diff --git a/.github/workflows/ostrich-benchmark.lock.yml b/.github/workflows/ostrich-benchmark.lock.yml
deleted file mode 100644
index 0482d964ee..0000000000
--- a/.github/workflows/ostrich-benchmark.lock.yml
+++ /dev/null
@@ -1,1579 +0,0 @@
-# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"78d9be12902490ac2e6792e6c0b0cbdc0007a49a6b5b27de7043d7e5f5917cfd","body_hash":"c57d701ac052e7a63092ff6b17a06bdb4588fd7ac8c1d366bfc2995f72a1b379","compiler_version":"v0.83.4","strict":true,"agent_id":"copilot","engine_versions":{"copilot":"1.0.75"}}
-# gh-aw-manifest: {"version":1,"secrets":["COPILOT_GITHUB_TOKEN","GH_AW_GITHUB_MCP_SERVER_TOKEN","GH_AW_GITHUB_TOKEN","GITHUB_TOKEN"],"actions":[{"repo":"actions/cache/restore","sha":"55cc8345863c7cc4c66a329aec7e433d2d1c52a9","version":"v6.1.0"},{"repo":"actions/cache/save","sha":"55cc8345863c7cc4c66a329aec7e433d2d1c52a9","version":"v6.1.0"},{"repo":"actions/checkout","sha":"3d3c42e5aac5ba805825da76410c181273ba90b1","version":"v7.0.1"},{"repo":"actions/checkout","sha":"de0fac2e4500dabe0009e67214ff5f5447ce83dd","version":"v6.0.2"},{"repo":"actions/download-artifact","sha":"3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c","version":"v8.0.1"},{"repo":"actions/github-script","sha":"3a2844b7e9c422d3c10d287c895573f7108da1b3","version":"v9.0.0"},{"repo":"actions/setup-node","sha":"820762786026740c76f36085b0efc47a31fe5020","version":"v7.0.0"},{"repo":"actions/upload-artifact","sha":"043fb46d1a93c77aae656e7c1c64a875d1fc6a0a","version":"v7.0.1"},{"repo":"github/gh-aw-actions/setup","sha":"v0.83.4","version":"v0.83.4"}],"containers":[{"image":"ghcr.io/github/gh-aw-firewall/agent:0.27.42","digest":"sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b","pinned_image":"ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b"},{"image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42","digest":"sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607","pinned_image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607"},{"image":"ghcr.io/github/gh-aw-firewall/squid:0.27.42","digest":"sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0","pinned_image":"ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0"},{"image":"ghcr.io/github/gh-aw-mcpg:v0.4.6","digest":"sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c","pinned_image":"ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c"},{"image":"ghcr.io/github/gh-aw-node","digest":"sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748","pinned_image":"ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748"},{"image":"ghcr.io/github/github-mcp-server:v1.7.0","digest":"sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308","pinned_image":"ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308"}]}
-# This file was automatically generated by gh-aw (v0.83.4). DO NOT EDIT. To debug this workflow, load the skill at https://github.com/github/gh-aw/blob/main/debug.md
-#
-# ___ _ _
-# / _ \ | | (_)
-# | |_| | __ _ ___ _ __ | |_ _ ___
-# | _ |/ _` |/ _ \ '_ \| __| |/ __|
-# | | | | (_| | __/ | | | |_| | (__
-# \_| |_/\__, |\___|_| |_|\__|_|\___|
-# __/ |
-# _ _ |___/
-# | | | | / _| |
-# | | | | ___ _ __ _ __| |_| | _____ ____
-# | |/\| |/ _ \ '__| |/ /| _| |/ _ \ \ /\ / / ___|
-# \ /\ / (_) | | | | ( | | | | (_) \ V V /\__ \
-# \/ \/ \___/|_| |_|\_\|_| |_|\___/ \_/\_/ |___/
-#
-#
-# To update this file, edit the corresponding .md file and run:
-# gh aw compile
-# Not all edits will cause changes to this file.
-#
-# For more information: https://github.github.com/gh-aw/introduction/overview/
-#
-# 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
-#
-# Secrets used:
-# - COPILOT_GITHUB_TOKEN
-# - GH_AW_GITHUB_MCP_SERVER_TOKEN
-# - GH_AW_GITHUB_TOKEN
-# - GITHUB_TOKEN
-#
-# Custom actions used:
-# - actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-# - actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-# - actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-# - actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-# - actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-# - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
-# - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 (source v9)
-# - actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
-# - actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-# - github/gh-aw-actions/setup@v0.83.4
-#
-# Container images used:
-# - ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b
-# - ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607
-# - ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0
-# - ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c
-# - ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748
-# - ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308
-
-name: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
-on:
- schedule:
- - cron: "0 6 * * *"
- workflow_dispatch:
- inputs:
- aw_context:
- default: ""
- description: "Agent caller context (used internally by Agentic Workflows)."
- required: false
- type: string
-
-permissions: {}
-
-concurrency:
- group: "gh-aw-${{ github.workflow }}"
-
-run-name: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
-
-jobs:
- activation:
- runs-on: ubuntu-slim
- permissions:
- actions: read
- contents: read
- env:
- GH_AW_MAX_DAILY_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_DAILY_AI_CREDITS || '5000' }}
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- comment_id: ""
- comment_repo: ""
- daily_ai_credits_exceeded: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_exceeded == 'true' }}
- daily_ai_credits_threshold: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_threshold || '' }}
- daily_ai_credits_total_effective_tokens: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_total_effective_tokens || '' }}
- engine_id: ${{ steps.generate_aw_info.outputs.engine_id }}
- lockdown_check_failed: ${{ steps.generate_aw_info.outputs.lockdown_check_failed == 'true' }}
- model: ${{ steps.generate_aw_info.outputs.model }}
- oauth_token_check_failed: ${{ steps.check-oauth-tokens.outputs.oauth_token_check_failed == 'true' }}
- secret_verification_result: ${{ steps.validate-secret.outputs.verification_result }}
- setup-parent-span-id: ${{ steps.setup.outputs.parent-span-id || steps.setup.outputs.span-id }}
- setup-span-id: ${{ steps.setup.outputs.span-id }}
- setup-trace-id: ${{ steps.setup.outputs.trace-id }}
- stale_lock_file_failed: ${{ steps.check-lock-file.outputs.stale_lock_file_failed == 'true' }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- safe-output-artifact-client: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/ostrich-benchmark.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Generate agentic run info
- id: generate_aw_info
- env:
- GH_AW_INFO_ENGINE_ID: "copilot"
- GH_AW_INFO_ENGINE_NAME: "GitHub Copilot CLI"
- GH_AW_INFO_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AGENT_VERSION: "1.0.75"
- GH_AW_INFO_CLI_VERSION: "v0.83.4"
- GH_AW_INFO_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_INFO_EXPERIMENTAL: "false"
- GH_AW_INFO_SUPPORTS_TOOLS_ALLOWLIST: "true"
- GH_AW_INFO_STAGED: "false"
- GH_AW_INFO_ALLOWED_DOMAINS: '["defaults","api.nuget.org"]'
- GH_AW_INFO_FIREWALL_ENABLED: "true"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_AWMG_VERSION: ""
- GH_AW_INFO_FIREWALL_TYPE: "squid"
- GH_AW_COMPILED_STRICT: "true"
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/generate_aw_info.cjs');
- await main(core, context);
- - name: Restore daily AIC usage cache
- id: restore-daily-aic-cache
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- continue-on-error: true
- uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-ostrichbenchmark-${{ github.run_id }}
- restore-keys: agentic-workflow-usage-ostrichbenchmark-
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Restore daily AIC usage cache (artifact fallback)
- id: restore-daily-aic-cache-fallback
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_RESTORE_DAILY_AIC_CACHE_HIT: ${{ steps.restore-daily-aic-cache.outputs.cache-hit }}
- GH_AW_RESTORE_DAILY_AIC_CACHE_MATCHED_KEY: ${{ steps.restore-daily-aic-cache.outputs.cache-matched-key }}
- with:
- github-token: ${{ secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/restore_aic_usage_cache_fallback.cjs');
- await main();
- - name: Check daily workflow token guardrail
- id: daily-effective-workflow-guardrail
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_WORKFLOW_ID: "ostrich-benchmark"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_WORKFLOW_DISPATCH_AW_CONTEXT: ${{ github.event.inputs.aw_context || '' }}
- GH_AW_HAS_SLASH_COMMAND: "false"
- GH_AW_HAS_LABEL_COMMAND: "false"
- GH_AW_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- GH_AW_MAX_DAILY_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_DAILY_AI_CREDITS || '5000' }}
- with:
- github-token: ${{ secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_daily_aic_workflow_guardrail.cjs');
- await main();
- - name: Validate COPILOT_GITHUB_TOKEN secret
- id: validate-secret
- run: bash "${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
- env:
- COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- - name: Check for OAuth tokens
- id: check-oauth-tokens
- run: bash "${RUNNER_TEMP}/gh-aw/actions/check_oauth_tokens.sh"
- env:
- COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }}
- - name: Checkout .github and .agents folders
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- with:
- persist-credentials: false
- sparse-checkout: |
- .github
- .agents
- .antigravity
- .claude
- .codex
- .gemini
- .opencode
- .pi
- sparse-checkout-cone-mode: true
- fetch-depth: 1
- - name: Save agent config folders for base branch restoration
- env:
- GH_AW_AGENT_FOLDERS: ".agents .antigravity .claude .codex .gemini .github .opencode .pi"
- GH_AW_AGENT_FILES: "AGENTS.md ANTIGRAVITY.md CLAUDE.md GEMINI.md PI.md opencode.jsonc"
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/save_base_github_folders.sh"
- - name: Check workflow lock file
- id: check-lock-file
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_WORKFLOW_FILE: "ostrich-benchmark.lock.yml"
- GH_AW_CONTEXT_WORKFLOW_REF: "${{ github.workflow_ref }}"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_workflow_timestamp_api.cjs');
- await main();
- - name: Check compile-agentic version
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_COMPILED_VERSION: "v0.83.4"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_version_updates.cjs');
- await main();
- - name: Log runtime features
- if: ${{ contains(toJSON(vars), '"GH_AW_RUNTIME_FEATURES":') }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/log_runtime_features_summary.sh"
- - name: Create prompt with built-in context
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_SAFE_OUTPUTS: ${{ runner.temp }}/gh-aw/safeoutputs/outputs.jsonl
- GH_AW_EXPR_1A3A194A: ${{ github.event.discussion.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'discussion' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_463A214A: ${{ github.event.pull_request.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'pull_request' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_802A9F6A: ${{ github.event.issue.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'issue' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_FF1D34CE: ${{ github.event.comment.id || fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').comment_id }}
- GH_AW_GITHUB_ACTOR: ${{ github.actor }}
- GH_AW_GITHUB_REPOSITORY: ${{ github.repository }}
- GH_AW_GITHUB_RUN_ID: ${{ github.run_id }}
- GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
- # poutine:ignore untrusted_checkout_exec
- run: |
- bash "${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh"
- {
- cat << 'GH_AW_PROMPT_4a75e6aa18275d18_EOF'
-
- GH_AW_PROMPT_4a75e6aa18275d18_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 << 'GH_AW_PROMPT_4a75e6aa18275d18_EOF'
-
- Tools: create_discussion, missing_tool, missing_data, noop
-
- GH_AW_PROMPT_4a75e6aa18275d18_EOF
- cat "${RUNNER_TEMP}/gh-aw/prompts/mcp_cli_tools_prompt.md"
- cat << 'GH_AW_PROMPT_4a75e6aa18275d18_EOF'
-
- The following GitHub context information is available for this workflow:
- {{#if github.actor}}
- - **actor**: __GH_AW_GITHUB_ACTOR__
- {{/if}}
- {{#if github.repository}}
- - **repository**: __GH_AW_GITHUB_REPOSITORY__
- {{/if}}
- {{#if github.workspace}}
- - **workspace**: __GH_AW_GITHUB_WORKSPACE__
- {{/if}}
- {{#if github.event.issue.number || (github.aw.context.item_type == 'issue' && github.aw.context.item_number)}}
- - **issue-number**: #__GH_AW_EXPR_802A9F6A__
- {{/if}}
- {{#if github.event.discussion.number || (github.aw.context.item_type == 'discussion' && github.aw.context.item_number)}}
- - **discussion-number**: #__GH_AW_EXPR_1A3A194A__
- {{/if}}
- {{#if github.event.pull_request.number || (github.aw.context.item_type == 'pull_request' && github.aw.context.item_number)}}
- - **pull-request-number**: #__GH_AW_EXPR_463A214A__
- {{/if}}
- {{#if github.event.comment.id || github.aw.context.comment_id}}
- - **comment-id**: __GH_AW_EXPR_FF1D34CE__
- {{/if}}
- {{#if github.run_id}}
- - **workflow-run-id**: __GH_AW_GITHUB_RUN_ID__
- {{/if}}
-
-
- GH_AW_PROMPT_4a75e6aa18275d18_EOF
- cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md"
- cat << 'GH_AW_PROMPT_4a75e6aa18275d18_EOF'
-
- {{#runtime-import .github/workflows/ostrich-benchmark.md}}
- GH_AW_PROMPT_4a75e6aa18275d18_EOF
- } > "$GH_AW_PROMPT"
- - name: Interpolate variables and render templates
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_ENGINE_ID: "copilot"
- 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');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/interpolate_prompt.cjs');
- await main();
- - name: Substitute placeholders
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_EXPR_1A3A194A: ${{ github.event.discussion.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'discussion' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_463A214A: ${{ github.event.pull_request.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'pull_request' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_802A9F6A: ${{ github.event.issue.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'issue' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_FF1D34CE: ${{ github.event.comment.id || fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').comment_id }}
- GH_AW_GITHUB_ACTOR: ${{ github.actor }}
- GH_AW_GITHUB_REPOSITORY: ${{ github.repository }}
- GH_AW_GITHUB_RUN_ID: ${{ github.run_id }}
- GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
- GH_AW_MCP_CLI_SERVERS_LIST: "- `github` — run `github --help` to see available tools\n- `safeoutputs` — run `safeoutputs --help` to see available tools"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
-
- const substitutePlaceholders = require('${{ runner.temp }}/gh-aw/actions/substitute_placeholders.cjs');
-
- // Call the substitution function
- return await substitutePlaceholders({
- file: process.env.GH_AW_PROMPT,
- substitutions: {
- GH_AW_EXPR_1A3A194A: process.env.GH_AW_EXPR_1A3A194A,
- GH_AW_EXPR_463A214A: process.env.GH_AW_EXPR_463A214A,
- GH_AW_EXPR_802A9F6A: process.env.GH_AW_EXPR_802A9F6A,
- GH_AW_EXPR_FF1D34CE: process.env.GH_AW_EXPR_FF1D34CE,
- GH_AW_GITHUB_ACTOR: process.env.GH_AW_GITHUB_ACTOR,
- GH_AW_GITHUB_REPOSITORY: process.env.GH_AW_GITHUB_REPOSITORY,
- GH_AW_GITHUB_RUN_ID: process.env.GH_AW_GITHUB_RUN_ID,
- GH_AW_GITHUB_WORKSPACE: process.env.GH_AW_GITHUB_WORKSPACE,
- GH_AW_MCP_CLI_SERVERS_LIST: process.env.GH_AW_MCP_CLI_SERVERS_LIST
- }
- });
- - name: Validate prompt placeholders
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/validate_prompt_placeholders.sh"
- - name: Print prompt
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/print_prompt_summary.sh"
- - name: Upload activation artifact
- if: success()
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: activation
- include-hidden-files: true
- path: |
- /tmp/gh-aw/aw_info.json
- /tmp/gh-aw/models.json
- /tmp/gh-aw/aw-prompts/prompt.txt
- /tmp/gh-aw/aw-prompts/prompt-template.txt
- /tmp/gh-aw/aw-prompts/prompt-import-tree.json
- /tmp/gh-aw/github_rate_limits.jsonl
- /tmp/gh-aw/base
- /tmp/gh-aw/.github/agents
- /tmp/gh-aw/.github/skills
- if-no-files-found: ignore
- retention-days: 1
-
- agent:
- needs: activation
- if: needs.activation.outputs.daily_ai_credits_exceeded != 'true'
- runs-on: ubuntu-latest
- permissions: read-all
- concurrency:
- group: "gh-aw-copilot-${{ github.workflow }}"
- queue: max
- env:
- DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
- GH_AW_ASSETS_ALLOWED_EXTS: ""
- GH_AW_ASSETS_BRANCH: ""
- GH_AW_ASSETS_MAX_SIZE_KB: 0
- GH_AW_MCP_LOG_DIR: /tmp/gh-aw/mcp-logs/safeoutputs
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- GH_AW_WORKFLOW_ID_SANITIZED: ostrichbenchmark
- outputs:
- agentic_engine_timeout: ${{ steps.detect-agent-errors.outputs.agentic_engine_timeout || 'false' }}
- ai_credits_rate_limit_error: ${{ steps.parse-mcp-gateway.outputs.ai_credits_rate_limit_error || 'false' }}
- aic: ${{ steps.parse-mcp-gateway.outputs.aic }}
- ambient_context: ${{ steps.parse-mcp-gateway.outputs.ambient_context }}
- checkout_pr_success: ${{ steps.checkout-pr.outputs.checkout_pr_success || 'true' }}
- effective_tokens: ${{ steps.parse-mcp-gateway.outputs.effective_tokens }}
- has_patch: ${{ steps.collect_output.outputs.has_patch }}
- http_400_response_error: ${{ steps.detect-agent-errors.outputs.http_400_response_error || 'false' }}
- inference_access_error: ${{ steps.detect-agent-errors.outputs.inference_access_error || 'false' }}
- invocation_cap_exceeded: ${{ steps.detect-agent-errors.outputs.invocation_cap_exceeded || 'false' }}
- mcp_policy_error: ${{ steps.detect-agent-errors.outputs.mcp_policy_error || 'false' }}
- model: ${{ needs.activation.outputs.model }}
- model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }}
- output: ${{ steps.collect_output.outputs.output }}
- output_types: ${{ steps.collect_output.outputs.output_types }}
- setup-parent-span-id: ${{ steps.setup.outputs.parent-span-id || steps.setup.outputs.span-id }}
- setup-span-id: ${{ steps.setup.outputs.span-id }}
- setup-trace-id: ${{ steps.setup.outputs.trace-id }}
- unknown_model_ai_credits: ${{ steps.parse-mcp-gateway.outputs.unknown_model_ai_credits || 'false' }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/ostrich-benchmark.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Set runtime paths
- id: set-runtime-paths
- run: |
- {
- echo "GH_AW_SAFE_OUTPUTS=${RUNNER_TEMP}/gh-aw/safeoutputs/outputs.jsonl"
- echo "GH_AW_SAFE_OUTPUTS_CONFIG_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/config.json"
- echo "GH_AW_SAFE_OUTPUTS_TOOLS_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/tools.json"
- } >> "$GITHUB_OUTPUT"
- - 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 }}
- - name: Download activation artifact
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: activation
- path: /tmp/gh-aw
- - name: Checkout c3 branch
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- with:
- fetch-depth: 1
- persist-credentials: false
- ref: c3
-
- - name: Configure Git credentials
- env:
- GITHUB_REPOSITORY: ${{ github.repository }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_TOKEN: ${{ github.token }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/configure_git_credentials.sh"
- - name: Checkout PR branch
- id: checkout-pr
- if: |
- github.event.pull_request || github.event.issue.pull_request || github.event_name == 'workflow_dispatch' && fromJSON(github.event.inputs.aw_context || '{}').item_type == 'pull_request'
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- 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');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/checkout_pr_branch.cjs');
- await main();
- - name: Install GitHub Copilot CLI
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh" 1.0.75
- env:
- GH_HOST: github.com
- - name: Install AWF binary
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.27.42 --rootless
- - name: Determine automatic lockdown mode for GitHub MCP Server
- id: determine-automatic-lockdown
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 (source v9)
- env:
- GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- 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');
- await determineAutomaticLockdown(github, context, core);
- - name: Restore agent config folders from base branch
- if: steps.checkout-pr.outcome == 'success'
- env:
- GH_AW_AGENT_FOLDERS: ".agents .antigravity .claude .codex .gemini .github .opencode .pi"
- GH_AW_AGENT_FILES: "AGENTS.md ANTIGRAVITY.md CLAUDE.md GEMINI.md PI.md opencode.jsonc"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_base_github_folders.sh"
- - name: Restore inline sub-agents from activation artifact
- env:
- GH_AW_SUB_AGENT_DIR: ".github/agents"
- GH_AW_SUB_AGENT_EXT: ".agent.md"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_inline_sub_agents.sh"
- - name: Restore inline skills from activation artifact
- env:
- GH_AW_SKILL_DIR: ".github/skills"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_inline_skills.sh"
- - name: Download container images
- run: bash "${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh" ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607 ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0 ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748 ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308
- - name: Generate Safe Outputs Config
- run: |
- mkdir -p "${RUNNER_TEMP}/gh-aw/safeoutputs"
- mkdir -p /tmp/gh-aw/safeoutputs
- mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs
- cat > "${RUNNER_TEMP}/gh-aw/safeoutputs/config.json" << 'GH_AW_SAFE_OUTPUTS_CONFIG_29a1cb7a8ad0205d_EOF'
- {"create_discussion":{"category":"agentic workflows","close_older_discussions":true,"expires":168,"fallback_to_issue":true,"max":1,"title_prefix":"[Ostrich Benchmark] "},"create_report_incomplete_issue":{},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"false"},"report_incomplete":{}}
- GH_AW_SAFE_OUTPUTS_CONFIG_29a1cb7a8ad0205d_EOF
- - name: Generate Safe Outputs Tools
- env:
- GH_AW_TOOLS_META_JSON: |
- {
- "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\"."
- },
- "repo_params": {},
- "dynamic_tools": []
- }
- GH_AW_VALIDATION_JSON: |
- {
- "create_discussion": {
- "defaultMax": 1,
- "fields": {
- "body": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 65000,
- "minLength": 64
- },
- "category": {
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- },
- "repo": {
- "type": "string",
- "maxLength": 256
- },
- "title": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- }
- }
- },
- "missing_data": {
- "defaultMax": 20,
- "fields": {
- "alternatives": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "context": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "data_type": {
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- },
- "reason": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- }
- }
- },
- "missing_tool": {
- "defaultMax": 20,
- "fields": {
- "alternatives": {
- "type": "string",
- "sanitize": true,
- "maxLength": 512
- },
- "reason": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "tool": {
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- }
- }
- },
- "noop": {
- "defaultMax": 1,
- "fields": {
- "message": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 65000
- }
- }
- },
- "report_incomplete": {
- "defaultMax": 5,
- "fields": {
- "details": {
- "type": "string",
- "sanitize": true,
- "maxLength": 65000
- },
- "reason": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 1024
- }
- }
- }
- }
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/generate_safe_outputs_tools.cjs');
- await main();
- - name: Start MCP Gateway
- id: start-mcp-gateway
- env:
- GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST: ${{ vars.GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST || 'true' }}
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- GH_AW_SAFE_OUTPUTS_CONFIG_PATH: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS_CONFIG_PATH }}
- GH_AW_SAFE_OUTPUTS_TOOLS_PATH: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS_TOOLS_PATH }}
- GITHUB_MCP_GUARD_MIN_INTEGRITY: ${{ steps.determine-automatic-lockdown.outputs.min_integrity }}
- GITHUB_MCP_GUARD_REPOS: ${{ steps.determine-automatic-lockdown.outputs.repos }}
- GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- run: |
- set -eo pipefail
- mkdir -p "${RUNNER_TEMP}/gh-aw/mcp-config"
-
- # Export gateway environment variables for MCP config and gateway script
- export MCP_GATEWAY_PORT="8080"
- export MCP_GATEWAY_DOMAIN="awmg-mcpg"
- export MCP_GATEWAY_HOST_DOMAIN="localhost"
- MCP_GATEWAY_API_KEY=$(openssl rand -base64 45 | tr -d '/+=')
- echo "::add-mask::${MCP_GATEWAY_API_KEY}"
- export MCP_GATEWAY_API_KEY
- export MCP_GATEWAY_PAYLOAD_DIR="/tmp/gh-aw/mcp-payloads"
- mkdir -p "${MCP_GATEWAY_PAYLOAD_DIR}"
- export MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD="524288"
- export DEBUG="*"
-
- export GH_AW_ENGINE="copilot"
- MCP_GATEWAY_UID=$(id -u 2>/dev/null || echo '0')
- MCP_GATEWAY_GID=$(id -g 2>/dev/null || echo '0')
- source "${RUNNER_TEMP}/gh-aw/actions/resolve_docker_socket_gid.sh"
- export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network bridge -p 127.0.0.1:'"${MCP_GATEWAY_PORT}"':'"${MCP_GATEWAY_PORT}"' --name awmg-mcpg --add-host host.docker.internal:host-gateway --user '"${MCP_GATEWAY_UID}"':'"${MCP_GATEWAY_GID}"' --group-add '"${DOCKER_SOCK_GID}"' -v '"${DOCKER_SOCK_PATH}"':/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 DOCKER_HOST=unix:///var/run/docker.sock -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_POLICY_ALLOW_CREATE_PULL_REQUEST -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 RUNNER_TEMP -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 -v '"${RUNNER_TEMP}"'/gh-aw/safeoutputs:'"${RUNNER_TEMP}"'/gh-aw/safeoutputs:rw ghcr.io/github/gh-aw-mcpg:v0.4.6'
-
- mkdir -p "$HOME/.copilot"
- GH_AW_NODE=$(which node 2>/dev/null || command -v node 2>/dev/null || echo node)
- cat << GH_AW_MCP_CONFIG_4dd92588edb04041_EOF | "$GH_AW_NODE" "${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.cjs"
- {
- "mcpServers": {
- "github": {
- "type": "stdio",
- "container": "ghcr.io/github/github-mcp-server:v1.7.0",
- "env": {
- "GITHUB_FEATURES": "fields_param",
- "GITHUB_HOST": "${GITHUB_SERVER_URL}",
- "GITHUB_PERSONAL_ACCESS_TOKEN": "${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": {
- "type": "stdio",
- "container": "ghcr.io/github/gh-aw-node",
- "mounts": ["\${GITHUB_WORKSPACE}:\${GITHUB_WORKSPACE}:rw", "${RUNNER_TEMP}/gh-aw/safeoutputs:${RUNNER_TEMP}/gh-aw/safeoutputs:rw", "/tmp/gh-aw:/tmp/gh-aw:rw"],
- "args": ["-w", "\${GITHUB_WORKSPACE}"],
- "entrypoint": "sh",
- "entrypointArgs": ["-c", "sh ${RUNNER_TEMP}/gh-aw/safeoutputs/start_safe_outputs_mcp.sh"],
- "env": {
- "DEBUG": "*",
- "DEFAULT_BRANCH": "\${DEFAULT_BRANCH}",
- "GH_AW_ASSETS_ALLOWED_EXTS": "\${GH_AW_ASSETS_ALLOWED_EXTS}",
- "GH_AW_ASSETS_BRANCH": "\${GH_AW_ASSETS_BRANCH}",
- "GH_AW_ASSETS_MAX_SIZE_KB": "\${GH_AW_ASSETS_MAX_SIZE_KB}",
- "GH_AW_MCP_LOG_DIR": "\${GH_AW_MCP_LOG_DIR}",
- "GH_AW_SAFE_OUTPUTS": "\${GH_AW_SAFE_OUTPUTS}",
- "GH_AW_SAFE_OUTPUTS_CONFIG_PATH": "\${GH_AW_SAFE_OUTPUTS_CONFIG_PATH}",
- "GH_AW_SAFE_OUTPUTS_TOOLS_PATH": "\${GH_AW_SAFE_OUTPUTS_TOOLS_PATH}",
- "GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST": "\${GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST}",
- "GITHUB_REPOSITORY": "\${GITHUB_REPOSITORY}",
- "GITHUB_SHA": "\${GITHUB_SHA}",
- "GITHUB_TOKEN": "\${GITHUB_TOKEN}",
- "GITHUB_WORKSPACE": "\${GITHUB_WORKSPACE}",
- "RUNNER_TEMP": "\${RUNNER_TEMP}"
- },
- "guard-policies": {
- "write-sink": {
- "accept": [
- "*"
- ],
- "sink-visibility": ${{ toJSON(steps.determine-automatic-lockdown.outputs.visibility) }}
- }
- }
- }
- },
- "gateway": {
- "port": $MCP_GATEWAY_PORT,
- "domain": "${MCP_GATEWAY_DOMAIN}",
- "apiKey": "${MCP_GATEWAY_API_KEY}",
- "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}",
- "startupTimeout": 120
- }
- }
- GH_AW_MCP_CONFIG_4dd92588edb04041_EOF
- - name: Mount MCP servers as CLIs
- id: mount-mcp-clis
- continue-on-error: true
- env:
- MCP_GATEWAY_API_KEY: ${{ steps.start-mcp-gateway.outputs.gateway-api-key }}
- MCP_GATEWAY_DOMAIN: ${{ steps.start-mcp-gateway.outputs.gateway-domain }}
- MCP_GATEWAY_PORT: ${{ steps.start-mcp-gateway.outputs.gateway-port }}
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/mount_mcp_as_cli.cjs');
- await main();
- - name: Clean credentials
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/clean_git_credentials.sh"
- - name: Audit pre-agent workspace
- id: pre_agent_audit
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/audit_pre_agent_workspace.sh"
- - name: Execute GitHub Copilot CLI
- id: agentic_execution
- # Copilot CLI tool arguments (sorted):
- timeout-minutes: 180
- run: |
- set -o pipefail
- printf '%s' "$(date +%s%3N)" > /tmp/gh-aw/agent_cli_start_ms.txt
- trap 'gh_aw_exit_code=$?; mkdir -p /tmp/gh-aw >/dev/null 2>&1 || true; printf "%s" "$gh_aw_exit_code" > /tmp/gh-aw/agent_execution_exit_code.txt || true; rm -f "$HOME/.copilot/settings.json"' EXIT
- mkdir -p "$HOME/.copilot"
- printf '%s' '{"builtInAgents":{"rubberDuck":false}}' > "$HOME/.copilot/settings.json"
- export XDG_CONFIG_HOME="$HOME"
- export GH_AW_MCP_CONFIG="$HOME/.copilot/mcp-config.json"
- touch /tmp/gh-aw/agent-step-summary.md
- GH_AW_NODE_BIN=$(command -v node 2>/dev/null || true)
- export GH_AW_NODE_BIN
- export COPILOT_API_KEY="$COPILOT_DUMMY_BYOK"
- (umask 177 && touch /tmp/gh-aw/agent-stdio.log)
- GH_AW_MAX_AI_CREDITS="${GH_AW_MAX_AI_CREDITS:-1000}"
- printf '%s\n' "{\"\$schema\":\"https://github.com/github/gh-aw-firewall/releases/download/v0.27.42/awf-config.schema.json\",\"network\":{\"allowDomains\":[\"api.business.githubcopilot.com\",\"api.enterprise.githubcopilot.com\",\"api.github.com\",\"api.githubcopilot.com\",\"api.individual.githubcopilot.com\",\"api.nuget.org\",\"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\"],\"isolation\":true,\"topologyAttach\":[\"awmg-mcpg\"]},\"apiProxy\":{\"enabled\":true,\"enableTokenSteering\":true,\"maxRuns\":500,\"maxAiCredits\":${GH_AW_MAX_AI_CREDITS},\"maxCacheMisses\":5,\"models\":{\"agent\":[\"sonnet-6x\",\"gpt-5.4\",\"gpt-5.5\",\"gpt-5.6\",\"gpt-5.3\",\"gemini-pro\",\"any\"],\"antigravity\":[\"copilot/antigravity*\",\"google/antigravity*\",\"gemini/antigravity*\"],\"any\":[\"copilot/*\",\"anthropic/*\",\"openai/*\",\"google/*\",\"gemini/*\"],\"claude\":[\"agent\"],\"codex\":[\"agent\"],\"coding\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\",\"gpt-5-codex\",\"kimi\"],\"computer-use\":[\"copilot/*computer-use*\",\"google/*computer-use*\",\"gemini/*computer-use*\",\"openai/*computer-use*\"],\"copilot\":[\"agent\"],\"deep-research\":[\"copilot/deep-research*\",\"copilot/o3-deep-research*\",\"copilot/o4-mini-deep-research*\",\"google/deep-research*\",\"gemini/deep-research*\",\"openai/o3-deep-research*\",\"openai/o4-mini-deep-research*\"],\"fable\":[\"copilot/*fable*\",\"anthropic/*fable*\"],\"gemini\":[\"agent\"],\"gemini-3-flash\":[\"copilot/gemini-3*flash*\",\"google/gemini-3*flash*\",\"gemini/gemini-3*flash*\"],\"gemini-3-pro\":[\"copilot/gemini-3*pro*\",\"google/gemini-3*pro*\",\"google/nano-banana*\",\"gemini/gemini-3*pro*\"],\"gemini-3.1-flash\":[\"copilot/gemini-3.1*flash*\",\"google/gemini-3.1*flash*\",\"gemini/gemini-3.1*flash*\"],\"gemini-3.1-pro\":[\"copilot/gemini-3.1*pro*\",\"google/gemini-3.1*pro*\",\"gemini/gemini-3.1*pro*\"],\"gemini-3.5-flash\":[\"copilot/gemini-3.5*flash*\",\"google/gemini-3.5*flash*\",\"gemini/gemini-3.5*flash*\"],\"gemini-3.6-flash\":[\"copilot/gemini-3.6*flash*\",\"google/gemini-3.6*flash*\",\"gemini/gemini-3.6*flash*\"],\"gemini-flash\":[\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"],\"gemini-flash-lite\":[\"copilot/gemini-*flash*lite*\",\"google/gemini-*flash*lite*\",\"gemini/gemini-*flash*lite*\"],\"gemini-omni\":[\"copilot/gemini-omni*\",\"google/gemini-omni*\",\"gemini/gemini-omni*\"],\"gemini-pro\":[\"copilot/gemini-*pro*\",\"google/gemini-*pro*\",\"gemini/gemini-*pro*\"],\"gemma\":[\"copilot/gemma*\",\"google/gemma*\",\"gemini/gemma*\"],\"gpt-5\":[\"copilot/gpt-5*\",\"openai/gpt-5*\"],\"gpt-5-codex\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\"],\"gpt-5-mini\":[\"copilot/gpt-5*mini*\",\"openai/gpt-5*mini*\"],\"gpt-5-nano\":[\"copilot/gpt-5*nano*\",\"openai/gpt-5*nano*\"],\"gpt-5-pro\":[\"copilot/gpt-5*pro*\",\"openai/gpt-5*pro*\"],\"gpt-5.1\":[\"copilot/gpt-5.1*\",\"openai/gpt-5.1*\"],\"gpt-5.2\":[\"copilot/gpt-5.2*\",\"openai/gpt-5.2*\"],\"gpt-5.3\":[\"copilot/gpt-5.3*\",\"openai/gpt-5.3*\"],\"gpt-5.4\":[\"copilot/gpt-5.4*\",\"openai/gpt-5.4*\"],\"gpt-5.5\":[\"copilot/gpt-5.5*\",\"openai/gpt-5.5*\"],\"gpt-5.6\":[\"copilot/gpt-5.6*\",\"openai/gpt-5.6*\"],\"haiku\":[\"copilot/*haiku*\",\"anthropic/*haiku*\"],\"image-generation\":[\"copilot/gpt-image*\",\"openai/gpt-image*\",\"openai/chatgpt-image*\",\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"google/imagen*\"],\"kimi\":[\"copilot/kimi*\",\"openai/kimi*\"],\"kiwi\":[\"copilot/kiwi*\",\"openai/kiwi*\"],\"large\":[\"fable\",\"sonnet\",\"gpt-5-pro\",\"gpt-5\",\"gemini-pro\"],\"lyria\":[\"google/lyria*\",\"gemini/lyria*\",\"copilot/lyria*\"],\"mai-code\":[\"copilot/MAI-Code*\",\"copilot/mai-code*\",\"openai/MAI-Code*\"],\"mai-code-1-flash-picker\":[\"copilot/MAI-Code-1-Flash-picker*\",\"copilot/mai-code-1-flash-picker*\",\"openai/MAI-Code-1-Flash-picker*\"],\"mini\":[\"haiku\",\"gpt-5-mini\",\"gpt-5-nano\",\"gemini-flash-lite\"],\"nano-banana\":[\"copilot/nano-banana*\",\"google/nano-banana*\",\"gemini/nano-banana*\"],\"opus\":[\"copilot/*opus*\",\"anthropic/*opus*\"],\"opusplan\":[\"opus?effort=high\"],\"raptor-mini\":[\"copilot/raptor*\",\"openai/raptor*\"],\"reasoning\":[\"copilot/o1*\",\"copilot/o3*\",\"copilot/o4*\",\"openai/o1*\",\"openai/o3*\",\"openai/o4*\"],\"robotics\":[\"copilot/*robotics*\",\"google/*robotics*\",\"gemini/*robotics*\"],\"small\":[\"mini\"],\"small-agent\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash\"],\"sonnet\":[\"copilot/*sonnet*\",\"anthropic/*sonnet*\"],\"sonnet-6x\":[\"copilot/*sonnet-4.5*\",\"copilot/*sonnet-4.6*\",\"copilot/*sonnet-5*\",\"copilot/*sonnet-4-5-*\",\"anthropic/*sonnet-4-5-*\",\"copilot/*sonnet-4-6*\",\"anthropic/*sonnet-4-6*\",\"anthropic/*sonnet-5*\"],\"summarization\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash-lite\",\"mini\"],\"veo\":[\"google/veo*\",\"gemini/veo*\"],\"vision\":[\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"]}},\"container\":{\"imageTag\":\"0.27.42,squid=sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0,agent=sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b,agent-act=sha256:a14ad974484aa518aab83d40f3f141175dfd171d3745e01c092375b970f73a20,api-proxy=sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607,cli-proxy=sha256:da006bf96d2d246dd269d57b233c1798d2ad63d6cd64ca02f7bf71045028781f\"},\"logging\":{\"proxyLogsDir\":\"/tmp/gh-aw/sandbox/firewall/logs\",\"auditDir\":\"/tmp/gh-aw/sandbox/firewall/audit\"}}" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- cp "${RUNNER_TEMP}/gh-aw/awf-config.json" /tmp/gh-aw/awf-config.json
