Files
agent-framework/python/packages/bedrock/tests/test_bedrock_settings.py
Giles Odigwe 5e33deff45 Python: Unify tool results as Content items with rich content support (#4331)
* feat(python): allow @tool functions to return rich content (images, audio)

Add support for tool functions to return Content objects that the model can perceive natively. Closes #4272

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Anthropic logging + mypy fix

* Address PR review: fix MCP ordering, fold helper into from_function_result, fix Chat client

- Preserve original content order in MCP tool results instead of text-first
- Move _build_function_result logic into Content.from_function_result()
- Chat Completions: inject user message for rich items (API only supports string tool content)
- Update tests for ordering and new from_function_result behavior

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Use native Responses API multi-part output, warn+omit for Chat client

- Responses client: put rich items directly in function_call_output's
  output field as list (native API support) instead of user message injection
- Chat client: warn and omit rich items (API doesn't support multi-part
  tool results), matching Ollama/Bedrock pattern
- Unify test image: use sample_image.jpg across all integration tests
- Add Azure OpenAI Responses integration test
- Assert model describes house image to verify perception

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix lint: remove print statement, wrap long line

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Address review feedback: bug fixes, single-pass MCP, unit tests

- Add isinstance guard in from_function_result for non-Content lists
- Fix Anthropic empty tool_content fallback to string result
- Fix Content(type='text', text=None) edge case in parse_result
- Rewrite MCP _parse_tool_result_from_mcp as single-pass (no index counters)
- Add Anthropic unit tests: data image, uri image, unsupported media, all-unsupported
- Add OpenAI Chat unit test: rich items warning and omission
- Add OpenAI Responses unit tests: function_result with/without items
- Add test_types tests: only-rich-items list, non-Content list fallback

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix pyright errors: add type ignore comments for Any list iteration

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix mypy/pyright: ensure ToolExecutionException receives str

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix lint: remove duplicate test_prepare_options_excludes_conversation_id

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* refactor: unify all tool results into Content items

* addressed copilot comments

* pyright fix

* small fix

* comments

* fix: address Copilot review - warnings, blob safety, dedup

- Add warning logs when rich content is dropped in Claude agent and
  MCP server handlers (matching Chat/Bedrock/Ollama pattern)
- Defensive blob URI construction: wrap plain base64 in data: prefix
- Simplify Chat client _prepare_content_for_openai to use content.result
- Simplify Responses client text-only path, remove redundant nesting
- Add test for plain base64 blob without data: prefix

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix token double-counting in compaction and address review comments

- Exclude items from _serialize_content() to prevent double-counting
  tokens when items mirrors result in function_result content
- Add rich content warning in GitHub Copilot agent tool handler
- Replace raw Content debug log with concise item count/type summary
- Update stale test comments about FunctionTool.invoke return type

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-03-12 22:30:09 +00:00

137 lines
4.4 KiB
Python

# Copyright (c) Microsoft. All rights reserved.
from __future__ import annotations
from unittest.mock import MagicMock
import pytest
from agent_framework import (
ChatOptions,
Content,
FunctionTool,
Message,
)
from agent_framework._settings import load_settings
from pydantic import BaseModel
from agent_framework_bedrock._chat_client import BedrockChatClient, BedrockSettings
class _WeatherArgs(BaseModel):
location: str
def _build_client() -> BedrockChatClient:
fake_runtime = MagicMock()
fake_runtime.converse.return_value = {}
return BedrockChatClient(model_id="test-model", client=fake_runtime)
def _dummy_weather(location: str) -> str: # pragma: no cover - helper
return f"Weather in {location}"
def test_settings_load_from_environment(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("BEDROCK_REGION", "us-west-2")
monkeypatch.setenv("BEDROCK_CHAT_MODEL_ID", "anthropic.claude-v2")
settings = load_settings(BedrockSettings, env_prefix="BEDROCK_")
assert settings["region"] == "us-west-2"
assert settings["chat_model_id"] == "anthropic.claude-v2"
def test_build_request_includes_tool_config() -> None:
client = _build_client()
tool = FunctionTool(name="get_weather", description="desc", func=_dummy_weather, input_model=_WeatherArgs)
options = {
"tools": [tool],
"tool_choice": {"mode": "required", "required_function_name": "get_weather"},
}
messages = [Message(role="user", contents=[Content.from_text(text="hi")])]
request = client._prepare_options(messages, options)
assert request["toolConfig"]["tools"][0]["toolSpec"]["name"] == "get_weather"
assert request["toolConfig"]["toolChoice"] == {"tool": {"name": "get_weather"}}
def test_build_request_serializes_tool_history() -> None:
client = _build_client()
options: ChatOptions = {}
messages = [
Message(role="user", contents=[Content.from_text(text="how's weather?")]),
Message(
role="assistant",
contents=[
Content.from_function_call(call_id="call-1", name="get_weather", arguments='{"location": "SEA"}')
],
),
Message(
role="tool",
contents=[Content.from_function_result(call_id="call-1", result='{"answer": "72F"}')],
),
]
request = client._prepare_options(messages, options)
assistant_block = request["messages"][1]["content"][0]["toolUse"]
result_block = request["messages"][2]["content"][0]["toolResult"]
assert assistant_block["name"] == "get_weather"
assert assistant_block["input"] == {"location": "SEA"}
assert result_block["toolUseId"] == "call-1"
assert result_block["content"][0]["json"] == {"answer": "72F"}
def test_process_response_parses_tool_use_and_result() -> None:
client = _build_client()
response = {
"modelId": "model",
"output": {
"message": {
"id": "msg-1",
"content": [
{"toolUse": {"toolUseId": "call-1", "name": "get_weather", "input": {"location": "NYC"}}},
{"text": "Calling tool"},
],
},
"completionReason": "tool_use",
},
}
chat_response = client._process_converse_response(response)
contents = chat_response.messages[0].contents
assert contents[0].type == "function_call"
assert contents[0].name == "get_weather"
assert contents[1].type == "text"
assert chat_response.finish_reason == client._map_finish_reason("tool_use")
def test_process_response_parses_tool_result() -> None:
client = _build_client()
response = {
"modelId": "model",
"output": {
"message": {
"id": "msg-2",
"content": [
{
"toolResult": {
"toolUseId": "call-1",
"status": "success",
"content": [{"json": {"answer": 42}}],
}
}
],
},
"completionReason": "end_turn",
},
}
chat_response = client._process_converse_response(response)
contents = chat_response.messages[0].contents
assert contents[0].type == "function_result"
assert "answer" in str(contents[0].result)
assert contents[0].items is not None