mirror of
https://github.com/anthropics/claude-code-action.git
synced 2026-01-23 06:54:13 +08:00
350 lines
12 KiB
YAML
350 lines
12 KiB
YAML
name: Test Structured Outputs
|
|
|
|
on:
|
|
push:
|
|
branches:
|
|
- main
|
|
pull_request:
|
|
workflow_dispatch:
|
|
|
|
permissions:
|
|
contents: read
|
|
|
|
jobs:
|
|
test-basic-types:
|
|
name: Test Basic Type Conversions
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
|
|
|
|
- name: Test with explicit values
|
|
id: test
|
|
uses: ./base-action
|
|
with:
|
|
prompt: |
|
|
Run this command: echo "test"
|
|
|
|
Then return EXACTLY these values:
|
|
- text_field: "hello"
|
|
- number_field: 42
|
|
- boolean_true: true
|
|
- boolean_false: false
|
|
json_schema: |
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"text_field": {"type": "string"},
|
|
"number_field": {"type": "number"},
|
|
"boolean_true": {"type": "boolean"},
|
|
"boolean_false": {"type": "boolean"}
|
|
},
|
|
"required": ["text_field", "number_field", "boolean_true", "boolean_false"]
|
|
}
|
|
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
|
|
claude_args: "--allowedTools Bash"
|
|
|
|
- name: Verify outputs
|
|
run: |
|
|
# Parse the structured_output JSON
|
|
OUTPUT='${{ steps.test.outputs.structured_output }}'
|
|
|
|
# Test string pass-through
|
|
TEXT_FIELD=$(echo "$OUTPUT" | jq -r '.text_field')
|
|
if [ "$TEXT_FIELD" != "hello" ]; then
|
|
echo "❌ String: expected 'hello', got '$TEXT_FIELD'"
|
|
exit 1
|
|
fi
|
|
|
|
# Test number → string conversion
|
|
NUMBER_FIELD=$(echo "$OUTPUT" | jq -r '.number_field')
|
|
if [ "$NUMBER_FIELD" != "42" ]; then
|
|
echo "❌ Number: expected '42', got '$NUMBER_FIELD'"
|
|
exit 1
|
|
fi
|
|
|
|
# Test boolean → "true" conversion
|
|
BOOLEAN_TRUE=$(echo "$OUTPUT" | jq -r '.boolean_true')
|
|
if [ "$BOOLEAN_TRUE" != "true" ]; then
|
|
echo "❌ Boolean true: expected 'true', got '$BOOLEAN_TRUE'"
|
|
exit 1
|
|
fi
|
|
|
|
# Test boolean → "false" conversion
|
|
BOOLEAN_FALSE=$(echo "$OUTPUT" | jq -r '.boolean_false')
|
|
if [ "$BOOLEAN_FALSE" != "false" ]; then
|
|
echo "❌ Boolean false: expected 'false', got '$BOOLEAN_FALSE'"
|
|
exit 1
|
|
fi
|
|
|
|
echo "✅ All basic type conversions correct"
|
|
|
|
test-complex-types:
|
|
name: Test Arrays and Objects
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
|
|
|
|
- name: Test complex types
|
|
id: test
|
|
uses: ./base-action
|
|
with:
|
|
prompt: |
|
|
Run: echo "ready"
|
|
|
|
Return EXACTLY:
|
|
- items: ["apple", "banana", "cherry"]
|
|
- config: {"key": "value", "count": 3}
|
|
- empty_array: []
|
|
json_schema: |
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"items": {
|
|
"type": "array",
|
|
"items": {"type": "string"}
|
|
},
|
|
"config": {"type": "object"},
|
|
"empty_array": {"type": "array"}
|
|
},
|
|
"required": ["items", "config", "empty_array"]
|
|
}
|
|
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
|
|
claude_args: "--allowedTools Bash"
|
|
|
|
- name: Verify JSON stringification
|
|
run: |
|
|
# Parse the structured_output JSON
|
|
OUTPUT='${{ steps.test.outputs.structured_output }}'
|
|
|
|
# Arrays should be JSON stringified
|
|
if ! echo "$OUTPUT" | jq -e '.items | length == 3' > /dev/null; then
|
|
echo "❌ Array not properly formatted"
|
|
echo "$OUTPUT" | jq '.items'
|
|
exit 1
|
