agent/agent-framework
1
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Python: Add tau2 benchmark integration with comprehensive testing and documentation (#817)

Browse Source 
* first commit to tau2-bench

* tau2-bench agent

* tau2 agent

* add condition

* checkpoint

* bug fix

* add tests

* fix tests

* add comments

* add comments

* minor fix

* fix

* batch test script

* .

* init.bak -> init.py

* fix mypy

* update readme

* fix env

* remove temp files

* setup tests

* fix gaia tasks

* fix tau2 tests

* fix coverage

* fix default version

* update cookiecutter template

---------

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
This commit is contained in:
Yuge Zhang
2025-09-21 16:08:45 -07:00
committed by GitHub
Unverified
parent 52790b9f6a
commit 205cd700c8
34 changed files with 3675 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/python-tests.yml
+29
View File
@@ -102,6 +102,35 @@ jobs:
name: coverage-${{ matrix.OS }}-${{ matrix.python-version }}-${{ env.PACKAGE_NAME }}
path: ./python/coverage_${{ matrix.OS }}_${{ matrix.python-version }}_${{ env.PACKAGE_NAME }}.xml
# Lab package tests
- name: Set environment variables - lab - win
if: ${{ matrix.os == 'windows-latest' }}
run: |
echo "PACKAGE_NAME=lab" | Out-File -FilePath $env:GITHUB_ENV -Append
- name: Set environment variables - lab
if: ${{ matrix.os != 'windows-latest' }}
run: |
echo "PACKAGE_NAME=lab" >> $GITHUB_ENV
- name: Test with pytest - lab - gaia
run: uv run poe --directory ./packages/${{ env.PACKAGE_NAME }}/gaia test -n logical --dist loadfile --dist worksteal --junitxml=coverage.xml
working-directory: ./python
- name: Test with pytest - lab - tau2
run: |
uv run poe --directory ./packages/${{ env.PACKAGE_NAME }}/tau2 setup-data
uv run poe --directory ./packages/${{ env.PACKAGE_NAME }}/tau2 test -n logical --dist loadfile --dist worksteal --junitxml=coverage.xml
uv run poe --directory ./packages/${{ env.PACKAGE_NAME }}/tau2 purge-data
working-directory: ./python
- name: Move coverage file - lab
run: |
mv ./packages/${{ env.PACKAGE_NAME }}/gaia/coverage.xml coverage_${{ matrix.OS }}_${{ matrix.python-version }}_${{ env.PACKAGE_NAME }}_gaia.xml
mv ./packages/${{ env.PACKAGE_NAME }}/tau2/coverage.xml coverage_${{ matrix.OS }}_${{ matrix.python-version }}_${{ env.PACKAGE_NAME }}_tau2.xml
working-directory: ./python
- name: Upload coverage artifact - lab
uses: actions/upload-artifact@v4
with:
name: coverage-${{ matrix.OS }}-${{ matrix.python-version }}-${{ env.PACKAGE_NAME }}
path: ./python/coverage_${{ matrix.OS }}_${{ matrix.python-version }}_${{ env.PACKAGE_NAME }}_*.xml
# Surface failing tests
- name: Surface failing tests
if: always()