mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00

Files

T

Emilien Mottet 3db2004e49 Python: read headers defensively to support stream wrappers without .headers (#6028 ) (#6029 )

`OpenAIChatClient._inner_get_response()` reads `.headers` on the raw streaming
response returned by `client.responses.with_raw_response.create(stream=True)`
(and its three sibling call sites - retrieve-streaming, non-streaming create
and background retrieve) to surface the `x-ms-served-model` Azure header,
introduced in #5910.

When `azure-ai-projects>=2.1.0` experimental GenAI tracing is enabled
(`AZURE_EXPERIMENTAL_ENABLE_GENAI_TRACING=true`), the instrumentor wraps the
raw streaming response in an inline `AsyncStreamWrapper` that exposes
`.response` but not `.headers`. Reading `raw_create_response.headers` then
raises `AttributeError: 'AsyncStreamWrapper' object has no attribute 'headers'`,
which `FoundryChatClient` rethrows as a `ChatClientException` and breaks every
streaming call (workflows and free chat).

Fix: read the header dict via `getattr(raw_response, "headers", None)` at all
four call sites. `_extract_served_model()` already short-circuits on `None`,
so the served-model surfacing degrades gracefully (model stays the deployment
alias) instead of crashing when the response is wrapped by an instrumentor
that does not proxy `.headers`.

Regression test added:
`test_streaming_response_without_headers_attribute_does_not_crash`
simulates a stream wrapper that raises `AttributeError` on `.headers` and
asserts the stream still completes with the deployment alias as `update.model`.

Fixes #6028

Co-authored-by: Emilien Mottet <emilien.mottet@michelin.com>

3db2004e49 · 2026-05-28 08:37:38 +00:00

History

agent_framework_openai

Python: read headers defensively to support stream wrappers without .headers (#6028 ) (#6029 )

2026-05-28 08:37:38 +00:00

tests

Python: read headers defensively to support stream wrappers without .headers (#6028 ) (#6029 )

2026-05-28 08:37:38 +00:00

AGENTS.md

Python: [BREAKING] Remove deprecated Python OpenAI/Azure AI surfaces (#4990 )

2026-03-31 20:36:21 +00:00

LICENSE

Python: [BREAKING] Python: Provider-leading client design & OpenAI package extraction (#4818 )

2026-03-25 09:56:29 +00:00

pyproject.toml

Python: bump package versions for 1.6.0 release (#6017 )

2026-05-22 01:59:20 +00:00

README.md

Python: [BREAKING] update to v1.0.0 (#5062 )

2026-04-02 15:26:30 +00:00

README.md

agent-framework-openai

OpenAI integration for Microsoft Agent Framework.

This package provides:

OpenAIChatClient for the OpenAI Responses API
OpenAIChatCompletionClient for the Chat Completions API
OpenAIEmbeddingClient for embeddings

Installation

pip install agent-framework-openai

Which chat client should I use?

Use OpenAIChatClient for new work unless you specifically need the Chat Completions API.

OpenAIChatClient uses the Responses API and is the preferred general-purpose chat client.
OpenAIChatCompletionClient uses the Chat Completions API and is mainly for compatibility with existing Chat Completions-based integrations.

The previous deprecated Responses alias has been removed. Use OpenAIChatClient directly.

Environment variables

OpenAI

These variables are used when the client is configured for OpenAI:

Variable	Purpose
`OPENAI_API_KEY`	OpenAI API key
`OPENAI_ORG_ID`	OpenAI organization ID
`OPENAI_BASE_URL`	Custom OpenAI-compatible base URL
`OPENAI_MODEL`	Generic fallback model
`OPENAI_CHAT_MODEL`	Preferred model for `OpenAIChatClient`
`OPENAI_CHAT_COMPLETION_MODEL`	Preferred model for `OpenAIChatCompletionClient`
`OPENAI_EMBEDDING_MODEL`	Preferred model for `OpenAIEmbeddingClient`

Model lookup order:

OpenAIChatClient: OPENAI_CHAT_MODEL -> OPENAI_MODEL
OpenAIChatCompletionClient: OPENAI_CHAT_COMPLETION_MODEL -> OPENAI_MODEL
OpenAIEmbeddingClient: OPENAI_EMBEDDING_MODEL -> OPENAI_MODEL

These model variables are only consulted when you do not pass model= directly. In other words, OpenAIChatClient(model="...") ignores OPENAI_CHAT_MODEL, and OpenAIChatCompletionClient(model="...") ignores OPENAI_CHAT_COMPLETION_MODEL.

Azure OpenAI

These variables are used when the client is configured for Azure OpenAI:

Variable	Purpose
`AZURE_OPENAI_ENDPOINT`	Azure OpenAI resource endpoint
`AZURE_OPENAI_BASE_URL`	Full Azure OpenAI base URL (`.../openai/v1`)
`AZURE_OPENAI_API_KEY`	Azure OpenAI API key
`AZURE_OPENAI_API_VERSION`	Azure OpenAI API version
`AZURE_OPENAI_MODEL`	Generic fallback deployment
`AZURE_OPENAI_CHAT_MODEL`	Preferred deployment for `OpenAIChatClient`
`AZURE_OPENAI_CHAT_COMPLETION_MODEL`	Preferred deployment for `OpenAIChatCompletionClient`
`AZURE_OPENAI_EMBEDDING_MODEL`	Preferred deployment for `OpenAIEmbeddingClient`

Deployment lookup order:

OpenAIChatClient: AZURE_OPENAI_CHAT_MODEL -> AZURE_OPENAI_MODEL
OpenAIChatCompletionClient: AZURE_OPENAI_CHAT_COMPLETION_MODEL -> AZURE_OPENAI_MODEL
OpenAIEmbeddingClient: AZURE_OPENAI_EMBEDDING_MODEL -> AZURE_OPENAI_MODEL

For Azure routing, the same rule applies: the client-specific deployment variable is checked first, then the generic AZURE_OPENAI_MODEL fallback. Passing model= overrides both environment variables.

When both OpenAI and Azure environment variables are present, the generic clients prefer OpenAI when OPENAI_API_KEY is configured. To use Azure explicitly, pass azure_endpoint or credential.

OpenAI example

from agent_framework.openai import OpenAIChatClient

client = OpenAIChatClient(model="gpt-4.1")

Azure OpenAI example

from azure.identity.aio import AzureCliCredential

from agent_framework.openai import OpenAIChatClient

client = OpenAIChatClient(
    model="my-responses-deployment",
    azure_endpoint="https://my-resource.openai.azure.com",
    credential=AzureCliCredential(),
)

ChatClient vs ChatCompletionClient

Use OpenAIChatClient when you want the Responses API as your default chat surface.

Use OpenAIChatCompletionClient when you specifically need the Chat Completions API:

from agent_framework.openai import OpenAIChatCompletionClient

client = OpenAIChatCompletionClient(model="gpt-4o-mini")