feat(groq): add performance service tier (#38339)

Groq's API now exposes a fourth service tier, `performance` — their
highest tier, providing reliable low latency for the most critical
production applications. `ChatGroq.service_tier` only accepted
`on_demand`, `flex`, and `auto`, so users who wanted to route requests
to the performance tier had no type-safe way to do so.

This widens the `service_tier` `Literal` to include `performance` and
documents it alongside the existing tiers. The value is passed straight
through to the Groq SDK as a constrained enum, so no validation or
mapping logic changes were needed.

Reference: [Groq service tiers
documentation](https://console.groq.com/docs/service-tiers).

An integration test case was added to `test_setting_service_tier_class`
mirroring the existing per-tier assertions; it exercises a live request
and so runs only with a Groq API key.

libs/partners/groq/langchain_groq/chat_models.py

@@ -430,7 +430,9 @@ class ChatGroq(BaseChatModel):
     max_tokens: int | None = None
     """Maximum number of tokens to generate."""
 
-    service_tier: Literal["on_demand", "flex", "auto"] = Field(default="on_demand")
+    service_tier: Literal["on_demand", "flex", "auto", "performance"] = Field(
+        default="on_demand"
+    )
     """Optional parameter that you can include to specify the service tier you'd like to
     use for requests.
 
@@ -440,6 +442,8 @@ class ChatGroq(BaseChatModel):
         reliability for workloads that don't require guaranteed processing.
     - `'auto'`: Uses on-demand rate limits, then falls back to `'flex'` if those
         limits are exceeded
+    - `'performance'`: Highest tier, providing reliable low latency for the most
+        critical production applications.
 
     See the [Groq documentation](https://console.groq.com/docs/flex-processing) for more
     details and a list of service tiers and descriptions.

libs/partners/groq/tests/integration_tests/test_chat_models.py

@@ -574,6 +574,9 @@ def test_setting_service_tier_class() -> None:
     response = chat.invoke([message])
     assert response.response_metadata.get("service_tier") == "on_demand"
 
+    chat = ChatGroq(model=DEFAULT_MODEL_NAME, service_tier="performance")
+    assert chat.service_tier == "performance"
+
     chat = ChatGroq(model=DEFAULT_MODEL_NAME)
     assert chat.service_tier == "on_demand"
     response = chat.invoke([message])