mirror of
https://github.com/zed-industries/zed.git
synced 2026-06-01 03:14:56 +07:00
97f0ab77ca
GitHub allows defining a default shell for all jobs on the workflow level, which we did not use before, yet practically did when it comes down to our usage of `named::bash`. Since this makes stuff quite verbose, I decided on using the defaults instead so the workflows become somewhat easier to audit when reading the generated files. Powershell steps continue to use Powershell, only the default for bash scripts was modified. Release Notes: - N/A
64 lines
2.1 KiB
YAML
64 lines
2.1 KiB
YAML
# Generated from xtask::workflows::run_agent_evals
|
|
# Rebuild with `cargo xtask workflows`.
|
|
name: run_agent_evals
|
|
env:
|
|
CARGO_TERM_COLOR: always
|
|
CARGO_INCREMENTAL: '0'
|
|
RUST_BACKTRACE: '1'
|
|
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
|
|
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
|
|
GOOGLE_AI_API_KEY: ${{ secrets.GOOGLE_AI_API_KEY }}
|
|
GOOGLE_CLOUD_PROJECT: ${{ secrets.GOOGLE_CLOUD_PROJECT }}
|
|
ZED_CLIENT_CHECKSUM_SEED: ${{ secrets.ZED_CLIENT_CHECKSUM_SEED }}
|
|
ZED_EVAL_TELEMETRY: '1'
|
|
MODEL_NAME: ${{ inputs.model_name }}
|
|
on:
|
|
workflow_dispatch:
|
|
inputs:
|
|
model_name:
|
|
description: model_name
|
|
required: true
|
|
type: string
|
|
jobs:
|
|
agent_evals:
|
|
runs-on: namespace-profile-16x32-ubuntu-2204
|
|
steps:
|
|
- name: steps::checkout_repo
|
|
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
|
|
with:
|
|
clean: false
|
|
- name: steps::cache_rust_dependencies_namespace
|
|
uses: namespacelabs/nscloud-cache-action@v1
|
|
with:
|
|
cache: rust
|
|
path: ~/.rustup
|
|
- name: steps::setup_linux
|
|
run: ./script/linux
|
|
- name: steps::install_mold
|
|
run: ./script/install-mold
|
|
- name: steps::download_wasi_sdk
|
|
run: ./script/download-wasi-sdk
|
|
- name: steps::setup_cargo_config
|
|
run: |
|
|
mkdir -p ./../.cargo
|
|
cp ./.cargo/ci-config.toml ./../.cargo/config.toml
|
|
- name: cargo build --package=eval
|
|
run: cargo build --package=eval
|
|
- name: run_agent_evals::agent_evals::run_eval
|
|
run: cargo run --package=eval -- --repetitions=8 --concurrency=1 --model "${MODEL_NAME}"
|
|
env:
|
|
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
|
|
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
|
|
GOOGLE_AI_API_KEY: ${{ secrets.GOOGLE_AI_API_KEY }}
|
|
GOOGLE_CLOUD_PROJECT: ${{ secrets.GOOGLE_CLOUD_PROJECT }}
|
|
- name: steps::cleanup_cargo_config
|
|
if: always()
|
|
run: |
|
|
rm -rf ./../.cargo
|
|
timeout-minutes: 600
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.ref_name }}-${{ github.ref_name == 'main' && github.sha || 'anysha' }}
|
|
cancel-in-progress: true
|
|
defaults:
|
|
run:
|
|
shell: bash -euxo pipefail {0}
|