- export GH_AW_MODELS_JSON_PATH="/tmp/gh-aw/models.json"
- GH_AW_DOCKER_HOST=""
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_DOCKER_HOST="${DOCKER_HOST}"
- fi
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_CHROOT_BINARIES_SOURCE_PATH="${RUNNER_TEMP}/gh-aw" GH_AW_CHROOT_IDENTITY_HOME="${RUNNER_TEMP}/gh-aw/home" node "${RUNNER_TEMP}/gh-aw/actions/patch_awf_chroot_config.cjs"
- fi
- GH_AW_TOOL_CACHE_MOUNT=""
- GH_AW_TOOL_CACHE="${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"
- if [ -d "$GH_AW_TOOL_CACHE" ]; then
- if [[ "$GH_AW_TOOL_CACHE" != /opt/* ]]; then
- GH_AW_TOOL_CACHE_MOUNT="$GH_AW_TOOL_CACHE:$GH_AW_TOOL_CACHE:ro"
- fi
- fi
- # shellcheck disable=SC1003,SC2016,SC2086
- awf --config "${RUNNER_TEMP}/gh-aw/awf-config.json" --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" ${GH_AW_TOOL_CACHE_MOUNT:+--mount "$GH_AW_TOOL_CACHE_MOUNT"} ${GH_AW_DOCKER_HOST:+--docker-host "$GH_AW_DOCKER_HOST"} --env-all --exclude-env COPILOT_GITHUB_TOKEN --exclude-env GITHUB_MCP_SERVER_TOKEN --exclude-env MCP_GATEWAY_API_KEY --log-level info --skip-pull \
- -- /bin/bash -c 'set +o histexpand; export PATH="${RUNNER_TEMP}/gh-aw/mcp-cli/bin:$PATH" && : "${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"; GH_AW_TOOL_CACHE="$RUNNER_TOOL_CACHE"; export PATH="$(find "$GH_AW_TOOL_CACHE" -maxdepth 5 -type d -name bin 2>/dev/null | tr '\''\n'\'' '\'':'\'')$PATH"; [ -n "$GOROOT" ] && export PATH="$GOROOT/bin:$PATH" || true; [ -n "$ERLANG_HOME" ] && export PATH="$ERLANG_HOME/bin:$PATH" || true && GH_AW_NODE_EXEC="${GH_AW_NODE_BIN:-}"; if [ -z "$GH_AW_NODE_EXEC" ] || [ ! -x "$GH_AW_NODE_EXEC" ]; then GH_AW_NODE_EXEC="$(command -v node 2>/dev/null || true)"; fi; if [ -z "$GH_AW_NODE_EXEC" ]; then echo "node runtime missing on this runner — check runtimes.node in workflow YAML" >&2; exit 127; fi; GH_AW_NPM_GLOBAL_ROOT="$(npm root -g 2>/dev/null || true)"; if [ -n "$GH_AW_NPM_GLOBAL_ROOT" ]; then export NODE_PATH="${GH_AW_NPM_GLOBAL_ROOT}${NODE_PATH:+:${NODE_PATH}}"; fi; "$GH_AW_NODE_EXEC" ${RUNNER_TEMP}/gh-aw/actions/copilot_harness.cjs /usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --no-ask-user --allow-all-tools --allow-all-paths --add-dir "${GITHUB_WORKSPACE}" --prompt-file /tmp/gh-aw/aw-prompts/prompt.txt' 2>&1 | tee -a /tmp/gh-aw/agent-stdio.log
- env:
- AWF_REFLECT_ENABLED: 1
- COPILOT_AGENT_RUNNER_TYPE: STANDALONE
- COPILOT_DUMMY_BYOK: dummy-byok-key-for-offline-mode
- COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- COPILOT_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_LLM_PROVIDER: github
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }}
- GH_AW_MAX_TURNS: ${{ vars.GH_AW_DEFAULT_MAX_TURNS || '' }}
- GH_AW_PHASE: agent
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- GH_AW_TIMEOUT_MINUTES: 180
- GH_AW_VERSION: v0.83.4
- GITHUB_API_URL: ${{ github.api_url }}
- GITHUB_AW: true
- GITHUB_COPILOT_INTEGRATION_ID: agentic-workflows
- GITHUB_HEAD_REF: ${{ github.head_ref }}
- GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- GITHUB_REF_NAME: ${{ github.ref_name }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_STEP_SUMMARY: /tmp/gh-aw/agent-step-summary.md
- GITHUB_WORKSPACE: ${{ github.workspace }}
- GIT_AUTHOR_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_AUTHOR_NAME: github-actions[bot]
- GIT_COMMITTER_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_COMMITTER_NAME: github-actions[bot]
- RUNNER_TEMP: ${{ runner.temp }}
- TRACEPARENT: ${{ env.GITHUB_AW_OTEL_TRACE_ID != '' && env.GITHUB_AW_OTEL_PARENT_SPAN_ID != '' && format('00-{0}-{1}-01', env.GITHUB_AW_OTEL_TRACE_ID, env.GITHUB_AW_OTEL_PARENT_SPAN_ID) || '' }}
- - name: Detect agent errors
- if: always()
- id: detect-agent-errors
- continue-on-error: true
- run: node "${RUNNER_TEMP}/gh-aw/actions/detect_agent_errors.cjs"
- - name: Configure Git credentials
- env:
- GITHUB_REPOSITORY: ${{ github.repository }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_TOKEN: ${{ github.token }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/configure_git_credentials.sh"
- - name: Copy Copilot session state files to logs
- if: always()
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/copy_copilot_session_state.sh"
- - name: Stop MCP Gateway
- if: always()
- continue-on-error: true
- env:
- MCP_GATEWAY_PORT: ${{ steps.start-mcp-gateway.outputs.gateway-port }}
- 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" "$GATEWAY_PID"
- - name: Redact secrets in logs
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/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'
- SECRET_COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- SECRET_GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }}
- SECRET_GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- 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
- if: always()
- env:
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- run: |
- mkdir -p /tmp/gh-aw
- cp "$GH_AW_SAFE_OUTPUTS" /tmp/gh-aw/safeoutputs.jsonl 2>/dev/null || true
- - name: Ingest agent output
- id: collect_output
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.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.nuget.org,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"
- 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');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/collect_ndjson_output.cjs');
- await main();
- - name: Parse agent logs for step summary
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: /tmp/gh-aw/sandbox/agent/logs/
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_copilot_log.cjs');
- await main();
- - name: Parse MCP Gateway logs for step summary
- if: always()
- id: parse-mcp-gateway
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_mcp_gateway_log.cjs');
- await main();
- - name: Print firewall logs
- if: always()
- continue-on-error: true
- env:
- AWF_LOGS_DIR: /tmp/gh-aw/sandbox/firewall/logs
- run: bash "${RUNNER_TEMP}/gh-aw/actions/print_firewall_logs.sh" --rootless
- - name: Parse token usage for step summary
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_token_usage.cjs');
- await main();
- - name: Print AWF reflect summary
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/awf_reflect_summary.cjs');
- await main();
- - name: Write agent output placeholder if missing
- if: always()
- run: |
- if [ ! -f /tmp/gh-aw/agent_output.json ]; then
- echo '{"items":[]}' > /tmp/gh-aw/agent_output.json
- fi
- - name: Upload agent artifacts
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: agent
- 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/agent_usage.json
- /tmp/gh-aw/agent-stdio.log
- /tmp/gh-aw/pre-agent-audit.txt
- /tmp/gh-aw/agent/
- /tmp/gh-aw/github_rate_limits.jsonl
- /tmp/gh-aw/safeoutputs.jsonl
- /tmp/gh-aw/agent_output.json
- /tmp/gh-aw/aw-*.patch
- /tmp/gh-aw/aw-*.bundle
- /tmp/gh-aw/awf-config.json
- /tmp/gh-aw/sandbox/firewall/logs/
- /tmp/gh-aw/sandbox/firewall/audit/
- /tmp/gh-aw/sandbox/firewall/awf-reflect.json
- if-no-files-found: ignore
-
- conclusion:
- needs:
- - activation
- - agent
- - detection
- - safe_outputs
- if: >
- always() && (needs.agent.result != 'skipped' || needs.activation.outputs.lockdown_check_failed == 'true' ||
- needs.activation.outputs.oauth_token_check_failed == 'true' || needs.activation.outputs.stale_lock_file_failed == 'true' ||
- needs.activation.outputs.secret_verification_result == 'failed' || needs.activation.outputs.daily_ai_credits_exceeded == 'true')
- runs-on: ubuntu-slim
- permissions:
- contents: read
- discussions: write
- issues: write
- concurrency:
- group: "gh-aw-conclusion-ostrich-benchmark"
- cancel-in-progress: false
- queue: max
- env:
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- incomplete_count: ${{ steps.report_incomplete.outputs.incomplete_count }}
- noop_message: ${{ steps.noop.outputs.noop_message }}
- tools_reported: ${{ steps.missing_tool.outputs.tools_reported }}
- total_count: ${{ steps.missing_tool.outputs.total_count }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/ostrich-benchmark.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Download safe outputs items manifest
- id: download-safe-outputs-manifest
- if: always()
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: safe-outputs-items
- path: /tmp/gh-aw/
- - name: Collect usage artifact files
- if: always()
- continue-on-error: true
- run: |
- mkdir -p /tmp/gh-aw/usage/agent /tmp/gh-aw/usage/detection
- echo "Usage artifact source file status:"
- for file in /tmp/gh-aw/aw_info.json /tmp/gh-aw/aw-info.jsonl /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/detection_usage.jsonl /tmp/gh-aw/evals/evals.jsonl /tmp/gh-aw/github_rate_limits.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl; do
- [ -f "$file" ] && echo "FOUND: $file" || echo "MISSING: $file"
- done
- [ -f /tmp/gh-aw/aw_info.json ] && cp /tmp/gh-aw/aw_info.json /tmp/gh-aw/usage/aw_info.json || true
- [ -f /tmp/gh-aw/aw-info.jsonl ] && cp /tmp/gh-aw/aw-info.jsonl /tmp/gh-aw/usage/aw-info.jsonl || true
- [ -f /tmp/gh-aw/agent_usage.json ] && cp /tmp/gh-aw/agent_usage.json /tmp/gh-aw/usage/agent_usage.json || true
- [ -f /tmp/gh-aw/agent_usage.jsonl ] && cp /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/usage/agent_usage.jsonl || true
- [ -f /tmp/gh-aw/detection_usage.jsonl ] && cp /tmp/gh-aw/detection_usage.jsonl /tmp/gh-aw/usage/detection_usage.jsonl || true
- [ -f /tmp/gh-aw/evals/evals.jsonl ] && cp /tmp/gh-aw/evals/evals.jsonl /tmp/gh-aw/usage/evals.jsonl || true
- [ -f /tmp/gh-aw/github_rate_limits.jsonl ] && cp /tmp/gh-aw/github_rate_limits.jsonl /tmp/gh-aw/usage/github_rate_limits.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -f /tmp/gh-aw/usage/agent/token_usage.jsonl ] || : > /tmp/gh-aw/usage/agent/token_usage.jsonl
- [ -f /tmp/gh-aw/usage/detection/token_usage.jsonl ] || : > /tmp/gh-aw/usage/detection/token_usage.jsonl
- mkdir -p /tmp/gh-aw/usage/activity
- node "${RUNNER_TEMP}/gh-aw/actions/generate_usage_activity_summary.cjs"
- find /tmp/gh-aw/usage -type f -print | sort
- - name: Upload usage artifact
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: usage
- path: |
- /tmp/gh-aw/usage/aw_info.json
- /tmp/gh-aw/usage/aw-info.jsonl
- /tmp/gh-aw/usage/agent_usage.json
- /tmp/gh-aw/usage/agent_usage.jsonl
- /tmp/gh-aw/usage/detection_usage.jsonl
- /tmp/gh-aw/usage/evals.jsonl
- /tmp/gh-aw/usage/github_rate_limits.jsonl
- /tmp/gh-aw/usage/agent/token_usage.jsonl
- /tmp/gh-aw/usage/detection/token_usage.jsonl
- /tmp/gh-aw/usage/activity/summary.json
- if-no-files-found: ignore
- - name: Restore daily AIC usage cache
- id: restore-daily-aic-cache-conclusion
- if: always()
- continue-on-error: true
- uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-ostrichbenchmark-${{ github.run_id }}
- restore-keys: agentic-workflow-usage-ostrichbenchmark-
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Write daily AIC usage cache entry
- id: write-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- github-token: ${{ github.token }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/write_daily_aic_usage_cache.cjs');
- await main();
- - name: Save daily AIC usage cache
- id: save-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-ostrichbenchmark-${{ github.run_id }}
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Upload daily AIC usage cache artifact
- id: upload-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: aic-usage-cache
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- if-no-files-found: ignore
- retention-days: 7
- - name: Process no-op messages
- id: noop
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_NOOP_MAX: "1"
- GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/ostrich-benchmark.md"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_AGENT_CONCLUSION: ${{ needs.agent.result }}
- GH_AW_NOOP_REPORT_AS_ISSUE: "false"
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_AMBIENT_CONTEXT: ${{ needs.agent.outputs.ambient_context }}
- GH_AW_WORKFLOW_ID: "ostrich-benchmark"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_noop_message.cjs');
- await main();
- - name: Log detection run
- id: detection_runs
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/ostrich-benchmark.md"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_DETECTION_CONCLUSION: ${{ needs.detection.outputs.detection_conclusion }}
- GH_AW_DETECTION_REASON: ${{ needs.detection.outputs.detection_reason }}
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_detection_runs.cjs');
- await main();
- - name: Record missing tool
- id: missing_tool
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_MISSING_TOOL_CREATE_ISSUE: "true"
- GH_AW_MISSING_TOOL_TITLE_PREFIX: "[missing tool]"
- GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/ostrich-benchmark.md"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/missing_tool.cjs');
- await main();
- - name: Record incomplete
- id: report_incomplete
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_REPORT_INCOMPLETE_CREATE_ISSUE: "true"
- GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/ostrich-benchmark.md"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/report_incomplete_handler.cjs');
- await main();
- - name: Handle agent failure
- id: handle_agent_failure
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/ostrich-benchmark.md"
- 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"
- GH_AW_ACTION_FAILURE_ISSUE_EXPIRES_HOURS: "168"
- GH_AW_ENGINE_ID: "copilot"
- GH_AW_SECRET_VERIFICATION_RESULT: ${{ needs.activation.outputs.secret_verification_result }}
- GH_AW_ENGINE_SECRET_FAILURE_MESSAGE: "**Alternative**: If your organization has a Copilot subscription, you can avoid the need for a personal access token by adding a top-level `permissions` block to your workflow file. This enables Copilot inference through the org using the built-in GitHub Actions token.\n\n```yaml\npermissions:\n copilot-requests: write\n```\n\nSee: https://github.github.com/gh-aw/reference/engines/#github-copilot-default"
- GH_AW_CHECKOUT_PR_SUCCESS: ${{ needs.agent.outputs.checkout_pr_success }}
- GH_AW_EFFECTIVE_TOKENS: ${{ needs.agent.outputs.effective_tokens || '' }}
- GH_AW_AI_CREDITS_RATE_LIMIT_ERROR: ${{ needs.agent.outputs.ai_credits_rate_limit_error || 'false' }}
- GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }}
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }}
- GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }}
- GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }}
- GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }}
- GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }}
- GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }}
- GH_AW_ENGINE_API_HOSTS: "api.enterprise.githubcopilot.com,api.githubcopilot.com,api.business.githubcopilot.com,api.individual.githubcopilot.com"
- 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_OAUTH_TOKEN_CHECK_FAILED: ${{ needs.activation.outputs.oauth_token_check_failed }}
- GH_AW_STALE_LOCK_FILE_FAILED: ${{ needs.activation.outputs.stale_lock_file_failed }}
- GH_AW_DAILY_AI_CREDITS_EXCEEDED: ${{ needs.activation.outputs.daily_ai_credits_exceeded }}
- GH_AW_DAILY_AI_CREDITS_TOTAL_EFFECTIVE_TOKENS: ${{ needs.activation.outputs.daily_ai_credits_total_effective_tokens }}
- GH_AW_DAILY_AI_CREDITS_THRESHOLD: ${{ needs.activation.outputs.daily_ai_credits_threshold }}
- GH_AW_GROUP_REPORTS: "false"
- GH_AW_FAILURE_REPORT_AS_ISSUE: "false"
- GH_AW_MISSING_TOOL_REPORT_AS_FAILURE: "true"
- GH_AW_MISSING_DATA_REPORT_AS_FAILURE: "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');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_agent_failure.cjs');
- await main();
-
- detection:
- needs:
- - activation
- - agent
- if: always() && needs.agent.result != 'skipped'
- runs-on: ubuntu-latest
- permissions:
- contents: read
- env:
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- aic: ${{ steps.parse_detection_token_usage.outputs.aic }}
- detection_conclusion: ${{ steps.detection_conclusion.outputs.conclusion }}
- detection_reason: ${{ steps.detection_conclusion.outputs.reason }}
- detection_success: ${{ steps.detection_conclusion.outputs.success }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/ostrich-benchmark.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Checkout repository for patch context
- if: needs.agent.outputs.has_patch == 'true'
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- with:
- persist-credentials: false
- # --- Threat Detection ---
- - name: Clean stale firewall files from agent artifact
- run: |
- rm -rf /tmp/gh-aw/sandbox/firewall/logs
- rm -rf /tmp/gh-aw/sandbox/firewall/audit
- - name: Download container images
- run: bash "${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh" ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607 ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0
- - name: Check if detection needed
- id: detection_guard
- if: always()
- env:
- OUTPUT_TYPES: ${{ needs.agent.outputs.output_types }}
- HAS_PATCH: ${{ needs.agent.outputs.has_patch }}
- run: |
- if [[ -n "$OUTPUT_TYPES" || "$HAS_PATCH" == "true" ]]; then
- echo "run_detection=true" >> "$GITHUB_OUTPUT"
- echo "Detection will run: output_types=$OUTPUT_TYPES, has_patch=$HAS_PATCH"
- else
- echo "run_detection=false" >> "$GITHUB_OUTPUT"
- echo "Detection skipped: no agent outputs or patches to analyze"
- fi
- - name: Clear MCP Config for detection
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- rm -f "${RUNNER_TEMP}/gh-aw/mcp-config/mcp-servers.json"
- rm -f "$HOME/.copilot/mcp-config.json"
- rm -f "$GITHUB_WORKSPACE/.gemini/settings.json"
- - name: Prepare threat detection files
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- mkdir -p /tmp/gh-aw/threat-detection/aw-prompts
- rm -f /tmp/gh-aw/agent_usage.json
- cp /tmp/gh-aw/aw-prompts/prompt.txt /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt 2>/dev/null || true
- if [ ! -s /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt ]; then
- echo "::warning::ERR_VALIDATION: Missing or empty detection context prompt at /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt. Ensure the agent artifact includes /tmp/gh-aw/aw-prompts/prompt.txt. Detection will continue with fallback workflow context."
- fi
- cp /tmp/gh-aw/agent_output.json /tmp/gh-aw/threat-detection/agent_output.json 2>/dev/null || true
- for f in /tmp/gh-aw/aw-*.patch; do
- [ -f "$f" ] && cp "$f" /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- done
- for f in /tmp/gh-aw/aw-*.bundle; do
- [ -f "$f" ] && cp "$f" /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- done
- echo "Prepared threat detection files:"
- ls -la /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- - name: Setup threat detection
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- 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: ${{ needs.agent.outputs.has_patch }}
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/setup_threat_detection.cjs');
- await main();
- - name: Ensure threat-detection directory and log
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- mkdir -p /tmp/gh-aw/threat-detection
- touch /tmp/gh-aw/threat-detection/detection.log
- - name: Setup Node.js
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
- with:
- node-version: '24'
- package-manager-cache: false
- - name: Install GitHub Copilot CLI
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh" 1.0.75
- env:
- GH_HOST: github.com
- - name: Install AWF binary
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.27.42
- - name: Execute GitHub Copilot CLI
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- continue-on-error: true
- id: detection_agentic_execution
- # Copilot CLI tool arguments (sorted):
- timeout-minutes: 20
- run: |
- set -o pipefail
- printf '%s' "$(date +%s%3N)" > /tmp/gh-aw/agent_cli_start_ms.txt
- trap 'gh_aw_exit_code=$?; mkdir -p /tmp/gh-aw >/dev/null 2>&1 || true; printf "%s" "$gh_aw_exit_code" > /tmp/gh-aw/agent_execution_exit_code.txt || true; rm -f "$HOME/.copilot/settings.json"' EXIT
- mkdir -p "$HOME/.copilot"
- printf '%s' '{"builtInAgents":{"rubberDuck":false}}' > "$HOME/.copilot/settings.json"
- export XDG_CONFIG_HOME="$HOME"
- touch /tmp/gh-aw/agent-step-summary.md
- GH_AW_NODE_BIN=$(command -v node 2>/dev/null || true)
- export GH_AW_NODE_BIN
- export COPILOT_API_KEY="$COPILOT_DUMMY_BYOK"
- (umask 177 && touch /tmp/gh-aw/threat-detection/detection.log)
- GH_AW_MAX_AI_CREDITS="${GH_AW_MAX_AI_CREDITS:-400}"
- printf '%s\n' "{\"\$schema\":\"https://github.com/github/gh-aw-firewall/releases/download/v0.27.42/awf-config.schema.json\",\"network\":{\"allowDomains\":[\"api.business.githubcopilot.com\",\"api.enterprise.githubcopilot.com\",\"api.github.com\",\"api.githubcopilot.com\",\"api.individual.githubcopilot.com\",\"github.com\",\"host.docker.internal\",\"registry.npmjs.org\",\"telemetry.enterprise.githubcopilot.com\"]},\"apiProxy\":{\"enabled\":true,\"enableTokenSteering\":true,\"maxRuns\":500,\"maxAiCredits\":${GH_AW_MAX_AI_CREDITS},\"maxCacheMisses\":5,\"models\":{\"agent\":[\"sonnet-6x\",\"gpt-5.4\",\"gpt-5.5\",\"gpt-5.6\",\"gpt-5.3\",\"gemini-pro\",\"any\"],\"antigravity\":[\"copilot/antigravity*\",\"google/antigravity*\",\"gemini/antigravity*\"],\"any\":[\"copilot/*\",\"anthropic/*\",\"openai/*\",\"google/*\",\"gemini/*\"],\"claude\":[\"agent\"],\"codex\":[\"agent\"],\"coding\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\",\"gpt-5-codex\",\"kimi\"],\"computer-use\":[\"copilot/*computer-use*\",\"google/*computer-use*\",\"gemini/*computer-use*\",\"openai/*computer-use*\"],\"copilot\":[\"agent\"],\"deep-research\":[\"copilot/deep-research*\",\"copilot/o3-deep-research*\",\"copilot/o4-mini-deep-research*\",\"google/deep-research*\",\"gemini/deep-research*\",\"openai/o3-deep-research*\",\"openai/o4-mini-deep-research*\"],\"fable\":[\"copilot/*fable*\",\"anthropic/*fable*\"],\"gemini\":[\"agent\"],\"gemini-3-flash\":[\"copilot/gemini-3*flash*\",\"google/gemini-3*flash*\",\"gemini/gemini-3*flash*\"],\"gemini-3-pro\":[\"copilot/gemini-3*pro*\",\"google/gemini-3*pro*\",\"google/nano-banana*\",\"gemini/gemini-3*pro*\"],\"gemini-3.1-flash\":[\"copilot/gemini-3.1*flash*\",\"google/gemini-3.1*flash*\",\"gemini/gemini-3.1*flash*\"],\"gemini-3.1-pro\":[\"copilot/gemini-3.1*pro*\",\"google/gemini-3.1*pro*\",\"gemini/gemini-3.1*pro*\"],\"gemini-3.5-flash\":[\"copilot/gemini-3.5*flash*\",\"google/gemini-3.5*flash*\",\"gemini/gemini-3.5*flash*\"],\"gemini-3.6-flash\":[\"copilot/gemini-3.6*flash*\",\"google/gemini-3.6*flash*\",\"gemini/gemini-3.6*flash*\"],\"gemini-flash\":[\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"],\"gemini-flash-lite\":[\"copilot/gemini-*flash*lite*\",\"google/gemini-*flash*lite*\",\"gemini/gemini-*flash*lite*\"],\"gemini-omni\":[\"copilot/gemini-omni*\",\"google/gemini-omni*\",\"gemini/gemini-omni*\"],\"gemini-pro\":[\"copilot/gemini-*pro*\",\"google/gemini-*pro*\",\"gemini/gemini-*pro*\"],\"gemma\":[\"copilot/gemma*\",\"google/gemma*\",\"gemini/gemma*\"],\"gpt-5\":[\"copilot/gpt-5*\",\"openai/gpt-5*\"],\"gpt-5-codex\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\"],\"gpt-5-mini\":[\"copilot/gpt-5*mini*\",\"openai/gpt-5*mini*\"],\"gpt-5-nano\":[\"copilot/gpt-5*nano*\",\"openai/gpt-5*nano*\"],\"gpt-5-pro\":[\"copilot/gpt-5*pro*\",\"openai/gpt-5*pro*\"],\"gpt-5.1\":[\"copilot/gpt-5.1*\",\"openai/gpt-5.1*\"],\"gpt-5.2\":[\"copilot/gpt-5.2*\",\"openai/gpt-5.2*\"],\"gpt-5.3\":[\"copilot/gpt-5.3*\",\"openai/gpt-5.3*\"],\"gpt-5.4\":[\"copilot/gpt-5.4*\",\"openai/gpt-5.4*\"],\"gpt-5.5\":[\"copilot/gpt-5.5*\",\"openai/gpt-5.5*\"],\"gpt-5.6\":[\"copilot/gpt-5.6*\",\"openai/gpt-5.6*\"],\"haiku\":[\"copilot/*haiku*\",\"anthropic/*haiku*\"],\"image-generation\":[\"copilot/gpt-image*\",\"openai/gpt-image*\",\"openai/chatgpt-image*\",\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"google/imagen*\"],\"kimi\":[\"copilot/kimi*\",\"openai/kimi*\"],\"kiwi\":[\"copilot/kiwi*\",\"openai/kiwi*\"],\"large\":[\"fable\",\"sonnet\",\"gpt-5-pro\",\"gpt-5\",\"gemini-pro\"],\"lyria\":[\"google/lyria*\",\"gemini/lyria*\",\"copilot/lyria*\"],\"mai-code\":[\"copilot/MAI-Code*\",\"copilot/mai-code*\",\"openai/MAI-Code*\"],\"mai-code-1-flash-picker\":[\"copilot/MAI-Code-1-Flash-picker*\",\"copilot/mai-code-1-flash-picker*\",\"openai/MAI-Code-1-Flash-picker*\"],\"mini\":[\"haiku\",\"gpt-5-mini\",\"gpt-5-nano\",\"gemini-flash-lite\"],\"nano-banana\":[\"copilot/nano-banana*\",\"google/nano-banana*\",\"gemini/nano-banana*\"],\"opus\":[\"copilot/*opus*\",\"anthropic/*opus*\"],\"opusplan\":[\"opus?effort=high\"],\"raptor-mini\":[\"copilot/raptor*\",\"openai/raptor*\"],\"reasoning\":[\"copilot/o1*\",\"copilot/o3*\",\"copilot/o4*\",\"openai/o1*\",\"openai/o3*\",\"openai/o4*\"],\"robotics\":[\"copilot/*robotics*\",\"google/*robotics*\",\"gemini/*robotics*\"],\"small\":[\"mini\"],\"small-agent\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash\"],\"sonnet\":[\"copilot/*sonnet*\",\"anthropic/*sonnet*\"],\"sonnet-6x\":[\"copilot/*sonnet-4.5*\",\"copilot/*sonnet-4.6*\",\"copilot/*sonnet-5*\",\"copilot/*sonnet-4-5-*\",\"anthropic/*sonnet-4-5-*\",\"copilot/*sonnet-4-6*\",\"anthropic/*sonnet-4-6*\",\"anthropic/*sonnet-5*\"],\"summarization\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash-lite\",\"mini\"],\"veo\":[\"google/veo*\",\"gemini/veo*\"],\"vision\":[\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"]}},\"container\":{\"imageTag\":\"0.27.42,squid=sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0,agent=sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b,agent-act=sha256:a14ad974484aa518aab83d40f3f141175dfd171d3745e01c092375b970f73a20,api-proxy=sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607,cli-proxy=sha256:da006bf96d2d246dd269d57b233c1798d2ad63d6cd64ca02f7bf71045028781f\"},\"logging\":{\"proxyLogsDir\":\"/tmp/gh-aw/sandbox/firewall/logs\",\"auditDir\":\"/tmp/gh-aw/sandbox/firewall/audit\"}}" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- cp "${RUNNER_TEMP}/gh-aw/awf-config.json" /tmp/gh-aw/awf-config.json
- export GH_AW_MODELS_JSON_PATH="/tmp/gh-aw/models.json"
- GH_AW_DOCKER_HOST=""
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_DOCKER_HOST="${DOCKER_HOST}"
- fi
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- _GH_AW_CHROOT_JSON=$(jq -c --arg src "${RUNNER_TEMP}/gh-aw" --arg user "$(id -un)" --argjson uid "$(id -u)" --argjson gid "$(id -g)" --arg home "${RUNNER_TEMP}/gh-aw/home" '.chroot={"binariesSourcePath":$src,"identity":{"user":$user,"uid":$uid,"gid":$gid,"home":$home}}' "${RUNNER_TEMP}/gh-aw/awf-config.json") || { echo "chroot config patch failed" >&2; exit 1; }
- printf '%s\n' "$_GH_AW_CHROOT_JSON" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- printf '%s\n' "$_GH_AW_CHROOT_JSON" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- fi
- GH_AW_TOOL_CACHE_MOUNT=""
- GH_AW_TOOL_CACHE="${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"
- if [ -d "$GH_AW_TOOL_CACHE" ]; then
- if [[ "$GH_AW_TOOL_CACHE" != /opt/* ]]; then
- GH_AW_TOOL_CACHE_MOUNT="$GH_AW_TOOL_CACHE:$GH_AW_TOOL_CACHE:ro"
- fi
- fi
- # shellcheck disable=SC1003,SC2016,SC2086
- awf --config "${RUNNER_TEMP}/gh-aw/awf-config.json" --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" ${GH_AW_TOOL_CACHE_MOUNT:+--mount "$GH_AW_TOOL_CACHE_MOUNT"} ${GH_AW_DOCKER_HOST:+--docker-host "$GH_AW_DOCKER_HOST"} --env-all --exclude-env COPILOT_GITHUB_TOKEN --log-level info --skip-pull \
- -- /bin/bash -c 'set +o histexpand; : "${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"; GH_AW_TOOL_CACHE="$RUNNER_TOOL_CACHE"; export PATH="$(find "$GH_AW_TOOL_CACHE" -maxdepth 5 -type d -name bin 2>/dev/null | tr '\''\n'\'' '\'':'\'')$PATH"; [ -n "$GOROOT" ] && export PATH="$GOROOT/bin:$PATH" || true; [ -n "$ERLANG_HOME" ] && export PATH="$ERLANG_HOME/bin:$PATH" || true && GH_AW_NODE_EXEC="${GH_AW_NODE_BIN:-}"; if [ -z "$GH_AW_NODE_EXEC" ] || [ ! -x "$GH_AW_NODE_EXEC" ]; then GH_AW_NODE_EXEC="$(command -v node 2>/dev/null || true)"; fi; if [ -z "$GH_AW_NODE_EXEC" ]; then echo "node runtime missing on this runner — check runtimes.node in workflow YAML" >&2; exit 127; fi; GH_AW_NPM_GLOBAL_ROOT="$(npm root -g 2>/dev/null || true)"; if [ -n "$GH_AW_NPM_GLOBAL_ROOT" ]; then export NODE_PATH="${GH_AW_NPM_GLOBAL_ROOT}${NODE_PATH:+:${NODE_PATH}}"; fi; "$GH_AW_NODE_EXEC" ${RUNNER_TEMP}/gh-aw/actions/copilot_harness.cjs /usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --no-ask-user --allow-all-tools --add-dir "${GITHUB_WORKSPACE}" --prompt-file /tmp/gh-aw/aw-prompts/prompt.txt' 2>&1 | tee -a /tmp/gh-aw/threat-detection/detection.log
- env:
- AWF_REFLECT_ENABLED: 1
- COPILOT_AGENT_RUNNER_TYPE: STANDALONE
- COPILOT_DUMMY_BYOK: dummy-byok-key-for-offline-mode
- COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- COPILOT_MODEL: ${{ vars.GH_AW_MODEL_DETECTION_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_LLM_PROVIDER: github
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_DETECTION_MAX_AI_CREDITS || '400' }}
- GH_AW_MAX_TURNS: ${{ vars.GH_AW_DEFAULT_MAX_TURNS || '' }}
- GH_AW_PHASE: detection
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_TIMEOUT_MINUTES: 20
- GH_AW_VERSION: v0.83.4
- GITHUB_API_URL: ${{ github.api_url }}
- GITHUB_AW: true
- GITHUB_COPILOT_INTEGRATION_ID: agentic-workflows
- GITHUB_HEAD_REF: ${{ github.head_ref }}
- GITHUB_REF_NAME: ${{ github.ref_name }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_STEP_SUMMARY: /tmp/gh-aw/agent-step-summary.md
- GITHUB_WORKSPACE: ${{ github.workspace }}
- GIT_AUTHOR_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_AUTHOR_NAME: github-actions[bot]
- GIT_COMMITTER_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_COMMITTER_NAME: github-actions[bot]
- RUNNER_TEMP: ${{ runner.temp }}
- TRACEPARENT: ${{ env.GITHUB_AW_OTEL_TRACE_ID != '' && env.GITHUB_AW_OTEL_PARENT_SPAN_ID != '' && format('00-{0}-{1}-01', env.GITHUB_AW_OTEL_TRACE_ID, env.GITHUB_AW_OTEL_PARENT_SPAN_ID) || '' }}
- - name: Parse threat detection token usage for step summary
- id: parse_detection_token_usage
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_TOKEN_USAGE_SUMMARY_TITLE: Threat Detection Token Usage
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_token_usage.cjs');
- await main();
- - name: Upload threat detection log
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: detection
- path: /tmp/gh-aw/threat-detection/detection.log
- if-no-files-found: ignore
- - name: Parse and conclude threat detection
- id: detection_conclusion
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- RUN_DETECTION: ${{ steps.detection_guard.outputs.run_detection }}
- DETECTION_AGENTIC_EXECUTION_OUTCOME: ${{ steps.detection_agentic_execution.outcome }}
- GH_AW_DETECTION_CONTINUE_ON_ERROR: "true"
- with:
- script: |
- try {
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_threat_detection_results.cjs');
- await main();
- } catch (loadErr) {
- const continueOnError = process.env.GH_AW_DETECTION_CONTINUE_ON_ERROR !== 'false';
- const detectionExecutionFailed = process.env.DETECTION_AGENTIC_EXECUTION_OUTCOME === 'failure';
- const msg = 'ERR_SYSTEM: \u274C Unexpected error loading threat detection module: ' + (loadErr && loadErr.message ? loadErr.message : String(loadErr));
- core.error(msg);
- core.setOutput('reason', 'parse_error');
- if (continueOnError && !detectionExecutionFailed) {
- core.warning('\u26A0\uFE0F ' + msg);
- core.setOutput('conclusion', 'warning');
- core.setOutput('success', 'false');
- } else {
- core.setOutput('conclusion', 'failure');
- core.setOutput('success', 'false');
- core.setFailed(msg);
- }
- }
-
- safe_outputs:
- needs:
- - activation
- - agent
- - detection
- if: (!cancelled()) && needs.agent.result != 'skipped' && needs.detection.result == 'success'
- runs-on: ubuntu-slim
- permissions:
- contents: read
- discussions: write
- issues: write
- timeout-minutes: 45
- env:
- GH_AW_AGENT_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_AMBIENT_CONTEXT: ${{ needs.agent.outputs.ambient_context }}
- GH_AW_CALLER_WORKFLOW_ID: "${{ github.repository }}/ostrich-benchmark"
- GH_AW_DETECTION_CONCLUSION: ${{ needs.detection.outputs.detection_conclusion }}
- GH_AW_DETECTION_REASON: ${{ needs.detection.outputs.detection_reason }}
- GH_AW_EFFECTIVE_TOKENS: ${{ needs.agent.outputs.effective_tokens }}
- GH_AW_ENGINE_ID: "copilot"
- GH_AW_ENGINE_MODEL: ${{ needs.agent.outputs.model }}
- GH_AW_ENGINE_VERSION: "1.0.75"
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_WORKFLOW_ID: "ostrich-benchmark"
- GH_AW_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/ostrich-benchmark.md"
- 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 }}
- create_discussion_error_count: ${{ steps.process_safe_outputs.outputs.create_discussion_error_count }}
- create_discussion_errors: ${{ steps.process_safe_outputs.outputs.create_discussion_errors }}
- process_safe_outputs_processed_count: ${{ steps.process_safe_outputs.outputs.processed_count }}
- process_safe_outputs_temporary_id_map: ${{ steps.process_safe_outputs.outputs.temporary_id_map }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "Ostrich Benchmark: Z3 c3 branch vs ZIPT"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/ostrich-benchmark.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Configure GH_HOST for enterprise compatibility
- id: ghes-host-config
- shell: bash
- run: | # zizmor: ignore[github-env] - GITHUB_SERVER_URL is set by GitHub Actions, not user input.
