mirrors/z3
3
0
Fork 0
mirror of https://github.com/Z3Prover/z3 synced 2026-04-22 03:43:29 +00:00
Code Activity

recompiled

Browse source 
Signed-off-by: Nikolaj Bjorner <nbjorner@microsoft.com>
This commit is contained in:
Nikolaj Bjorner 2026-03-20 16:32:44 -07:00
parent 488c02711d
commit ccdfdbb176
17 changed files with 998 additions and 604 deletions
Download patch file Download diff file Expand all files Collapse all files

436
.github/workflows/ostrich-benchmark.lock.yml generated vendored
View file

@ -1,3 +1,4 @@
#
# ___ _ _
# / _ \ | | (_)
# | |_| | __ _ ___ _ __ | |_ _ ___
@ -12,7 +13,7 @@
# \ /\ / (_) | | | | ( | | | | (_) \ V V /\__ \
# \/ \/ \___/|_| |_|\_\|_| |_|\___/ \_/\_/ |___/
#
# This file was automatically generated by gh-aw (v0.62.4). DO NOT EDIT.
# This file was automatically generated by gh-aw (v0.57.2). DO NOT EDIT.
#
# To update this file, edit the corresponding .md file and run:
# gh aw compile
@ -22,9 +23,9 @@
#
# Run Z3 string solver benchmarks (seq vs nseq) and ZIPT on all Ostrich benchmarks from tests/ostrich.zip on the c3 branch and post results as a GitHub discussion
#
# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"3ac70e9acd74c08c55c4c8e60b61e24db0f1e0dbd5bc8e25c62af0279aea4d6b","compiler_version":"v0.62.4","strict":true,"agent_id":"copilot"}
# gh-aw-metadata: {"schema_version":"v2","frontmatter_hash":"3ac70e9acd74c08c55c4c8e60b61e24db0f1e0dbd5bc8e25c62af0279aea4d6b","compiler_version":"v0.57.2","strict":true}
name: "Ostrich Benchmark"
name: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
"on":
schedule:
- cron: "0 6 * * *"
@ -35,7 +36,7 @@ permissions: {}
concurrency:
group: "gh-aw-${{ github.workflow }}"
run-name: "Ostrich Benchmark"
run-name: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
jobs:
activation:
@ -45,14 +46,13 @@ jobs:
outputs:
comment_id: ""
comment_repo: ""
lockdown_check_failed: ${{ steps.generate_aw_info.outputs.lockdown_check_failed == 'true' }}
model: ${{ steps.generate_aw_info.outputs.model }}
secret_verification_result: ${{ steps.validate-secret.outputs.verification_result }}
steps:
- name: Setup Scripts
uses: github/gh-aw-actions/setup@v0.62.4
uses: github/gh-aw/actions/setup@32b3a711a9ee97d38e3989c90af0385aff0066a7 # v0.57.2
with:
destination: ${{ runner.temp }}/gh-aw/actions
destination: /opt/gh-aw/actions
- name: Generate agentic run info
id: generate_aw_info
env:
@ -61,27 +61,25 @@ jobs:
GH_AW_INFO_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || '' }}
GH_AW_INFO_VERSION: ""
GH_AW_INFO_AGENT_VERSION: "latest"
GH_AW_INFO_CLI_VERSION: "v0.62.4"
GH_AW_INFO_WORKFLOW_NAME: "Ostrich Benchmark"
GH_AW_INFO_CLI_VERSION: "v0.57.2"
GH_AW_INFO_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
GH_AW_INFO_EXPERIMENTAL: "false"
GH_AW_INFO_SUPPORTS_TOOLS_ALLOWLIST: "true"
GH_AW_INFO_STAGED: "false"
GH_AW_INFO_ALLOWED_DOMAINS: '["defaults"]'
GH_AW_INFO_FIREWALL_ENABLED: "true"
GH_AW_INFO_AWF_VERSION: "v0.24.5"
GH_AW_INFO_AWF_VERSION: "v0.23.0"
GH_AW_INFO_AWMG_VERSION: ""
GH_AW_INFO_FIREWALL_TYPE: "squid"
GH_AW_COMPILED_STRICT: "true"
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
with:
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/generate_aw_info.cjs');
const { main } = require('/opt/gh-aw/actions/generate_aw_info.cjs');
await main(core, context);
- name: Validate COPILOT_GITHUB_TOKEN secret
id: validate-secret
run: ${RUNNER_TEMP}/gh-aw/actions/validate_multi_secret.sh COPILOT_GITHUB_TOKEN 'GitHub Copilot CLI' https://github.github.com/gh-aw/reference/engines/#github-copilot-default
run: /opt/gh-aw/actions/validate_multi_secret.sh COPILOT_GITHUB_TOKEN 'GitHub Copilot CLI' https://github.github.com/gh-aw/reference/engines/#github-copilot-default
env:
COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- name: Checkout .github and .agents folders
@ -99,9 +97,9 @@ jobs:
GH_AW_WORKFLOW_FILE: "ostrich-benchmark.lock.yml"
with:
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/check_workflow_timestamp_api.cjs');
const { main } = require('/opt/gh-aw/actions/check_workflow_timestamp_api.cjs');
await main();
- name: Create prompt with built-in context
env:
@ -116,15 +114,15 @@ jobs:
GH_AW_GITHUB_RUN_ID: ${{ github.run_id }}
GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
run: |
bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh
bash /opt/gh-aw/actions/create_prompt_first.sh
{
cat << 'GH_AW_PROMPT_EOF'
<system>
GH_AW_PROMPT_EOF
cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md"
cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md"
cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md"
cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md"
cat "/opt/gh-aw/prompts/xpia.md"
cat "/opt/gh-aw/prompts/temp_folder_prompt.md"
cat "/opt/gh-aw/prompts/markdown.md"
cat "/opt/gh-aw/prompts/safe_outputs_prompt.md"
cat << 'GH_AW_PROMPT_EOF'
<safe-output-tools>
Tools: create_discussion, missing_tool, missing_data, noop
@ -158,7 +156,6 @@ jobs:
</github-context>
GH_AW_PROMPT_EOF
cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md"
cat << 'GH_AW_PROMPT_EOF'
</system>
GH_AW_PROMPT_EOF
@ -170,11 +167,13 @@ jobs:
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
env:
GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
GH_AW_GITHUB_REPOSITORY: ${{ github.repository }}
GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
with:
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/interpolate_prompt.cjs');
const { main } = require('/opt/gh-aw/actions/interpolate_prompt.cjs');
await main();
- name: Substitute placeholders
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
@ -190,10 +189,10 @@ jobs:
GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
with:
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const substitutePlaceholders = require('${{ runner.temp }}/gh-aw/actions/substitute_placeholders.cjs');
const substitutePlaceholders = require('/opt/gh-aw/actions/substitute_placeholders.cjs');
// Call the substitution function
return await substitutePlaceholders({
@ -212,14 +211,14 @@ jobs:
- name: Validate prompt placeholders
env:
GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
run: bash ${RUNNER_TEMP}/gh-aw/actions/validate_prompt_placeholders.sh
run: bash /opt/gh-aw/actions/validate_prompt_placeholders.sh
- name: Print prompt
env:
GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
run: bash ${RUNNER_TEMP}/gh-aw/actions/print_prompt_summary.sh
run: bash /opt/gh-aw/actions/print_prompt_summary.sh
- name: Upload activation artifact
if: success()
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7
with:
name: activation
path: |
@ -239,6 +238,9 @@ jobs:
GH_AW_ASSETS_BRANCH: ""
GH_AW_ASSETS_MAX_SIZE_KB: 0
GH_AW_MCP_LOG_DIR: /tmp/gh-aw/mcp-logs/safeoutputs
GH_AW_SAFE_OUTPUTS: /opt/gh-aw/safeoutputs/outputs.jsonl
GH_AW_SAFE_OUTPUTS_CONFIG_PATH: /opt/gh-aw/safeoutputs/config.json
GH_AW_SAFE_OUTPUTS_TOOLS_PATH: /opt/gh-aw/safeoutputs/tools.json
GH_AW_WORKFLOW_ID_SANITIZED: ostrichbenchmark
outputs:
checkout_pr_success: ${{ steps.checkout-pr.outputs.checkout_pr_success || 'true' }}
@ -251,20 +253,11 @@ jobs:
output_types: ${{ steps.collect_output.outputs.output_types }}
steps:
- name: Setup Scripts
uses: github/gh-aw-actions/setup@v0.62.4
uses: github/gh-aw/actions/setup@32b3a711a9ee97d38e3989c90af0385aff0066a7 # v0.57.2
with:
destination: ${{ runner.temp }}/gh-aw/actions
- name: Set runtime paths
run: |
echo "GH_AW_SAFE_OUTPUTS=${RUNNER_TEMP}/gh-aw/safeoutputs/outputs.jsonl" >> "$GITHUB_ENV"
echo "GH_AW_SAFE_OUTPUTS_CONFIG_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/config.json" >> "$GITHUB_ENV"
echo "GH_AW_SAFE_OUTPUTS_TOOLS_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/tools.json" >> "$GITHUB_ENV"
destination: /opt/gh-aw/actions
- name: Create gh-aw temp directory
run: bash ${RUNNER_TEMP}/gh-aw/actions/create_gh_aw_tmp_dir.sh
- name: Configure gh CLI for GitHub Enterprise
run: bash ${RUNNER_TEMP}/gh-aw/actions/configure_gh_for_ghe.sh
env:
GH_TOKEN: ${{ github.token }}
run: bash /opt/gh-aw/actions/create_gh_aw_tmp_dir.sh
- name: Checkout c3 branch
uses: actions/checkout@93cb6efe18208431cddfb8368fd83d5badbf9bfd # v5
with:
@ -294,16 +287,14 @@ jobs:
with:
github-token: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/checkout_pr_branch.cjs');
const { main } = require('/opt/gh-aw/actions/checkout_pr_branch.cjs');
await main();
- name: Install GitHub Copilot CLI
run: ${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh latest
env:
GH_HOST: github.com
- name: Install AWF binary
run: bash ${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh v0.24.5
run: /opt/gh-aw/actions/install_copilot_cli.sh latest
- name: Install awf binary
run: bash /opt/gh-aw/actions/install_awf_binary.sh v0.23.0
- name: Determine automatic lockdown mode for GitHub MCP Server
id: determine-automatic-lockdown
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
@ -312,30 +303,150 @@ jobs:
GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }}
with:
script: |
const determineAutomaticLockdown = require('${{ runner.temp }}/gh-aw/actions/determine_automatic_lockdown.cjs');