|
fi
|
|
|
|
# Objects should be JSON stringified
|
|
if ! echo "$OUTPUT" | jq -e '.config.key == "value"' > /dev/null; then
|
|
echo "❌ Object not properly formatted"
|
|
echo "$OUTPUT" | jq '.config'
|
|
exit 1
|
|
fi
|
|
|
|
# Empty arrays should work
|
|
if ! echo "$OUTPUT" | jq -e '.empty_array | length == 0' > /dev/null; then
|
|
echo "❌ Empty array not properly formatted"
|
|
echo "$OUTPUT" | jq '.empty_array'
|
|
exit 1
|
|
fi
|
|
|
|
echo "✅ All complex types handled correctly"
|
|
|
|
test-edge-cases:
|
|
name: Test Edge Cases
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
|
|
|
|
- name: Test edge cases
|
|
id: test
|
|
uses: ./base-action
|
|
with:
|
|
prompt: |
|
|
Run: echo "test"
|
|
|
|
Return EXACTLY:
|
|
- zero: 0
|
|
- empty_string: ""
|
|
- negative: -5
|
|
- decimal: 3.14
|
|
json_schema: |
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"zero": {"type": "number"},
|
|
"empty_string": {"type": "string"},
|
|
"negative": {"type": "number"},
|
|
"decimal": {"type": "number"}
|
|
},
|
|
"required": ["zero", "empty_string", "negative", "decimal"]
|
|
}
|
|
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
|
|
claude_args: "--allowedTools Bash"
|
|
|
|
- name: Verify edge cases
|
|
run: |
|
|
# Parse the structured_output JSON
|
|
OUTPUT='${{ steps.test.outputs.structured_output }}'
|
|
|
|
# Zero should be "0", not empty or falsy
|
|
ZERO=$(echo "$OUTPUT" | jq -r '.zero')
|
|
if [ "$ZERO" != "0" ]; then
|
|
echo "❌ Zero: expected '0', got '$ZERO'"
|
|
exit 1
|
|
fi
|
|
|
|
# Empty string should be empty (not "null" or missing)
|
|
EMPTY_STRING=$(echo "$OUTPUT" | jq -r '.empty_string')
|
|
if [ "$EMPTY_STRING" != "" ]; then
|
|
echo "❌ Empty string: expected '', got '$EMPTY_STRING'"
|
|
exit 1
|
|
fi
|
|
|
|
# Negative numbers should work
|
|
NEGATIVE=$(echo "$OUTPUT" | jq -r '.negative')
|
|
if [ "$NEGATIVE" != "-5" ]; then
|
|
echo "❌ Negative: expected '-5', got '$NEGATIVE'"
|
|
exit 1
|
|
fi
|
|
|
|
# Decimals should preserve precision
|
|
DECIMAL=$(echo "$OUTPUT" | jq -r '.decimal')
|
|
if [ "$DECIMAL" != "3.14" ]; then
|
|
echo "❌ Decimal: expected '3.14', got '$DECIMAL'"
|
|
exit 1
|
|
fi
|
|
|
|
echo "✅ All edge cases handled correctly"
|
|
|
|
test-name-sanitization:
|
|
name: Test Output Name Sanitization
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
|
|
|
|
- name: Test special characters in field names
|
|
id: test
|
|
uses: ./base-action
|
|
with:
|
|
prompt: |
|
|
Run: echo "test"
|
|
Return EXACTLY: {test-result: "passed", item_count: 10}
|
|
json_schema: |
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"test-result": {"type": "string"},
|
|
"item_count": {"type": "number"}
|
|
},
|
|
"required": ["test-result", "item_count"]
|
|
}
|
|
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
|
|
claude_args: "--allowedTools Bash"
|
|
|
|
- name: Verify sanitized names work
|
|
run: |
|
|
# Parse the structured_output JSON
|
|
OUTPUT='${{ steps.test.outputs.structured_output }}'
|
|
|
|
# Hyphens should be preserved in the JSON
|
|
TEST_RESULT=$(echo "$OUTPUT" | jq -r '.["test-result"]')
|
|
if [ "$TEST_RESULT" != "passed" ]; then
|
|
echo "❌ Hyphenated name failed: expected 'passed', got '$TEST_RESULT'"
|
|
exit 1
|
|
fi
|
|
|
|
# Underscores should work
|
|
