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

* 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
+2 -1
View File
@@ -20,6 +20,7 @@ dev = [
"pytest>=8.4.1",
"pytest-asyncio>=1.0.0",
"pytest-cov>=6.2.1",
"pytest-env>=1.1.5",
"pytest-xdist[psutil]>=3.8.0",
"pytest-timeout>=2.3.1",
"mypy>=1.16.1",
@@ -164,7 +165,7 @@ exclude_dirs = ["tests", "./run_tasks_in_packages_if_exists.py", "./check_md_cod
executor.type = "uv"
[tool.poe.tasks]
markdown-code-lint = """uv run python check_md_code_blocks.py README.md ./packages/**/README.md ./samples/**/*.md --exclude cookiecutter-agent-framework-lab"""
markdown-code-lint = """uv run python check_md_code_blocks.py README.md ./packages/**/README.md ./samples/**/*.md --exclude cookiecutter-agent-framework-lab --exclude tau2"""
samples-code-check = """pyright ./samples"""
docs-install = "uv sync --all-packages --all-extras --dev -U --prerelease=if-necessary-or-explicit --group=docs"
docs-clean = "rm -rf docs/build"