const determineAutomaticLockdown = require('/opt/gh-aw/actions/determine_automatic_lockdown.cjs');
await determineAutomaticLockdown(github, context, core);
- name: Download container images
run: bash ${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh ghcr.io/github/gh-aw-firewall/agent:0.24.5 ghcr.io/github/gh-aw-firewall/api-proxy:0.24.5 ghcr.io/github/gh-aw-firewall/squid:0.24.5 ghcr.io/github/gh-aw-mcpg:v0.1.19 ghcr.io/github/github-mcp-server:v0.32.0 node:lts-alpine
run: bash /opt/gh-aw/actions/download_docker_images.sh ghcr.io/github/gh-aw-firewall/agent:0.23.0 ghcr.io/github/gh-aw-firewall/api-proxy:0.23.0 ghcr.io/github/gh-aw-firewall/squid:0.23.0 ghcr.io/github/gh-aw-mcpg:v0.1.8 ghcr.io/github/github-mcp-server:v0.32.0 node:lts-alpine
- name: Write Safe Outputs Config
run: |
mkdir -p ${RUNNER_TEMP}/gh-aw/safeoutputs
mkdir -p /opt/gh-aw/safeoutputs
mkdir -p /tmp/gh-aw/safeoutputs
mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs
cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_EOF'
cat > /opt/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_EOF'
{"create_discussion":{"expires":168,"max":1},"create_missing_tool_issue":{"max":1,"title_prefix":"[missing tool]"},"missing_data":{},"missing_tool":{},"noop":{"max":1}}
GH_AW_SAFE_OUTPUTS_CONFIG_EOF
- name: Write Safe Outputs Tools
run: |
cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_EOF'
{
"description_suffixes": {
"create_discussion": " CONSTRAINTS: Maximum 1 discussion(s) can be created. Title will be prefixed with \"[Ostrich Benchmark] \". Discussions will be created in category \"agentic workflows\"."
cat > /opt/gh-aw/safeoutputs/tools.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_EOF'
[
{
"description": "Create a GitHub discussion for announcements, Q\u0026A, reports, status updates, or community conversations. Use this for content that benefits from threaded replies, doesn't require task tracking, or serves as documentation. For actionable work items that need assignment and status tracking, use create_issue instead. CONSTRAINTS: Maximum 1 discussion(s) can be created. Title will be prefixed with \"[Ostrich Benchmark] \". Discussions will be created in category \"agentic workflows\".",
"inputSchema": {
"additionalProperties": false,
"properties": {
"body": {
"description": "Discussion content in Markdown. Do NOT repeat the title as a heading since it already appears as the discussion's h1. Include all relevant context, findings, or questions.",
"type": "string"
},
"category": {
"description": "Discussion category by name (e.g., 'General'), slug (e.g., 'general'), or ID. If omitted, uses the first available category. Category must exist in the repository.",
"type": "string"
},
"integrity": {
"description": "Trustworthiness level of the message source (e.g., \"low\", \"medium\", \"high\").",
"type": "string"
},
"secrecy": {
"description": "Confidentiality level of the message content (e.g., \"public\", \"internal\", \"private\").",
"type": "string"
},
"title": {
"description": "Concise discussion title summarizing the topic. The title appears as the main heading, so keep it brief and descriptive.",
"type": "string"
}
},
"required": [
"title",
"body"
],
"type": "object"
},
"name": "create_discussion"
},
"repo_params": {},
"dynamic_tools": []
}
GH_AW_SAFE_OUTPUTS_TOOLS_META_EOF
cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_EOF'
{
"description": "Report that a tool or capability needed to complete the task is not available, or share any information you deem important about missing functionality or limitations. Use this when you cannot accomplish what was requested because the required functionality is missing or access is restricted.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"alternatives": {
"description": "Any workarounds, manual steps, or alternative approaches the user could take (max 256 characters).",
"type": "string"
},
"integrity": {
"description": "Trustworthiness level of the message source (e.g., \"low\", \"medium\", \"high\").",
"type": "string"
},
"reason": {
"description": "Explanation of why this tool is needed or what information you want to share about the limitation (max 256 characters).",
"type": "string"
},
"secrecy": {
"description": "Confidentiality level of the message content (e.g., \"public\", \"internal\", \"private\").",
"type": "string"
},
"tool": {
"description": "Optional: Name or description of the missing tool or capability (max 128 characters). Be specific about what functionality is needed.",
