fix(a2a): read a stored card's capabilities the way the spec does and keep one Authorization line

litellm/llms/a2a/chat/transformation.py

@@ -38,7 +38,7 @@ _REGISTRY_PARAMS_KEPT_OUT_OF_OPTIONAL_PARAMS: Final = (
 
 def _card_declares_no_streaming(agent_card_params: Mapping[str, object]) -> bool:
     capabilities: Final = agent_card_params.get("capabilities")
-    return isinstance(capabilities, Mapping) and capabilities.get("streaming") is False
+    return isinstance(capabilities, Mapping) and not capabilities.get("streaming")
 
 
 def _registry_api_key(agent_litellm_params: dict[str, object]) -> str | None:

litellm/proxy/agent_endpoints/a2a_endpoints.py

@@ -176,14 +176,15 @@ def _forwarding_headers(
     agent_extra_headers: Mapping[str, str] | None,
     backend_auth_header: Mapping[str, str] | None,
 ) -> dict[str, str] | None:
+    backend_auth: Final = tuple(backend_auth_header.items()) if backend_auth_header else ()
+    minted_names: Final = frozenset(name.lower() for name, _ in backend_auth)
     passthrough: Final = tuple(
         (name, value)
         for name, value in (agent_extra_headers.items() if agent_extra_headers else ())
-        if not name.lower().startswith("x-litellm-")
+        if not name.lower().startswith("x-litellm-") and name.lower() not in minted_names
     )
     trace_id: Final = request_data.get("litellm_trace_id")
     trace: Final = (("X-LiteLLM-Trace-Id", str(trace_id)),) if trace_id else ()
-    backend_auth: Final = backend_auth_header.items() if backend_auth_header else ()
     merged: Final = dict((*passthrough, *caller_identity.items(), *trace, *backend_auth))
     return merged or None
 

tests/test_litellm/proxy/agent_endpoints/test_a2a_endpoints.py

@@ -2642,3 +2642,18 @@ async def test_handle_stream_message_is_untouched_while_keepalives_are_unconfigu
 
     assert not any(chunk.startswith(":") for chunk in chunks)
     assert json.loads(chunks[-1].removeprefix("data: "))["result"]["kind"] == "task"
+
+
+def test_forwarding_headers_minted_bearer_replaces_a_forwarded_authorization_of_any_case():
+    """A client header the admin chose to forward keeps the casing the config named it with, so a forwarded
+    `authorization` must not travel next to the minted `Authorization` as a second header line."""
+    from litellm.proxy.agent_endpoints.a2a_endpoints import _forwarding_headers
+
+    merged = _forwarding_headers(
+        caller_identity={},
+        request_data={},
+        agent_extra_headers={"authorization": "Bearer client-token", "X-Custom": "kept"},
+        backend_auth_header={"Authorization": "Bearer minted-token"},
+    )
+
+    assert merged == {"X-Custom": "kept", "Authorization": "Bearer minted-token"}

tests/test_litellm/test_a2a_registry_lookup.py

@@ -75,10 +75,29 @@ def test_a2a_registry_integration():
     assert post.call_args.kwargs["headers"]["X-Agent"] == "static"
 
 
-def test_streaming_chat_to_an_agent_whose_card_declines_streaming_uses_a_blocking_send():
+def _foundry_card_stored_through_the_agents_api() -> dict:
+    from litellm.proxy.a2a.agent_card import merge_agent_card
+
+    return merge_agent_card(
+        {"name": "Foundry", "url": "https://foundry.example.com/a2a", "capabilities": {"streaming": False}},
+        proxy_url="http://localhost:4000/a2a/foundry-agent",
+        proxy_base_url="http://localhost:4000",
+    )
+
+
+@pytest.mark.parametrize(
+    "agent_card_params",
+    [
+        {"url": "https://foundry.example.com/a2a", "capabilities": {"streaming": False}},
+        _foundry_card_stored_through_the_agents_api(),
+    ],
+    ids=["card registered verbatim from config.yaml", "card stored through POST /v1/agents"],
+)
+def test_streaming_chat_to_an_agent_whose_card_declines_streaming_uses_a_blocking_send(agent_card_params: dict):
     """Microsoft Foundry agents publish `capabilities.streaming: false` and answer message/stream with a
     JSON-RPC error. A streaming chat call to such an agent must post a blocking message/send and hand the
-    caller the answer as a stream, and an agent whose card is silent about streaming keeps message/stream."""
+    caller the answer as a stream, whether the card was registered verbatim from config.yaml or stored
+    through POST /v1/agents, which keeps only truthy capabilities and so drops the `false` itself."""
     from litellm.llms.custom_httpx.http_handler import HTTPHandler
     from litellm.proxy.agent_endpoints.agent_registry import global_agent_registry
     from litellm.types.agents import AgentResponse
@@ -86,7 +105,7 @@ def test_streaming_chat_to_an_agent_whose_card_declines_streaming_uses_a_blockin
     foundry_agent = AgentResponse(
         agent_id="foundry-id",
         agent_name="foundry-agent",
-        agent_card_params={"url": "https://foundry.example.com/a2a", "capabilities": {"streaming": False}},
+        agent_card_params=agent_card_params,
         litellm_params={"api_key": "registry-key"},
     )
     client = HTTPHandler()
@@ -126,14 +145,22 @@ def test_streaming_chat_to_an_agent_whose_card_declines_streaming_uses_a_blockin
     assert chunks[-1].choices[0].finish_reason == "stop"
 
 
-def test_registry_lookup_leaves_streaming_alone_when_the_card_does_not_decline_it():
+@pytest.mark.parametrize(
+    "agent_card_params",
+    [
+        {"url": "https://agent.example.com/a2a"},
+        {"url": "https://agent.example.com/a2a", "capabilities": {"streaming": True}},
+    ],
+    ids=["card without a capabilities block", "card says streaming true"],
+)
+def test_registry_lookup_leaves_streaming_alone_when_the_card_does_not_decline_it(agent_card_params: dict):
     from litellm.proxy.agent_endpoints.agent_registry import global_agent_registry
     from litellm.types.agents import AgentResponse
 
     silent_agent = AgentResponse(
         agent_id="silent-id",
         agent_name="silent-agent",
-        agent_card_params={"url": "https://agent.example.com/a2a"},
+        agent_card_params=agent_card_params,
         litellm_params={"api_key": "registry-key"},
     )
     original_agents = global_agent_registry.agent_list.copy()