ITEM_COUNT=$(echo "$OUTPUT" | jq -r '.item_count')
|
|
if [ "$ITEM_COUNT" != "10" ]; then
|
|
echo "❌ Underscore name failed: expected '10', got '$ITEM_COUNT'"
|
|
exit 1
|
|
fi
|
|
|
|
echo "✅ Name sanitization works"
|
|
|
|
test-execution-file-structure:
|
|
name: Test Execution File Format
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
|
|
|
|
- name: Run with structured output
|
|
id: test
|
|
uses: ./base-action
|
|
with:
|
|
prompt: "Run: echo 'complete'. Return: {done: true}"
|
|
json_schema: |
|
|
{
|
|
"type": "object",
|
|
"properties": {
|
|
"done": {"type": "boolean"}
|
|
},
|
|
"required": ["done"]
|
|
}
|
|
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
|
|
claude_args: "--allowedTools Bash"
|
|
|
|
- name: Verify execution file contains structured_output
|
|
run: |
|
|
FILE="${{ steps.test.outputs.execution_file }}"
|
|
|
|
# Check file exists
|
|
if [ ! -f "$FILE" ]; then
|
|
echo "❌ Execution file missing"
|
|
exit 1
|
|
fi
|
|
|
|
# Check for structured_output field
|
|
if ! jq -e '.[] | select(.type == "result") | .structured_output' "$FILE" > /dev/null; then
|
|
echo "❌ No structured_output in execution file"
|
|
cat "$FILE"
|
|
exit 1
|
|
fi
|
|
|
|
# Verify the actual value
|
|
DONE=$(jq -r '.[] | select(.type == "result") | .structured_output.done' "$FILE")
|
|
if [ "$DONE" != "true" ]; then
|
|
echo "❌ Wrong value in execution file"
|
|
exit 1
|
|
fi
|
|
|
|
echo "✅ Execution file format correct"
|
|
|
|
test-summary:
|
|
name: Summary
|
|
runs-on: ubuntu-latest
|
|
needs:
|
|
- test-basic-types
|
|
- test-complex-types
|
|
- test-edge-cases
|
|
- test-name-sanitization
|
|
- test-execution-file-structure
|
|
if: always()
|
|
steps:
|
|
- name: Generate Summary
|
|
run: |
|
|
echo "# Structured Output Tests (Optimized)" >> $GITHUB_STEP_SUMMARY
|
|
echo "" >> $GITHUB_STEP_SUMMARY
|
|
echo "Fast, deterministic tests using explicit prompts" >> $GITHUB_STEP_SUMMARY
|
|
echo "" >> $GITHUB_STEP_SUMMARY
|
|
echo "| Test | Result |" >> $GITHUB_STEP_SUMMARY
|
|
echo "|------|--------|" >> $GITHUB_STEP_SUMMARY
|
|
echo "| Basic Types | ${{ needs.test-basic-types.result == 'success' && '✅ PASS' || '❌ FAIL' }} |" >> $GITHUB_STEP_SUMMARY
|
|
echo "| Complex Types | ${{ needs.test-complex-types.result == 'success' && '✅ PASS' || '❌ FAIL' }} |" >> $GITHUB_STEP_SUMMARY
|
|
echo "| Edge Cases | ${{ needs.test-edge-cases.result == 'success' && '✅ PASS' || '❌ FAIL' }} |" >> $GITHUB_STEP_SUMMARY
|
|
echo "| Name Sanitization | ${{ needs.test-name-sanitization.result == 'success' && '✅ PASS' || '❌ FAIL' }} |" >> $GITHUB_STEP_SUMMARY
|
|
echo "| Execution File | ${{ needs.test-execution-file-structure.result == 'success' && '✅ PASS' || '❌ FAIL' }} |" >> $GITHUB_STEP_SUMMARY
|
|
|
|
# Check if all passed
|
|
ALL_PASSED=${{
|
|
needs.test-basic-types.result == 'success' &&
|
|
needs.test-complex-types.result == 'success' &&
|
|
needs.test-edge-cases.result == 'success' &&
|
|
needs.test-name-sanitization.result == 'success' &&
|
|
needs.test-execution-file-structure.result == 'success'
|
|
}}
|
|
|
|
if [ "$ALL_PASSED" = "true" ]; then
|
|
echo "" >> $GITHUB_STEP_SUMMARY
|
|
echo "## ✅ All Tests Passed" >> $GITHUB_STEP_SUMMARY
|
|
else
|
|
echo "" >> $GITHUB_STEP_SUMMARY
|
|
echo "## ❌ Some Tests Failed" >> $GITHUB_STEP_SUMMARY
|
|
exit 1
|
|
fi
|