"type": "string"
}
},
"required": [
"reason"
],
"type": "object"
},
"name": "missing_tool"
},
{
"description": "Log a transparency message when no significant actions are needed. Use this to confirm workflow completion and provide visibility when analysis is complete but no changes or outputs are required (e.g., 'No issues found', 'All checks passed'). This ensures the workflow produces human-visible output even when no other actions are taken.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"integrity": {
"description": "Trustworthiness level of the message source (e.g., \"low\", \"medium\", \"high\").",
"type": "string"
},
"message": {
"description": "Status or completion message to log. Should explain what was analyzed and the outcome (e.g., 'Code review complete - no issues found', 'Analysis complete - all tests passing').",
"type": "string"
},
"secrecy": {
"description": "Confidentiality level of the message content (e.g., \"public\", \"internal\", \"private\").",
"type": "string"
}
},
"required": [
"message"
],
"type": "object"
},
"name": "noop"
},
{
"description": "Report that data or information needed to complete the task is not available. Use this when you cannot accomplish what was requested because required data, context, or information is missing.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"alternatives": {
"description": "Any workarounds, manual steps, or alternative approaches the user could take (max 256 characters).",
"type": "string"
},
"context": {
"description": "Additional context about the missing data or where it should come from (max 256 characters).",
"type": "string"
},
"data_type": {
"description": "Type or description of the missing data or information (max 128 characters). Be specific about what data is needed.",
"type": "string"
},
"integrity": {
"description": "Trustworthiness level of the message source (e.g., \"low\", \"medium\", \"high\").",
"type": "string"
},
"reason": {
"description": "Explanation of why this data is needed to complete the task (max 256 characters).",
"type": "string"
},
"secrecy": {
"description": "Confidentiality level of the message content (e.g., \"public\", \"internal\", \"private\").",
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "missing_data"
}
]
GH_AW_SAFE_OUTPUTS_TOOLS_EOF
cat > /opt/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_EOF'
{
"create_discussion": {
"defaultMax": 1,
@ -422,7 +533,6 @@ jobs:
}
}
GH_AW_SAFE_OUTPUTS_VALIDATION_EOF
node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs
- name: Generate Safe Outputs MCP Server Config
id: safe-outputs-config
run: |
@ -447,8 +557,8 @@ jobs:
DEBUG: '*'
GH_AW_SAFE_OUTPUTS_PORT: ${{ steps.safe-outputs-config.outputs.safe_outputs_port }}
GH_AW_SAFE_OUTPUTS_API_KEY: ${{ steps.safe-outputs-config.outputs.safe_outputs_api_key }}
GH_AW_SAFE_OUTPUTS_TOOLS_PATH: ${{ runner.temp }}/gh-aw/safeoutputs/tools.json
GH_AW_SAFE_OUTPUTS_CONFIG_PATH: ${{ runner.temp }}/gh-aw/safeoutputs/config.json
GH_AW_SAFE_OUTPUTS_TOOLS_PATH: /opt/gh-aw/safeoutputs/tools.json
GH_AW_SAFE_OUTPUTS_CONFIG_PATH: /opt/gh-aw/safeoutputs/config.json
GH_AW_MCP_LOG_DIR: /tmp/gh-aw/mcp-logs/safeoutputs
run: |
# Environment variables are set above to prevent template injection
@ -459,7 +569,7 @@ jobs:
export GH_AW_SAFE_OUTPUTS_CONFIG_PATH
export GH_AW_MCP_LOG_DIR
bash ${RUNNER_TEMP}/gh-aw/actions/start_safe_outputs_server.sh
bash /opt/gh-aw/actions/start_safe_outputs_server.sh
- name: Start MCP Gateway
id: start-mcp-gateway
@ -467,8 +577,7 @@ jobs:
GH_AW_SAFE_OUTPUTS: ${{ env.GH_AW_SAFE_OUTPUTS }}
GH_AW_SAFE_OUTPUTS_API_KEY: ${{ steps.safe-outputs-start.outputs.api_key }}
GH_AW_SAFE_OUTPUTS_PORT: ${{ steps.safe-outputs-start.outputs.port }}
GITHUB_MCP_GUARD_MIN_INTEGRITY: ${{ steps.determine-automatic-lockdown.outputs.min_integrity }}
GITHUB_MCP_GUARD_REPOS: ${{ steps.determine-automatic-lockdown.outputs.repos }}
GITHUB_MCP_LOCKDOWN: ${{ steps.determine-automatic-lockdown.outputs.lockdown == 'true' && '1' || '0' }}
GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
run: |
set -eo pipefail
@ -486,26 +595,20 @@ jobs:
export DEBUG="*"
export GH_AW_ENGINE="copilot"
export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.1.19'
export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_LOCKDOWN -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.1.8'
mkdir -p /home/runner/.copilot
cat << GH_AW_MCP_CONFIG_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh
cat << GH_AW_MCP_CONFIG_EOF | bash /opt/gh-aw/actions/start_mcp_gateway.sh
{
"mcpServers": {
"github": {
"type": "stdio",
"container": "ghcr.io/github/github-mcp-server:v0.32.0",
"env": {
"GITHUB_HOST": "\${GITHUB_SERVER_URL}",
"GITHUB_LOCKDOWN_MODE": "$GITHUB_MCP_LOCKDOWN",
"GITHUB_PERSONAL_ACCESS_TOKEN": "\${GITHUB_MCP_SERVER_TOKEN}",
"GITHUB_READ_ONLY": "1",
"GITHUB_TOOLSETS": "context,repos,issues,pull_requests"
},
"guard-policies": {
"allow-only": {
"min-integrity": "$GITHUB_MCP_GUARD_MIN_INTEGRITY",
"repos": "$GITHUB_MCP_GUARD_REPOS"
}
}
},
"safeoutputs": {
@ -513,13 +616,6 @@ jobs:
"url": "http://host.docker.internal:$GH_AW_SAFE_OUTPUTS_PORT",
"headers": {
"Authorization": "\${GH_AW_SAFE_OUTPUTS_API_KEY}"
},
"guard-policies": {
"write-sink": {
"accept": [
"*"
]
}
}
}
},
@ -532,13 +628,12 @@ jobs:
}
GH_AW_MCP_CONFIG_EOF
- name: Download activation artifact
uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8
with:
name: activation
path: /tmp/gh-aw
- name: Clean git credentials
continue-on-error: true
run: bash ${RUNNER_TEMP}/gh-aw/actions/clean_git_credentials.sh
run: bash /opt/gh-aw/actions/clean_git_credentials.sh
- name: Execute GitHub Copilot CLI
id: agentic_execution
# Copilot CLI tool arguments (sorted):
@ -547,7 +642,7 @@ jobs:
set -o pipefail
touch /tmp/gh-aw/agent-step-summary.md
# shellcheck disable=SC1003
sudo -E awf --env-all --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" --allow-domains "api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,github.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,ppa.launchpad.net,raw.githubusercontent.com,registry.npmjs.org,s.symcb.com,s.symcd.com,security.ubuntu.com,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com,www.googleapis.com" --log-level info --proxy-logs-dir /tmp/gh-aw/sandbox/firewall/logs --enable-host-access --image-tag 0.24.5 --skip-pull --enable-api-proxy \
sudo -E awf --env-all --container-workdir "${GITHUB_WORKSPACE}" --allow-domains "api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,github.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,ppa.launchpad.net,raw.githubusercontent.com,registry.npmjs.org,s.symcb.com,s.symcd.com,security.ubuntu.com,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com" --log-level info --proxy-logs-dir /tmp/gh-aw/sandbox/firewall/logs --enable-host-access --image-tag 0.23.0 --skip-pull --enable-api-proxy \
-- /bin/bash -c '/usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --add-dir "${GITHUB_WORKSPACE}" --disable-builtin-mcps --allow-all-tools --allow-all-paths --prompt "$(cat /tmp/gh-aw/aw-prompts/prompt.txt)"' 2>&1 | tee -a /tmp/gh-aw/agent-stdio.log
env:
COPILOT_AGENT_RUNNER_TYPE: STANDALONE
@ -557,7 +652,7 @@ jobs:
GH_AW_PHASE: agent
GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
GH_AW_SAFE_OUTPUTS: ${{ env.GH_AW_SAFE_OUTPUTS }}
GH_AW_VERSION: v0.62.4
GH_AW_VERSION: v0.57.2
GITHUB_API_URL: ${{ github.api_url }}
GITHUB_AW: true
GITHUB_HEAD_REF: ${{ github.head_ref }}
@ -575,7 +670,7 @@ jobs:
id: detect-inference-error
if: always()
continue-on-error: true
run: bash ${RUNNER_TEMP}/gh-aw/actions/detect_inference_access_error.sh
run: bash /opt/gh-aw/actions/detect_inference_access_error.sh
- name: Configure Git credentials
env:
REPO_NAME: ${{ github.repository }}
@ -613,15 +708,15 @@ jobs:
MCP_GATEWAY_API_KEY: ${{ steps.start-mcp-gateway.outputs.gateway-api-key }}
GATEWAY_PID: ${{ steps.start-mcp-gateway.outputs.gateway-pid }}
run: |
bash ${RUNNER_TEMP}/gh-aw/actions/stop_mcp_gateway.sh "$GATEWAY_PID"
bash /opt/gh-aw/actions/stop_mcp_gateway.sh "$GATEWAY_PID"
- name: Redact secrets in logs
if: always()
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
with:
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/redact_secrets.cjs');
const { main } = require('/opt/gh-aw/actions/redact_secrets.cjs');
await main();
env:
GH_AW_SECRET_NAMES: 'COPILOT_GITHUB_TOKEN,GH_AW_GITHUB_MCP_SERVER_TOKEN,GH_AW_GITHUB_TOKEN,GITHUB_TOKEN'
@ -631,27 +726,44 @@ jobs:
SECRET_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Append agent step summary
if: always()
run: bash ${RUNNER_TEMP}/gh-aw/actions/append_agent_step_summary.sh
- name: Copy Safe Outputs
run: bash /opt/gh-aw/actions/append_agent_step_summary.sh
- name: Upload Safe Outputs
if: always()
run: |
mkdir -p /tmp/gh-aw
cp "$GH_AW_SAFE_OUTPUTS" /tmp/gh-aw/safeoutputs.jsonl 2>/dev/null || true
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7
with:
name: safe-output
path: ${{ env.GH_AW_SAFE_OUTPUTS }}
if-no-files-found: warn