- # Derive GH_HOST from GITHUB_SERVER_URL so the gh CLI targets the correct
- # GitHub instance (GHES/GHEC). On github.com this is a harmless no-op.
- GH_HOST="${GITHUB_SERVER_URL#https://}"
- GH_HOST="${GH_HOST#http://}"
- echo "GH_HOST=${GH_HOST}" >> "$GITHUB_ENV"
- - name: Process Safe Outputs
- id: process_safe_outputs
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_COMMENT_ID: ${{ needs.activation.outputs.comment_id }}
- GH_AW_ALLOWED_DOMAINS: "api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.nuget.org,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"
- 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] \"},\"create_report_incomplete_issue\":{},\"missing_data\":{},\"missing_tool\":{},\"noop\":{\"max\":1,\"report-as-issue\":\"false\"},\"report_incomplete\":{}}"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/process_safe_outputs.cjs');
- await main();
- - name: Upload Safe Outputs Items
- if: always()
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: safe-outputs-items
- path: |
- /tmp/gh-aw/safe-output-items.jsonl
- /tmp/gh-aw/temporary-id-map.json
- /tmp/gh-aw/process-safe-outputs.stdout.log
- /tmp/gh-aw/process-safe-outputs.stderr.log
- if-no-files-found: ignore
diff --git a/.github/workflows/ostrich-benchmark.md b/.github/workflows/ostrich-benchmark.md
deleted file mode 100644
index 9d868e0c2d..0000000000
--- a/.github/workflows/ostrich-benchmark.md
+++ /dev/null
@@ -1,461 +0,0 @@
----
-description: Run Z3 string solver benchmarks (seq vs nseq) plus ZIPT, cvc5, and Ostrich2 on all Ostrich benchmarks from tests/ostrich.zip on the c3 branch and post results as a GitHub discussion
-
-on:
- schedule:
- - cron: "0 6 * * *"
- workflow_dispatch:
-
-permissions: read-all
-
-network:
- allowed:
- - defaults
- - api.nuget.org
-
-tools:
- bash: true
- github:
- toolsets: [default]
-
-safe-outputs:
- report-failure-as-issue: false
- create-discussion:
- title-prefix: "[Ostrich Benchmark] "
- category: "Agentic Workflows"
- close-older-discussions: true
- missing-tool:
- create-issue: true
- noop:
- report-as-issue: false
-
-timeout-minutes: 180
-
-steps:
- - name: Checkout c3 branch
- uses: actions/checkout@v6.0.2
- with:
- ref: c3
- fetch-depth: 1
- persist-credentials: false
-
----
-
-
-# Ostrich Benchmark: Z3 c3 branch vs ZIPT, cvc5, and Ostrich2
-
-You are an AI agent that benchmarks Z3 string solvers (`seq` and `nseq`) plus ZIPT, cvc5, and Ostrich2 on all SMT-LIB2 benchmarks from the `tests/ostrich.zip` archive on the `c3` branch, and publishes a summary report as a GitHub discussion.
-
-## Context
-
-- **Repository**: ${{ github.repository }}
-- **Workspace**: ${{ github.workspace }}
-- **Branch**: c3 (already checked out by the workflow setup step)
-
-## Phase 1: Build Z3
-
-Build Z3 from the checked-out `c3` branch using CMake + Ninja, including the .NET bindings required by ZIPT.
-
-```bash
-cd ${{ github.workspace }}
-
-# Install build dependencies if missing
-sudo apt-get install -y ninja-build cmake python3 zstd dotnet-sdk-8.0 unzip 2>/dev/null || true
-
-# Configure the build in Release mode for better performance and lower memory usage
-# (Release mode is sufficient for benchmarking; the workflow does not use -tr: trace flags)
-mkdir -p build
-cd build
-cmake .. -G Ninja -DCMAKE_BUILD_TYPE=Release -DZ3_BUILD_DOTNET_BINDINGS=ON 2>&1 | tail -20
-
-# Build z3 binary and .NET bindings SYNCHRONOUSLY (do NOT add & to background these commands).
-# Running ninja in the background while the LLM agent is also active causes OOM and kills the
-# agent process. Wait for each build command to finish before continuing.
-# -j1 limits parallelism to reduce peak memory usage alongside the LLM agent process.
-ninja z3 2>&1 | tail -30
-ninja build_z3_dotnet_bindings 2>&1 | tail -20
-
-# Verify the build succeeded
-./z3 --version
-
-# Locate the Microsoft.Z3.dll produced by the build
-Z3_DOTNET_DLL=$(find . -name "Microsoft.Z3.dll" -not -path "*/obj/*" | head -1)
-if [ -z "$Z3_DOTNET_DLL" ]; then
- echo "ERROR: Microsoft.Z3.dll not found after build"
- exit 1
-fi
-echo "Found Microsoft.Z3.dll at: $Z3_DOTNET_DLL"
-```
-
-If the build fails, report the error clearly and exit without proceeding.
-
-Once the binary is confirmed working, call the `noop` safe-output tool with the message `"Z3 built successfully from the c3 branch. Starting ZIPT/cvc5/Ostrich2 build and benchmark — results will be posted as a GitHub Discussion once complete."` This keepalive call refreshes the safe-output MCP session before the long build and benchmark phases begin, preventing a session timeout.
-
-## Phase 2a: Clone and Build ZIPT, cvc5, and Ostrich2
-
-Clone and build the external solvers.
-
-```bash
-cd ${{ github.workspace }}
-
-# Re-locate the Microsoft.Z3.dll if needed
-Z3_DOTNET_DLL=$(find build -name "Microsoft.Z3.dll" -not -path "*/obj/*" | head -1)
-Z3_LIB_DIR=${{ github.workspace }}/build
-
-# Clone ZIPT (parikh branch)
-git clone --depth=1 --branch parikh https://github.com/CEisenhofer/ZIPT.git /tmp/zipt
-
-# Patch ZIPT.csproj to point at the freshly built Microsoft.Z3.dll
-# (the repo has a Windows-relative hardcoded path that won't exist here)
-sed -i "s|.*|$Z3_DOTNET_DLL|" /tmp/zipt/ZIPT/ZIPT.csproj
-
-# Build ZIPT in Release mode
-cd /tmp/zipt/ZIPT
-dotnet build --configuration Release 2>&1 | tail -20
-
-# Locate the built ZIPT.dll
-ZIPT_DLL=$(find /tmp/zipt/ZIPT/bin/Release -name "ZIPT.dll" | head -1)
-if [ -z "$ZIPT_DLL" ]; then
- echo "ERROR: ZIPT.dll not found after build"
- exit 1
-fi
-echo "ZIPT binary: $ZIPT_DLL"
-
-# Make libz3.so visible to the .NET runtime at ZIPT startup
-ZIPT_OUT_DIR=$(dirname "$ZIPT_DLL")
-if cp "$Z3_LIB_DIR/libz3.so" "$ZIPT_OUT_DIR/" 2>/dev/null; then
- echo "Copied libz3.so to $ZIPT_OUT_DIR"
-else
- echo "WARNING: could not copy libz3.so to $ZIPT_OUT_DIR — setting LD_LIBRARY_PATH fallback"
-fi
-export LD_LIBRARY_PATH="$Z3_LIB_DIR${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
-echo "ZIPT build complete."
-
-# Build cvc5 from source (minimal build with string support)
-git clone --depth=1 https://github.com/cvc5/cvc5.git /tmp/cvc5
-cd /tmp/cvc5
-./configure.sh --auto-download --static-binary 2>&1 | tail -30
-cd build
-make -j"$(nproc)" 2>&1 | tail -40
-
-if [ -x "/tmp/cvc5/build/bin/cvc5" ]; then
- echo "cvc5 binary: /tmp/cvc5/build/bin/cvc5"
-else
- echo "WARNING: cvc5 build failed or binary missing"
-fi
-
-# Build Ostrich2 from source
-cd ${{ github.workspace }}
-git clone --depth=1 https://github.com/uuverifiers/ostrich.git /tmp/ostrich2
-cd /tmp/ostrich2
-sudo apt-get install -y openjdk-17-jdk-headless sbt 2>/dev/null || true
-sbt assembly 2>&1 | tail -40
-
-if [ -x "/tmp/ostrich2/ostrich" ]; then
- echo "Ostrich2 launcher: /tmp/ostrich2/ostrich"
-else
- echo "WARNING: Ostrich2 build failed or launcher missing"
-fi
-```
-
-If any external solver build fails, note the error in the report and continue with the remaining solvers.
-
-## Phase 2b: Extract Benchmark Files
-
-Extract all SMT-LIB2 files from the `tests/ostrich.zip` archive.
-
-```bash
-cd ${{ github.workspace }}
-
-# Extract the zip archive
-mkdir -p /tmp/ostrich_benchmarks
-unzip -q tests/ostrich.zip -d /tmp/ostrich_benchmarks
-
-# List all .smt2 files
-find /tmp/ostrich_benchmarks -name "*.smt2" -type f | sort > /tmp/all_ostrich_files.txt
-TOTAL_FILES=$(wc -l < /tmp/all_ostrich_files.txt)
-echo "Total Ostrich .smt2 files: $TOTAL_FILES"
-
-if [ "$TOTAL_FILES" -eq 0 ]; then
- echo "ERROR: No .smt2 files found in tests/ostrich.zip"
- exit 1
-fi
-```
-
-Once the benchmark files are confirmed, call the `noop` safe-output tool with the message `"Benchmark files ready: Ostrich .smt2 files extracted. Starting benchmark run — this may take over an hour."` This second keepalive refreshes the safe-output MCP session immediately before the long per-file benchmark loop begins.
-
-## Phase 3: Run Benchmarks
-
-Run every file from `/tmp/all_ostrich_files.txt` with both Z3 string solvers plus ZIPT, cvc5, and Ostrich2. Use a **5-second timeout** per run.
-
-For each file, run:
-1. `z3 smt.string_solver=seq -T:5 ` — seq solver
-2. `z3 smt.string_solver=nseq -T:5 ` — nseq (ZIPT) solver
-3. `dotnet -t:5000 ` — standalone ZIPT solver (milliseconds)
-4. `cvc5 --lang smt2 --tlimit-per=5000 ` — cvc5 (milliseconds)
-5. `ostrich -timeout=5 ` — Ostrich2 (seconds; fallback to outer timeout if unsupported)
-
-Capture:
-- **Verdict**: `sat`, `unsat`, `unknown`, `timeout` (if exit code indicates timeout or process is killed), or `bug` (if a solver crashes / produces a non-standard result)
-- **Time** (seconds): wall-clock time for the run
-- A row is flagged `SOUNDNESS_DISAGREEMENT` when any two solvers that both produced a definitive answer (sat/unsat) disagree
-
-Use a bash script to automate this:
-
-```bash
-#!/usr/bin/env bash
-set -euo pipefail
-
-Z3=${{ github.workspace }}/build/z3
-ZIPT_DLL=$(find /tmp/zipt/ZIPT/bin/Release -name "ZIPT.dll" 2>/dev/null | head -1)
-CVC5_BIN=/tmp/cvc5/build/bin/cvc5
-OSTRICH2_BIN=/tmp/ostrich2/ostrich
-ZIPT_AVAILABLE=false
-[ -n "$ZIPT_DLL" ] && ZIPT_AVAILABLE=true
-CVC5_AVAILABLE=false
-[ -x "$CVC5_BIN" ] && CVC5_AVAILABLE=true
-OSTRICH2_AVAILABLE=false
-[ -x "$OSTRICH2_BIN" ] && OSTRICH2_AVAILABLE=true
-
-# Ensure libz3.so is on the dynamic-linker path for the .NET runtime
-export LD_LIBRARY_PATH=${{ github.workspace }}/build${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}
-
-RESULTS=/tmp/benchmark_results.tsv
-mkdir -p /tmp/ostrich_run
-
-echo -e "file\tseq_verdict\tseq_time\tnseq_verdict\tnseq_time\tzipt_verdict\tzipt_time\tcvc5_verdict\tcvc5_time\tostrich2_verdict\tostrich2_time\tnotes" > "$RESULTS"
-
-run_and_parse() {
- local sat_pattern="$1"
- local unsat_pattern="$2"
- local unknown_pattern="$3"
- local bug_pattern="$4"
- shift 4
- local start end elapsed verdict output exit_code
-
- start=$(date +%s%3N)
- set +e
- output=$("$@" 2>&1)
- exit_code=$?
- set -e
- end=$(date +%s%3N)
- elapsed=$(echo "scale=3; ($end - $start) / 1000" | bc)
-
- if [ "$exit_code" -eq 124 ]; then
- verdict="timeout"
- elif echo "$output" | grep -Eqi "$unsat_pattern"; then
- verdict="unsat"
- elif echo "$output" | grep -Eqi "$sat_pattern"; then
- verdict="sat"
- elif echo "$output" | grep -Eqi "$unknown_pattern"; then
- verdict="unknown"
- elif echo "$output" | grep -Eqi "$bug_pattern"; then
- verdict="bug"
- else
- verdict="unknown"
- fi
-
- echo "$verdict $elapsed"
-}
-
-run_z3_seq() {
- local file="$1"
- run_and_parse "^sat$" "^unsat$" "^unknown$" "error|assertion|segfault|SIGABRT|exception" \
- timeout 7 "$Z3" "smt.string_solver=seq" -T:5 "$file"
-}
-
-run_z3_nseq() {
- local file="$1"
- run_and_parse "^sat$" "^unsat$" "^unknown$" "error|assertion|segfault|SIGABRT|exception" \
- timeout 7 "$Z3" "smt.string_solver=nseq" -T:5 "$file"
-}
-
-run_zipt() {
- local file="$1"
-
- if [ "$ZIPT_AVAILABLE" != "true" ]; then
- echo "n/a 0.000"
- return
- fi
-
- # ZIPT prints the filename on the first line, then SAT/UNSAT/UNKNOWN on subsequent lines
- run_and_parse "^SAT$" "^UNSAT$" "^UNKNOWN$" "error|crash|exception|Unsupported" \
- timeout 7 dotnet "$ZIPT_DLL" -t:5000 "$file"
-}
-
-run_cvc5() {
- local file="$1"
-
- if [ "$CVC5_AVAILABLE" != "true" ]; then
- echo "n/a 0.000"
- return
- fi
-
- run_and_parse "^sat$" "^unsat$" "^unknown$" "error|fatal|exception|segfault|assert" \
- timeout 7 "$CVC5_BIN" --lang smt2 --tlimit-per=5000 "$file"
-}
-
-run_ostrich2() {
- local file="$1"
-
- if [ "$OSTRICH2_AVAILABLE" != "true" ]; then
- echo "n/a 0.000"
- return
- fi
-
- run_and_parse "^sat$" "^unsat$" "^unknown$" "error|fatal|exception|segfault|assert|Unsupported" \
- timeout 7 "$OSTRICH2_BIN" -timeout=5 "$file"
-}
-
-COUNTER=0
-while IFS= read -r file; do
- COUNTER=$((COUNTER + 1))
- fname=$(basename "$file")
-
- seq_result=$(run_z3_seq "$file")
- nseq_result=$(run_z3_nseq "$file")
- zipt_result=$(run_zipt "$file")
- cvc5_result=$(run_cvc5 "$file")
- ostrich2_result=$(run_ostrich2 "$file")
-
- seq_verdict=$(echo "$seq_result" | cut -d' ' -f1)
- seq_time=$(echo "$seq_result" | cut -d' ' -f2)
- nseq_verdict=$(echo "$nseq_result" | cut -d' ' -f1)
- nseq_time=$(echo "$nseq_result" | cut -d' ' -f2)
- zipt_verdict=$(echo "$zipt_result" | cut -d' ' -f1)
- zipt_time=$(echo "$zipt_result" | cut -d' ' -f2)
- cvc5_verdict=$(echo "$cvc5_result" | cut -d' ' -f1)
- cvc5_time=$(echo "$cvc5_result" | cut -d' ' -f2)
- ostrich2_verdict=$(echo "$ostrich2_result" | cut -d' ' -f1)
- ostrich2_time=$(echo "$ostrich2_result" | cut -d' ' -f2)
-
- # Flag soundness disagreement when any two definitive verdicts disagree
- notes=""
- declare -A definitive_map
- [ "$seq_verdict" = "sat" ] || [ "$seq_verdict" = "unsat" ] && definitive_map[seq]="$seq_verdict"
- [ "$nseq_verdict" = "sat" ] || [ "$nseq_verdict" = "unsat" ] && definitive_map[nseq]="$nseq_verdict"
- [ "$zipt_verdict" = "sat" ] || [ "$zipt_verdict" = "unsat" ] && definitive_map[zipt]="$zipt_verdict"
- [ "$cvc5_verdict" = "sat" ] || [ "$cvc5_verdict" = "unsat" ] && definitive_map[cvc5]="$cvc5_verdict"
- [ "$ostrich2_verdict" = "sat" ] || [ "$ostrich2_verdict" = "unsat" ] && definitive_map[ostrich2]="$ostrich2_verdict"
- has_sat=false; has_unsat=false
- for v in "${definitive_map[@]}"; do
- [ "$v" = "sat" ] && has_sat=true
- [ "$v" = "unsat" ] && has_unsat=true
- done
- if $has_sat && $has_unsat; then
- notes="SOUNDNESS_DISAGREEMENT"
- fi
-
- echo -e "$fname\t$seq_verdict\t$seq_time\t$nseq_verdict\t$nseq_time\t$zipt_verdict\t$zipt_time\t$cvc5_verdict\t$cvc5_time\t$ostrich2_verdict\t$ostrich2_time\t$notes" >> "$RESULTS"
- echo "[$COUNTER] [$fname] seq=$seq_verdict(${seq_time}s) nseq=$nseq_verdict(${nseq_time}s) zipt=$zipt_verdict(${zipt_time}s) cvc5=$cvc5_verdict(${cvc5_time}s) ostrich2=$ostrich2_verdict(${ostrich2_time}s) $notes"
-done < /tmp/all_ostrich_files.txt
-
-echo "Benchmark run complete. Results saved to $RESULTS"
-```
-
-Save this script to `/tmp/run_ostrich_benchmarks.sh`, make it executable, and run it. Do not skip any file.
-
-## Phase 4: Generate Summary Report
-
-Read `/tmp/benchmark_results.tsv` and compute statistics. Then generate a Markdown report.
-
-Compute:
-- **Total benchmarks**: total number of files run
-- **Per solver (seq, nseq, ZIPT, cvc5, and Ostrich2)**: count of sat / unsat / unknown / timeout / bug verdicts
-- **Total time used**: sum of all times for each solver
-- **Average time per benchmark**: total_time / total_files
-- **Soundness disagreements**: files where any two solvers that both returned a definitive answer disagree
-- **Bugs / crashes**: files with error/crash verdicts
-
-Format the report as a GitHub Discussion post (GitHub-flavored Markdown):
-
-```markdown
-### Ostrich Benchmark Report — Z3 c3 branch
-
-**Date**:
-**Branch**: c3
-**Benchmark set**: Ostrich (all files from tests/ostrich.zip)
-**Timeout**: 5 seconds per benchmark (`-T:5` for Z3; `-t:5000` for ZIPT; `--tlimit-per=5000` for cvc5; `-timeout=5` for Ostrich2)
-
----
-
-### Summary
-
-| Metric | seq solver | nseq solver | ZIPT solver | cvc5 solver | Ostrich2 solver |
-|--------|-----------|-------------|-------------|-------------|-----------------|
-| sat | X | X | X | X | X |
-| unsat | X | X | X | X | X |
-| unknown | X | X | X | X | X |
-| timeout | X | X | X | X | X |
-| bug/crash | X | X | X | X | X |
-| **Total time (s)** | X.XXX | X.XXX | X.XXX | X.XXX | X.XXX |
-| **Avg time/benchmark (s)** | X.XXX | X.XXX | X.XXX | X.XXX | X.XXX |
-
-**Soundness disagreements** (any two solvers return conflicting sat/unsat): N
-
----
-
-### Per-File Results
-
-
-Click to expand full per-file table
-
-| # | File | seq verdict | seq time (s) | nseq verdict | nseq time (s) | ZIPT verdict | ZIPT time (s) | cvc5 verdict | cvc5 time (s) | Ostrich2 verdict | Ostrich2 time (s) | Notes |
-|---|------|-------------|-------------|--------------|--------------|--------------|--------------|--------------|---------------|------------------|-------------------|-------|
-| 1 | benchmark_0001.smt2 | sat | 0.123 | sat | 0.456 | sat | 0.789 | sat | 0.111 | sat | 0.222 | |
-| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
-
-
-
----
-
-### Notable Issues
-
-#### Soundness Disagreements (Critical)
-
-
-#### Crashes / Bugs
-
-
-#### Slow Benchmarks (> 4s)
-
-
----
-
-*Generated automatically by the Ostrich Benchmark workflow on the c3 branch.*
-```
-
-## Phase 5: Post to GitHub Discussion
-
-Post the Markdown report as a new GitHub Discussion using the `create-discussion` safe output.
-
-- **Category**: "Agentic Workflows"
-- **Title**: `[Ostrich Benchmark] Z3 c3 branch — `
-- Close older discussions with the same title prefix to avoid clutter.
-
-## Guidelines
-
-- **Always build from c3 branch**: The workspace is already checked out on c3; don't change branches.
-- **Synchronous builds only**: Never run `ninja` (or any other build command) in the background using `&`. Running the build concurrently with LLM inference causes the agent process to be killed by the OOM killer (exit 137) because C++ compilation and the LLM together exceed available RAM. Always wait for each build command to finish before proceeding.
-- **Release build**: The build uses `CMAKE_BUILD_TYPE=Release` for lower memory footprint and faster compilation on the GitHub Actions runner. The benchmark only needs verdict and timing output; no `-tr:` trace flags are used.
-- **Run all benchmarks**: Unlike the QF_S workflow, run every file in the archive — do not randomly sample.
-- **5-second timeout**: Pass `-T:5` to Z3 (both seq and nseq), `-t:5000` to ZIPT, `--tlimit-per=5000` to cvc5, and `-timeout=5` to Ostrich2. Use `timeout 7` as the outer OS-level guard to allow solvers to exit cleanly before being killed.
-- **Be precise with timing**: Use millisecond-precision timestamps and report times in seconds with 3 decimal places.
-- **Distinguish timeout from unknown**: A timeout is different from `(unknown)` returned by a solver within its time budget.
-- **ZIPT output format**: ZIPT prints the input filename on the first line, then `SAT`, `UNSAT`, or `UNKNOWN` on subsequent lines. Parse accordingly.
-- **cvc5 and Ostrich2 availability**: If cvc5 or Ostrich2 build/setup fails, keep benchmarking with available solvers and emit `n/a` verdict/time for unavailable ones.
-- **Report soundness bugs prominently**: If any benchmark shows a conflict between any two solvers that both returned a definitive sat/unsat answer, highlight it as a critical finding and name which pair disagrees.
-- **Handle build failures gracefully**: If Z3 fails to build, report the error and create a brief discussion noting the build failure. If any external solver (ZIPT/cvc5/Ostrich2) fails to build, continue with available solver columns and note `n/a` for unavailable solvers.
-- **Large report**: Always put the per-file table in a `` collapsible section since there may be many files.
-- **Progress logging**: Print a line per file as you run it (e.g., `[N] [filename] seq=...`) so the workflow log shows progress even for large benchmark sets.
-
-## Safe Output Guarantee
-
-You **MUST** call either `create_discussion` or `noop` before the workflow ends, regardless of what happened during execution:
-
-- **Build succeeded, benchmarks ran**: Call `create_discussion` with the full report.
-- **Build succeeded, benchmarks partially ran**: Call `create_discussion` with whatever results were collected and a note about what could not be completed.
-- **Z3 build failed**: Call `noop` with a brief message describing the build error.
-- **No benchmarks could be run**: Call `noop` with a summary of what failed and why.
