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

Files

T

Eduard van Valkenburg 8ed50009c6 Python: Centralize tool result parsing in FunctionTool.invoke() (#3854 )

* Centralize tool result parsing in FunctionTool.invoke()

- Add parse_result static method to FunctionTool that converts raw
  function return values to strings at invocation time
- Add result_parser parameter to FunctionTool and @tool decorator
  for custom parsing
- Remove prepare_function_call_results from all 9 consumer files
  and from the public API
- Update MCPTool to parse MCP types directly to strings via
  _parse_tool_result_from_mcp and _parse_prompt_result_from_mcp
- Change MCPTool parse_tool_results/parse_prompt_results type from
  Literal[True] | Callable | None to Callable | None
- Remove ReturnT type parameter from FunctionTool (now single
  generic ArgsT since invoke() always returns str)
- Update all subclass signatures and docstrings

Fixes #1147

* Fix test_mcp_tool_call_tool_with_meta_integration for string results

The test was still accessing result[0].additional_properties but
invoke() now returns a string, not a list of Content objects.

* Fix SIM108 lint: use binary operator for output assignment

* Fix bedrock: use FunctionTool.parse_result instead of str() fallback

str(result) turns None into literal 'None' and dicts into Python reprs
with single quotes, breaking JSON parsing. Use the shared parse_result
which handles None as '' and serializes via json.dumps.

* updated lock

* updates from feedback

8ed50009c6 · 2026-02-12 13:49:42 +00:00

History

agent_framework_orchestrations

Python: Centralize tool result parsing in FunctionTool.invoke() (#3854 )

2026-02-12 13:49:42 +00:00

tests

Python: (samples): adopt AzureOpenAIResponsesClient, reorganize orchestration examples, and fix workflow/orchestration bugs (#3873 )

2026-02-12 10:46:58 +00:00

LICENSE

[BREAKING] Python: Move orchestrations to dedicated package (#3685 )

2026-02-05 03:05:13 +00:00

pyproject.toml

Update package versions (#3838 )

2026-02-11 00:20:29 +00:00

README.md

Python: replace pre-commit with prek, add PEP 723 script deps, clean up dev dependencies (#3748 )

2026-02-09 17:51:01 +00:00

README.md

Agent Framework Orchestrations

Orchestration patterns for Microsoft Agent Framework. This package provides high-level builders for common multi-agent workflow patterns.

Installation

pip install agent-framework-orchestrations --pre

Orchestration Patterns

SequentialBuilder

Chain agents/executors in sequence, passing conversation context along:

from agent_framework.orchestrations import SequentialBuilder

workflow = SequentialBuilder(participants=[agent1, agent2, agent3]).build()

ConcurrentBuilder

Fan-out to multiple agents in parallel, then aggregate results:

from agent_framework.orchestrations import ConcurrentBuilder

workflow = ConcurrentBuilder(participants=[agent1, agent2, agent3]).build()

HandoffBuilder

Decentralized agent routing where agents decide handoff targets:

from agent_framework.orchestrations import HandoffBuilder

workflow = (
    HandoffBuilder()
    .participants([triage, billing, support])
    .with_start_agent(triage)
    .build()
)

GroupChatBuilder

Orchestrator-directed multi-agent conversations:

from agent_framework.orchestrations import GroupChatBuilder

workflow = GroupChatBuilder(
    participants=[agent1, agent2],
    selection_func=my_selector,
).build()

MagenticBuilder

Sophisticated multi-agent orchestration using the Magentic One pattern:

from agent_framework.orchestrations import MagenticBuilder

workflow = MagenticBuilder(
    participants=[researcher, writer, reviewer],
    manager_agent=manager_agent,
).build()

Documentation

For more information, see the Agent Framework documentation.