bench: migrate Haiku calls to @anthropic-ai/claude-agent-sdk (auto-de… #15

	name: CI

	on:
	push:
	branches: [main]
	pull_request:
	branches: [main]

	permissions:
	contents: read

	jobs:
	test:
	name: Test (Node ${{ matrix.node }})
	runs-on: ubuntu-latest
	strategy:
	fail-fast: false
	matrix:
	node: ['18', '20', '22']
	steps:
	- uses: actions/checkout@v4

	- name: Setup Node.js
	uses: actions/setup-node@v4
	with:
	node-version: ${{ matrix.node }}
	cache: 'npm'

	- name: Install dependencies
	run: npm ci

	- name: Build TypeScript
	run: npm run build

	- name: Run test suite
	run: npm test
	env:
	# Ensure hooks cannot accidentally POST to a real port during tests
	CONTEXT_MEM_API_PORT: '1'

	typecheck:
	name: Typecheck
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-node@v4
	with:
	node-version: '20'
	cache: 'npm'
	- name: Install dependencies
	run: npm ci
	- name: Build TypeScript
	run: npm run build
	- name: Type-check (tsc --noEmit)
	run: npm run lint

	bench-quick:
	name: Benchmark smoke (50 queries)
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-node@v4
	with:
	node-version: '20'
	cache: 'npm'
	- name: Install dependencies
	run: npm ci
	- name: Build TypeScript
	run: npm run build
	- name: Check for LongMemEval dataset
	id: dataset
	run: \|
	if [ -f /tmp/longmemeval-data/longmemeval_s_cleaned.json ]; then
	echo "present=true" >> "$GITHUB_OUTPUT"
	else
	echo "present=false" >> "$GITHUB_OUTPUT"
	fi
	- name: Run quick benchmark
	if: steps.dataset.outputs.present == 'true'
	continue-on-error: true # benchmark command failure must not block CI green
	run: npm run bench:quick

Navigation Menu