8724884b00
Add benchmarks using Criterion for: - XML tool-call parsing (single and multi-call) - Native tool-call parsing - SQLite memory store/recall/count operations - Full agent turn cycle (text-only and with tool call) Add CI workflow (.github/workflows/benchmarks.yml) that: - Runs benchmarks on push to main and on PRs - Uploads Criterion results as artifacts - Posts benchmark summary as PR comment for regression visibility Ref: https://github.com/zeroclaw-labs/zeroclaw/issues/618 (item 7) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
103 lines
3.7 KiB
YAML
103 lines
3.7 KiB
YAML
name: Performance Benchmarks
|
|
|
|
on:
|
|
push:
|
|
branches: [main]
|
|
pull_request:
|
|
branches: [main]
|
|
workflow_dispatch:
|
|
|
|
concurrency:
|
|
group: bench-${{ github.event.pull_request.number || github.sha }}
|
|
cancel-in-progress: true
|
|
|
|
permissions:
|
|
contents: read
|
|
pull-requests: write
|
|
|
|
env:
|
|
CARGO_TERM_COLOR: always
|
|
|
|
jobs:
|
|
benchmarks:
|
|
name: Criterion Benchmarks
|
|
runs-on: blacksmith-2vcpu-ubuntu-2404
|
|
timeout-minutes: 30
|
|
steps:
|
|
- uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
|
|
- uses: dtolnay/rust-toolchain@631a55b12751854ce901bb631d5902ceb48146f7 # stable
|
|
with:
|
|
toolchain: 1.92.0
|
|
- uses: Swatinem/rust-cache@779680da715d629ac1d338a641029a2f4372abb5 # v2
|
|
|
|
- name: Run benchmarks
|
|
run: cargo bench --locked 2>&1 | tee benchmark_output.txt
|
|
|
|
- name: Upload benchmark results
|
|
if: always()
|
|
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4
|
|
with:
|
|
name: benchmark-results
|
|
path: |
|
|
target/criterion/
|
|
benchmark_output.txt
|
|
retention-days: 30
|
|
|
|
- name: Post benchmark summary on PR
|
|
if: github.event_name == 'pull_request'
|
|
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
|
|
with:
|
|
script: |
|
|
const fs = require('fs');
|
|
const output = fs.readFileSync('benchmark_output.txt', 'utf8');
|
|
|
|
// Extract Criterion result lines
|
|
const lines = output.split('\n').filter(l =>
|
|
l.includes('time:') || l.includes('change:') || l.includes('Performance')
|
|
);
|
|
|
|
if (lines.length === 0) {
|
|
core.info('No benchmark results to post.');
|
|
return;
|
|
}
|
|
|
|
const body = [
|
|
'## 📊 Benchmark Results',
|
|
'',
|
|
'```',
|
|
lines.join('\n'),
|
|
'```',
|
|
'',
|
|
'<details><summary>Full output</summary>',
|
|
'',
|
|
'```',
|
|
output.substring(0, 60000),
|
|
'```',
|
|
'</details>',
|
|
].join('\n');
|
|
|
|
// Find and update or create comment
|
|
const { data: comments } = await github.rest.issues.listComments({
|
|
owner: context.repo.owner,
|
|
repo: context.repo.repo,
|
|
issue_number: context.payload.pull_request.number,
|
|
});
|
|
|
|
const marker = '## 📊 Benchmark Results';
|
|
const existing = comments.find(c => c.body && c.body.startsWith(marker));
|
|
|
|
if (existing) {
|
|
await github.rest.issues.updateComment({
|
|
owner: context.repo.owner,
|
|
repo: context.repo.repo,
|
|
comment_id: existing.id,
|
|
body,
|
|
});
|
|
} else {
|
|
await github.rest.issues.createComment({
|
|
owner: context.repo.owner,
|
|
repo: context.repo.repo,
|
|
issue_number: context.payload.pull_request.number,
|
|
body,
|
|
});
|
|
}
|