-
-Failing to produce any safe output triggers an automatic workflow-failure issue that clutters the repository.
diff --git a/.github/workflows/specbot-crash-analyzer.lock.yml b/.github/workflows/specbot-crash-analyzer.lock.yml
deleted file mode 100644
index 6fe01e5d23..0000000000
--- a/.github/workflows/specbot-crash-analyzer.lock.yml
+++ /dev/null
@@ -1,1715 +0,0 @@
-# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"75b7aac4b5b7f7d73ab2cbf90b693f26cd644b09210f428a02c15512e1661729","body_hash":"7030f1fac5beec9af23f992361435bd8fc32966ed8d1711e73e230a8f71aaf39","compiler_version":"v0.83.4","strict":true,"agent_id":"copilot","engine_versions":{"copilot":"1.0.75"}}
-# gh-aw-manifest: {"version":1,"secrets":["COPILOT_GITHUB_TOKEN","GH_AW_GITHUB_MCP_SERVER_TOKEN","GH_AW_GITHUB_TOKEN","GITHUB_TOKEN"],"actions":[{"repo":"actions/cache/restore","sha":"55cc8345863c7cc4c66a329aec7e433d2d1c52a9","version":"v6.1.0"},{"repo":"actions/cache/save","sha":"55cc8345863c7cc4c66a329aec7e433d2d1c52a9","version":"v6.1.0"},{"repo":"actions/checkout","sha":"3d3c42e5aac5ba805825da76410c181273ba90b1","version":"v7.0.1"},{"repo":"actions/checkout","sha":"de0fac2e4500dabe0009e67214ff5f5447ce83dd","version":"v6.0.2"},{"repo":"actions/download-artifact","sha":"3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c","version":"v8.0.1"},{"repo":"actions/github-script","sha":"3a2844b7e9c422d3c10d287c895573f7108da1b3","version":"v9.0.0"},{"repo":"actions/setup-node","sha":"820762786026740c76f36085b0efc47a31fe5020","version":"v7.0.0"},{"repo":"actions/upload-artifact","sha":"043fb46d1a93c77aae656e7c1c64a875d1fc6a0a","version":"v7.0.1"},{"repo":"github/gh-aw-actions/setup","sha":"v0.83.4","version":"v0.83.4"}],"containers":[{"image":"ghcr.io/github/gh-aw-firewall/agent:0.27.42","digest":"sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b","pinned_image":"ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b"},{"image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42","digest":"sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607","pinned_image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607"},{"image":"ghcr.io/github/gh-aw-firewall/squid:0.27.42","digest":"sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0","pinned_image":"ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0"},{"image":"ghcr.io/github/gh-aw-mcpg:v0.4.6","digest":"sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c","pinned_image":"ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c"},{"image":"ghcr.io/github/gh-aw-node","digest":"sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748","pinned_image":"ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748"},{"image":"ghcr.io/github/github-mcp-server:v1.7.0","digest":"sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308","pinned_image":"ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308"}]}
-# This file was automatically generated by gh-aw (v0.83.4). DO NOT EDIT. To debug this workflow, load the skill at https://github.com/github/gh-aw/blob/main/debug.md
-#
-# ___ _ _
-# / _ \ | | (_)
-# | |_| | __ _ ___ _ __ | |_ _ ___
-# | _ |/ _` |/ _ \ '_ \| __| |/ __|
-# | | | | (_| | __/ | | | |_| | (__
-# \_| |_/\__, |\___|_| |_|\__|_|\___|
-# __/ |
-# _ _ |___/
-# | | | | / _| |
-# | | | | ___ _ __ _ __| |_| | _____ ____
-# | |/\| |/ _ \ '__| |/ /| _| |/ _ \ \ /\ / / ___|
-# \ /\ / (_) | | | | ( | | | | (_) \ V V /\__ \
-# \/ \/ \___/|_| |_|\_\|_| |_|\___/ \_/\_/ |___/
-#
-#
-# To update this file, edit the corresponding .md file and run:
-# gh aw compile
-# Not all edits will cause changes to this file.
-#
-# For more information: https://github.github.com/gh-aw/introduction/overview/
-#
-# Build Z3 in debug mode from the c3 branch, compile and run the specbot tests, identify root causes for any crashes, and post findings as a GitHub Discussion.
-#
-# Secrets used:
-# - COPILOT_GITHUB_TOKEN
-# - GH_AW_GITHUB_MCP_SERVER_TOKEN
-# - GH_AW_GITHUB_TOKEN
-# - GITHUB_TOKEN
-#
-# Custom actions used:
-# - actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-# - actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-# - actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-# - actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-# - actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-# - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
-# - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 (source v9)
-# - actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
-# - actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-# - github/gh-aw-actions/setup@v0.83.4
-#
-# Container images used:
-# - ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b
-# - ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607
-# - ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0
-# - ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c
-# - ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748
-# - ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308
-
-name: "Specbot Crash Analyzer"
-on:
- workflow_dispatch:
- inputs:
- aw_context:
- default: ""
- description: "Agent caller context (used internally by Agentic Workflows)."
- required: false
- type: string
-
-permissions: {}
-
-concurrency:
- group: "gh-aw-${{ github.workflow }}"
-
-run-name: "Specbot Crash Analyzer"
-
-jobs:
- activation:
- runs-on: ubuntu-slim
- permissions:
- actions: read
- contents: read
- env:
- GH_AW_MAX_DAILY_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_DAILY_AI_CREDITS || '5000' }}
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- comment_id: ""
- comment_repo: ""
- daily_ai_credits_exceeded: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_exceeded == 'true' }}
- daily_ai_credits_threshold: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_threshold || '' }}
- daily_ai_credits_total_effective_tokens: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_total_effective_tokens || '' }}
- engine_id: ${{ steps.generate_aw_info.outputs.engine_id }}
- lockdown_check_failed: ${{ steps.generate_aw_info.outputs.lockdown_check_failed == 'true' }}
- model: ${{ steps.generate_aw_info.outputs.model }}
- oauth_token_check_failed: ${{ steps.check-oauth-tokens.outputs.oauth_token_check_failed == 'true' }}
- setup-parent-span-id: ${{ steps.setup.outputs.parent-span-id || steps.setup.outputs.span-id }}
- setup-span-id: ${{ steps.setup.outputs.span-id }}
- setup-trace-id: ${{ steps.setup.outputs.trace-id }}
- stale_lock_file_failed: ${{ steps.check-lock-file.outputs.stale_lock_file_failed == 'true' }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- safe-output-artifact-client: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/specbot-crash-analyzer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Generate agentic run info
- id: generate_aw_info
- env:
- GH_AW_INFO_ENGINE_ID: "copilot"
- GH_AW_INFO_ENGINE_NAME: "GitHub Copilot CLI"
- GH_AW_INFO_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AGENT_VERSION: "1.0.75"
- GH_AW_INFO_CLI_VERSION: "v0.83.4"
- GH_AW_INFO_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_INFO_EXPERIMENTAL: "false"
- GH_AW_INFO_SUPPORTS_TOOLS_ALLOWLIST: "true"
- GH_AW_INFO_STAGED: "false"
- GH_AW_INFO_ALLOWED_DOMAINS: '["defaults"]'
- GH_AW_INFO_FIREWALL_ENABLED: "true"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_AWMG_VERSION: ""
- GH_AW_INFO_FIREWALL_TYPE: "squid"
- GH_AW_COMPILED_STRICT: "true"
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/generate_aw_info.cjs');
- await main(core, context);
- - name: Restore daily AIC usage cache
- id: restore-daily-aic-cache
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- continue-on-error: true
- uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-specbotcrashanalyzer-${{ github.run_id }}
- restore-keys: agentic-workflow-usage-specbotcrashanalyzer-
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Restore daily AIC usage cache (artifact fallback)
- id: restore-daily-aic-cache-fallback
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_RESTORE_DAILY_AIC_CACHE_HIT: ${{ steps.restore-daily-aic-cache.outputs.cache-hit }}
- GH_AW_RESTORE_DAILY_AIC_CACHE_MATCHED_KEY: ${{ steps.restore-daily-aic-cache.outputs.cache-matched-key }}
- with:
- github-token: ${{ secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/restore_aic_usage_cache_fallback.cjs');
- await main();
- - name: Check daily workflow token guardrail
- id: daily-effective-workflow-guardrail
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_WORKFLOW_ID: "specbot-crash-analyzer"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_WORKFLOW_DISPATCH_AW_CONTEXT: ${{ github.event.inputs.aw_context || '' }}
- GH_AW_HAS_SLASH_COMMAND: "false"
- GH_AW_HAS_LABEL_COMMAND: "false"
- GH_AW_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- GH_AW_MAX_DAILY_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_DAILY_AI_CREDITS || '5000' }}
- with:
- github-token: ${{ secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_daily_aic_workflow_guardrail.cjs');
- await main();
- - name: Check for OAuth tokens
- id: check-oauth-tokens
- run: bash "${RUNNER_TEMP}/gh-aw/actions/check_oauth_tokens.sh"
- env:
- COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }}
- - name: Checkout .github and .agents folders
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- with:
- persist-credentials: false
- sparse-checkout: |
- .github
- .agents
- .antigravity
- .claude
- .codex
- .gemini
- .opencode
- .pi
- sparse-checkout-cone-mode: true
- fetch-depth: 1
- - name: Save agent config folders for base branch restoration
- env:
- GH_AW_AGENT_FOLDERS: ".agents .antigravity .claude .codex .gemini .github .opencode .pi"
- GH_AW_AGENT_FILES: "AGENTS.md ANTIGRAVITY.md CLAUDE.md GEMINI.md PI.md opencode.jsonc"
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/save_base_github_folders.sh"
- - name: Check workflow lock file
- id: check-lock-file
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_WORKFLOW_FILE: "specbot-crash-analyzer.lock.yml"
- GH_AW_CONTEXT_WORKFLOW_REF: "${{ github.workflow_ref }}"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_workflow_timestamp_api.cjs');
- await main();
- - name: Check compile-agentic version
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_COMPILED_VERSION: "v0.83.4"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_version_updates.cjs');
- await main();
- - name: Log runtime features
- if: ${{ contains(toJSON(vars), '"GH_AW_RUNTIME_FEATURES":') }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/log_runtime_features_summary.sh"
- - name: Create prompt with built-in context
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_SAFE_OUTPUTS: ${{ runner.temp }}/gh-aw/safeoutputs/outputs.jsonl
- GH_AW_EXPR_1A3A194A: ${{ github.event.discussion.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'discussion' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_463A214A: ${{ github.event.pull_request.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'pull_request' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_802A9F6A: ${{ github.event.issue.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'issue' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_FF1D34CE: ${{ github.event.comment.id || fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').comment_id }}
- GH_AW_GITHUB_ACTOR: ${{ github.actor }}
- GH_AW_GITHUB_REPOSITORY: ${{ github.repository }}
- GH_AW_GITHUB_RUN_ID: ${{ github.run_id }}
- GH_AW_GITHUB_WORKFLOW: ${{ github.workflow }}
- GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
- # poutine:ignore untrusted_checkout_exec
- run: |
- bash "${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh"
- {
- cat << 'GH_AW_PROMPT_a2b6b8b2fc7de20f_EOF'
-
- GH_AW_PROMPT_a2b6b8b2fc7de20f_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/cache_memory_prompt.md"
- cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md"
- cat << 'GH_AW_PROMPT_a2b6b8b2fc7de20f_EOF'
-
- Tools: create_discussion, missing_tool, missing_data, noop
-
- GH_AW_PROMPT_a2b6b8b2fc7de20f_EOF
- cat "${RUNNER_TEMP}/gh-aw/prompts/mcp_cli_tools_prompt.md"
- cat << 'GH_AW_PROMPT_a2b6b8b2fc7de20f_EOF'
-
- The following GitHub context information is available for this workflow:
- {{#if github.actor}}
- - **actor**: __GH_AW_GITHUB_ACTOR__
- {{/if}}
- {{#if github.repository}}
- - **repository**: __GH_AW_GITHUB_REPOSITORY__
- {{/if}}
- {{#if github.workspace}}
- - **workspace**: __GH_AW_GITHUB_WORKSPACE__
- {{/if}}
- {{#if github.event.issue.number || (github.aw.context.item_type == 'issue' && github.aw.context.item_number)}}
- - **issue-number**: #__GH_AW_EXPR_802A9F6A__
- {{/if}}
- {{#if github.event.discussion.number || (github.aw.context.item_type == 'discussion' && github.aw.context.item_number)}}
- - **discussion-number**: #__GH_AW_EXPR_1A3A194A__
- {{/if}}
- {{#if github.event.pull_request.number || (github.aw.context.item_type == 'pull_request' && github.aw.context.item_number)}}
- - **pull-request-number**: #__GH_AW_EXPR_463A214A__
- {{/if}}
- {{#if github.event.comment.id || github.aw.context.comment_id}}
- - **comment-id**: __GH_AW_EXPR_FF1D34CE__
- {{/if}}
- {{#if github.run_id}}
- - **workflow-run-id**: __GH_AW_GITHUB_RUN_ID__
- {{/if}}
-
-
- GH_AW_PROMPT_a2b6b8b2fc7de20f_EOF
- cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md"
- cat << 'GH_AW_PROMPT_a2b6b8b2fc7de20f_EOF'
-
- {{#runtime-import .github/workflows/specbot-crash-analyzer.md}}
- GH_AW_PROMPT_a2b6b8b2fc7de20f_EOF
- } > "$GH_AW_PROMPT"
- - name: Interpolate variables and render templates
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_ENGINE_ID: "copilot"
- GH_AW_GITHUB_REPOSITORY: ${{ github.repository }}
- GH_AW_GITHUB_RUN_ID: ${{ github.run_id }}
- GH_AW_GITHUB_WORKFLOW: ${{ github.workflow }}
- GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/interpolate_prompt.cjs');
- await main();
- - name: Substitute placeholders
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_ALLOWED_EXTENSIONS: ''
- GH_AW_CACHE_DESCRIPTION: ''
- GH_AW_CACHE_DIR: '/tmp/gh-aw/cache-memory/'
- GH_AW_EXPR_1A3A194A: ${{ github.event.discussion.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'discussion' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_463A214A: ${{ github.event.pull_request.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'pull_request' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_802A9F6A: ${{ github.event.issue.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'issue' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_FF1D34CE: ${{ github.event.comment.id || fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').comment_id }}
- GH_AW_GITHUB_ACTOR: ${{ github.actor }}
- GH_AW_GITHUB_REPOSITORY: ${{ github.repository }}
- GH_AW_GITHUB_RUN_ID: ${{ github.run_id }}
- GH_AW_GITHUB_WORKFLOW: ${{ github.workflow }}
- GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
- GH_AW_MCP_CLI_SERVERS_LIST: "- `github` — run `github --help` to see available tools\n- `safeoutputs` — run `safeoutputs --help` to see available tools"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
-
- const substitutePlaceholders = require('${{ runner.temp }}/gh-aw/actions/substitute_placeholders.cjs');
-
- // Call the substitution function
- return await substitutePlaceholders({
- file: process.env.GH_AW_PROMPT,
- substitutions: {
- GH_AW_ALLOWED_EXTENSIONS: process.env.GH_AW_ALLOWED_EXTENSIONS,
- GH_AW_CACHE_DESCRIPTION: process.env.GH_AW_CACHE_DESCRIPTION,
- GH_AW_CACHE_DIR: process.env.GH_AW_CACHE_DIR,
- GH_AW_EXPR_1A3A194A: process.env.GH_AW_EXPR_1A3A194A,
- GH_AW_EXPR_463A214A: process.env.GH_AW_EXPR_463A214A,
- GH_AW_EXPR_802A9F6A: process.env.GH_AW_EXPR_802A9F6A,
- GH_AW_EXPR_FF1D34CE: process.env.GH_AW_EXPR_FF1D34CE,
- GH_AW_GITHUB_ACTOR: process.env.GH_AW_GITHUB_ACTOR,
- GH_AW_GITHUB_REPOSITORY: process.env.GH_AW_GITHUB_REPOSITORY,
- GH_AW_GITHUB_RUN_ID: process.env.GH_AW_GITHUB_RUN_ID,
- GH_AW_GITHUB_WORKFLOW: process.env.GH_AW_GITHUB_WORKFLOW,
- GH_AW_GITHUB_WORKSPACE: process.env.GH_AW_GITHUB_WORKSPACE,
- GH_AW_MCP_CLI_SERVERS_LIST: process.env.GH_AW_MCP_CLI_SERVERS_LIST
- }
- });
- - name: Validate prompt placeholders
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/validate_prompt_placeholders.sh"
- - name: Print prompt
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/print_prompt_summary.sh"
- - name: Upload activation artifact
- if: success()
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: activation
- include-hidden-files: true
- path: |
- /tmp/gh-aw/aw_info.json
- /tmp/gh-aw/models.json
- /tmp/gh-aw/aw-prompts/prompt.txt
- /tmp/gh-aw/aw-prompts/prompt-template.txt
- /tmp/gh-aw/aw-prompts/prompt-import-tree.json
- /tmp/gh-aw/github_rate_limits.jsonl
- /tmp/gh-aw/base
- /tmp/gh-aw/.github/agents
- /tmp/gh-aw/.github/skills
- if-no-files-found: ignore
- retention-days: 1
-
- agent:
- needs: activation
- if: needs.activation.outputs.daily_ai_credits_exceeded != 'true'
- runs-on: ubuntu-latest
- permissions:
- contents: read
- copilot-requests: write
- discussions: read
- issues: read
- pull-requests: read
- env:
- DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
- GH_AW_ASSETS_ALLOWED_EXTS: ""
- GH_AW_ASSETS_BRANCH: ""
- GH_AW_ASSETS_MAX_SIZE_KB: 0
- GH_AW_MCP_LOG_DIR: /tmp/gh-aw/mcp-logs/safeoutputs
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- GH_AW_WORKFLOW_ID_SANITIZED: specbotcrashanalyzer
- outputs:
- agentic_engine_timeout: ${{ steps.detect-agent-errors.outputs.agentic_engine_timeout || 'false' }}
- ai_credits_rate_limit_error: ${{ steps.parse-mcp-gateway.outputs.ai_credits_rate_limit_error || 'false' }}
- aic: ${{ steps.parse-mcp-gateway.outputs.aic }}
- ambient_context: ${{ steps.parse-mcp-gateway.outputs.ambient_context }}
- cache_memory_restore_0_cache_hit: ${{ steps.restore_cache_memory_0.outputs.cache-hit || 'false' }}
- cache_memory_restore_0_matched_key: ${{ steps.restore_cache_memory_0.outputs.cache-matched-key || '' }}
- checkout_pr_success: ${{ steps.checkout-pr.outputs.checkout_pr_success || 'true' }}
- effective_tokens: ${{ steps.parse-mcp-gateway.outputs.effective_tokens }}
- has_patch: ${{ steps.collect_output.outputs.has_patch }}
- http_400_response_error: ${{ steps.detect-agent-errors.outputs.http_400_response_error || 'false' }}
- inference_access_error: ${{ steps.detect-agent-errors.outputs.inference_access_error || 'false' }}
- invocation_cap_exceeded: ${{ steps.detect-agent-errors.outputs.invocation_cap_exceeded || 'false' }}
- mcp_policy_error: ${{ steps.detect-agent-errors.outputs.mcp_policy_error || 'false' }}
- model: ${{ needs.activation.outputs.model }}
- model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }}
- output: ${{ steps.collect_output.outputs.output }}
- output_types: ${{ steps.collect_output.outputs.output_types }}
- setup-parent-span-id: ${{ steps.setup.outputs.parent-span-id || steps.setup.outputs.span-id }}
- setup-span-id: ${{ steps.setup.outputs.span-id }}
- setup-trace-id: ${{ steps.setup.outputs.trace-id }}
- unknown_model_ai_credits: ${{ steps.parse-mcp-gateway.outputs.unknown_model_ai_credits || 'false' }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/specbot-crash-analyzer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Set runtime paths
- id: set-runtime-paths
- run: |
- {
- echo "GH_AW_SAFE_OUTPUTS=${RUNNER_TEMP}/gh-aw/safeoutputs/outputs.jsonl"
- echo "GH_AW_SAFE_OUTPUTS_CONFIG_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/config.json"
- echo "GH_AW_SAFE_OUTPUTS_TOOLS_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/tools.json"
- } >> "$GITHUB_OUTPUT"
- - 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: ${{ github.token }}
- - name: Download activation artifact
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: activation
- path: /tmp/gh-aw
- # Cache memory file share configuration from frontmatter processed below
- - name: Create cache-memory directory
- run: bash "${RUNNER_TEMP}/gh-aw/actions/create_cache_memory_dir.sh"
- - name: Restore cache-memory file share data
- id: restore_cache_memory_0
- uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}-${{ github.run_id }}
- path: /tmp/gh-aw/cache-memory
- restore-keys: |
- memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}-
- - name: Setup cache-memory git repository
- env:
- GH_AW_CACHE_DIR: /tmp/gh-aw/cache-memory
- GH_AW_MIN_INTEGRITY: none
- run: bash "${RUNNER_TEMP}/gh-aw/actions/setup_cache_memory_git.sh"
- - name: Checkout c3 branch
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- with:
- persist-credentials: false
- ref: c3
- - name: Install build dependencies
- run: |
- sudo apt-get update -y
- sudo apt-get install -y cmake ninja-build python3 gcc g++ 2>&1 | tail -5
- - continue-on-error: true
- id: build-z3
- name: Build Z3 in debug mode
- run: |
- mkdir -p build/debug specbot-results
- cd build/debug
- cmake -G Ninja -DCMAKE_BUILD_TYPE=Debug ../.. 2>&1 | tee ../../specbot-results/cmake.log
- ninja 2>&1 | tee ../../specbot-results/build.log
- BUILD_EXIT=$?
- cd ../..
- echo "build_exit=${BUILD_EXIT}" >> specbot-results/build-status.txt
- ls -la build/debug/libz3* build/debug/*.so* 2>/dev/null >> specbot-results/build-status.txt || echo "Library not found" >> specbot-results/build-status.txt
- exit $BUILD_EXIT
- - continue-on-error: true
- name: Compile specbot tests
- run: "mkdir -p specbot-results\ngcc -g -O0 \\\n -I src/api \\\n specbot/test_specbot_seq.c \\\n -L build/debug \\\n -lz3 \\\n -Wl,-rpath,\"${GITHUB_WORKSPACE}/build/debug\" \\\n -o specbot-results/test_specbot_seq \\\n 2>&1 | tee specbot-results/compile_specbot_seq.log\necho \"compile_specbot_seq_exit=$?\" >> specbot-results/compile-status.txt\n\ngcc -g -O0 \\\n -I src/api \\\n specbot/test_deeptest_seq.c \\\n -L build/debug \\\n -lz3 \\\n -Wl,-rpath,\"${GITHUB_WORKSPACE}/build/debug\" \\\n -o specbot-results/test_deeptest_seq \\\n 2>&1 | tee specbot-results/compile_deeptest_seq.log\necho \"compile_deeptest_seq_exit=$?\" >> specbot-results/compile-status.txt\n"
- - continue-on-error: true
- name: Run specbot tests
- run: |-
- mkdir -p specbot-results
- if [ -f specbot-results/test_specbot_seq ]; then
- LD_LIBRARY_PATH="${GITHUB_WORKSPACE}/build/debug" timeout 120 specbot-results/test_specbot_seq > specbot-results/test_specbot_seq.log 2>&1
- SPECBOT_EXIT=$?
- echo "specbot_seq_exit=${SPECBOT_EXIT}" >> specbot-results/test-status.txt
- else
- echo "Binary not compiled" > specbot-results/test_specbot_seq.log
- echo "specbot_seq_exit=127" >> specbot-results/test-status.txt
- fi
-
- if [ -f specbot-results/test_deeptest_seq ]; then
- LD_LIBRARY_PATH="${GITHUB_WORKSPACE}/build/debug" timeout 120 specbot-results/test_deeptest_seq > specbot-results/test_deeptest_seq.log 2>&1
- DEEPTEST_EXIT=$?
- echo "deeptest_seq_exit=${DEEPTEST_EXIT}" >> specbot-results/test-status.txt
- else
- echo "Binary not compiled" > specbot-results/test_deeptest_seq.log
- echo "deeptest_seq_exit=127" >> specbot-results/test-status.txt
- fi
-
- - name: Configure Git credentials
- env:
- GITHUB_REPOSITORY: ${{ github.repository }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_TOKEN: ${{ github.token }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/configure_git_credentials.sh"
- - name: Checkout PR branch
- id: checkout-pr
- if: |
- github.event.pull_request || github.event.issue.pull_request || github.event_name == 'workflow_dispatch' && fromJSON(github.event.inputs.aw_context || '{}').item_type == 'pull_request'
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- 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');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/checkout_pr_branch.cjs');
- await main();
- - name: Install GitHub Copilot CLI
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh" 1.0.75
- env:
- GH_HOST: github.com
- - name: Install AWF binary
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.27.42 --rootless
- - name: Determine automatic lockdown mode for GitHub MCP Server
- id: determine-automatic-lockdown
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 (source v9)
- env:
- GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- 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');
- await determineAutomaticLockdown(github, context, core);
- - name: Restore agent config folders from base branch
- if: steps.checkout-pr.outcome == 'success'
- env:
- GH_AW_AGENT_FOLDERS: ".agents .antigravity .claude .codex .gemini .github .opencode .pi"
- GH_AW_AGENT_FILES: "AGENTS.md ANTIGRAVITY.md CLAUDE.md GEMINI.md PI.md opencode.jsonc"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_base_github_folders.sh"
- - name: Restore inline sub-agents from activation artifact
- env:
- GH_AW_SUB_AGENT_DIR: ".github/agents"
- GH_AW_SUB_AGENT_EXT: ".agent.md"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_inline_sub_agents.sh"
- - name: Restore inline skills from activation artifact
- env:
- GH_AW_SKILL_DIR: ".github/skills"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_inline_skills.sh"
- - name: Download container images
- run: bash "${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh" ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607 ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0 ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748 ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308
- - name: Generate Safe Outputs Config
- run: |
- mkdir -p "${RUNNER_TEMP}/gh-aw/safeoutputs"
- mkdir -p /tmp/gh-aw/safeoutputs
- mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs
- cat > "${RUNNER_TEMP}/gh-aw/safeoutputs/config.json" << 'GH_AW_SAFE_OUTPUTS_CONFIG_415cb03cfffd6980_EOF'
- {"create_discussion":{"category":"agentic workflows","close_older_discussions":true,"expires":168,"fallback_to_issue":true,"max":1,"title_prefix":"[Specbot] "},"create_report_incomplete_issue":{},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"false"},"report_incomplete":{}}
- GH_AW_SAFE_OUTPUTS_CONFIG_415cb03cfffd6980_EOF
- - name: Generate Safe Outputs Tools
- env:
- GH_AW_TOOLS_META_JSON: |
- {
- "description_suffixes": {
- "create_discussion": " CONSTRAINTS: Maximum 1 discussion(s) can be created. Title will be prefixed with \"[Specbot] \". Discussions will be created in category \"agentic workflows\"."