- name: Ingest agent output
id: collect_output
if: always()
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
env:
GH_AW_SAFE_OUTPUTS: ${{ env.GH_AW_SAFE_OUTPUTS }}
GH_AW_ALLOWED_DOMAINS: "api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,github.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,ppa.launchpad.net,raw.githubusercontent.com,registry.npmjs.org,s.symcb.com,s.symcd.com,security.ubuntu.com,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com,www.googleapis.com"
GH_AW_ALLOWED_DOMAINS: "api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,github.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,ppa.launchpad.net,raw.githubusercontent.com,registry.npmjs.org,s.symcb.com,s.symcd.com,security.ubuntu.com,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com"
GITHUB_SERVER_URL: ${{ github.server_url }}
GITHUB_API_URL: ${{ github.api_url }}
with:
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/collect_ndjson_output.cjs');
const { main } = require('/opt/gh-aw/actions/collect_ndjson_output.cjs');
await main();
- name: Upload sanitized agent output
if: always() && env.GH_AW_AGENT_OUTPUT
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7
with:
name: agent-output
path: ${{ env.GH_AW_AGENT_OUTPUT }}
if-no-files-found: warn
- name: Upload engine output files
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7
with:
name: agent_outputs
path: |
/tmp/gh-aw/sandbox/agent/logs/
/tmp/gh-aw/redacted-urls.log
if-no-files-found: ignore
- name: Parse agent logs for step summary
if: always()
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
@ -659,18 +771,18 @@ jobs:
GH_AW_AGENT_OUTPUT: /tmp/gh-aw/sandbox/agent/logs/
with:
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_copilot_log.cjs');
const { main } = require('/opt/gh-aw/actions/parse_copilot_log.cjs');
await main();
- name: Parse MCP Gateway logs for step summary
if: always()
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
with:
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_mcp_gateway_log.cjs');
const { main } = require('/opt/gh-aw/actions/parse_mcp_gateway_log.cjs');
await main();
- name: Print firewall logs
if: always()
@ -690,19 +802,15 @@ jobs:
- name: Upload agent artifacts
if: always()
continue-on-error: true
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7
with:
name: agent
name: agent-artifacts
path: |
/tmp/gh-aw/aw-prompts/prompt.txt
/tmp/gh-aw/sandbox/agent/logs/
/tmp/gh-aw/redacted-urls.log
/tmp/gh-aw/mcp-logs/
/tmp/gh-aw/sandbox/firewall/logs/
/tmp/gh-aw/agent-stdio.log
/tmp/gh-aw/agent/
/tmp/gh-aw/safeoutputs.jsonl
/tmp/gh-aw/agent_output.json
if-no-files-found: ignore
# --- Threat Detection (inline) ---
- name: Check if detection needed
@ -740,14 +848,14 @@ jobs:
if: always() && steps.detection_guard.outputs.run_detection == 'true'
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
env:
WORKFLOW_NAME: "Ostrich Benchmark"
WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
WORKFLOW_DESCRIPTION: "Run Z3 string solver benchmarks (seq vs nseq) and ZIPT on all Ostrich benchmarks from tests/ostrich.zip on the c3 branch and post results as a GitHub discussion"
HAS_PATCH: ${{ steps.collect_output.outputs.has_patch }}
with:
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/setup_threat_detection.cjs');
const { main } = require('/opt/gh-aw/actions/setup_threat_detection.cjs');
await main();
- name: Ensure threat-detection directory and log
if: always() && steps.detection_guard.outputs.run_detection == 'true'
@ -770,7 +878,7 @@ jobs:
set -o pipefail
touch /tmp/gh-aw/agent-step-summary.md
# shellcheck disable=SC1003
sudo -E awf --env-all --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" --allow-domains "api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,github.com,host.docker.internal,raw.githubusercontent.com,registry.npmjs.org,telemetry.enterprise.githubcopilot.com" --log-level info --proxy-logs-dir /tmp/gh-aw/sandbox/firewall/logs --enable-host-access --image-tag 0.24.5 --skip-pull --enable-api-proxy \
sudo -E awf --env-all --container-workdir "${GITHUB_WORKSPACE}" --allow-domains "api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,github.com,host.docker.internal,raw.githubusercontent.com,registry.npmjs.org,telemetry.enterprise.githubcopilot.com" --log-level info --proxy-logs-dir /tmp/gh-aw/sandbox/firewall/logs --enable-host-access --image-tag 0.23.0 --skip-pull --enable-api-proxy \
