agent/agent-framework
1
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Inline the served-model header override at its two call sites

Browse Source 
The `_apply_served_model_header` helper was a 1-line wrapper around
`_extract_served_model`. Inlining the `if served_model is not None: ...`
matches the pattern already used in the streaming paths and folds the
explanatory docstring onto `_extract_served_model` (which is now the
single place that knows about the header).

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Eduard van Valkenburg
2026-05-19 07:57:56 +02:00
committed by eavanvalkenburg
Unverified
parent 6d6b35d8b3
commit fb731d7626
1 changed files with 12 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/packages/openai/agent_framework_openai/_chat_client.py
+12 -13
View File
@@ -706,7 +706,9 @@ class RawOpenAIChatClient( # type: ignore[misc]
except Exception as ex:
self._handle_request_error(ex)
chat_response = self._parse_response_from_openai(response, options=validated_options)
self._apply_served_model_header(chat_response, raw_response.headers)
served_model = self._extract_served_model(raw_response.headers)
if served_model is not None:
chat_response.model = served_model
# Once the background response completes, drop the continuation_token from
# the caller's options dict. FunctionInvocationLayer reuses the same dict
# across tool-loop iterations, so leaving it in place makes the next iteration
@@ -726,26 +728,23 @@ class RawOpenAIChatClient( # type: ignore[misc]
except Exception as ex:
self._handle_request_error(ex)
chat_response = self._parse_response_from_openai(response, options=validated_options)
self._apply_served_model_header(chat_response, raw_response.headers)
served_model = self._extract_served_model(raw_response.headers)
if served_model is not None:
chat_response.model = served_model
return chat_response
return _get_response()
@classmethod
def _apply_served_model_header(cls, chat_response: ChatResponse, headers: Any) -> None:
"""Override ``ChatResponse.model`` with the Azure OpenAI served-model header when present.
def _extract_served_model(cls, headers: Any) -> str | None:
"""Return the Azure OpenAI ``x-ms-served-model`` response header value when present.
Azure OpenAI Responses API returns the deployment alias in ``response.model`` but the actual
snapshot served via the ``x-ms-served-model`` response header. When present, the served
snapshot is the source of truth for observability and downstream callers.
snapshot served via the ``x-ms-served-model`` response header (e.g. ``gpt-5-nano-2025-08-07``
vs deployment alias ``gpt-5-nano``). When present, the served snapshot is the source of truth
for observability and downstream callers. Empty/whitespace-only header values are rejected
here so every caller can simply check ``if served_model is not None``.
"""
served_model = cls._extract_served_model(headers)
if served_model is not None:
chat_response.model = served_model
@classmethod
def _extract_served_model(cls, headers: Any) -> str | None:
"""Return the ``x-ms-served-model`` response header value when present and non-empty."""
if headers is None:
return None
served_model = headers.get(cls.SERVED_MODEL_HEADER)