- },
- "repo_params": {},
- "dynamic_tools": []
- }
- GH_AW_VALIDATION_JSON: |
- {
- "create_discussion": {
- "defaultMax": 1,
- "fields": {
- "body": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 65000,
- "minLength": 64
- },
- "category": {
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- },
- "repo": {
- "type": "string",
- "maxLength": 256
- },
- "title": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- }
- }
- },
- "missing_data": {
- "defaultMax": 20,
- "fields": {
- "alternatives": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "context": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "data_type": {
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- },
- "reason": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- }
- }
- },
- "missing_tool": {
- "defaultMax": 20,
- "fields": {
- "alternatives": {
- "type": "string",
- "sanitize": true,
- "maxLength": 512
- },
- "reason": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "tool": {
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- }
- }
- },
- "noop": {
- "defaultMax": 1,
- "fields": {
- "message": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 65000
- }
- }
- },
- "report_incomplete": {
- "defaultMax": 5,
- "fields": {
- "details": {
- "type": "string",
- "sanitize": true,
- "maxLength": 65000
- },
- "reason": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 1024
- }
- }
- }
- }
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/generate_safe_outputs_tools.cjs');
- await main();
- - name: Start MCP Gateway
- id: start-mcp-gateway
- env:
- GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST: ${{ vars.GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST || 'true' }}
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- GH_AW_SAFE_OUTPUTS_CONFIG_PATH: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS_CONFIG_PATH }}
- GH_AW_SAFE_OUTPUTS_TOOLS_PATH: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS_TOOLS_PATH }}
- GITHUB_MCP_GUARD_MIN_INTEGRITY: ${{ steps.determine-automatic-lockdown.outputs.min_integrity }}
- GITHUB_MCP_GUARD_REPOS: ${{ steps.determine-automatic-lockdown.outputs.repos }}
- GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- run: |
- set -eo pipefail
- mkdir -p "${RUNNER_TEMP}/gh-aw/mcp-config"
-
- # Export gateway environment variables for MCP config and gateway script
- export MCP_GATEWAY_PORT="8080"
- export MCP_GATEWAY_DOMAIN="awmg-mcpg"
- export MCP_GATEWAY_HOST_DOMAIN="localhost"
- MCP_GATEWAY_API_KEY=$(openssl rand -base64 45 | tr -d '/+=')
- echo "::add-mask::${MCP_GATEWAY_API_KEY}"
- export MCP_GATEWAY_API_KEY
- export MCP_GATEWAY_PAYLOAD_DIR="/tmp/gh-aw/mcp-payloads"
- mkdir -p "${MCP_GATEWAY_PAYLOAD_DIR}"
- export MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD="524288"
- export DEBUG="*"
-
- export GH_AW_ENGINE="copilot"
- MCP_GATEWAY_UID=$(id -u 2>/dev/null || echo '0')
- MCP_GATEWAY_GID=$(id -g 2>/dev/null || echo '0')
- source "${RUNNER_TEMP}/gh-aw/actions/resolve_docker_socket_gid.sh"
- export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network bridge -p 127.0.0.1:'"${MCP_GATEWAY_PORT}"':'"${MCP_GATEWAY_PORT}"' --name awmg-mcpg --add-host host.docker.internal:host-gateway --user '"${MCP_GATEWAY_UID}"':'"${MCP_GATEWAY_GID}"' --group-add '"${DOCKER_SOCK_GID}"' -v '"${DOCKER_SOCK_PATH}"':/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 DOCKER_HOST=unix:///var/run/docker.sock -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_POLICY_ALLOW_CREATE_PULL_REQUEST -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 RUNNER_TEMP -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 -v '"${RUNNER_TEMP}"'/gh-aw/safeoutputs:'"${RUNNER_TEMP}"'/gh-aw/safeoutputs:rw ghcr.io/github/gh-aw-mcpg:v0.4.6'
-
- mkdir -p "$HOME/.copilot"
- GH_AW_NODE=$(which node 2>/dev/null || command -v node 2>/dev/null || echo node)
- cat << GH_AW_MCP_CONFIG_e78cb78a8c3ab64c_EOF | "$GH_AW_NODE" "${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.cjs"
- {
- "mcpServers": {
- "github": {
- "type": "stdio",
- "container": "ghcr.io/github/github-mcp-server:v1.7.0",
- "env": {
- "GITHUB_FEATURES": "fields_param",
- "GITHUB_HOST": "${GITHUB_SERVER_URL}",
- "GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_MCP_SERVER_TOKEN}",
- "GITHUB_READ_ONLY": "1",
- "GITHUB_TOOLSETS": "context,repos,issues,pull_requests,discussions"
- },
- "guard-policies": {
- "allow-only": {
- "min-integrity": "$GITHUB_MCP_GUARD_MIN_INTEGRITY",
- "repos": "$GITHUB_MCP_GUARD_REPOS"
- }
- }
- },
- "safeoutputs": {
- "type": "stdio",
- "container": "ghcr.io/github/gh-aw-node",
- "mounts": ["\${GITHUB_WORKSPACE}:\${GITHUB_WORKSPACE}:rw", "${RUNNER_TEMP}/gh-aw/safeoutputs:${RUNNER_TEMP}/gh-aw/safeoutputs:rw", "/tmp/gh-aw:/tmp/gh-aw:rw"],
- "args": ["-w", "\${GITHUB_WORKSPACE}"],
- "entrypoint": "sh",
- "entrypointArgs": ["-c", "sh ${RUNNER_TEMP}/gh-aw/safeoutputs/start_safe_outputs_mcp.sh"],
- "env": {
- "DEBUG": "*",
- "DEFAULT_BRANCH": "\${DEFAULT_BRANCH}",
- "GH_AW_ASSETS_ALLOWED_EXTS": "\${GH_AW_ASSETS_ALLOWED_EXTS}",
- "GH_AW_ASSETS_BRANCH": "\${GH_AW_ASSETS_BRANCH}",
- "GH_AW_ASSETS_MAX_SIZE_KB": "\${GH_AW_ASSETS_MAX_SIZE_KB}",
- "GH_AW_MCP_LOG_DIR": "\${GH_AW_MCP_LOG_DIR}",
- "GH_AW_SAFE_OUTPUTS": "\${GH_AW_SAFE_OUTPUTS}",
- "GH_AW_SAFE_OUTPUTS_CONFIG_PATH": "\${GH_AW_SAFE_OUTPUTS_CONFIG_PATH}",
- "GH_AW_SAFE_OUTPUTS_TOOLS_PATH": "\${GH_AW_SAFE_OUTPUTS_TOOLS_PATH}",
- "GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST": "\${GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST}",
- "GITHUB_REPOSITORY": "\${GITHUB_REPOSITORY}",
- "GITHUB_SHA": "\${GITHUB_SHA}",
- "GITHUB_TOKEN": "\${GITHUB_TOKEN}",
- "GITHUB_WORKSPACE": "\${GITHUB_WORKSPACE}",
- "RUNNER_TEMP": "\${RUNNER_TEMP}"
- },
- "guard-policies": {
- "write-sink": {
- "accept": [
- "*"
- ],
- "sink-visibility": ${{ toJSON(steps.determine-automatic-lockdown.outputs.visibility) }}
- }
- }
- }
- },
- "gateway": {
- "port": $MCP_GATEWAY_PORT,
- "domain": "${MCP_GATEWAY_DOMAIN}",
- "apiKey": "${MCP_GATEWAY_API_KEY}",
- "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}",
- "startupTimeout": 120
- }
- }
- GH_AW_MCP_CONFIG_e78cb78a8c3ab64c_EOF
- - name: Mount MCP servers as CLIs
- id: mount-mcp-clis
- continue-on-error: true
- env:
- MCP_GATEWAY_API_KEY: ${{ steps.start-mcp-gateway.outputs.gateway-api-key }}
- MCP_GATEWAY_DOMAIN: ${{ steps.start-mcp-gateway.outputs.gateway-domain }}
- MCP_GATEWAY_PORT: ${{ steps.start-mcp-gateway.outputs.gateway-port }}
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/mount_mcp_as_cli.cjs');
- await main();
- - name: Clean credentials
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/clean_git_credentials.sh"
- - name: Audit pre-agent workspace
- id: pre_agent_audit
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/audit_pre_agent_workspace.sh"
- - name: Execute GitHub Copilot CLI
- id: agentic_execution
- # Copilot CLI tool arguments (sorted):
- timeout-minutes: 120
- run: |
- set -o pipefail
- printf '%s' "$(date +%s%3N)" > /tmp/gh-aw/agent_cli_start_ms.txt
- trap 'gh_aw_exit_code=$?; mkdir -p /tmp/gh-aw >/dev/null 2>&1 || true; printf "%s" "$gh_aw_exit_code" > /tmp/gh-aw/agent_execution_exit_code.txt || true; rm -f "$HOME/.copilot/settings.json"' EXIT
- mkdir -p "$HOME/.copilot"
- printf '%s' '{"builtInAgents":{"rubberDuck":false}}' > "$HOME/.copilot/settings.json"
- export XDG_CONFIG_HOME="$HOME"
- export GH_AW_MCP_CONFIG="$HOME/.copilot/mcp-config.json"
- touch /tmp/gh-aw/agent-step-summary.md
- GH_AW_NODE_BIN=$(command -v node 2>/dev/null || true)
- export GH_AW_NODE_BIN
- export COPILOT_API_KEY="$COPILOT_DUMMY_BYOK"
- (umask 177 && touch /tmp/gh-aw/agent-stdio.log)
- GH_AW_MAX_AI_CREDITS="${GH_AW_MAX_AI_CREDITS:-1000}"
- printf '%s\n' "{\"\$schema\":\"https://github.com/github/gh-aw-firewall/releases/download/v0.27.42/awf-config.schema.json\",\"network\":{\"allowDomains\":[\"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\"],\"isolation\":true,\"topologyAttach\":[\"awmg-mcpg\"]},\"apiProxy\":{\"enabled\":true,\"enableTokenSteering\":true,\"maxRuns\":500,\"maxAiCredits\":${GH_AW_MAX_AI_CREDITS},\"maxCacheMisses\":5,\"models\":{\"agent\":[\"sonnet-6x\",\"gpt-5.4\",\"gpt-5.5\",\"gpt-5.6\",\"gpt-5.3\",\"gemini-pro\",\"any\"],\"antigravity\":[\"copilot/antigravity*\",\"google/antigravity*\",\"gemini/antigravity*\"],\"any\":[\"copilot/*\",\"anthropic/*\",\"openai/*\",\"google/*\",\"gemini/*\"],\"claude\":[\"agent\"],\"codex\":[\"agent\"],\"coding\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\",\"gpt-5-codex\",\"kimi\"],\"computer-use\":[\"copilot/*computer-use*\",\"google/*computer-use*\",\"gemini/*computer-use*\",\"openai/*computer-use*\"],\"copilot\":[\"agent\"],\"deep-research\":[\"copilot/deep-research*\",\"copilot/o3-deep-research*\",\"copilot/o4-mini-deep-research*\",\"google/deep-research*\",\"gemini/deep-research*\",\"openai/o3-deep-research*\",\"openai/o4-mini-deep-research*\"],\"fable\":[\"copilot/*fable*\",\"anthropic/*fable*\"],\"gemini\":[\"agent\"],\"gemini-3-flash\":[\"copilot/gemini-3*flash*\",\"google/gemini-3*flash*\",\"gemini/gemini-3*flash*\"],\"gemini-3-pro\":[\"copilot/gemini-3*pro*\",\"google/gemini-3*pro*\",\"google/nano-banana*\",\"gemini/gemini-3*pro*\"],\"gemini-3.1-flash\":[\"copilot/gemini-3.1*flash*\",\"google/gemini-3.1*flash*\",\"gemini/gemini-3.1*flash*\"],\"gemini-3.1-pro\":[\"copilot/gemini-3.1*pro*\",\"google/gemini-3.1*pro*\",\"gemini/gemini-3.1*pro*\"],\"gemini-3.5-flash\":[\"copilot/gemini-3.5*flash*\",\"google/gemini-3.5*flash*\",\"gemini/gemini-3.5*flash*\"],\"gemini-3.6-flash\":[\"copilot/gemini-3.6*flash*\",\"google/gemini-3.6*flash*\",\"gemini/gemini-3.6*flash*\"],\"gemini-flash\":[\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"],\"gemini-flash-lite\":[\"copilot/gemini-*flash*lite*\",\"google/gemini-*flash*lite*\",\"gemini/gemini-*flash*lite*\"],\"gemini-omni\":[\"copilot/gemini-omni*\",\"google/gemini-omni*\",\"gemini/gemini-omni*\"],\"gemini-pro\":[\"copilot/gemini-*pro*\",\"google/gemini-*pro*\",\"gemini/gemini-*pro*\"],\"gemma\":[\"copilot/gemma*\",\"google/gemma*\",\"gemini/gemma*\"],\"gpt-5\":[\"copilot/gpt-5*\",\"openai/gpt-5*\"],\"gpt-5-codex\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\"],\"gpt-5-mini\":[\"copilot/gpt-5*mini*\",\"openai/gpt-5*mini*\"],\"gpt-5-nano\":[\"copilot/gpt-5*nano*\",\"openai/gpt-5*nano*\"],\"gpt-5-pro\":[\"copilot/gpt-5*pro*\",\"openai/gpt-5*pro*\"],\"gpt-5.1\":[\"copilot/gpt-5.1*\",\"openai/gpt-5.1*\"],\"gpt-5.2\":[\"copilot/gpt-5.2*\",\"openai/gpt-5.2*\"],\"gpt-5.3\":[\"copilot/gpt-5.3*\",\"openai/gpt-5.3*\"],\"gpt-5.4\":[\"copilot/gpt-5.4*\",\"openai/gpt-5.4*\"],\"gpt-5.5\":[\"copilot/gpt-5.5*\",\"openai/gpt-5.5*\"],\"gpt-5.6\":[\"copilot/gpt-5.6*\",\"openai/gpt-5.6*\"],\"haiku\":[\"copilot/*haiku*\",\"anthropic/*haiku*\"],\"image-generation\":[\"copilot/gpt-image*\",\"openai/gpt-image*\",\"openai/chatgpt-image*\",\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"google/imagen*\"],\"kimi\":[\"copilot/kimi*\",\"openai/kimi*\"],\"kiwi\":[\"copilot/kiwi*\",\"openai/kiwi*\"],\"large\":[\"fable\",\"sonnet\",\"gpt-5-pro\",\"gpt-5\",\"gemini-pro\"],\"lyria\":[\"google/lyria*\",\"gemini/lyria*\",\"copilot/lyria*\"],\"mai-code\":[\"copilot/MAI-Code*\",\"copilot/mai-code*\",\"openai/MAI-Code*\"],\"mai-code-1-flash-picker\":[\"copilot/MAI-Code-1-Flash-picker*\",\"copilot/mai-code-1-flash-picker*\",\"openai/MAI-Code-1-Flash-picker*\"],\"mini\":[\"haiku\",\"gpt-5-mini\",\"gpt-5-nano\",\"gemini-flash-lite\"],\"nano-banana\":[\"copilot/nano-banana*\",\"google/nano-banana*\",\"gemini/nano-banana*\"],\"opus\":[\"copilot/*opus*\",\"anthropic/*opus*\"],\"opusplan\":[\"opus?effort=high\"],\"raptor-mini\":[\"copilot/raptor*\",\"openai/raptor*\"],\"reasoning\":[\"copilot/o1*\",\"copilot/o3*\",\"copilot/o4*\",\"openai/o1*\",\"openai/o3*\",\"openai/o4*\"],\"robotics\":[\"copilot/*robotics*\",\"google/*robotics*\",\"gemini/*robotics*\"],\"small\":[\"mini\"],\"small-agent\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash\"],\"sonnet\":[\"copilot/*sonnet*\",\"anthropic/*sonnet*\"],\"sonnet-6x\":[\"copilot/*sonnet-4.5*\",\"copilot/*sonnet-4.6*\",\"copilot/*sonnet-5*\",\"copilot/*sonnet-4-5-*\",\"anthropic/*sonnet-4-5-*\",\"copilot/*sonnet-4-6*\",\"anthropic/*sonnet-4-6*\",\"anthropic/*sonnet-5*\"],\"summarization\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash-lite\",\"mini\"],\"veo\":[\"google/veo*\",\"gemini/veo*\"],\"vision\":[\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"]}},\"container\":{\"imageTag\":\"0.27.42,squid=sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0,agent=sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b,agent-act=sha256:a14ad974484aa518aab83d40f3f141175dfd171d3745e01c092375b970f73a20,api-proxy=sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607,cli-proxy=sha256:da006bf96d2d246dd269d57b233c1798d2ad63d6cd64ca02f7bf71045028781f\"},\"logging\":{\"proxyLogsDir\":\"/tmp/gh-aw/sandbox/firewall/logs\",\"auditDir\":\"/tmp/gh-aw/sandbox/firewall/audit\"}}" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- cp "${RUNNER_TEMP}/gh-aw/awf-config.json" /tmp/gh-aw/awf-config.json
- export GH_AW_MODELS_JSON_PATH="/tmp/gh-aw/models.json"
- GH_AW_DOCKER_HOST=""
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_DOCKER_HOST="${DOCKER_HOST}"
- fi
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_CHROOT_BINARIES_SOURCE_PATH="${RUNNER_TEMP}/gh-aw" GH_AW_CHROOT_IDENTITY_HOME="${RUNNER_TEMP}/gh-aw/home" node "${RUNNER_TEMP}/gh-aw/actions/patch_awf_chroot_config.cjs"
- fi
- GH_AW_TOOL_CACHE_MOUNT=""
- GH_AW_TOOL_CACHE="${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"
- if [ -d "$GH_AW_TOOL_CACHE" ]; then
- if [[ "$GH_AW_TOOL_CACHE" != /opt/* ]]; then
- GH_AW_TOOL_CACHE_MOUNT="$GH_AW_TOOL_CACHE:$GH_AW_TOOL_CACHE:ro"
- fi
- fi
- # shellcheck disable=SC1003,SC2016,SC2086
- awf --config "${RUNNER_TEMP}/gh-aw/awf-config.json" --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" ${GH_AW_TOOL_CACHE_MOUNT:+--mount "$GH_AW_TOOL_CACHE_MOUNT"} ${GH_AW_DOCKER_HOST:+--docker-host "$GH_AW_DOCKER_HOST"} --env-all --exclude-env COPILOT_GITHUB_TOKEN --exclude-env GITHUB_MCP_SERVER_TOKEN --exclude-env MCP_GATEWAY_API_KEY --log-level info --skip-pull \
- -- /bin/bash -c 'set +o histexpand; export PATH="${RUNNER_TEMP}/gh-aw/mcp-cli/bin:$PATH" && : "${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"; GH_AW_TOOL_CACHE="$RUNNER_TOOL_CACHE"; export PATH="$(find "$GH_AW_TOOL_CACHE" -maxdepth 5 -type d -name bin 2>/dev/null | tr '\''\n'\'' '\'':'\'')$PATH"; [ -n "$GOROOT" ] && export PATH="$GOROOT/bin:$PATH" || true; [ -n "$ERLANG_HOME" ] && export PATH="$ERLANG_HOME/bin:$PATH" || true && GH_AW_NODE_EXEC="${GH_AW_NODE_BIN:-}"; if [ -z "$GH_AW_NODE_EXEC" ] || [ ! -x "$GH_AW_NODE_EXEC" ]; then GH_AW_NODE_EXEC="$(command -v node 2>/dev/null || true)"; fi; if [ -z "$GH_AW_NODE_EXEC" ]; then echo "node runtime missing on this runner — check runtimes.node in workflow YAML" >&2; exit 127; fi; GH_AW_NPM_GLOBAL_ROOT="$(npm root -g 2>/dev/null || true)"; if [ -n "$GH_AW_NPM_GLOBAL_ROOT" ]; then export NODE_PATH="${GH_AW_NPM_GLOBAL_ROOT}${NODE_PATH:+:${NODE_PATH}}"; fi; "$GH_AW_NODE_EXEC" ${RUNNER_TEMP}/gh-aw/actions/copilot_harness.cjs /usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --no-ask-user --allow-all-tools --add-dir /tmp/gh-aw/cache-memory/ --allow-all-paths --add-dir "${GITHUB_WORKSPACE}" --prompt-file /tmp/gh-aw/aw-prompts/prompt.txt' 2>&1 | tee -a /tmp/gh-aw/agent-stdio.log
- env:
- AWF_REFLECT_ENABLED: 1
- COPILOT_AGENT_RUNNER_TYPE: STANDALONE
- COPILOT_DUMMY_BYOK: dummy-byok-key-for-offline-mode
- COPILOT_GITHUB_TOKEN: ${{ github.token }}
- COPILOT_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_LLM_PROVIDER: github
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }}
- GH_AW_MAX_TURNS: ${{ vars.GH_AW_DEFAULT_MAX_TURNS || '' }}
- GH_AW_PHASE: agent
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- GH_AW_TIMEOUT_MINUTES: 120
- GH_AW_VERSION: v0.83.4
- GITHUB_API_URL: ${{ github.api_url }}
- GITHUB_AW: true
- GITHUB_COPILOT_INTEGRATION_ID: agentic-workflows
- GITHUB_HEAD_REF: ${{ github.head_ref }}
- GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- GITHUB_REF_NAME: ${{ github.ref_name }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_STEP_SUMMARY: /tmp/gh-aw/agent-step-summary.md
- GITHUB_WORKSPACE: ${{ github.workspace }}
- GIT_AUTHOR_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_AUTHOR_NAME: github-actions[bot]
- GIT_COMMITTER_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_COMMITTER_NAME: github-actions[bot]
- RUNNER_TEMP: ${{ runner.temp }}
- S2STOKENS: true
- TRACEPARENT: ${{ env.GITHUB_AW_OTEL_TRACE_ID != '' && env.GITHUB_AW_OTEL_PARENT_SPAN_ID != '' && format('00-{0}-{1}-01', env.GITHUB_AW_OTEL_TRACE_ID, env.GITHUB_AW_OTEL_PARENT_SPAN_ID) || '' }}
- - name: Detect agent errors
- if: always()
- id: detect-agent-errors
- continue-on-error: true
- run: node "${RUNNER_TEMP}/gh-aw/actions/detect_agent_errors.cjs"
- - name: Configure Git credentials
- env:
- GITHUB_REPOSITORY: ${{ github.repository }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_TOKEN: ${{ github.token }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/configure_git_credentials.sh"
- - name: Copy Copilot session state files to logs
- if: always()
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/copy_copilot_session_state.sh"
- - name: Stop MCP Gateway
- if: always()
- continue-on-error: true
- env:
- MCP_GATEWAY_PORT: ${{ steps.start-mcp-gateway.outputs.gateway-port }}
- 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" "$GATEWAY_PID"
- - name: Redact secrets in logs
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/redact_secrets.cjs');
- await main();
- env:
- GH_AW_SECRET_NAMES: 'GH_AW_GITHUB_MCP_SERVER_TOKEN,GH_AW_GITHUB_TOKEN,GITHUB_TOKEN'
- SECRET_GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }}
- SECRET_GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- 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
- if: always()
- env:
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- run: |
- mkdir -p /tmp/gh-aw
- cp "$GH_AW_SAFE_OUTPUTS" /tmp/gh-aw/safeoutputs.jsonl 2>/dev/null || true
- - name: Ingest agent output
- id: collect_output
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.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"
- 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');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/collect_ndjson_output.cjs');
- await main();
- - name: Parse agent logs for step summary
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: /tmp/gh-aw/sandbox/agent/logs/
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_copilot_log.cjs');
- await main();
- - name: Parse MCP Gateway logs for step summary
- if: always()
- id: parse-mcp-gateway
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_mcp_gateway_log.cjs');
- await main();
- - name: Print firewall logs
- if: always()
- continue-on-error: true
- env:
- AWF_LOGS_DIR: /tmp/gh-aw/sandbox/firewall/logs
- run: bash "${RUNNER_TEMP}/gh-aw/actions/print_firewall_logs.sh" --rootless
- - name: Parse token usage for step summary
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_token_usage.cjs');
- await main();
- - name: Print AWF reflect summary
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/awf_reflect_summary.cjs');
- await main();
- - name: Write agent output placeholder if missing
- if: always()
- run: |
- if [ ! -f /tmp/gh-aw/agent_output.json ]; then
- echo '{"items":[]}' > /tmp/gh-aw/agent_output.json
- fi
- - name: Commit cache-memory changes
- if: always()
- env:
- GH_AW_CACHE_DIR: /tmp/gh-aw/cache-memory
- run: bash "${RUNNER_TEMP}/gh-aw/actions/commit_cache_memory_git.sh"
- - name: Check cache-memory git integrity
- if: always()
- continue-on-error: true
- env:
- GH_AW_CACHE_DIR: /tmp/gh-aw/cache-memory
- run: bash "${RUNNER_TEMP}/gh-aw/actions/check_cache_memory_git_integrity.sh"
- - name: Upload cache-memory data as artifact
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- if: always()
- with:
- name: cache-memory
- include-hidden-files: true
- path: /tmp/gh-aw/cache-memory
- - name: Upload agent artifacts
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: agent
- 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/agent_usage.json
- /tmp/gh-aw/agent-stdio.log
- /tmp/gh-aw/pre-agent-audit.txt
- /tmp/gh-aw/agent/
- /tmp/gh-aw/github_rate_limits.jsonl
- /tmp/gh-aw/safeoutputs.jsonl
- /tmp/gh-aw/agent_output.json
- /tmp/gh-aw/aw-*.patch
- /tmp/gh-aw/aw-*.bundle
- /tmp/gh-aw/awf-config.json
- /tmp/gh-aw/sandbox/firewall/logs/
- /tmp/gh-aw/sandbox/firewall/audit/
- /tmp/gh-aw/sandbox/firewall/awf-reflect.json
- if-no-files-found: ignore
-
- conclusion:
- needs:
- - activation
- - agent
- - detection
- - safe_outputs
- - update_cache_memory
- if: >
- always() && (needs.agent.result != 'skipped' || needs.activation.outputs.lockdown_check_failed == 'true' ||
- needs.activation.outputs.oauth_token_check_failed == 'true' || needs.activation.outputs.stale_lock_file_failed == 'true' ||
- needs.activation.outputs.daily_ai_credits_exceeded == 'true')
- runs-on: ubuntu-slim
- permissions:
- contents: read
- discussions: write
- issues: write
- concurrency:
- group: "gh-aw-conclusion-specbot-crash-analyzer"
- cancel-in-progress: false
- queue: max
- env:
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- incomplete_count: ${{ steps.report_incomplete.outputs.incomplete_count }}
- noop_message: ${{ steps.noop.outputs.noop_message }}
- tools_reported: ${{ steps.missing_tool.outputs.tools_reported }}
- total_count: ${{ steps.missing_tool.outputs.total_count }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/specbot-crash-analyzer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Download safe outputs items manifest
- id: download-safe-outputs-manifest
- if: always()
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: safe-outputs-items
- path: /tmp/gh-aw/
- - name: Collect usage artifact files
- if: always()
- continue-on-error: true
- run: |
- mkdir -p /tmp/gh-aw/usage/agent /tmp/gh-aw/usage/detection
- echo "Usage artifact source file status:"
- for file in /tmp/gh-aw/aw_info.json /tmp/gh-aw/aw-info.jsonl /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/detection_usage.jsonl /tmp/gh-aw/evals/evals.jsonl /tmp/gh-aw/github_rate_limits.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl; do
- [ -f "$file" ] && echo "FOUND: $file" || echo "MISSING: $file"
- done
- [ -f /tmp/gh-aw/aw_info.json ] && cp /tmp/gh-aw/aw_info.json /tmp/gh-aw/usage/aw_info.json || true
- [ -f /tmp/gh-aw/aw-info.jsonl ] && cp /tmp/gh-aw/aw-info.jsonl /tmp/gh-aw/usage/aw-info.jsonl || true
- [ -f /tmp/gh-aw/agent_usage.json ] && cp /tmp/gh-aw/agent_usage.json /tmp/gh-aw/usage/agent_usage.json || true
- [ -f /tmp/gh-aw/agent_usage.jsonl ] && cp /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/usage/agent_usage.jsonl || true
- [ -f /tmp/gh-aw/detection_usage.jsonl ] && cp /tmp/gh-aw/detection_usage.jsonl /tmp/gh-aw/usage/detection_usage.jsonl || true
- [ -f /tmp/gh-aw/evals/evals.jsonl ] && cp /tmp/gh-aw/evals/evals.jsonl /tmp/gh-aw/usage/evals.jsonl || true
- [ -f /tmp/gh-aw/github_rate_limits.jsonl ] && cp /tmp/gh-aw/github_rate_limits.jsonl /tmp/gh-aw/usage/github_rate_limits.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -f /tmp/gh-aw/usage/agent/token_usage.jsonl ] || : > /tmp/gh-aw/usage/agent/token_usage.jsonl
- [ -f /tmp/gh-aw/usage/detection/token_usage.jsonl ] || : > /tmp/gh-aw/usage/detection/token_usage.jsonl
- mkdir -p /tmp/gh-aw/usage/activity
- node "${RUNNER_TEMP}/gh-aw/actions/generate_usage_activity_summary.cjs"
- find /tmp/gh-aw/usage -type f -print | sort
- - name: Upload usage artifact
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: usage
- path: |
- /tmp/gh-aw/usage/aw_info.json
- /tmp/gh-aw/usage/aw-info.jsonl
- /tmp/gh-aw/usage/agent_usage.json
- /tmp/gh-aw/usage/agent_usage.jsonl
- /tmp/gh-aw/usage/detection_usage.jsonl
- /tmp/gh-aw/usage/evals.jsonl
- /tmp/gh-aw/usage/github_rate_limits.jsonl
- /tmp/gh-aw/usage/agent/token_usage.jsonl
- /tmp/gh-aw/usage/detection/token_usage.jsonl
- /tmp/gh-aw/usage/activity/summary.json
- if-no-files-found: ignore
- - name: Restore daily AIC usage cache
- id: restore-daily-aic-cache-conclusion
- if: always()
- continue-on-error: true
- uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-specbotcrashanalyzer-${{ github.run_id }}
- restore-keys: agentic-workflow-usage-specbotcrashanalyzer-
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Write daily AIC usage cache entry
- id: write-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- github-token: ${{ github.token }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/write_daily_aic_usage_cache.cjs');
- await main();
- - name: Save daily AIC usage cache
- id: save-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-specbotcrashanalyzer-${{ github.run_id }}
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Upload daily AIC usage cache artifact
- id: upload-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: aic-usage-cache
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- if-no-files-found: ignore
- retention-days: 7
- - name: Process no-op messages
- id: noop
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_NOOP_MAX: "1"
- GH_AW_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/specbot-crash-analyzer.md"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_AGENT_CONCLUSION: ${{ needs.agent.result }}
- GH_AW_NOOP_REPORT_AS_ISSUE: "false"
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_AMBIENT_CONTEXT: ${{ needs.agent.outputs.ambient_context }}
- GH_AW_WORKFLOW_ID: "specbot-crash-analyzer"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_noop_message.cjs');
- await main();
- - name: Log detection run
- id: detection_runs
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/specbot-crash-analyzer.md"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_DETECTION_CONCLUSION: ${{ needs.detection.outputs.detection_conclusion }}
- GH_AW_DETECTION_REASON: ${{ needs.detection.outputs.detection_reason }}
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_detection_runs.cjs');
- await main();
- - name: Record missing tool
- id: missing_tool
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_MISSING_TOOL_CREATE_ISSUE: "true"
- GH_AW_MISSING_TOOL_TITLE_PREFIX: "[missing tool]"
- GH_AW_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/specbot-crash-analyzer.md"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/missing_tool.cjs');
- await main();
- - name: Record incomplete
- id: report_incomplete
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_REPORT_INCOMPLETE_CREATE_ISSUE: "true"
- GH_AW_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/specbot-crash-analyzer.md"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/report_incomplete_handler.cjs');
- await main();
- - name: Handle agent failure
- id: handle_agent_failure
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/specbot-crash-analyzer.md"
- 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: "specbot-crash-analyzer"
- GH_AW_ACTION_FAILURE_ISSUE_EXPIRES_HOURS: "168"
- GH_AW_ENGINE_ID: "copilot"
- GH_AW_CHECKOUT_PR_SUCCESS: ${{ needs.agent.outputs.checkout_pr_success }}
- GH_AW_EFFECTIVE_TOKENS: ${{ needs.agent.outputs.effective_tokens || '' }}
- GH_AW_AI_CREDITS_RATE_LIMIT_ERROR: ${{ needs.agent.outputs.ai_credits_rate_limit_error || 'false' }}
- GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }}
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }}
- GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }}
- GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }}
- GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }}
- GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }}
- GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }}
- GH_AW_ENGINE_API_HOSTS: "api.enterprise.githubcopilot.com,api.githubcopilot.com,api.business.githubcopilot.com,api.individual.githubcopilot.com"
- 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_OAUTH_TOKEN_CHECK_FAILED: ${{ needs.activation.outputs.oauth_token_check_failed }}
- GH_AW_STALE_LOCK_FILE_FAILED: ${{ needs.activation.outputs.stale_lock_file_failed }}
- GH_AW_DAILY_AI_CREDITS_EXCEEDED: ${{ needs.activation.outputs.daily_ai_credits_exceeded }}
- GH_AW_DAILY_AI_CREDITS_TOTAL_EFFECTIVE_TOKENS: ${{ needs.activation.outputs.daily_ai_credits_total_effective_tokens }}
- GH_AW_DAILY_AI_CREDITS_THRESHOLD: ${{ needs.activation.outputs.daily_ai_credits_threshold }}
- GH_AW_GROUP_REPORTS: "false"
- GH_AW_FAILURE_REPORT_AS_ISSUE: "false"
- GH_AW_MISSING_TOOL_REPORT_AS_FAILURE: "true"
- GH_AW_MISSING_DATA_REPORT_AS_FAILURE: "true"
- GH_AW_TIMEOUT_MINUTES: "120"
- GH_AW_CACHE_MEMORY_ENABLED: "true"
- GH_AW_CACHE_MEMORY_RESTORE_0_MATCHED_KEY: ${{ needs.agent.outputs.cache_memory_restore_0_matched_key || '' }}
- GH_AW_CACHE_MEMORY_RESTORE_0_CACHE_HIT: ${{ needs.agent.outputs.cache_memory_restore_0_cache_hit || 'false' }}
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_agent_failure.cjs');
- await main();
-
- detection:
- needs:
- - activation
- - agent
- if: always() && needs.agent.result != 'skipped'
- runs-on: ubuntu-latest
- permissions:
- contents: read
- copilot-requests: write
- env:
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- aic: ${{ steps.parse_detection_token_usage.outputs.aic }}
- detection_conclusion: ${{ steps.detection_conclusion.outputs.conclusion }}
- detection_reason: ${{ steps.detection_conclusion.outputs.reason }}
- detection_success: ${{ steps.detection_conclusion.outputs.success }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/specbot-crash-analyzer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Checkout repository for patch context
- if: needs.agent.outputs.has_patch == 'true'
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- with:
- persist-credentials: false
- # --- Threat Detection ---
- - name: Clean stale firewall files from agent artifact
- run: |
- rm -rf /tmp/gh-aw/sandbox/firewall/logs
- rm -rf /tmp/gh-aw/sandbox/firewall/audit
- - name: Download container images
- run: bash "${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh" ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607 ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0
- - name: Check if detection needed
- id: detection_guard
- if: always()
- env:
- OUTPUT_TYPES: ${{ needs.agent.outputs.output_types }}
- HAS_PATCH: ${{ needs.agent.outputs.has_patch }}
- run: |
- if [[ -n "$OUTPUT_TYPES" || "$HAS_PATCH" == "true" ]]; then
- echo "run_detection=true" >> "$GITHUB_OUTPUT"
- echo "Detection will run: output_types=$OUTPUT_TYPES, has_patch=$HAS_PATCH"
- else
- echo "run_detection=false" >> "$GITHUB_OUTPUT"
- echo "Detection skipped: no agent outputs or patches to analyze"
- fi
- - name: Clear MCP Config for detection
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- rm -f "${RUNNER_TEMP}/gh-aw/mcp-config/mcp-servers.json"
- rm -f "$HOME/.copilot/mcp-config.json"
- rm -f "$GITHUB_WORKSPACE/.gemini/settings.json"
- - name: Prepare threat detection files
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- mkdir -p /tmp/gh-aw/threat-detection/aw-prompts
- rm -f /tmp/gh-aw/agent_usage.json
- cp /tmp/gh-aw/aw-prompts/prompt.txt /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt 2>/dev/null || true
- if [ ! -s /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt ]; then
- echo "::warning::ERR_VALIDATION: Missing or empty detection context prompt at /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt. Ensure the agent artifact includes /tmp/gh-aw/aw-prompts/prompt.txt. Detection will continue with fallback workflow context."
- fi
- cp /tmp/gh-aw/agent_output.json /tmp/gh-aw/threat-detection/agent_output.json 2>/dev/null || true
- for f in /tmp/gh-aw/aw-*.patch; do
- [ -f "$f" ] && cp "$f" /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- done
- for f in /tmp/gh-aw/aw-*.bundle; do
- [ -f "$f" ] && cp "$f" /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- done
- echo "Prepared threat detection files:"
- ls -la /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- - name: Setup threat detection
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- WORKFLOW_NAME: "Specbot Crash Analyzer"
- WORKFLOW_DESCRIPTION: "Build Z3 in debug mode from the c3 branch, compile and run the specbot tests, identify root causes for any crashes, and post findings as a GitHub Discussion."
