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

Files

T

Eduard van Valkenburg 55398e21df Python: Add max_function_calls to FunctionInvocationConfiguration (#2329 ) (#4175 )

* Add max_function_calls to FunctionInvocationConfiguration (#2329)

Add a new per-request max_function_calls setting to FunctionInvocationConfiguration
that limits the total number of individual function invocations across all iterations
within a single get_response call. This complements max_iterations (which limits LLM
roundtrips) by providing a hard cap on actual tool executions regardless of parallelism.

- Add max_function_calls field to FunctionInvocationConfiguration (default: None/unlimited)
- Track cumulative function call count in both streaming and non-streaming tool loops
- Force tool_choice='none' when the limit is reached
- Add validation in normalize_function_invocation_configuration
- Improve docstrings for FunctionInvocationConfiguration, FunctionTool, and @tool
  to clarify semantics of max_iterations vs max_function_calls vs max_invocations
- Add tests for parallel calls, single calls, unlimited mode, and config validation

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

* Add sample for controlling total tool executions

Showcases all three mechanisms for limiting tool executions:
1. max_iterations — caps LLM roundtrips
2. max_function_calls — caps total individual function invocations per request
3. max_invocations — lifetime cap on a specific tool instance
Plus a combined scenario demonstrating defense in depth.

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

* Suppress ruff E305/fmt in hosting sample to preserve XML doc tags

The XML snippet tags (# <create_agent> / # </create_agent>) are used for
docs extraction and must stay adjacent to the code they wrap. Both ruff
check (E305) and ruff format add blank lines after the function definition,
pushing the closing tag away. Suppress with ruff: noqa: E305 and fmt: off.

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

* Add per-agent tool wrapping scenario to control_total_tool_executions sample

Show that wrapping the same callable with @tool multiple times creates
independent FunctionTool instances with separate invocation counters,
enabling per-agent max_invocations budgets for shared functions.

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

* Clarify max_function_calls is a best-effort limit

The limit is checked after each batch of parallel calls completes, so the
current batch always runs to completion even if it overshoots the limit.

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

* Address PR review: fix docstring reference, clarify best-effort in sample

- Fix malformed Sphinx :attr: role in FunctionTool docstring — use plain
  backtick reference instead
- Update sample to say 'best-effort cap' instead of 'hard cap' for
  max_function_calls, noting it's checked between iterations
- Parametrize pattern is correct (fixture override, matching existing tests)

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

* clarify max_invocations limits

---------

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

55398e21df · 2026-02-24 01:00:25 +00:00

History

01_hello_agent.py

Python: Add load_dotenv() to samples for .env file support (#4043 )

2026-02-19 10:55:13 +00:00

02_add_tools.py

Python: Add load_dotenv() to samples for .env file support (#4043 )

2026-02-19 10:55:13 +00:00

03_multi_turn.py

Python: Add load_dotenv() to samples for .env file support (#4043 )

2026-02-19 10:55:13 +00:00

04_memory.py

Simplify memory sample to use session state (#4085 )

2026-02-19 15:34:49 +00:00

05_first_workflow.py

Python: Add load_dotenv() to samples for .env file support (#4043 )

2026-02-19 10:55:13 +00:00

06_host_your_agent.py

Python: Add max_function_calls to FunctionInvocationConfiguration (#2329 ) (#4175 )

2026-02-24 01:00:25 +00:00

README.md

Python: Fix tool normalization and provider sample consolidation (#3953 )

2026-02-16 16:30:38 +00:00

README.md

Get Started with Agent Framework for Python

This folder contains a progressive set of samples that introduce the core concepts of Agent Framework one step at a time.

Prerequisites

pip install agent-framework --pre

Set the required environment variables:

export AZURE_AI_PROJECT_ENDPOINT="https://your-project-endpoint"
export AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME="gpt-4o"   # optional, defaults to gpt-4o

Samples

#	File	What you'll learn
1	01_hello_agent.py	Create your first agent and run it (streaming and non-streaming).
2	02_add_tools.py	Define a function tool with `@tool` and attach it to an agent.
3	03_multi_turn.py	Keep conversation history across turns with `AgentThread`.
4	04_memory.py	Add dynamic context with a custom `ContextProvider`.
5	05_first_workflow.py	Chain executors into a workflow with edges.
6	06_host_your_agent.py	Host a single agent with Azure Functions.

Run any sample with:

python 01_hello_agent.py

These samples use Azure Foundry models with the Responses API. To switch providers, just replace the client, see all providers