off (sends `reasoning: {effort: none}`); 0 = send nothing.
+    reasoning_max_tokens: Annotated[int, Field(ge=-1, le=100_000)] | None = None
     context_token_budget: Annotated[int, Field(ge=256, le=200_000)] | None = None
     narrator_prompt: Prose | None = None
     stream: bool | None = None