- HAS_PATCH: ${{ needs.agent.outputs.has_patch }}
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/setup_threat_detection.cjs');
- await main();
- - name: Ensure threat-detection directory and log
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- mkdir -p /tmp/gh-aw/threat-detection
- touch /tmp/gh-aw/threat-detection/detection.log
- - name: Setup Node.js
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
- with:
- node-version: '24'
- package-manager-cache: false
- - name: Install GitHub Copilot CLI
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh" 1.0.75
- env:
- GH_HOST: github.com
- - name: Install AWF binary
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.27.42
- - name: Execute GitHub Copilot CLI
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- continue-on-error: true
- id: detection_agentic_execution
- # Copilot CLI tool arguments (sorted):
- timeout-minutes: 20
- run: |
- set -o pipefail
- printf '%s' "$(date +%s%3N)" > /tmp/gh-aw/agent_cli_start_ms.txt
- trap 'gh_aw_exit_code=$?; mkdir -p /tmp/gh-aw >/dev/null 2>&1 || true; printf "%s" "$gh_aw_exit_code" > /tmp/gh-aw/agent_execution_exit_code.txt || true; rm -f "$HOME/.copilot/settings.json"' EXIT
- mkdir -p "$HOME/.copilot"
- printf '%s' '{"builtInAgents":{"rubberDuck":false}}' > "$HOME/.copilot/settings.json"
- export XDG_CONFIG_HOME="$HOME"
- touch /tmp/gh-aw/agent-step-summary.md
- GH_AW_NODE_BIN=$(command -v node 2>/dev/null || true)
- export GH_AW_NODE_BIN
- export COPILOT_API_KEY="$COPILOT_DUMMY_BYOK"
- (umask 177 && touch /tmp/gh-aw/threat-detection/detection.log)
- GH_AW_MAX_AI_CREDITS="${GH_AW_MAX_AI_CREDITS:-400}"
- printf '%s\n' "{\"\$schema\":\"https://github.com/github/gh-aw-firewall/releases/download/v0.27.42/awf-config.schema.json\",\"network\":{\"allowDomains\":[\"api.business.githubcopilot.com\",\"api.enterprise.githubcopilot.com\",\"api.github.com\",\"api.githubcopilot.com\",\"api.individual.githubcopilot.com\",\"github.com\",\"host.docker.internal\",\"registry.npmjs.org\",\"telemetry.enterprise.githubcopilot.com\"]},\"apiProxy\":{\"enabled\":true,\"enableTokenSteering\":true,\"maxRuns\":500,\"maxAiCredits\":${GH_AW_MAX_AI_CREDITS},\"maxCacheMisses\":5,\"models\":{\"agent\":[\"sonnet-6x\",\"gpt-5.4\",\"gpt-5.5\",\"gpt-5.6\",\"gpt-5.3\",\"gemini-pro\",\"any\"],\"antigravity\":[\"copilot/antigravity*\",\"google/antigravity*\",\"gemini/antigravity*\"],\"any\":[\"copilot/*\",\"anthropic/*\",\"openai/*\",\"google/*\",\"gemini/*\"],\"claude\":[\"agent\"],\"codex\":[\"agent\"],\"coding\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\",\"gpt-5-codex\",\"kimi\"],\"computer-use\":[\"copilot/*computer-use*\",\"google/*computer-use*\",\"gemini/*computer-use*\",\"openai/*computer-use*\"],\"copilot\":[\"agent\"],\"deep-research\":[\"copilot/deep-research*\",\"copilot/o3-deep-research*\",\"copilot/o4-mini-deep-research*\",\"google/deep-research*\",\"gemini/deep-research*\",\"openai/o3-deep-research*\",\"openai/o4-mini-deep-research*\"],\"fable\":[\"copilot/*fable*\",\"anthropic/*fable*\"],\"gemini\":[\"agent\"],\"gemini-3-flash\":[\"copilot/gemini-3*flash*\",\"google/gemini-3*flash*\",\"gemini/gemini-3*flash*\"],\"gemini-3-pro\":[\"copilot/gemini-3*pro*\",\"google/gemini-3*pro*\",\"google/nano-banana*\",\"gemini/gemini-3*pro*\"],\"gemini-3.1-flash\":[\"copilot/gemini-3.1*flash*\",\"google/gemini-3.1*flash*\",\"gemini/gemini-3.1*flash*\"],\"gemini-3.1-pro\":[\"copilot/gemini-3.1*pro*\",\"google/gemini-3.1*pro*\",\"gemini/gemini-3.1*pro*\"],\"gemini-3.5-flash\":[\"copilot/gemini-3.5*flash*\",\"google/gemini-3.5*flash*\",\"gemini/gemini-3.5*flash*\"],\"gemini-3.6-flash\":[\"copilot/gemini-3.6*flash*\",\"google/gemini-3.6*flash*\",\"gemini/gemini-3.6*flash*\"],\"gemini-flash\":[\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"],\"gemini-flash-lite\":[\"copilot/gemini-*flash*lite*\",\"google/gemini-*flash*lite*\",\"gemini/gemini-*flash*lite*\"],\"gemini-omni\":[\"copilot/gemini-omni*\",\"google/gemini-omni*\",\"gemini/gemini-omni*\"],\"gemini-pro\":[\"copilot/gemini-*pro*\",\"google/gemini-*pro*\",\"gemini/gemini-*pro*\"],\"gemma\":[\"copilot/gemma*\",\"google/gemma*\",\"gemini/gemma*\"],\"gpt-5\":[\"copilot/gpt-5*\",\"openai/gpt-5*\"],\"gpt-5-codex\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\"],\"gpt-5-mini\":[\"copilot/gpt-5*mini*\",\"openai/gpt-5*mini*\"],\"gpt-5-nano\":[\"copilot/gpt-5*nano*\",\"openai/gpt-5*nano*\"],\"gpt-5-pro\":[\"copilot/gpt-5*pro*\",\"openai/gpt-5*pro*\"],\"gpt-5.1\":[\"copilot/gpt-5.1*\",\"openai/gpt-5.1*\"],\"gpt-5.2\":[\"copilot/gpt-5.2*\",\"openai/gpt-5.2*\"],\"gpt-5.3\":[\"copilot/gpt-5.3*\",\"openai/gpt-5.3*\"],\"gpt-5.4\":[\"copilot/gpt-5.4*\",\"openai/gpt-5.4*\"],\"gpt-5.5\":[\"copilot/gpt-5.5*\",\"openai/gpt-5.5*\"],\"gpt-5.6\":[\"copilot/gpt-5.6*\",\"openai/gpt-5.6*\"],\"haiku\":[\"copilot/*haiku*\",\"anthropic/*haiku*\"],\"image-generation\":[\"copilot/gpt-image*\",\"openai/gpt-image*\",\"openai/chatgpt-image*\",\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"google/imagen*\"],\"kimi\":[\"copilot/kimi*\",\"openai/kimi*\"],\"kiwi\":[\"copilot/kiwi*\",\"openai/kiwi*\"],\"large\":[\"fable\",\"sonnet\",\"gpt-5-pro\",\"gpt-5\",\"gemini-pro\"],\"lyria\":[\"google/lyria*\",\"gemini/lyria*\",\"copilot/lyria*\"],\"mai-code\":[\"copilot/MAI-Code*\",\"copilot/mai-code*\",\"openai/MAI-Code*\"],\"mai-code-1-flash-picker\":[\"copilot/MAI-Code-1-Flash-picker*\",\"copilot/mai-code-1-flash-picker*\",\"openai/MAI-Code-1-Flash-picker*\"],\"mini\":[\"haiku\",\"gpt-5-mini\",\"gpt-5-nano\",\"gemini-flash-lite\"],\"nano-banana\":[\"copilot/nano-banana*\",\"google/nano-banana*\",\"gemini/nano-banana*\"],\"opus\":[\"copilot/*opus*\",\"anthropic/*opus*\"],\"opusplan\":[\"opus?effort=high\"],\"raptor-mini\":[\"copilot/raptor*\",\"openai/raptor*\"],\"reasoning\":[\"copilot/o1*\",\"copilot/o3*\",\"copilot/o4*\",\"openai/o1*\",\"openai/o3*\",\"openai/o4*\"],\"robotics\":[\"copilot/*robotics*\",\"google/*robotics*\",\"gemini/*robotics*\"],\"small\":[\"mini\"],\"small-agent\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash\"],\"sonnet\":[\"copilot/*sonnet*\",\"anthropic/*sonnet*\"],\"sonnet-6x\":[\"copilot/*sonnet-4.5*\",\"copilot/*sonnet-4.6*\",\"copilot/*sonnet-5*\",\"copilot/*sonnet-4-5-*\",\"anthropic/*sonnet-4-5-*\",\"copilot/*sonnet-4-6*\",\"anthropic/*sonnet-4-6*\",\"anthropic/*sonnet-5*\"],\"summarization\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash-lite\",\"mini\"],\"veo\":[\"google/veo*\",\"gemini/veo*\"],\"vision\":[\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"]}},\"container\":{\"imageTag\":\"0.27.42,squid=sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0,agent=sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b,agent-act=sha256:a14ad974484aa518aab83d40f3f141175dfd171d3745e01c092375b970f73a20,api-proxy=sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607,cli-proxy=sha256:da006bf96d2d246dd269d57b233c1798d2ad63d6cd64ca02f7bf71045028781f\"},\"logging\":{\"proxyLogsDir\":\"/tmp/gh-aw/sandbox/firewall/logs\",\"auditDir\":\"/tmp/gh-aw/sandbox/firewall/audit\"}}" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- cp "${RUNNER_TEMP}/gh-aw/awf-config.json" /tmp/gh-aw/awf-config.json
- export GH_AW_MODELS_JSON_PATH="/tmp/gh-aw/models.json"
- GH_AW_DOCKER_HOST=""
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_DOCKER_HOST="${DOCKER_HOST}"
- fi
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- _GH_AW_CHROOT_JSON=$(jq -c --arg src "${RUNNER_TEMP}/gh-aw" --arg user "$(id -un)" --argjson uid "$(id -u)" --argjson gid "$(id -g)" --arg home "${RUNNER_TEMP}/gh-aw/home" '.chroot={"binariesSourcePath":$src,"identity":{"user":$user,"uid":$uid,"gid":$gid,"home":$home}}' "${RUNNER_TEMP}/gh-aw/awf-config.json") || { echo "chroot config patch failed" >&2; exit 1; }
- printf '%s\n' "$_GH_AW_CHROOT_JSON" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- printf '%s\n' "$_GH_AW_CHROOT_JSON" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- fi
- GH_AW_TOOL_CACHE_MOUNT=""
- GH_AW_TOOL_CACHE="${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"
- if [ -d "$GH_AW_TOOL_CACHE" ]; then
- if [[ "$GH_AW_TOOL_CACHE" != /opt/* ]]; then
- GH_AW_TOOL_CACHE_MOUNT="$GH_AW_TOOL_CACHE:$GH_AW_TOOL_CACHE:ro"
- fi
- fi
- # shellcheck disable=SC1003,SC2016,SC2086
- awf --config "${RUNNER_TEMP}/gh-aw/awf-config.json" --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" ${GH_AW_TOOL_CACHE_MOUNT:+--mount "$GH_AW_TOOL_CACHE_MOUNT"} ${GH_AW_DOCKER_HOST:+--docker-host "$GH_AW_DOCKER_HOST"} --env-all --exclude-env COPILOT_GITHUB_TOKEN --log-level info --skip-pull \
- -- /bin/bash -c 'set +o histexpand; : "${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"; GH_AW_TOOL_CACHE="$RUNNER_TOOL_CACHE"; export PATH="$(find "$GH_AW_TOOL_CACHE" -maxdepth 5 -type d -name bin 2>/dev/null | tr '\''\n'\'' '\'':'\'')$PATH"; [ -n "$GOROOT" ] && export PATH="$GOROOT/bin:$PATH" || true; [ -n "$ERLANG_HOME" ] && export PATH="$ERLANG_HOME/bin:$PATH" || true && GH_AW_NODE_EXEC="${GH_AW_NODE_BIN:-}"; if [ -z "$GH_AW_NODE_EXEC" ] || [ ! -x "$GH_AW_NODE_EXEC" ]; then GH_AW_NODE_EXEC="$(command -v node 2>/dev/null || true)"; fi; if [ -z "$GH_AW_NODE_EXEC" ]; then echo "node runtime missing on this runner — check runtimes.node in workflow YAML" >&2; exit 127; fi; GH_AW_NPM_GLOBAL_ROOT="$(npm root -g 2>/dev/null || true)"; if [ -n "$GH_AW_NPM_GLOBAL_ROOT" ]; then export NODE_PATH="${GH_AW_NPM_GLOBAL_ROOT}${NODE_PATH:+:${NODE_PATH}}"; fi; "$GH_AW_NODE_EXEC" ${RUNNER_TEMP}/gh-aw/actions/copilot_harness.cjs /usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --no-ask-user --allow-all-tools --add-dir "${GITHUB_WORKSPACE}" --prompt-file /tmp/gh-aw/aw-prompts/prompt.txt' 2>&1 | tee -a /tmp/gh-aw/threat-detection/detection.log
- env:
- AWF_REFLECT_ENABLED: 1
- COPILOT_AGENT_RUNNER_TYPE: STANDALONE
- COPILOT_DUMMY_BYOK: dummy-byok-key-for-offline-mode
- COPILOT_GITHUB_TOKEN: ${{ github.token }}
- COPILOT_MODEL: ${{ vars.GH_AW_MODEL_DETECTION_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_LLM_PROVIDER: github
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_DETECTION_MAX_AI_CREDITS || '400' }}
- GH_AW_MAX_TURNS: ${{ vars.GH_AW_DEFAULT_MAX_TURNS || '' }}
- GH_AW_PHASE: detection
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_TIMEOUT_MINUTES: 20
- GH_AW_VERSION: v0.83.4
- GITHUB_API_URL: ${{ github.api_url }}
- GITHUB_AW: true
- GITHUB_COPILOT_INTEGRATION_ID: agentic-workflows
- GITHUB_HEAD_REF: ${{ github.head_ref }}
- GITHUB_REF_NAME: ${{ github.ref_name }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_STEP_SUMMARY: /tmp/gh-aw/agent-step-summary.md
- GITHUB_WORKSPACE: ${{ github.workspace }}
- GIT_AUTHOR_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_AUTHOR_NAME: github-actions[bot]
- GIT_COMMITTER_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_COMMITTER_NAME: github-actions[bot]
- RUNNER_TEMP: ${{ runner.temp }}
- S2STOKENS: true
- TRACEPARENT: ${{ env.GITHUB_AW_OTEL_TRACE_ID != '' && env.GITHUB_AW_OTEL_PARENT_SPAN_ID != '' && format('00-{0}-{1}-01', env.GITHUB_AW_OTEL_TRACE_ID, env.GITHUB_AW_OTEL_PARENT_SPAN_ID) || '' }}
- - name: Parse threat detection token usage for step summary
- id: parse_detection_token_usage
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_TOKEN_USAGE_SUMMARY_TITLE: Threat Detection Token Usage
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_token_usage.cjs');
- await main();
- - name: Upload threat detection log
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: detection
- path: /tmp/gh-aw/threat-detection/detection.log
- if-no-files-found: ignore
- - name: Parse and conclude threat detection
- id: detection_conclusion
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- RUN_DETECTION: ${{ steps.detection_guard.outputs.run_detection }}
- DETECTION_AGENTIC_EXECUTION_OUTCOME: ${{ steps.detection_agentic_execution.outcome }}
- GH_AW_DETECTION_CONTINUE_ON_ERROR: "true"
- with:
- script: |
- try {
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_threat_detection_results.cjs');
- await main();
- } catch (loadErr) {
- const continueOnError = process.env.GH_AW_DETECTION_CONTINUE_ON_ERROR !== 'false';
- const detectionExecutionFailed = process.env.DETECTION_AGENTIC_EXECUTION_OUTCOME === 'failure';
- const msg = 'ERR_SYSTEM: \u274C Unexpected error loading threat detection module: ' + (loadErr && loadErr.message ? loadErr.message : String(loadErr));
- core.error(msg);
- core.setOutput('reason', 'parse_error');
- if (continueOnError && !detectionExecutionFailed) {
- core.warning('\u26A0\uFE0F ' + msg);
- core.setOutput('conclusion', 'warning');
- core.setOutput('success', 'false');
- } else {
- core.setOutput('conclusion', 'failure');
- core.setOutput('success', 'false');
- core.setFailed(msg);
- }
- }
-
- safe_outputs:
- needs:
- - activation
- - agent
- - detection
- if: (!cancelled()) && needs.agent.result != 'skipped' && needs.detection.result == 'success'
- runs-on: ubuntu-slim
- permissions:
- contents: read
- discussions: write
- issues: write
- timeout-minutes: 45
- env:
- GH_AW_AGENT_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_AMBIENT_CONTEXT: ${{ needs.agent.outputs.ambient_context }}
- GH_AW_CALLER_WORKFLOW_ID: "${{ github.repository }}/specbot-crash-analyzer"
- GH_AW_DETECTION_CONCLUSION: ${{ needs.detection.outputs.detection_conclusion }}
- GH_AW_DETECTION_REASON: ${{ needs.detection.outputs.detection_reason }}
- GH_AW_EFFECTIVE_TOKENS: ${{ needs.agent.outputs.effective_tokens }}
- GH_AW_ENGINE_ID: "copilot"
- GH_AW_ENGINE_MODEL: ${{ needs.agent.outputs.model }}
- GH_AW_ENGINE_VERSION: "1.0.75"
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_WORKFLOW_ID: "specbot-crash-analyzer"
- GH_AW_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/specbot-crash-analyzer.md"
- 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 }}
- create_discussion_error_count: ${{ steps.process_safe_outputs.outputs.create_discussion_error_count }}
- create_discussion_errors: ${{ steps.process_safe_outputs.outputs.create_discussion_errors }}
- process_safe_outputs_processed_count: ${{ steps.process_safe_outputs.outputs.processed_count }}
- process_safe_outputs_temporary_id_map: ${{ steps.process_safe_outputs.outputs.temporary_id_map }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/specbot-crash-analyzer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Configure GH_HOST for enterprise compatibility
- id: ghes-host-config
- shell: bash
- run: | # zizmor: ignore[github-env] - GITHUB_SERVER_URL is set by GitHub Actions, not user input.
- # Derive GH_HOST from GITHUB_SERVER_URL so the gh CLI targets the correct
- # GitHub instance (GHES/GHEC). On github.com this is a harmless no-op.
- GH_HOST="${GITHUB_SERVER_URL#https://}"
- GH_HOST="${GH_HOST#http://}"
- echo "GH_HOST=${GH_HOST}" >> "$GITHUB_ENV"
- - name: Process Safe Outputs
- id: process_safe_outputs
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_COMMENT_ID: ${{ needs.activation.outputs.comment_id }}
- 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"
- 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\":\"[Specbot] \"},\"create_report_incomplete_issue\":{},\"missing_data\":{},\"missing_tool\":{},\"noop\":{\"max\":1,\"report-as-issue\":\"false\"},\"report_incomplete\":{}}"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/process_safe_outputs.cjs');
- await main();
- - name: Upload Safe Outputs Items
- if: always()
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: safe-outputs-items
- path: |
- /tmp/gh-aw/safe-output-items.jsonl
- /tmp/gh-aw/temporary-id-map.json
- /tmp/gh-aw/process-safe-outputs.stdout.log
- /tmp/gh-aw/process-safe-outputs.stderr.log
- if-no-files-found: ignore
-
- update_cache_memory:
- needs:
- - activation
- - agent
- - detection
- if: always() && needs.detection.result == 'success' && needs.agent.result == 'success'
- runs-on: ubuntu-slim
- permissions:
- actions: write
- env:
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- GH_AW_WORKFLOW_ID_SANITIZED: specbotcrashanalyzer
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "Specbot Crash Analyzer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/specbot-crash-analyzer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download cache-memory artifact (default)
- id: download_cache_default
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- continue-on-error: true
- with:
- name: cache-memory
- path: /tmp/gh-aw/cache-memory
- - name: Check if cache-memory folder has content (default)
- id: check_cache_default
- shell: bash
- run: |
- if [ -d "/tmp/gh-aw/cache-memory" ] && [ "$(ls -A /tmp/gh-aw/cache-memory 2>/dev/null)" ]; then
- echo "has_content=true" >> "$GITHUB_OUTPUT"
- else
- echo "has_content=false" >> "$GITHUB_OUTPUT"
- fi
- - name: Save cache-memory to cache (default)
- if: steps.check_cache_default.outputs.has_content == 'true'
- uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}-${{ github.run_id }}
- path: /tmp/gh-aw/cache-memory
diff --git a/.github/workflows/specbot-crash-analyzer.md b/.github/workflows/specbot-crash-analyzer.md
deleted file mode 100644
index 5e63d31d5c..0000000000
--- a/.github/workflows/specbot-crash-analyzer.md
+++ /dev/null
@@ -1,253 +0,0 @@
----
-description: >
- Build Z3 in debug mode from the c3 branch, compile and run the specbot tests,
- identify root causes for any crashes, and post findings as a GitHub Discussion.
-
-on:
- workflow_dispatch:
-
-timeout-minutes: 120
-
-permissions:
- contents: read
- issues: read
- pull-requests: read
- discussions: read
- copilot-requests: write
-
-network: defaults
-
-tools:
- cache-memory: true
- github:
- toolsets: [default, discussions]
- bash: [":*"]
- edit: {}
-
-safe-outputs:
- report-failure-as-issue: false
- create-discussion:
- title-prefix: "[Specbot] "
- category: "Agentic Workflows"
- close-older-discussions: true
- missing-tool:
- create-issue: true
- noop:
- report-as-issue: false
-
-steps:
- - name: Checkout c3 branch
- uses: actions/checkout@v6.0.2
- with:
- ref: c3
- persist-credentials: false
-
- - name: Install build dependencies
- run: |
- sudo apt-get update -y
- sudo apt-get install -y cmake ninja-build python3 gcc g++ 2>&1 | tail -5
-
- - name: Build Z3 in debug mode
- id: build-z3
- continue-on-error: true
- run: |
- mkdir -p build/debug specbot-results
- cd build/debug
- cmake -G Ninja -DCMAKE_BUILD_TYPE=Debug ../.. 2>&1 | tee ../../specbot-results/cmake.log
- ninja 2>&1 | tee ../../specbot-results/build.log
- BUILD_EXIT=$?
- cd ../..
- echo "build_exit=${BUILD_EXIT}" >> specbot-results/build-status.txt
- ls -la build/debug/libz3* build/debug/*.so* 2>/dev/null >> specbot-results/build-status.txt || echo "Library not found" >> specbot-results/build-status.txt
- exit $BUILD_EXIT
-
- - name: Compile specbot tests
- continue-on-error: true
- run: |
- mkdir -p specbot-results
- gcc -g -O0 \
- -I src/api \
- specbot/test_specbot_seq.c \
- -L build/debug \
- -lz3 \
- -Wl,-rpath,"${GITHUB_WORKSPACE}/build/debug" \
- -o specbot-results/test_specbot_seq \
- 2>&1 | tee specbot-results/compile_specbot_seq.log
- echo "compile_specbot_seq_exit=$?" >> specbot-results/compile-status.txt
-
- gcc -g -O0 \
- -I src/api \
- specbot/test_deeptest_seq.c \
- -L build/debug \
- -lz3 \
- -Wl,-rpath,"${GITHUB_WORKSPACE}/build/debug" \
- -o specbot-results/test_deeptest_seq \
- 2>&1 | tee specbot-results/compile_deeptest_seq.log
- echo "compile_deeptest_seq_exit=$?" >> specbot-results/compile-status.txt
-
- - name: Run specbot tests
- continue-on-error: true
- run: |
- mkdir -p specbot-results
- if [ -f specbot-results/test_specbot_seq ]; then
- LD_LIBRARY_PATH="${GITHUB_WORKSPACE}/build/debug" timeout 120 specbot-results/test_specbot_seq > specbot-results/test_specbot_seq.log 2>&1
- SPECBOT_EXIT=$?
- echo "specbot_seq_exit=${SPECBOT_EXIT}" >> specbot-results/test-status.txt
- else
- echo "Binary not compiled" > specbot-results/test_specbot_seq.log
- echo "specbot_seq_exit=127" >> specbot-results/test-status.txt
- fi
-
- if [ -f specbot-results/test_deeptest_seq ]; then
- LD_LIBRARY_PATH="${GITHUB_WORKSPACE}/build/debug" timeout 120 specbot-results/test_deeptest_seq > specbot-results/test_deeptest_seq.log 2>&1
- DEEPTEST_EXIT=$?
- echo "deeptest_seq_exit=${DEEPTEST_EXIT}" >> specbot-results/test-status.txt
- else
- echo "Binary not compiled" > specbot-results/test_deeptest_seq.log
- echo "deeptest_seq_exit=127" >> specbot-results/test-status.txt
- fi
-
----
-
-# Specbot Crash Analyzer
-
-## Job Description
-
-Your name is ${{ github.workflow }}. You are an expert C/C++ and SMT solver analyst for the Z3 theorem prover
-repository `${{ github.repository }}`. The pre-steps above have already built Z3 in debug mode from the `c3`
-branch, compiled and run the specbot test suite, and saved all output to the `specbot-results/` directory in
-the workspace (`${{ github.workspace }}/specbot-results/`). Your task is to analyze those results, diagnose
-any crash root causes by reading the relevant source files, and publish a structured findings report as a
-GitHub Discussion.
-
-**Do not try to build Z3 or run tests yourself.** All build and test output is already in `specbot-results/`.
-
-## Your Task
-
-### 1. Read the Pre-Generated Results
-
-All build and test outputs are in `specbot-results/` (relative to the workspace root). Read each file:
-
-```bash
-# Build status
-cat specbot-results/build-status.txt 2>/dev/null || echo "No build status"
-
-# Compile status
-cat specbot-results/compile-status.txt 2>/dev/null || echo "No compile status"
-
-# Test status
-cat specbot-results/test-status.txt 2>/dev/null || echo "No test status"
-
-# Test output from test_specbot_seq
-cat specbot-results/test_specbot_seq.log 2>/dev/null || echo "No test_specbot_seq output"
-
-# Test output from test_deeptest_seq
-cat specbot-results/test_deeptest_seq.log 2>/dev/null || echo "No test_deeptest_seq output"
-
-# Last 30 lines of the build log
-tail -30 specbot-results/build.log 2>/dev/null || echo "No build log"
-```
-
-If `specbot-results/build-status.txt` shows `build_exit=0`, the build succeeded.
-If it shows a non-zero exit, include the last 50 lines of `specbot-results/build.log` in the report
-under a "Build Failure" section.
-
-If `specbot-results/compile-status.txt` shows a non-zero exit for a test, include the compile error
-from `specbot-results/compile_specbot_seq.log` or `specbot-results/compile_deeptest_seq.log`.
-
-Collect every line containing `CRASH` or `ABORT` from the test log files — these are the crashes to analyze.
-
-### 2. Diagnose Each Crash
-
-For each crashed test function, perform the following analysis:
-
-1. **Identify the test body**: read `specbot/test_specbot_seq.c` or `specbot/test_deeptest_seq.c`
- to understand what Z3 API calls the test makes and what invariants it exercises.
-
-2. **Find the likely crash site**: the test exercises the Z3 Nielsen/nseq string solver. Relevant source files are:
- - `src/smt/seq_solver.h` and `src/smt/seq_solver.cpp` (or nearby files)
- - `src/smt/seq_axioms.cpp`, `src/smt/seq_eq_solver.cpp`, `src/smt/seq_regex.cpp`
- - `src/math/lp/` for length-arithmetic paths
- - `src/api/z3_api.h` for the public API entry points
-
- Use `grep` and `view` to locate assertion macros, `UNREACHABLE()`, `SASSERT`, or `throw` statements
- in the code paths exercised by the failing test. Example:
- ```bash
- grep -rn "SASSERT\|UNREACHABLE\|Z3_CATCH" src/smt/seq_solver.cpp 2>/dev/null | head -30
- ```
-
-3. **Hypothesize root cause**: based on the Z3 API calls in the test and the assertion/throw sites in
- the solver source, state the most likely root cause. Common categories include:
- - Violated invariant (SASSERT/UNREACHABLE hit due to unexpected solver state)
- - Use-after-free or dangling reference during push/pop
- - Unhandled edge case in Nielsen graph construction
- - Missing theory-combination lemma between string length and integer arithmetic
-
-4. **Suggest a fix**: propose a minimal, concrete fix — e.g., a guard condition, an additional lemma,
- a missing reference-count increment, or a missing case in a switch/match.
-
-### 3. Generate the Report
-
-After analyzing all crashes, produce a structured GitHub Discussion in the "Agentic Workflows" category
-using `create-discussion`.
-
-The discussion body must follow this structure (use `###` and lower for headers):
-
-```
-### Summary
-
-- Build: Debug (CMake + Ninja, c3 branch)
-- Tests compiled: N
-- Tests run: N
-- Tests passed: N
-- Tests crashed: N
-- Tests timed out: N
-
-### Crash Findings
-
-For each crash, one subsection:
-
-####
-
-**Test file**: `specbot/test_specbot_seq.c` or `specbot/test_deeptest_seq.c`
-
-**Observed failure**: ABORT/CRASH — one-line description of what was caught
-
-**Root cause hypothesis**: explanation of which assertion or code path was hit and why
-
-**Suggested fix**: concrete proposed change (file, function, what to add/change)
-
----
-
-### Tests Passed
-
-List of test names that passed.
-
-
-Full Test Output
-
-Raw stdout/stderr from both test binaries.
-
-
-
-
-Build Log
-
-Last 30 lines of the ninja build output.
-
-
-```
-
-If there are no crashes at all, write a "No Crashes Found" summary celebrating that all tests passed,
-and include the full test output in a collapsible section.
-
-Use `mentions: false` behavior — do not mention any GitHub usernames in the report.
-
-Format workflow run references as: `[§${{ github.run_id }}](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }})`.
-
-## Usage
-
-Trigger via **Actions → Specbot Crash Analyzer → Run workflow** on any branch. The pre-steps
-always check out the `c3` branch where `specbot/test_specbot_seq.c` and
-`specbot/test_deeptest_seq.c` live, build Z3, run the tests, and save results to `specbot-results/`.
-The agent then analyzes the results and posts a discussion to the "Agentic Workflows" category.
diff --git a/.github/workflows/tptp-benchmark.lock.yml b/.github/workflows/tptp-benchmark.lock.yml
deleted file mode 100644
index cc13513777..0000000000
--- a/.github/workflows/tptp-benchmark.lock.yml
+++ /dev/null
@@ -1,1586 +0,0 @@
-# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"941a41fa2bca88df96e4dcbd8e0fb4a38b99edad52753933f4f2247270639ade","body_hash":"c8dc70436710705ec44e1f6b0236a2e5b314b3aec02708ef192cab1bb4099dce","compiler_version":"v0.83.4","strict":true,"agent_id":"copilot","engine_versions":{"copilot":"1.0.75"}}
-# gh-aw-manifest: {"version":1,"secrets":["COPILOT_GITHUB_TOKEN","GH_AW_GITHUB_MCP_SERVER_TOKEN","GH_AW_GITHUB_TOKEN","GITHUB_TOKEN"],"actions":[{"repo":"actions/cache/restore","sha":"55cc8345863c7cc4c66a329aec7e433d2d1c52a9","version":"v6.1.0"},{"repo":"actions/cache/save","sha":"55cc8345863c7cc4c66a329aec7e433d2d1c52a9","version":"v6.1.0"},{"repo":"actions/checkout","sha":"3d3c42e5aac5ba805825da76410c181273ba90b1","version":"v7.0.1"},{"repo":"actions/checkout","sha":"de0fac2e4500dabe0009e67214ff5f5447ce83dd","version":"v6.0.2"},{"repo":"actions/download-artifact","sha":"3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c","version":"v8.0.1"},{"repo":"actions/github-script","sha":"3a2844b7e9c422d3c10d287c895573f7108da1b3","version":"v9.0.0"},{"repo":"actions/setup-node","sha":"820762786026740c76f36085b0efc47a31fe5020","version":"v7.0.0"},{"repo":"actions/upload-artifact","sha":"043fb46d1a93c77aae656e7c1c64a875d1fc6a0a","version":"v7.0.1"},{"repo":"github/gh-aw-actions/setup","sha":"v0.83.4","version":"v0.83.4"}],"containers":[{"image":"ghcr.io/github/gh-aw-firewall/agent:0.27.42","digest":"sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b","pinned_image":"ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b"},{"image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42","digest":"sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607","pinned_image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607"},{"image":"ghcr.io/github/gh-aw-firewall/squid:0.27.42","digest":"sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0","pinned_image":"ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0"},{"image":"ghcr.io/github/gh-aw-mcpg:v0.4.6","digest":"sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c","pinned_image":"ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c"},{"image":"ghcr.io/github/gh-aw-node","digest":"sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748","pinned_image":"ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748"},{"image":"ghcr.io/github/github-mcp-server:v1.7.0","digest":"sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308","pinned_image":"ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308"}]}
-# This file was automatically generated by gh-aw (v0.83.4). DO NOT EDIT. To debug this workflow, load the skill at https://github.com/github/gh-aw/blob/main/debug.md
-#
-# ___ _ _
-# / _ \ | | (_)
-# | |_| | __ _ ___ _ __ | |_ _ ___
-# | _ |/ _` |/ _ \ '_ \| __| |/ __|
-# | | | | (_| | __/ | | | |_| | (__
-# \_| |_/\__, |\___|_| |_|\__|_|\___|
-# __/ |
-# _ _ |___/
-# | | | | / _| |
-# | | | | ___ _ __ _ __| |_| | _____ ____
-# | |/\| |/ _ \ '__| |/ /| _| |/ _ \ \ /\ / / ___|
-# \ /\ / (_) | | | | ( | | | | (_) \ V V /\__ \
-# \/ \/ \___/|_| |_|\_\|_| |_|\___/ \_/\_/ |___/
-#
-#
-# To update this file, edit the corresponding .md file and run:
-# gh aw compile
-# Not all edits will cause changes to this file.
-#
-# For more information: https://github.github.com/gh-aw/introduction/overview/
-#
-# Weekly benchmark of Z3's TPTP front-end against 500 random TPTP problems. Downloads TPTP benchmarks from tptp.org, resolves axiom dependencies, skips large problems, runs each with a 5-second timeout, and posts a discrepancy/crash report as a GitHub discussion.
-#
-# Secrets used:
-# - COPILOT_GITHUB_TOKEN
-# - GH_AW_GITHUB_MCP_SERVER_TOKEN
-# - GH_AW_GITHUB_TOKEN
-# - GITHUB_TOKEN
-#
-# Custom actions used:
-# - actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-# - actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-# - actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-# - actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-# - actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-# - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
-# - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 (source v9)
-# - actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
-# - actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-# - github/gh-aw-actions/setup@v0.83.4
-#
-# Container images used:
-# - ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b
-# - ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607
-# - ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0
-# - ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c
-# - ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748
-# - ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308
-
-name: "TPTP Front-End Benchmark"
-on:
- schedule:
- - cron: "0 6 * * 1"
- workflow_dispatch:
- inputs:
- aw_context:
- default: ""
- description: "Agent caller context (used internally by Agentic Workflows)."