-- /bin/bash -c '/usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --add-dir "${GITHUB_WORKSPACE}" --disable-builtin-mcps --allow-tool '\''shell(cat)'\'' --allow-tool '\''shell(grep)'\'' --allow-tool '\''shell(head)'\'' --allow-tool '\''shell(jq)'\'' --allow-tool '\''shell(ls)'\'' --allow-tool '\''shell(tail)'\'' --allow-tool '\''shell(wc)'\'' --prompt "$(cat /tmp/gh-aw/aw-prompts/prompt.txt)"' 2>&1 | tee -a /tmp/gh-aw/threat-detection/detection.log
env:
COPILOT_AGENT_RUNNER_TYPE: STANDALONE
@ -778,7 +886,7 @@ jobs:
COPILOT_MODEL: ${{ vars.GH_AW_MODEL_DETECTION_COPILOT || '' }}
GH_AW_PHASE: detection
GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
GH_AW_VERSION: v0.62.4
GH_AW_VERSION: v0.57.2
GITHUB_API_URL: ${{ github.api_url }}
GITHUB_AW: true
GITHUB_HEAD_REF: ${{ github.head_ref }}
@ -797,15 +905,15 @@ jobs:
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
with:
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_threat_detection_results.cjs');
const { main } = require('/opt/gh-aw/actions/parse_threat_detection_results.cjs');
await main();
- name: Upload threat detection log
if: always() && steps.detection_guard.outputs.run_detection == 'true'
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7
with:
name: detection
name: threat-detection.log
path: /tmp/gh-aw/threat-detection/detection.log
if-no-files-found: ignore
- name: Set detection conclusion
@ -834,7 +942,7 @@ jobs:
- activation
- agent
- safe_outputs
if: (always()) && ((needs.agent.result != 'skipped') || (needs.activation.outputs.lockdown_check_failed == 'true'))
if: (always()) && (needs.agent.result != 'skipped')
runs-on: ubuntu-slim
permissions:
contents: read
@ -849,35 +957,35 @@ jobs:
total_count: ${{ steps.missing_tool.outputs.total_count }}
steps:
- name: Setup Scripts
uses: github/gh-aw-actions/setup@v0.62.4
uses: github/gh-aw/actions/setup@32b3a711a9ee97d38e3989c90af0385aff0066a7 # v0.57.2
with:
destination: ${{ runner.temp }}/gh-aw/actions
destination: /opt/gh-aw/actions
- name: Download agent output artifact
id: download-agent-output
continue-on-error: true
uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8
with:
name: agent
path: /tmp/gh-aw/
name: agent-output
path: /tmp/gh-aw/safeoutputs/
- name: Setup agent output environment variable
if: steps.download-agent-output.outcome == 'success'
run: |
mkdir -p /tmp/gh-aw/
find "/tmp/gh-aw/" -type f -print
echo "GH_AW_AGENT_OUTPUT=/tmp/gh-aw/agent_output.json" >> "$GITHUB_ENV"
mkdir -p /tmp/gh-aw/safeoutputs/
find "/tmp/gh-aw/safeoutputs/" -type f -print
echo "GH_AW_AGENT_OUTPUT=/tmp/gh-aw/safeoutputs/agent_output.json" >> "$GITHUB_ENV"
- name: Process No-Op Messages
id: noop
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
env:
GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
GH_AW_NOOP_MAX: "1"
GH_AW_WORKFLOW_NAME: "Ostrich Benchmark"
GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
with:
github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/noop.cjs');
const { main } = require('/opt/gh-aw/actions/noop.cjs');
await main();
- name: Record Missing Tool
id: missing_tool
@ -886,21 +994,20 @@ jobs:
GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
GH_AW_MISSING_TOOL_CREATE_ISSUE: "true"
GH_AW_MISSING_TOOL_TITLE_PREFIX: "[missing tool]"
GH_AW_WORKFLOW_NAME: "Ostrich Benchmark"
GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
with:
github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/missing_tool.cjs');
const { main } = require('/opt/gh-aw/actions/missing_tool.cjs');
await main();
- name: Handle Agent Failure
id: handle_agent_failure
if: always()
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
env:
GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
GH_AW_WORKFLOW_NAME: "Ostrich Benchmark"
GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
GH_AW_AGENT_CONCLUSION: ${{ needs.agent.result }}
GH_AW_WORKFLOW_ID: "ostrich-benchmark"
@ -909,23 +1016,22 @@ jobs:
GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }}
GH_AW_CREATE_DISCUSSION_ERRORS: ${{ needs.safe_outputs.outputs.create_discussion_errors }}
GH_AW_CREATE_DISCUSSION_ERROR_COUNT: ${{ needs.safe_outputs.outputs.create_discussion_error_count }}
GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }}
GH_AW_GROUP_REPORTS: "false"
GH_AW_FAILURE_REPORT_AS_ISSUE: "true"
GH_AW_TIMEOUT_MINUTES: "180"
with:
github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_agent_failure.cjs');
const { main } = require('/opt/gh-aw/actions/handle_agent_failure.cjs');
await main();
- name: Handle No-Op Message
id: handle_noop_message
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
env:
GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
GH_AW_WORKFLOW_NAME: "Ostrich Benchmark"
GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
GH_AW_AGENT_CONCLUSION: ${{ needs.agent.result }}
GH_AW_NOOP_MESSAGE: ${{ steps.noop.outputs.noop_message }}
@ -933,9 +1039,9 @@ jobs:
with:
github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_noop_message.cjs');
const { main } = require('/opt/gh-aw/actions/handle_noop_message.cjs');
await main();
safe_outputs:
@ -951,7 +1057,7 @@ jobs:
GH_AW_CALLER_WORKFLOW_ID: "${{ github.repository }}/ostrich-benchmark"
GH_AW_ENGINE_ID: "copilot"
GH_AW_WORKFLOW_ID: "ostrich-benchmark"
GH_AW_WORKFLOW_NAME: "Ostrich Benchmark"
GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
outputs:
code_push_failure_count: ${{ steps.process_safe_outputs.outputs.code_push_failure_count }}
code_push_failure_errors: ${{ steps.process_safe_outputs.outputs.code_push_failure_errors }}
@ -961,51 +1067,43 @@ jobs:
process_safe_outputs_temporary_id_map: ${{ steps.process_safe_outputs.outputs.temporary_id_map }}
steps:
- name: Setup Scripts
uses: github/gh-aw-actions/setup@v0.62.4
uses: github/gh-aw/actions/setup@32b3a711a9ee97d38e3989c90af0385aff0066a7 # v0.57.2
with:
destination: ${{ runner.temp }}/gh-aw/actions
destination: /opt/gh-aw/actions
- name: Download agent output artifact
id: download-agent-output
continue-on-error: true
uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
uses: actions/download-artifact@70fc10c6e5e1ce46ad2ea6f2b72d43f7d47b13c3 # v8
with:
name: agent
path: /tmp/gh-aw/
name: agent-output
path: /tmp/gh-aw/safeoutputs/
- name: Setup agent output environment variable
if: steps.download-agent-output.outcome == 'success'
run: |
mkdir -p /tmp/gh-aw/
find "/tmp/gh-aw/" -type f -print
echo "GH_AW_AGENT_OUTPUT=/tmp/gh-aw/agent_output.json" >> "$GITHUB_ENV"
- name: Configure GH_HOST for enterprise compatibility
shell: bash
run: |
# Derive GH_HOST from GITHUB_SERVER_URL so the gh CLI targets the correct
# GitHub instance (GHES/GHEC). On github.com this is a harmless no-op.
GH_HOST="${GITHUB_SERVER_URL#https://}"
GH_HOST="${GH_HOST#http://}"
echo "GH_HOST=${GH_HOST}" >> "$GITHUB_ENV"
mkdir -p /tmp/gh-aw/safeoutputs/
find "/tmp/gh-aw/safeoutputs/" -type f -print
echo "GH_AW_AGENT_OUTPUT=/tmp/gh-aw/safeoutputs/agent_output.json" >> "$GITHUB_ENV"
- name: Process Safe Outputs
id: process_safe_outputs
uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8
env:
GH_AW_AGENT_OUTPUT: ${{ env.GH_AW_AGENT_OUTPUT }}
GH_AW_ALLOWED_DOMAINS: "api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,github.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,ppa.launchpad.net,raw.githubusercontent.com,registry.npmjs.org,s.symcb.com,s.symcd.com,security.ubuntu.com,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com,www.googleapis.com"
GH_AW_ALLOWED_DOMAINS: "api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,github.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,ppa.launchpad.net,raw.githubusercontent.com,registry.npmjs.org,s.symcb.com,s.symcd.com,security.ubuntu.com,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com"
GITHUB_SERVER_URL: ${{ github.server_url }}
GITHUB_API_URL: ${{ github.api_url }}
GH_AW_SAFE_OUTPUTS_HANDLER_CONFIG: "{\"create_discussion\":{\"category\":\"agentic workflows\",\"close_older_discussions\":true,\"expires\":168,\"fallback_to_issue\":true,\"max\":1,\"title_prefix\":\"[Ostrich Benchmark] \"},\"missing_data\":{},\"missing_tool\":{},\"noop\":{\"max\":1,\"report-as-issue\":\"false\"}}"
GH_AW_SAFE_OUTPUTS_HANDLER_CONFIG: "{\"create_discussion\":{\"category\":\"agentic workflows\",\"close_older_discussions\":true,\"expires\":168,\"fallback_to_issue\":true,\"max\":1,\"title_prefix\":\"[Ostrich Benchmark] \"},\"missing_data\":{},\"missing_tool\":{}}"
with:
github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
script: |
const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
const { setupGlobals } = require('/opt/gh-aw/actions/setup_globals.cjs');
setupGlobals(core, github, context, exec, io);
const { main } = require('${{ runner.temp }}/gh-aw/actions/safe_output_handler_manager.cjs');
const { main } = require('/opt/gh-aw/actions/safe_output_handler_manager.cjs');
await main();
- name: Upload safe output items
- name: Upload safe output items manifest
if: always()
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7
with:
name: safe-output-items
path: /tmp/gh-aw/safe-output-items.jsonl
if-no-files-found: ignore
path: /tmp/safe-output-items.jsonl
if-no-files-found: warn