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

Files

T

Eduard van Valkenburg 6acab3d1d6 Python: [BREAKING] Standardize model selection on model (#4999 )

* Refactor Anthropic model option and provider clients

Rename the Anthropic client model option from model_id to model, add provider-specific Anthropic wrappers for Foundry, Bedrock, and Vertex, and expose them through the Anthropic, Foundry, Amazon, and Google namespaces. Update core option handling, docs, samples, and tests accordingly.

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

* Fix Anthropic skills sample typing

Cast the Anthropic beta client to Any in the skills sample so the pre-commit sample pyright check no longer fails on beta skills and files endpoints that are not exposed by the current SDK stubs.

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

* undo sample mypy

* Retry CI after transient external failures

Retrigger PR validation after an unrelated Copilot review workflow SAML failure and a transient external tau2 git fetch failure in the Windows Python test setup.

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

* Address review feedback on model option merging

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

* Address Anthropic compatibility review feedback

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

* moved all to `model`

* fixes for azure ai search

* Python: standardize remaining sample env var names

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

* Python: fix foundry-local pyright compatibility

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

* updated env vars in cicd

---------

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

6acab3d1d6 · 2026-04-01 19:00:18 +00:00

History

code_defined_skill

Python: [BREAKING] Standardize model selection on model (#4999 )

2026-04-01 19:00:18 +00:00

file_based_skill

Python: [BREAKING] Standardize model selection on model (#4999 )

2026-04-01 19:00:18 +00:00

mixed_skills

Python: [BREAKING] Standardize model selection on model (#4999 )

2026-04-01 19:00:18 +00:00

script_approval

Python: [BREAKING] Standardize model selection on model (#4999 )

2026-04-01 19:00:18 +00:00

README.md

Python: Add Python feature lifecycle decorators for released APIs (#4975 )

2026-03-31 19:40:08 +00:00

subprocess_script_runner.py

Python: Add Python feature lifecycle decorators for released APIs (#4975 )

2026-03-31 19:40:08 +00:00

README.md

Agent Skills Samples

These samples demonstrate how to use Agent Skills — modular packages of instructions, resources, and scripts that extend an agent's capabilities. Skills follow the Agent Skills specification and use progressive disclosure to optimize token usage.

Learning Path

Start with file-based or code-defined skills, then explore combining them and adding approval workflows.

Sample	Description
file_based_skill	Define skills as `SKILL.md` files on disk with reference documents and executable scripts. Uses the unit-converter skill.
code_defined_skill	Define skills entirely in Python code using `Skill`, `@skill.resource`, and `@skill.script` decorators. Uses a code-defined unit-converter skill.
mixed_skills	Combine code-defined and file-based skills in a single agent. Uses a code-defined volume-converter and a file-based unit-converter.
script_approval	Require human-in-the-loop approval before executing skill scripts

Key Concepts

Progressive Disclosure

Skills use a three-step interaction model to minimize token usage:

Advertise — Skill names and descriptions (~100 tokens each) are injected into the system prompt
Load — Full instructions are loaded on-demand via the load_skill tool
Access — Resources are read via read_skill_resource; scripts are executed via run_skill_script

File-Based vs Code-Defined Skills

Aspect	File-Based	Code-Defined
Definition	`SKILL.md` files on disk	`Skill` instances in Python
Resources	Static files in `references/` and `assets/` directories	Callable functions via `@skill.resource` decorator
Scripts	Python files in `scripts/` directory (executed via subprocess)	Callable functions via `@skill.script` decorator (executed in-process)
Discovery	Automatic via `skill_paths` parameter	Explicit via `skills` parameter
Dynamic content	No (static files only)	Yes (functions can generate content at runtime)

Both types can be combined in a single SkillsProvider — see the mixed_skills sample.

Script Execution

Skills can include executable scripts. How a script runs depends on how it was defined:

	Code-Defined Scripts	File-Based Scripts
Defined via	`@skill.script` decorator	`.py` files in `scripts/` directory
Execution	In-process (direct function call)	Delegated to a `script_runner`
`script_runner` needed?	No — runs in-process automatically	Yes — required

The script_runner parameter on SkillsProvider is only applicable to file-based scripts. Code-defined scripts are always executed in-process regardless of this setting. See file_based_skill for an example using a SkillScriptRunner callable with a subprocess runner, and code_defined_skill for in-process scripts that need no runner.

Prerequisites

All samples require:

An Azure AI Foundry project with a deployed model (e.g. gpt-4o-mini)
Azure CLI authentication (az login)
Environment variables set in a .env file (see python/.env.example)

Suppressing the experimental warning

The Agent Skills APIs in these samples are still experimental. Each sample includes a short commented warnings.filterwarnings(...) snippet near the imports. Uncomment it if you want to suppress the Skills warning before using the experimental APIs.