- required: false
- type: string
-
-permissions: {}
-
-concurrency:
- group: "gh-aw-${{ github.workflow }}"
-
-run-name: "TPTP Front-End Benchmark"
-
-jobs:
- activation:
- runs-on: ubuntu-slim
- permissions:
- actions: read
- contents: read
- env:
- GH_AW_MAX_DAILY_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_DAILY_AI_CREDITS || '5000' }}
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- comment_id: ""
- comment_repo: ""
- daily_ai_credits_exceeded: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_exceeded == 'true' }}
- daily_ai_credits_threshold: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_threshold || '' }}
- daily_ai_credits_total_effective_tokens: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_total_effective_tokens || '' }}
- engine_id: ${{ steps.generate_aw_info.outputs.engine_id }}
- lockdown_check_failed: ${{ steps.generate_aw_info.outputs.lockdown_check_failed == 'true' }}
- model: ${{ steps.generate_aw_info.outputs.model }}
- oauth_token_check_failed: ${{ steps.check-oauth-tokens.outputs.oauth_token_check_failed == 'true' }}
- setup-parent-span-id: ${{ steps.setup.outputs.parent-span-id || steps.setup.outputs.span-id }}
- setup-span-id: ${{ steps.setup.outputs.span-id }}
- setup-trace-id: ${{ steps.setup.outputs.trace-id }}
- stale_lock_file_failed: ${{ steps.check-lock-file.outputs.stale_lock_file_failed == 'true' }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- safe-output-artifact-client: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/tptp-benchmark.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Generate agentic run info
- id: generate_aw_info
- env:
- GH_AW_INFO_ENGINE_ID: "copilot"
- GH_AW_INFO_ENGINE_NAME: "GitHub Copilot CLI"
- GH_AW_INFO_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AGENT_VERSION: "1.0.75"
- GH_AW_INFO_CLI_VERSION: "v0.83.4"
- GH_AW_INFO_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_INFO_EXPERIMENTAL: "false"
- GH_AW_INFO_SUPPORTS_TOOLS_ALLOWLIST: "true"
- GH_AW_INFO_STAGED: "false"
- GH_AW_INFO_ALLOWED_DOMAINS: '["defaults","tptp.org"]'
- GH_AW_INFO_FIREWALL_ENABLED: "true"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_AWMG_VERSION: ""
- GH_AW_INFO_FIREWALL_TYPE: "squid"
- GH_AW_COMPILED_STRICT: "true"
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/generate_aw_info.cjs');
- await main(core, context);
- - name: Restore daily AIC usage cache
- id: restore-daily-aic-cache
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- continue-on-error: true
- uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-tptpbenchmark-${{ github.run_id }}
- restore-keys: agentic-workflow-usage-tptpbenchmark-
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Restore daily AIC usage cache (artifact fallback)
- id: restore-daily-aic-cache-fallback
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_RESTORE_DAILY_AIC_CACHE_HIT: ${{ steps.restore-daily-aic-cache.outputs.cache-hit }}
- GH_AW_RESTORE_DAILY_AIC_CACHE_MATCHED_KEY: ${{ steps.restore-daily-aic-cache.outputs.cache-matched-key }}
- with:
- github-token: ${{ secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/restore_aic_usage_cache_fallback.cjs');
- await main();
- - name: Check daily workflow token guardrail
- id: daily-effective-workflow-guardrail
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_WORKFLOW_ID: "tptp-benchmark"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_WORKFLOW_DISPATCH_AW_CONTEXT: ${{ github.event.inputs.aw_context || '' }}
- GH_AW_HAS_SLASH_COMMAND: "false"
- GH_AW_HAS_LABEL_COMMAND: "false"
- GH_AW_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- GH_AW_MAX_DAILY_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_DAILY_AI_CREDITS || '5000' }}
- with:
- github-token: ${{ secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_daily_aic_workflow_guardrail.cjs');
- await main();
- - name: Check for OAuth tokens
- id: check-oauth-tokens
- run: bash "${RUNNER_TEMP}/gh-aw/actions/check_oauth_tokens.sh"
- env:
- COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }}
- - name: Checkout .github and .agents folders
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- with:
- persist-credentials: false
- sparse-checkout: |
- .github
- .agents
- .antigravity
- .claude
- .codex
- .gemini
- .opencode
- .pi
- sparse-checkout-cone-mode: true
- fetch-depth: 1
- - name: Save agent config folders for base branch restoration
- env:
- GH_AW_AGENT_FOLDERS: ".agents .antigravity .claude .codex .gemini .github .opencode .pi"
- GH_AW_AGENT_FILES: "AGENTS.md ANTIGRAVITY.md CLAUDE.md GEMINI.md PI.md opencode.jsonc"
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/save_base_github_folders.sh"
- - name: Check workflow lock file
- id: check-lock-file
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_WORKFLOW_FILE: "tptp-benchmark.lock.yml"
- GH_AW_CONTEXT_WORKFLOW_REF: "${{ github.workflow_ref }}"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_workflow_timestamp_api.cjs');
- await main();
- - name: Check compile-agentic version
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_COMPILED_VERSION: "v0.83.4"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_version_updates.cjs');
- await main();
- - name: Log runtime features
- if: ${{ contains(toJSON(vars), '"GH_AW_RUNTIME_FEATURES":') }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/log_runtime_features_summary.sh"
- - name: Create prompt with built-in context
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_SAFE_OUTPUTS: ${{ runner.temp }}/gh-aw/safeoutputs/outputs.jsonl
- GH_AW_EXPR_1A3A194A: ${{ github.event.discussion.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'discussion' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_463A214A: ${{ github.event.pull_request.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'pull_request' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_802A9F6A: ${{ github.event.issue.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'issue' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_FF1D34CE: ${{ github.event.comment.id || fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').comment_id }}
- GH_AW_GITHUB_ACTOR: ${{ github.actor }}
- GH_AW_GITHUB_REPOSITORY: ${{ github.repository }}
- GH_AW_GITHUB_RUN_ID: ${{ github.run_id }}
- GH_AW_GITHUB_WORKFLOW: ${{ github.workflow }}
- GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
- # poutine:ignore untrusted_checkout_exec
- run: |
- bash "${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh"
- {
- cat << 'GH_AW_PROMPT_93a00b92db3cfdba_EOF'
-
- GH_AW_PROMPT_93a00b92db3cfdba_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 << 'GH_AW_PROMPT_93a00b92db3cfdba_EOF'
-
- Tools: create_discussion, missing_tool, missing_data, noop
-
- GH_AW_PROMPT_93a00b92db3cfdba_EOF
- cat "${RUNNER_TEMP}/gh-aw/prompts/mcp_cli_tools_prompt.md"
- cat << 'GH_AW_PROMPT_93a00b92db3cfdba_EOF'
-
- The following GitHub context information is available for this workflow:
- {{#if github.actor}}
- - **actor**: __GH_AW_GITHUB_ACTOR__
- {{/if}}
- {{#if github.repository}}
- - **repository**: __GH_AW_GITHUB_REPOSITORY__
- {{/if}}
- {{#if github.workspace}}
- - **workspace**: __GH_AW_GITHUB_WORKSPACE__
- {{/if}}
- {{#if github.event.issue.number || (github.aw.context.item_type == 'issue' && github.aw.context.item_number)}}
- - **issue-number**: #__GH_AW_EXPR_802A9F6A__
- {{/if}}
- {{#if github.event.discussion.number || (github.aw.context.item_type == 'discussion' && github.aw.context.item_number)}}
- - **discussion-number**: #__GH_AW_EXPR_1A3A194A__
- {{/if}}
- {{#if github.event.pull_request.number || (github.aw.context.item_type == 'pull_request' && github.aw.context.item_number)}}
- - **pull-request-number**: #__GH_AW_EXPR_463A214A__
- {{/if}}
- {{#if github.event.comment.id || github.aw.context.comment_id}}
- - **comment-id**: __GH_AW_EXPR_FF1D34CE__
- {{/if}}
- {{#if github.run_id}}
- - **workflow-run-id**: __GH_AW_GITHUB_RUN_ID__
- {{/if}}
-
-
- GH_AW_PROMPT_93a00b92db3cfdba_EOF
- cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md"
- cat << 'GH_AW_PROMPT_93a00b92db3cfdba_EOF'
-
- {{#runtime-import .github/workflows/tptp-benchmark.md}}
- GH_AW_PROMPT_93a00b92db3cfdba_EOF
- } > "$GH_AW_PROMPT"
- - name: Interpolate variables and render templates
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_ENGINE_ID: "copilot"
- GH_AW_GITHUB_REPOSITORY: ${{ github.repository }}
- GH_AW_GITHUB_RUN_ID: ${{ github.run_id }}
- GH_AW_GITHUB_WORKFLOW: ${{ github.workflow }}
- GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/interpolate_prompt.cjs');
- await main();
- - name: Substitute placeholders
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_EXPR_1A3A194A: ${{ github.event.discussion.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'discussion' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_463A214A: ${{ github.event.pull_request.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'pull_request' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_802A9F6A: ${{ github.event.issue.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'issue' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_FF1D34CE: ${{ github.event.comment.id || fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').comment_id }}
- GH_AW_GITHUB_ACTOR: ${{ github.actor }}
- GH_AW_GITHUB_REPOSITORY: ${{ github.repository }}
- GH_AW_GITHUB_RUN_ID: ${{ github.run_id }}
- GH_AW_GITHUB_WORKFLOW: ${{ github.workflow }}
- GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
- GH_AW_MCP_CLI_SERVERS_LIST: "- `github` — run `github --help` to see available tools\n- `safeoutputs` — run `safeoutputs --help` to see available tools"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
-
- const substitutePlaceholders = require('${{ runner.temp }}/gh-aw/actions/substitute_placeholders.cjs');
-
- // Call the substitution function
- return await substitutePlaceholders({
- file: process.env.GH_AW_PROMPT,
- substitutions: {
- GH_AW_EXPR_1A3A194A: process.env.GH_AW_EXPR_1A3A194A,
- GH_AW_EXPR_463A214A: process.env.GH_AW_EXPR_463A214A,
- GH_AW_EXPR_802A9F6A: process.env.GH_AW_EXPR_802A9F6A,
- GH_AW_EXPR_FF1D34CE: process.env.GH_AW_EXPR_FF1D34CE,
- GH_AW_GITHUB_ACTOR: process.env.GH_AW_GITHUB_ACTOR,
- GH_AW_GITHUB_REPOSITORY: process.env.GH_AW_GITHUB_REPOSITORY,
- GH_AW_GITHUB_RUN_ID: process.env.GH_AW_GITHUB_RUN_ID,
- GH_AW_GITHUB_WORKFLOW: process.env.GH_AW_GITHUB_WORKFLOW,
- GH_AW_GITHUB_WORKSPACE: process.env.GH_AW_GITHUB_WORKSPACE,
- GH_AW_MCP_CLI_SERVERS_LIST: process.env.GH_AW_MCP_CLI_SERVERS_LIST
- }
- });
- - name: Validate prompt placeholders
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/validate_prompt_placeholders.sh"
- - name: Print prompt
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/print_prompt_summary.sh"
- - name: Upload activation artifact
- if: success()
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: activation
- include-hidden-files: true
- path: |
- /tmp/gh-aw/aw_info.json
- /tmp/gh-aw/models.json
- /tmp/gh-aw/aw-prompts/prompt.txt
- /tmp/gh-aw/aw-prompts/prompt-template.txt
- /tmp/gh-aw/aw-prompts/prompt-import-tree.json
- /tmp/gh-aw/github_rate_limits.jsonl
- /tmp/gh-aw/base
- /tmp/gh-aw/.github/agents
- /tmp/gh-aw/.github/skills
- if-no-files-found: ignore
- retention-days: 1
-
- agent:
- needs: activation
- if: needs.activation.outputs.daily_ai_credits_exceeded != 'true'
- runs-on: ubuntu-latest
- permissions:
- contents: read
- copilot-requests: write
- issues: read
- pull-requests: read
- concurrency:
- group: "gh-aw-copilot-${{ github.workflow }}"
- queue: max
- env:
- DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
- GH_AW_ASSETS_ALLOWED_EXTS: ""
- GH_AW_ASSETS_BRANCH: ""
- GH_AW_ASSETS_MAX_SIZE_KB: 0
- GH_AW_MCP_LOG_DIR: /tmp/gh-aw/mcp-logs/safeoutputs
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- GH_AW_WORKFLOW_ID_SANITIZED: tptpbenchmark
- outputs:
- agentic_engine_timeout: ${{ steps.detect-agent-errors.outputs.agentic_engine_timeout || 'false' }}
- ai_credits_rate_limit_error: ${{ steps.parse-mcp-gateway.outputs.ai_credits_rate_limit_error || 'false' }}
- aic: ${{ steps.parse-mcp-gateway.outputs.aic }}
- ambient_context: ${{ steps.parse-mcp-gateway.outputs.ambient_context }}
- checkout_pr_success: ${{ steps.checkout-pr.outputs.checkout_pr_success || 'true' }}
- effective_tokens: ${{ steps.parse-mcp-gateway.outputs.effective_tokens }}
- has_patch: ${{ steps.collect_output.outputs.has_patch }}
- http_400_response_error: ${{ steps.detect-agent-errors.outputs.http_400_response_error || 'false' }}
- inference_access_error: ${{ steps.detect-agent-errors.outputs.inference_access_error || 'false' }}
- invocation_cap_exceeded: ${{ steps.detect-agent-errors.outputs.invocation_cap_exceeded || 'false' }}
- mcp_policy_error: ${{ steps.detect-agent-errors.outputs.mcp_policy_error || 'false' }}
- model: ${{ needs.activation.outputs.model }}
- model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }}
- output: ${{ steps.collect_output.outputs.output }}
- output_types: ${{ steps.collect_output.outputs.output_types }}
- setup-parent-span-id: ${{ steps.setup.outputs.parent-span-id || steps.setup.outputs.span-id }}
- setup-span-id: ${{ steps.setup.outputs.span-id }}
- setup-trace-id: ${{ steps.setup.outputs.trace-id }}
- unknown_model_ai_credits: ${{ steps.parse-mcp-gateway.outputs.unknown_model_ai_credits || 'false' }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/tptp-benchmark.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Set runtime paths
- id: set-runtime-paths
- run: |
- {
- echo "GH_AW_SAFE_OUTPUTS=${RUNNER_TEMP}/gh-aw/safeoutputs/outputs.jsonl"
- echo "GH_AW_SAFE_OUTPUTS_CONFIG_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/config.json"
- echo "GH_AW_SAFE_OUTPUTS_TOOLS_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/tools.json"
- } >> "$GITHUB_OUTPUT"
- - 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: ${{ github.token }}
- - name: Download activation artifact
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: activation
- path: /tmp/gh-aw
- - name: Checkout repository
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- with:
- persist-credentials: false
- - name: Install build dependencies
- run: |
- sudo apt-get update -y -q
- sudo apt-get install -y cmake ninja-build python3 wget curl bc
- - name: Build Z3
- run: "mkdir -p /tmp/z3-build\ncd /tmp/z3-build\ncmake \"$GITHUB_WORKSPACE\" \\\n -G Ninja \\\n -DCMAKE_BUILD_TYPE=Release \\\n -DZ3_BUILD_TEST_EXECUTABLES=OFF\nninja -j$(nproc) z3\n./z3 --version"
-
- - name: Configure Git credentials
- env:
- GITHUB_REPOSITORY: ${{ github.repository }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_TOKEN: ${{ github.token }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/configure_git_credentials.sh"
- - name: Checkout PR branch
- id: checkout-pr
- if: |
- github.event.pull_request || github.event.issue.pull_request || github.event_name == 'workflow_dispatch' && fromJSON(github.event.inputs.aw_context || '{}').item_type == 'pull_request'
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- 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');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/checkout_pr_branch.cjs');
- await main();
- - name: Install GitHub Copilot CLI
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh" 1.0.75
- env:
- GH_HOST: github.com
- - name: Install AWF binary
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.27.42 --rootless
- - name: Determine automatic lockdown mode for GitHub MCP Server
- id: determine-automatic-lockdown
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 (source v9)
- env:
- GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- 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');
- await determineAutomaticLockdown(github, context, core);
- - name: Restore agent config folders from base branch
- if: steps.checkout-pr.outcome == 'success'
- env:
- GH_AW_AGENT_FOLDERS: ".agents .antigravity .claude .codex .gemini .github .opencode .pi"
- GH_AW_AGENT_FILES: "AGENTS.md ANTIGRAVITY.md CLAUDE.md GEMINI.md PI.md opencode.jsonc"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_base_github_folders.sh"
- - name: Restore inline sub-agents from activation artifact
- env:
- GH_AW_SUB_AGENT_DIR: ".github/agents"
- GH_AW_SUB_AGENT_EXT: ".agent.md"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_inline_sub_agents.sh"
- - name: Restore inline skills from activation artifact
- env:
- GH_AW_SKILL_DIR: ".github/skills"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_inline_skills.sh"
- - name: Download container images
- run: bash "${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh" ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607 ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0 ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748 ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308
- - name: Generate Safe Outputs Config
- run: |
- mkdir -p "${RUNNER_TEMP}/gh-aw/safeoutputs"
- mkdir -p /tmp/gh-aw/safeoutputs
- mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs
- cat > "${RUNNER_TEMP}/gh-aw/safeoutputs/config.json" << 'GH_AW_SAFE_OUTPUTS_CONFIG_784cc762b36517a2_EOF'
- {"create_discussion":{"category":"agentic workflows","close_older_discussions":true,"expires":336,"fallback_to_issue":true,"max":1,"title_prefix":"[TPTP Benchmark] "},"create_report_incomplete_issue":{},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"false"},"report_incomplete":{}}
- GH_AW_SAFE_OUTPUTS_CONFIG_784cc762b36517a2_EOF
- - name: Generate Safe Outputs Tools
- env:
- GH_AW_TOOLS_META_JSON: |
- {
- "description_suffixes": {
- "create_discussion": " CONSTRAINTS: Maximum 1 discussion(s) can be created. Title will be prefixed with \"[TPTP Benchmark] \". Discussions will be created in category \"agentic workflows\"."
- },
- "repo_params": {},
- "dynamic_tools": []
- }
- GH_AW_VALIDATION_JSON: |
- {
- "create_discussion": {
- "defaultMax": 1,
- "fields": {
- "body": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 65000,
- "minLength": 64
- },
- "category": {
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- },
- "repo": {
- "type": "string",
- "maxLength": 256
- },
- "title": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- }
- }
- },
- "missing_data": {
- "defaultMax": 20,
- "fields": {
- "alternatives": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "context": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "data_type": {
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- },
- "reason": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- }
- }
- },
- "missing_tool": {
- "defaultMax": 20,
- "fields": {
- "alternatives": {
- "type": "string",
- "sanitize": true,
- "maxLength": 512
- },
- "reason": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "tool": {
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- }
- }
- },
- "noop": {
- "defaultMax": 1,
- "fields": {
- "message": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 65000
- }
- }
- },
- "report_incomplete": {
- "defaultMax": 5,
- "fields": {
- "details": {
- "type": "string",
- "sanitize": true,
- "maxLength": 65000
- },
- "reason": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 1024
- }
- }
- }
- }
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/generate_safe_outputs_tools.cjs');
- await main();
- - name: Start MCP Gateway
- id: start-mcp-gateway
- env:
- GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST: ${{ vars.GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST || 'true' }}
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- GH_AW_SAFE_OUTPUTS_CONFIG_PATH: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS_CONFIG_PATH }}
- GH_AW_SAFE_OUTPUTS_TOOLS_PATH: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS_TOOLS_PATH }}
- GITHUB_MCP_GUARD_MIN_INTEGRITY: ${{ steps.determine-automatic-lockdown.outputs.min_integrity }}
- GITHUB_MCP_GUARD_REPOS: ${{ steps.determine-automatic-lockdown.outputs.repos }}
- GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- run: |
- set -eo pipefail
- mkdir -p "${RUNNER_TEMP}/gh-aw/mcp-config"
-
- # Export gateway environment variables for MCP config and gateway script
- export MCP_GATEWAY_PORT="8080"
- export MCP_GATEWAY_DOMAIN="awmg-mcpg"
- export MCP_GATEWAY_HOST_DOMAIN="localhost"
- MCP_GATEWAY_API_KEY=$(openssl rand -base64 45 | tr -d '/+=')
- echo "::add-mask::${MCP_GATEWAY_API_KEY}"
- export MCP_GATEWAY_API_KEY
- export MCP_GATEWAY_PAYLOAD_DIR="/tmp/gh-aw/mcp-payloads"
- mkdir -p "${MCP_GATEWAY_PAYLOAD_DIR}"
- export MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD="524288"
- export DEBUG="*"
-
- export GH_AW_ENGINE="copilot"
- MCP_GATEWAY_UID=$(id -u 2>/dev/null || echo '0')
- MCP_GATEWAY_GID=$(id -g 2>/dev/null || echo '0')
- source "${RUNNER_TEMP}/gh-aw/actions/resolve_docker_socket_gid.sh"
- export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network bridge -p 127.0.0.1:'"${MCP_GATEWAY_PORT}"':'"${MCP_GATEWAY_PORT}"' --name awmg-mcpg --add-host host.docker.internal:host-gateway --user '"${MCP_GATEWAY_UID}"':'"${MCP_GATEWAY_GID}"' --group-add '"${DOCKER_SOCK_GID}"' -v '"${DOCKER_SOCK_PATH}"':/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 DOCKER_HOST=unix:///var/run/docker.sock -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_POLICY_ALLOW_CREATE_PULL_REQUEST -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 RUNNER_TEMP -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 -v '"${RUNNER_TEMP}"'/gh-aw/safeoutputs:'"${RUNNER_TEMP}"'/gh-aw/safeoutputs:rw ghcr.io/github/gh-aw-mcpg:v0.4.6'
-
- mkdir -p "$HOME/.copilot"
- GH_AW_NODE=$(which node 2>/dev/null || command -v node 2>/dev/null || echo node)
- cat << GH_AW_MCP_CONFIG_4dd92588edb04041_EOF | "$GH_AW_NODE" "${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.cjs"
- {
- "mcpServers": {
- "github": {
- "type": "stdio",
- "container": "ghcr.io/github/github-mcp-server:v1.7.0",
- "env": {
- "GITHUB_FEATURES": "fields_param",
- "GITHUB_HOST": "${GITHUB_SERVER_URL}",
- "GITHUB_PERSONAL_ACCESS_TOKEN": "${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": {
- "type": "stdio",
- "container": "ghcr.io/github/gh-aw-node",
- "mounts": ["\${GITHUB_WORKSPACE}:\${GITHUB_WORKSPACE}:rw", "${RUNNER_TEMP}/gh-aw/safeoutputs:${RUNNER_TEMP}/gh-aw/safeoutputs:rw", "/tmp/gh-aw:/tmp/gh-aw:rw"],
- "args": ["-w", "\${GITHUB_WORKSPACE}"],
- "entrypoint": "sh",
- "entrypointArgs": ["-c", "sh ${RUNNER_TEMP}/gh-aw/safeoutputs/start_safe_outputs_mcp.sh"],
- "env": {
- "DEBUG": "*",
- "DEFAULT_BRANCH": "\${DEFAULT_BRANCH}",
- "GH_AW_ASSETS_ALLOWED_EXTS": "\${GH_AW_ASSETS_ALLOWED_EXTS}",
- "GH_AW_ASSETS_BRANCH": "\${GH_AW_ASSETS_BRANCH}",
- "GH_AW_ASSETS_MAX_SIZE_KB": "\${GH_AW_ASSETS_MAX_SIZE_KB}",
- "GH_AW_MCP_LOG_DIR": "\${GH_AW_MCP_LOG_DIR}",
- "GH_AW_SAFE_OUTPUTS": "\${GH_AW_SAFE_OUTPUTS}",
- "GH_AW_SAFE_OUTPUTS_CONFIG_PATH": "\${GH_AW_SAFE_OUTPUTS_CONFIG_PATH}",
- "GH_AW_SAFE_OUTPUTS_TOOLS_PATH": "\${GH_AW_SAFE_OUTPUTS_TOOLS_PATH}",
- "GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST": "\${GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST}",
- "GITHUB_REPOSITORY": "\${GITHUB_REPOSITORY}",
- "GITHUB_SHA": "\${GITHUB_SHA}",
- "GITHUB_TOKEN": "\${GITHUB_TOKEN}",
- "GITHUB_WORKSPACE": "\${GITHUB_WORKSPACE}",
- "RUNNER_TEMP": "\${RUNNER_TEMP}"
- },
- "guard-policies": {
- "write-sink": {
- "accept": [
- "*"
- ],
- "sink-visibility": ${{ toJSON(steps.determine-automatic-lockdown.outputs.visibility) }}
- }
- }
- }
- },
- "gateway": {
- "port": $MCP_GATEWAY_PORT,
- "domain": "${MCP_GATEWAY_DOMAIN}",
- "apiKey": "${MCP_GATEWAY_API_KEY}",
- "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}",
- "startupTimeout": 120
- }
- }
- GH_AW_MCP_CONFIG_4dd92588edb04041_EOF
- - name: Mount MCP servers as CLIs
- id: mount-mcp-clis
- continue-on-error: true
- env:
- MCP_GATEWAY_API_KEY: ${{ steps.start-mcp-gateway.outputs.gateway-api-key }}
- MCP_GATEWAY_DOMAIN: ${{ steps.start-mcp-gateway.outputs.gateway-domain }}
- MCP_GATEWAY_PORT: ${{ steps.start-mcp-gateway.outputs.gateway-port }}
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/mount_mcp_as_cli.cjs');
- await main();
- - name: Clean credentials
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/clean_git_credentials.sh"
- - name: Audit pre-agent workspace
- id: pre_agent_audit
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/audit_pre_agent_workspace.sh"
- - name: Execute GitHub Copilot CLI
- id: agentic_execution
- # Copilot CLI tool arguments (sorted):
- timeout-minutes: 300
- run: |
- set -o pipefail
- printf '%s' "$(date +%s%3N)" > /tmp/gh-aw/agent_cli_start_ms.txt
- trap 'gh_aw_exit_code=$?; mkdir -p /tmp/gh-aw >/dev/null 2>&1 || true; printf "%s" "$gh_aw_exit_code" > /tmp/gh-aw/agent_execution_exit_code.txt || true; rm -f "$HOME/.copilot/settings.json"' EXIT
- mkdir -p "$HOME/.copilot"
- printf '%s' '{"builtInAgents":{"rubberDuck":false}}' > "$HOME/.copilot/settings.json"
- export XDG_CONFIG_HOME="$HOME"
- export GH_AW_MCP_CONFIG="$HOME/.copilot/mcp-config.json"
- touch /tmp/gh-aw/agent-step-summary.md
- GH_AW_NODE_BIN=$(command -v node 2>/dev/null || true)
- export GH_AW_NODE_BIN
- export COPILOT_API_KEY="$COPILOT_DUMMY_BYOK"
- (umask 177 && touch /tmp/gh-aw/agent-stdio.log)
- GH_AW_MAX_AI_CREDITS="${GH_AW_MAX_AI_CREDITS:-1000}"
- printf '%s\n' "{\"\$schema\":\"https://github.com/github/gh-aw-firewall/releases/download/v0.27.42/awf-config.schema.json\",\"network\":{\"allowDomains\":[\"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\",\"tptp.org\",\"ts-crl.ws.symantec.com\",\"ts-ocsp.ws.symantec.com\",\"www.googleapis.com\"],\"isolation\":true,\"topologyAttach\":[\"awmg-mcpg\"]},\"apiProxy\":{\"enabled\":true,\"enableTokenSteering\":true,\"maxRuns\":500,\"maxAiCredits\":${GH_AW_MAX_AI_CREDITS},\"maxCacheMisses\":5,\"models\":{\"agent\":[\"sonnet-6x\",\"gpt-5.4\",\"gpt-5.5\",\"gpt-5.6\",\"gpt-5.3\",\"gemini-pro\",\"any\"],\"antigravity\":[\"copilot/antigravity*\",\"google/antigravity*\",\"gemini/antigravity*\"],\"any\":[\"copilot/*\",\"anthropic/*\",\"openai/*\",\"google/*\",\"gemini/*\"],\"claude\":[\"agent\"],\"codex\":[\"agent\"],\"coding\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\",\"gpt-5-codex\",\"kimi\"],\"computer-use\":[\"copilot/*computer-use*\",\"google/*computer-use*\",\"gemini/*computer-use*\",\"openai/*computer-use*\"],\"copilot\":[\"agent\"],\"deep-research\":[\"copilot/deep-research*\",\"copilot/o3-deep-research*\",\"copilot/o4-mini-deep-research*\",\"google/deep-research*\",\"gemini/deep-research*\",\"openai/o3-deep-research*\",\"openai/o4-mini-deep-research*\"],\"fable\":[\"copilot/*fable*\",\"anthropic/*fable*\"],\"gemini\":[\"agent\"],\"gemini-3-flash\":[\"copilot/gemini-3*flash*\",\"google/gemini-3*flash*\",\"gemini/gemini-3*flash*\"],\"gemini-3-pro\":[\"copilot/gemini-3*pro*\",\"google/gemini-3*pro*\",\"google/nano-banana*\",\"gemini/gemini-3*pro*\"],\"gemini-3.1-flash\":[\"copilot/gemini-3.1*flash*\",\"google/gemini-3.1*flash*\",\"gemini/gemini-3.1*flash*\"],\"gemini-3.1-pro\":[\"copilot/gemini-3.1*pro*\",\"google/gemini-3.1*pro*\",\"gemini/gemini-3.1*pro*\"],\"gemini-3.5-flash\":[\"copilot/gemini-3.5*flash*\",\"google/gemini-3.5*flash*\",\"gemini/gemini-3.5*flash*\"],\"gemini-3.6-flash\":[\"copilot/gemini-3.6*flash*\",\"google/gemini-3.6*flash*\",\"gemini/gemini-3.6*flash*\"],\"gemini-flash\":[\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"],\"gemini-flash-lite\":[\"copilot/gemini-*flash*lite*\",\"google/gemini-*flash*lite*\",\"gemini/gemini-*flash*lite*\"],\"gemini-omni\":[\"copilot/gemini-omni*\",\"google/gemini-omni*\",\"gemini/gemini-omni*\"],\"gemini-pro\":[\"copilot/gemini-*pro*\",\"google/gemini-*pro*\",\"gemini/gemini-*pro*\"],\"gemma\":[\"copilot/gemma*\",\"google/gemma*\",\"gemini/gemma*\"],\"gpt-5\":[\"copilot/gpt-5*\",\"openai/gpt-5*\"],\"gpt-5-codex\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\"],\"gpt-5-mini\":[\"copilot/gpt-5*mini*\",\"openai/gpt-5*mini*\"],\"gpt-5-nano\":[\"copilot/gpt-5*nano*\",\"openai/gpt-5*nano*\"],\"gpt-5-pro\":[\"copilot/gpt-5*pro*\",\"openai/gpt-5*pro*\"],\"gpt-5.1\":[\"copilot/gpt-5.1*\",\"openai/gpt-5.1*\"],\"gpt-5.2\":[\"copilot/gpt-5.2*\",\"openai/gpt-5.2*\"],\"gpt-5.3\":[\"copilot/gpt-5.3*\",\"openai/gpt-5.3*\"],\"gpt-5.4\":[\"copilot/gpt-5.4*\",\"openai/gpt-5.4*\"],\"gpt-5.5\":[\"copilot/gpt-5.5*\",\"openai/gpt-5.5*\"],\"gpt-5.6\":[\"copilot/gpt-5.6*\",\"openai/gpt-5.6*\"],\"haiku\":[\"copilot/*haiku*\",\"anthropic/*haiku*\"],\"image-generation\":[\"copilot/gpt-image*\",\"openai/gpt-image*\",\"openai/chatgpt-image*\",\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"google/imagen*\"],\"kimi\":[\"copilot/kimi*\",\"openai/kimi*\"],\"kiwi\":[\"copilot/kiwi*\",\"openai/kiwi*\"],\"large\":[\"fable\",\"sonnet\",\"gpt-5-pro\",\"gpt-5\",\"gemini-pro\"],\"lyria\":[\"google/lyria*\",\"gemini/lyria*\",\"copilot/lyria*\"],\"mai-code\":[\"copilot/MAI-Code*\",\"copilot/mai-code*\",\"openai/MAI-Code*\"],\"mai-code-1-flash-picker\":[\"copilot/MAI-Code-1-Flash-picker*\",\"copilot/mai-code-1-flash-picker*\",\"openai/MAI-Code-1-Flash-picker*\"],\"mini\":[\"haiku\",\"gpt-5-mini\",\"gpt-5-nano\",\"gemini-flash-lite\"],\"nano-banana\":[\"copilot/nano-banana*\",\"google/nano-banana*\",\"gemini/nano-banana*\"],\"opus\":[\"copilot/*opus*\",\"anthropic/*opus*\"],\"opusplan\":[\"opus?effort=high\"],\"raptor-mini\":[\"copilot/raptor*\",\"openai/raptor*\"],\"reasoning\":[\"copilot/o1*\",\"copilot/o3*\",\"copilot/o4*\",\"openai/o1*\",\"openai/o3*\",\"openai/o4*\"],\"robotics\":[\"copilot/*robotics*\",\"google/*robotics*\",\"gemini/*robotics*\"],\"small\":[\"mini\"],\"small-agent\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash\"],\"sonnet\":[\"copilot/*sonnet*\",\"anthropic/*sonnet*\"],\"sonnet-6x\":[\"copilot/*sonnet-4.5*\",\"copilot/*sonnet-4.6*\",\"copilot/*sonnet-5*\",\"copilot/*sonnet-4-5-*\",\"anthropic/*sonnet-4-5-*\",\"copilot/*sonnet-4-6*\",\"anthropic/*sonnet-4-6*\",\"anthropic/*sonnet-5*\"],\"summarization\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash-lite\",\"mini\"],\"veo\":[\"google/veo*\",\"gemini/veo*\"],\"vision\":[\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"]}},\"container\":{\"imageTag\":\"0.27.42,squid=sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0,agent=sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b,agent-act=sha256:a14ad974484aa518aab83d40f3f141175dfd171d3745e01c092375b970f73a20,api-proxy=sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607,cli-proxy=sha256:da006bf96d2d246dd269d57b233c1798d2ad63d6cd64ca02f7bf71045028781f\"},\"logging\":{\"proxyLogsDir\":\"/tmp/gh-aw/sandbox/firewall/logs\",\"auditDir\":\"/tmp/gh-aw/sandbox/firewall/audit\"}}" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- cp "${RUNNER_TEMP}/gh-aw/awf-config.json" /tmp/gh-aw/awf-config.json
- export GH_AW_MODELS_JSON_PATH="/tmp/gh-aw/models.json"
- GH_AW_DOCKER_HOST=""
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_DOCKER_HOST="${DOCKER_HOST}"
- fi
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_CHROOT_BINARIES_SOURCE_PATH="${RUNNER_TEMP}/gh-aw" GH_AW_CHROOT_IDENTITY_HOME="${RUNNER_TEMP}/gh-aw/home" node "${RUNNER_TEMP}/gh-aw/actions/patch_awf_chroot_config.cjs"
- fi
- GH_AW_TOOL_CACHE_MOUNT=""
- GH_AW_TOOL_CACHE="${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"
- if [ -d "$GH_AW_TOOL_CACHE" ]; then
- if [[ "$GH_AW_TOOL_CACHE" != /opt/* ]]; then
- GH_AW_TOOL_CACHE_MOUNT="$GH_AW_TOOL_CACHE:$GH_AW_TOOL_CACHE:ro"
- fi
- fi
- # shellcheck disable=SC1003,SC2016,SC2086
- awf --config "${RUNNER_TEMP}/gh-aw/awf-config.json" --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" ${GH_AW_TOOL_CACHE_MOUNT:+--mount "$GH_AW_TOOL_CACHE_MOUNT"} ${GH_AW_DOCKER_HOST:+--docker-host "$GH_AW_DOCKER_HOST"} --env-all --exclude-env COPILOT_GITHUB_TOKEN --exclude-env GITHUB_MCP_SERVER_TOKEN --exclude-env MCP_GATEWAY_API_KEY --log-level info --skip-pull \
- -- /bin/bash -c 'set +o histexpand; export PATH="${RUNNER_TEMP}/gh-aw/mcp-cli/bin:$PATH" && : "${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"; GH_AW_TOOL_CACHE="$RUNNER_TOOL_CACHE"; export PATH="$(find "$GH_AW_TOOL_CACHE" -maxdepth 5 -type d -name bin 2>/dev/null | tr '\''\n'\'' '\'':'\'')$PATH"; [ -n "$GOROOT" ] && export PATH="$GOROOT/bin:$PATH" || true; [ -n "$ERLANG_HOME" ] && export PATH="$ERLANG_HOME/bin:$PATH" || true && GH_AW_NODE_EXEC="${GH_AW_NODE_BIN:-}"; if [ -z "$GH_AW_NODE_EXEC" ] || [ ! -x "$GH_AW_NODE_EXEC" ]; then GH_AW_NODE_EXEC="$(command -v node 2>/dev/null || true)"; fi; if [ -z "$GH_AW_NODE_EXEC" ]; then echo "node runtime missing on this runner — check runtimes.node in workflow YAML" >&2; exit 127; fi; GH_AW_NPM_GLOBAL_ROOT="$(npm root -g 2>/dev/null || true)"; if [ -n "$GH_AW_NPM_GLOBAL_ROOT" ]; then export NODE_PATH="${GH_AW_NPM_GLOBAL_ROOT}${NODE_PATH:+:${NODE_PATH}}"; fi; "$GH_AW_NODE_EXEC" ${RUNNER_TEMP}/gh-aw/actions/copilot_harness.cjs /usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --no-ask-user --allow-all-tools --allow-all-paths --add-dir "${GITHUB_WORKSPACE}" --prompt-file /tmp/gh-aw/aw-prompts/prompt.txt' 2>&1 | tee -a /tmp/gh-aw/agent-stdio.log
- env:
- AWF_REFLECT_ENABLED: 1
- COPILOT_AGENT_RUNNER_TYPE: STANDALONE
- COPILOT_DUMMY_BYOK: dummy-byok-key-for-offline-mode
- COPILOT_GITHUB_TOKEN: ${{ github.token }}
- COPILOT_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_LLM_PROVIDER: github
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }}
- GH_AW_MAX_TURNS: ${{ vars.GH_AW_DEFAULT_MAX_TURNS || '' }}
- GH_AW_PHASE: agent
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- GH_AW_TIMEOUT_MINUTES: 300
- GH_AW_VERSION: v0.83.4
- GITHUB_API_URL: ${{ github.api_url }}
- GITHUB_AW: true
- GITHUB_COPILOT_INTEGRATION_ID: agentic-workflows
- GITHUB_HEAD_REF: ${{ github.head_ref }}
- GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- GITHUB_REF_NAME: ${{ github.ref_name }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_STEP_SUMMARY: /tmp/gh-aw/agent-step-summary.md
- GITHUB_WORKSPACE: ${{ github.workspace }}
- GIT_AUTHOR_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_AUTHOR_NAME: github-actions[bot]
- GIT_COMMITTER_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_COMMITTER_NAME: github-actions[bot]
- RUNNER_TEMP: ${{ runner.temp }}
- S2STOKENS: true
- TRACEPARENT: ${{ env.GITHUB_AW_OTEL_TRACE_ID != '' && env.GITHUB_AW_OTEL_PARENT_SPAN_ID != '' && format('00-{0}-{1}-01', env.GITHUB_AW_OTEL_TRACE_ID, env.GITHUB_AW_OTEL_PARENT_SPAN_ID) || '' }}
- - name: Detect agent errors
- if: always()
- id: detect-agent-errors
- continue-on-error: true
- run: node "${RUNNER_TEMP}/gh-aw/actions/detect_agent_errors.cjs"
- - name: Configure Git credentials
- env:
- GITHUB_REPOSITORY: ${{ github.repository }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_TOKEN: ${{ github.token }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/configure_git_credentials.sh"
- - name: Copy Copilot session state files to logs
- if: always()
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/copy_copilot_session_state.sh"
- - name: Stop MCP Gateway
- if: always()
- continue-on-error: true
- env:
- MCP_GATEWAY_PORT: ${{ steps.start-mcp-gateway.outputs.gateway-port }}
- 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" "$GATEWAY_PID"
- - name: Redact secrets in logs
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/redact_secrets.cjs');
- await main();
- env:
- GH_AW_SECRET_NAMES: 'GH_AW_GITHUB_MCP_SERVER_TOKEN,GH_AW_GITHUB_TOKEN,GITHUB_TOKEN'
- SECRET_GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }}
- SECRET_GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- 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
- if: always()
- env:
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- run: |
- mkdir -p /tmp/gh-aw
- cp "$GH_AW_SAFE_OUTPUTS" /tmp/gh-aw/safeoutputs.jsonl 2>/dev/null || true
- - name: Ingest agent output
- id: collect_output
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.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,tptp.org,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com,www.googleapis.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');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/collect_ndjson_output.cjs');
- await main();
- - name: Parse agent logs for step summary
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: /tmp/gh-aw/sandbox/agent/logs/
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_copilot_log.cjs');
- await main();
- - name: Parse MCP Gateway logs for step summary
- if: always()
- id: parse-mcp-gateway
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_mcp_gateway_log.cjs');
- await main();
- - name: Print firewall logs
- if: always()
- continue-on-error: true
- env:
- AWF_LOGS_DIR: /tmp/gh-aw/sandbox/firewall/logs
- run: bash "${RUNNER_TEMP}/gh-aw/actions/print_firewall_logs.sh" --rootless
- - name: Parse token usage for step summary
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_token_usage.cjs');
- await main();
- - name: Print AWF reflect summary
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/awf_reflect_summary.cjs');
- await main();
- - name: Write agent output placeholder if missing
- if: always()
- run: |
- if [ ! -f /tmp/gh-aw/agent_output.json ]; then
- echo '{"items":[]}' > /tmp/gh-aw/agent_output.json
- fi
- - name: Upload agent artifacts
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: agent
- 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/agent_usage.json
- /tmp/gh-aw/agent-stdio.log
- /tmp/gh-aw/pre-agent-audit.txt
- /tmp/gh-aw/agent/
- /tmp/gh-aw/github_rate_limits.jsonl
- /tmp/gh-aw/safeoutputs.jsonl
- /tmp/gh-aw/agent_output.json
- /tmp/gh-aw/aw-*.patch
- /tmp/gh-aw/aw-*.bundle
- /tmp/gh-aw/awf-config.json
- /tmp/gh-aw/sandbox/firewall/logs/
- /tmp/gh-aw/sandbox/firewall/audit/
- /tmp/gh-aw/sandbox/firewall/awf-reflect.json
- if-no-files-found: ignore
-
- conclusion:
- needs:
- - activation
- - agent
- - detection
- - safe_outputs
- if: >
- always() && (needs.agent.result != 'skipped' || needs.activation.outputs.lockdown_check_failed == 'true' ||
- needs.activation.outputs.oauth_token_check_failed == 'true' || needs.activation.outputs.stale_lock_file_failed == 'true' ||
- needs.activation.outputs.daily_ai_credits_exceeded == 'true')
- runs-on: ubuntu-slim
- permissions:
- contents: read
- discussions: write
- issues: write
- concurrency:
- group: "gh-aw-conclusion-tptp-benchmark"
- cancel-in-progress: false
- queue: max
- env:
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- incomplete_count: ${{ steps.report_incomplete.outputs.incomplete_count }}
- noop_message: ${{ steps.noop.outputs.noop_message }}
- tools_reported: ${{ steps.missing_tool.outputs.tools_reported }}
- total_count: ${{ steps.missing_tool.outputs.total_count }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/tptp-benchmark.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Download safe outputs items manifest
- id: download-safe-outputs-manifest
- if: always()
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: safe-outputs-items
- path: /tmp/gh-aw/
- - name: Collect usage artifact files
- if: always()
- continue-on-error: true
- run: |
- mkdir -p /tmp/gh-aw/usage/agent /tmp/gh-aw/usage/detection
- echo "Usage artifact source file status:"
- for file in /tmp/gh-aw/aw_info.json /tmp/gh-aw/aw-info.jsonl /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/detection_usage.jsonl /tmp/gh-aw/evals/evals.jsonl /tmp/gh-aw/github_rate_limits.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl; do
- [ -f "$file" ] && echo "FOUND: $file" || echo "MISSING: $file"
- done
- [ -f /tmp/gh-aw/aw_info.json ] && cp /tmp/gh-aw/aw_info.json /tmp/gh-aw/usage/aw_info.json || true
- [ -f /tmp/gh-aw/aw-info.jsonl ] && cp /tmp/gh-aw/aw-info.jsonl /tmp/gh-aw/usage/aw-info.jsonl || true
- [ -f /tmp/gh-aw/agent_usage.json ] && cp /tmp/gh-aw/agent_usage.json /tmp/gh-aw/usage/agent_usage.json || true
- [ -f /tmp/gh-aw/agent_usage.jsonl ] && cp /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/usage/agent_usage.jsonl || true
- [ -f /tmp/gh-aw/detection_usage.jsonl ] && cp /tmp/gh-aw/detection_usage.jsonl /tmp/gh-aw/usage/detection_usage.jsonl || true
- [ -f /tmp/gh-aw/evals/evals.jsonl ] && cp /tmp/gh-aw/evals/evals.jsonl /tmp/gh-aw/usage/evals.jsonl || true
- [ -f /tmp/gh-aw/github_rate_limits.jsonl ] && cp /tmp/gh-aw/github_rate_limits.jsonl /tmp/gh-aw/usage/github_rate_limits.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -f /tmp/gh-aw/usage/agent/token_usage.jsonl ] || : > /tmp/gh-aw/usage/agent/token_usage.jsonl
- [ -f /tmp/gh-aw/usage/detection/token_usage.jsonl ] || : > /tmp/gh-aw/usage/detection/token_usage.jsonl
- mkdir -p /tmp/gh-aw/usage/activity
- node "${RUNNER_TEMP}/gh-aw/actions/generate_usage_activity_summary.cjs"
- find /tmp/gh-aw/usage -type f -print | sort
- - name: Upload usage artifact
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: usage
- path: |
- /tmp/gh-aw/usage/aw_info.json
- /tmp/gh-aw/usage/aw-info.jsonl
- /tmp/gh-aw/usage/agent_usage.json
- /tmp/gh-aw/usage/agent_usage.jsonl
- /tmp/gh-aw/usage/detection_usage.jsonl
- /tmp/gh-aw/usage/evals.jsonl
- /tmp/gh-aw/usage/github_rate_limits.jsonl
- /tmp/gh-aw/usage/agent/token_usage.jsonl
- /tmp/gh-aw/usage/detection/token_usage.jsonl
- /tmp/gh-aw/usage/activity/summary.json
- if-no-files-found: ignore
- - name: Restore daily AIC usage cache
- id: restore-daily-aic-cache-conclusion
- if: always()
- continue-on-error: true
- uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-tptpbenchmark-${{ github.run_id }}
- restore-keys: agentic-workflow-usage-tptpbenchmark-
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Write daily AIC usage cache entry
- id: write-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- github-token: ${{ github.token }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/write_daily_aic_usage_cache.cjs');
- await main();
- - name: Save daily AIC usage cache
- id: save-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-tptpbenchmark-${{ github.run_id }}
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Upload daily AIC usage cache artifact
- id: upload-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: aic-usage-cache
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- if-no-files-found: ignore
- retention-days: 7
- - name: Process no-op messages
- id: noop
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_NOOP_MAX: "1"
- GH_AW_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/tptp-benchmark.md"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_AGENT_CONCLUSION: ${{ needs.agent.result }}
- GH_AW_NOOP_REPORT_AS_ISSUE: "false"
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_AMBIENT_CONTEXT: ${{ needs.agent.outputs.ambient_context }}
- GH_AW_WORKFLOW_ID: "tptp-benchmark"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_noop_message.cjs');
- await main();
- - name: Log detection run
- id: detection_runs
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/tptp-benchmark.md"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_DETECTION_CONCLUSION: ${{ needs.detection.outputs.detection_conclusion }}
- GH_AW_DETECTION_REASON: ${{ needs.detection.outputs.detection_reason }}
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_detection_runs.cjs');
- await main();
- - name: Record missing tool
- id: missing_tool
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_MISSING_TOOL_CREATE_ISSUE: "true"
- GH_AW_MISSING_TOOL_TITLE_PREFIX: "[missing tool]"
- GH_AW_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/tptp-benchmark.md"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/missing_tool.cjs');
- await main();
- - name: Record incomplete
- id: report_incomplete
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_REPORT_INCOMPLETE_CREATE_ISSUE: "true"
- GH_AW_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/tptp-benchmark.md"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/report_incomplete_handler.cjs');
- await main();
- - name: Handle agent failure
- id: handle_agent_failure
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/tptp-benchmark.md"
- 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: "tptp-benchmark"
- GH_AW_ACTION_FAILURE_ISSUE_EXPIRES_HOURS: "168"
- GH_AW_ENGINE_ID: "copilot"
- GH_AW_CHECKOUT_PR_SUCCESS: ${{ needs.agent.outputs.checkout_pr_success }}
- GH_AW_EFFECTIVE_TOKENS: ${{ needs.agent.outputs.effective_tokens || '' }}
- GH_AW_AI_CREDITS_RATE_LIMIT_ERROR: ${{ needs.agent.outputs.ai_credits_rate_limit_error || 'false' }}
- GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }}
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }}
- GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }}
- GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }}
- GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }}
- GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }}
- GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }}
- GH_AW_ENGINE_API_HOSTS: "api.enterprise.githubcopilot.com,api.githubcopilot.com,api.business.githubcopilot.com,api.individual.githubcopilot.com"
- 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_OAUTH_TOKEN_CHECK_FAILED: ${{ needs.activation.outputs.oauth_token_check_failed }}
- GH_AW_STALE_LOCK_FILE_FAILED: ${{ needs.activation.outputs.stale_lock_file_failed }}
- GH_AW_DAILY_AI_CREDITS_EXCEEDED: ${{ needs.activation.outputs.daily_ai_credits_exceeded }}
- GH_AW_DAILY_AI_CREDITS_TOTAL_EFFECTIVE_TOKENS: ${{ needs.activation.outputs.daily_ai_credits_total_effective_tokens }}
- GH_AW_DAILY_AI_CREDITS_THRESHOLD: ${{ needs.activation.outputs.daily_ai_credits_threshold }}
- GH_AW_GROUP_REPORTS: "false"
- GH_AW_FAILURE_REPORT_AS_ISSUE: "false"
- GH_AW_MISSING_TOOL_REPORT_AS_FAILURE: "true"
- GH_AW_MISSING_DATA_REPORT_AS_FAILURE: "true"
- GH_AW_TIMEOUT_MINUTES: "300"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_agent_failure.cjs');
- await main();
-
- detection:
- needs:
- - activation
- - agent
- if: always() && needs.agent.result != 'skipped'
- runs-on: ubuntu-latest
- permissions:
- contents: read
- copilot-requests: write
- env:
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- aic: ${{ steps.parse_detection_token_usage.outputs.aic }}
- detection_conclusion: ${{ steps.detection_conclusion.outputs.conclusion }}
- detection_reason: ${{ steps.detection_conclusion.outputs.reason }}
- detection_success: ${{ steps.detection_conclusion.outputs.success }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/tptp-benchmark.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Checkout repository for patch context
- if: needs.agent.outputs.has_patch == 'true'
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- with:
- persist-credentials: false
- # --- Threat Detection ---
- - name: Clean stale firewall files from agent artifact
- run: |
- rm -rf /tmp/gh-aw/sandbox/firewall/logs
- rm -rf /tmp/gh-aw/sandbox/firewall/audit
- - name: Download container images
- run: bash "${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh" ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607 ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0
- - name: Check if detection needed
- id: detection_guard
- if: always()
- env:
- OUTPUT_TYPES: ${{ needs.agent.outputs.output_types }}
- HAS_PATCH: ${{ needs.agent.outputs.has_patch }}
- run: |
- if [[ -n "$OUTPUT_TYPES" || "$HAS_PATCH" == "true" ]]; then
- echo "run_detection=true" >> "$GITHUB_OUTPUT"
- echo "Detection will run: output_types=$OUTPUT_TYPES, has_patch=$HAS_PATCH"
- else
- echo "run_detection=false" >> "$GITHUB_OUTPUT"
- echo "Detection skipped: no agent outputs or patches to analyze"
- fi
- - name: Clear MCP Config for detection
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- rm -f "${RUNNER_TEMP}/gh-aw/mcp-config/mcp-servers.json"
- rm -f "$HOME/.copilot/mcp-config.json"
- rm -f "$GITHUB_WORKSPACE/.gemini/settings.json"
- - name: Prepare threat detection files
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- mkdir -p /tmp/gh-aw/threat-detection/aw-prompts
- rm -f /tmp/gh-aw/agent_usage.json
- cp /tmp/gh-aw/aw-prompts/prompt.txt /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt 2>/dev/null || true
- if [ ! -s /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt ]; then
- echo "::warning::ERR_VALIDATION: Missing or empty detection context prompt at /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt. Ensure the agent artifact includes /tmp/gh-aw/aw-prompts/prompt.txt. Detection will continue with fallback workflow context."
- fi
- cp /tmp/gh-aw/agent_output.json /tmp/gh-aw/threat-detection/agent_output.json 2>/dev/null || true
- for f in /tmp/gh-aw/aw-*.patch; do
- [ -f "$f" ] && cp "$f" /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- done
- for f in /tmp/gh-aw/aw-*.bundle; do
- [ -f "$f" ] && cp "$f" /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- done
- echo "Prepared threat detection files:"
- ls -la /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- - name: Setup threat detection
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- WORKFLOW_NAME: "TPTP Front-End Benchmark"
- WORKFLOW_DESCRIPTION: "Weekly benchmark of Z3's TPTP front-end against 500 random TPTP problems. Downloads TPTP benchmarks from tptp.org, resolves axiom dependencies, skips large problems, runs each with a 5-second timeout, and posts a discrepancy/crash report as a GitHub discussion."
- HAS_PATCH: ${{ needs.agent.outputs.has_patch }}
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/setup_threat_detection.cjs');
- await main();
- - name: Ensure threat-detection directory and log
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- mkdir -p /tmp/gh-aw/threat-detection
- touch /tmp/gh-aw/threat-detection/detection.log
- - name: Setup Node.js
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
- with:
- node-version: '24'
- package-manager-cache: false
- - name: Install GitHub Copilot CLI
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh" 1.0.75
- env:
- GH_HOST: github.com
- - name: Install AWF binary
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.27.42
- - name: Execute GitHub Copilot CLI
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- continue-on-error: true
- id: detection_agentic_execution
- # Copilot CLI tool arguments (sorted):
- timeout-minutes: 20
- run: |
- set -o pipefail
- printf '%s' "$(date +%s%3N)" > /tmp/gh-aw/agent_cli_start_ms.txt
- trap 'gh_aw_exit_code=$?; mkdir -p /tmp/gh-aw >/dev/null 2>&1 || true; printf "%s" "$gh_aw_exit_code" > /tmp/gh-aw/agent_execution_exit_code.txt || true; rm -f "$HOME/.copilot/settings.json"' EXIT
- mkdir -p "$HOME/.copilot"
- printf '%s' '{"builtInAgents":{"rubberDuck":false}}' > "$HOME/.copilot/settings.json"
- export XDG_CONFIG_HOME="$HOME"
- touch /tmp/gh-aw/agent-step-summary.md
- GH_AW_NODE_BIN=$(command -v node 2>/dev/null || true)
- export GH_AW_NODE_BIN
- export COPILOT_API_KEY="$COPILOT_DUMMY_BYOK"
- (umask 177 && touch /tmp/gh-aw/threat-detection/detection.log)
- GH_AW_MAX_AI_CREDITS="${GH_AW_MAX_AI_CREDITS:-400}"
- printf '%s\n' "{\"\$schema\":\"https://github.com/github/gh-aw-firewall/releases/download/v0.27.42/awf-config.schema.json\",\"network\":{\"allowDomains\":[\"api.business.githubcopilot.com\",\"api.enterprise.githubcopilot.com\",\"api.github.com\",\"api.githubcopilot.com\",\"api.individual.githubcopilot.com\",\"github.com\",\"host.docker.internal\",\"registry.npmjs.org\",\"telemetry.enterprise.githubcopilot.com\"]},\"apiProxy\":{\"enabled\":true,\"enableTokenSteering\":true,\"maxRuns\":500,\"maxAiCredits\":${GH_AW_MAX_AI_CREDITS},\"maxCacheMisses\":5,\"models\":{\"agent\":[\"sonnet-6x\",\"gpt-5.4\",\"gpt-5.5\",\"gpt-5.6\",\"gpt-5.3\",\"gemini-pro\",\"any\"],\"antigravity\":[\"copilot/antigravity*\",\"google/antigravity*\",\"gemini/antigravity*\"],\"any\":[\"copilot/*\",\"anthropic/*\",\"openai/*\",\"google/*\",\"gemini/*\"],\"claude\":[\"agent\"],\"codex\":[\"agent\"],\"coding\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\",\"gpt-5-codex\",\"kimi\"],\"computer-use\":[\"copilot/*computer-use*\",\"google/*computer-use*\",\"gemini/*computer-use*\",\"openai/*computer-use*\"],\"copilot\":[\"agent\"],\"deep-research\":[\"copilot/deep-research*\",\"copilot/o3-deep-research*\",\"copilot/o4-mini-deep-research*\",\"google/deep-research*\",\"gemini/deep-research*\",\"openai/o3-deep-research*\",\"openai/o4-mini-deep-research*\"],\"fable\":[\"copilot/*fable*\",\"anthropic/*fable*\"],\"gemini\":[\"agent\"],\"gemini-3-flash\":[\"copilot/gemini-3*flash*\",\"google/gemini-3*flash*\",\"gemini/gemini-3*flash*\"],\"gemini-3-pro\":[\"copilot/gemini-3*pro*\",\"google/gemini-3*pro*\",\"google/nano-banana*\",\"gemini/gemini-3*pro*\"],\"gemini-3.1-flash\":[\"copilot/gemini-3.1*flash*\",\"google/gemini-3.1*flash*\",\"gemini/gemini-3.1*flash*\"],\"gemini-3.1-pro\":[\"copilot/gemini-3.1*pro*\",\"google/gemini-3.1*pro*\",\"gemini/gemini-3.1*pro*\"],\"gemini-3.5-flash\":[\"copilot/gemini-3.5*flash*\",\"google/gemini-3.5*flash*\",\"gemini/gemini-3.5*flash*\"],\"gemini-3.6-flash\":[\"copilot/gemini-3.6*flash*\",\"google/gemini-3.6*flash*\",\"gemini/gemini-3.6*flash*\"],\"gemini-flash\":[\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"],\"gemini-flash-lite\":[\"copilot/gemini-*flash*lite*\",\"google/gemini-*flash*lite*\",\"gemini/gemini-*flash*lite*\"],\"gemini-omni\":[\"copilot/gemini-omni*\",\"google/gemini-omni*\",\"gemini/gemini-omni*\"],\"gemini-pro\":[\"copilot/gemini-*pro*\",\"google/gemini-*pro*\",\"gemini/gemini-*pro*\"],\"gemma\":[\"copilot/gemma*\",\"google/gemma*\",\"gemini/gemma*\"],\"gpt-5\":[\"copilot/gpt-5*\",\"openai/gpt-5*\"],\"gpt-5-codex\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\"],\"gpt-5-mini\":[\"copilot/gpt-5*mini*\",\"openai/gpt-5*mini*\"],\"gpt-5-nano\":[\"copilot/gpt-5*nano*\",\"openai/gpt-5*nano*\"],\"gpt-5-pro\":[\"copilot/gpt-5*pro*\",\"openai/gpt-5*pro*\"],\"gpt-5.1\":[\"copilot/gpt-5.1*\",\"openai/gpt-5.1*\"],\"gpt-5.2\":[\"copilot/gpt-5.2*\",\"openai/gpt-5.2*\"],\"gpt-5.3\":[\"copilot/gpt-5.3*\",\"openai/gpt-5.3*\"],\"gpt-5.4\":[\"copilot/gpt-5.4*\",\"openai/gpt-5.4*\"],\"gpt-5.5\":[\"copilot/gpt-5.5*\",\"openai/gpt-5.5*\"],\"gpt-5.6\":[\"copilot/gpt-5.6*\",\"openai/gpt-5.6*\"],\"haiku\":[\"copilot/*haiku*\",\"anthropic/*haiku*\"],\"image-generation\":[\"copilot/gpt-image*\",\"openai/gpt-image*\",\"openai/chatgpt-image*\",\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"google/imagen*\"],\"kimi\":[\"copilot/kimi*\",\"openai/kimi*\"],\"kiwi\":[\"copilot/kiwi*\",\"openai/kiwi*\"],\"large\":[\"fable\",\"sonnet\",\"gpt-5-pro\",\"gpt-5\",\"gemini-pro\"],\"lyria\":[\"google/lyria*\",\"gemini/lyria*\",\"copilot/lyria*\"],\"mai-code\":[\"copilot/MAI-Code*\",\"copilot/mai-code*\",\"openai/MAI-Code*\"],\"mai-code-1-flash-picker\":[\"copilot/MAI-Code-1-Flash-picker*\",\"copilot/mai-code-1-flash-picker*\",\"openai/MAI-Code-1-Flash-picker*\"],\"mini\":[\"haiku\",\"gpt-5-mini\",\"gpt-5-nano\",\"gemini-flash-lite\"],\"nano-banana\":[\"copilot/nano-banana*\",\"google/nano-banana*\",\"gemini/nano-banana*\"],\"opus\":[\"copilot/*opus*\",\"anthropic/*opus*\"],\"opusplan\":[\"opus?effort=high\"],\"raptor-mini\":[\"copilot/raptor*\",\"openai/raptor*\"],\"reasoning\":[\"copilot/o1*\",\"copilot/o3*\",\"copilot/o4*\",\"openai/o1*\",\"openai/o3*\",\"openai/o4*\"],\"robotics\":[\"copilot/*robotics*\",\"google/*robotics*\",\"gemini/*robotics*\"],\"small\":[\"mini\"],\"small-agent\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash\"],\"sonnet\":[\"copilot/*sonnet*\",\"anthropic/*sonnet*\"],\"sonnet-6x\":[\"copilot/*sonnet-4.5*\",\"copilot/*sonnet-4.6*\",\"copilot/*sonnet-5*\",\"copilot/*sonnet-4-5-*\",\"anthropic/*sonnet-4-5-*\",\"copilot/*sonnet-4-6*\",\"anthropic/*sonnet-4-6*\",\"anthropic/*sonnet-5*\"],\"summarization\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash-lite\",\"mini\"],\"veo\":[\"google/veo*\",\"gemini/veo*\"],\"vision\":[\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"]}},\"container\":{\"imageTag\":\"0.27.42,squid=sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0,agent=sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b,agent-act=sha256:a14ad974484aa518aab83d40f3f141175dfd171d3745e01c092375b970f73a20,api-proxy=sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607,cli-proxy=sha256:da006bf96d2d246dd269d57b233c1798d2ad63d6cd64ca02f7bf71045028781f\"},\"logging\":{\"proxyLogsDir\":\"/tmp/gh-aw/sandbox/firewall/logs\",\"auditDir\":\"/tmp/gh-aw/sandbox/firewall/audit\"}}" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- cp "${RUNNER_TEMP}/gh-aw/awf-config.json" /tmp/gh-aw/awf-config.json
- export GH_AW_MODELS_JSON_PATH="/tmp/gh-aw/models.json"
- GH_AW_DOCKER_HOST=""
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_DOCKER_HOST="${DOCKER_HOST}"
- fi
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- _GH_AW_CHROOT_JSON=$(jq -c --arg src "${RUNNER_TEMP}/gh-aw" --arg user "$(id -un)" --argjson uid "$(id -u)" --argjson gid "$(id -g)" --arg home "${RUNNER_TEMP}/gh-aw/home" '.chroot={"binariesSourcePath":$src,"identity":{"user":$user,"uid":$uid,"gid":$gid,"home":$home}}' "${RUNNER_TEMP}/gh-aw/awf-config.json") || { echo "chroot config patch failed" >&2; exit 1; }
- printf '%s\n' "$_GH_AW_CHROOT_JSON" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- printf '%s\n' "$_GH_AW_CHROOT_JSON" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- fi
- GH_AW_TOOL_CACHE_MOUNT=""
- GH_AW_TOOL_CACHE="${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"
- if [ -d "$GH_AW_TOOL_CACHE" ]; then
- if [[ "$GH_AW_TOOL_CACHE" != /opt/* ]]; then
- GH_AW_TOOL_CACHE_MOUNT="$GH_AW_TOOL_CACHE:$GH_AW_TOOL_CACHE:ro"
- fi
- fi
- # shellcheck disable=SC1003,SC2016,SC2086
- awf --config "${RUNNER_TEMP}/gh-aw/awf-config.json" --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" ${GH_AW_TOOL_CACHE_MOUNT:+--mount "$GH_AW_TOOL_CACHE_MOUNT"} ${GH_AW_DOCKER_HOST:+--docker-host "$GH_AW_DOCKER_HOST"} --env-all --exclude-env COPILOT_GITHUB_TOKEN --log-level info --skip-pull \
- -- /bin/bash -c 'set +o histexpand; : "${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"; GH_AW_TOOL_CACHE="$RUNNER_TOOL_CACHE"; export PATH="$(find "$GH_AW_TOOL_CACHE" -maxdepth 5 -type d -name bin 2>/dev/null | tr '\''\n'\'' '\'':'\'')$PATH"; [ -n "$GOROOT" ] && export PATH="$GOROOT/bin:$PATH" || true; [ -n "$ERLANG_HOME" ] && export PATH="$ERLANG_HOME/bin:$PATH" || true && GH_AW_NODE_EXEC="${GH_AW_NODE_BIN:-}"; if [ -z "$GH_AW_NODE_EXEC" ] || [ ! -x "$GH_AW_NODE_EXEC" ]; then GH_AW_NODE_EXEC="$(command -v node 2>/dev/null || true)"; fi; if [ -z "$GH_AW_NODE_EXEC" ]; then echo "node runtime missing on this runner — check runtimes.node in workflow YAML" >&2; exit 127; fi; GH_AW_NPM_GLOBAL_ROOT="$(npm root -g 2>/dev/null || true)"; if [ -n "$GH_AW_NPM_GLOBAL_ROOT" ]; then export NODE_PATH="${GH_AW_NPM_GLOBAL_ROOT}${NODE_PATH:+:${NODE_PATH}}"; fi; "$GH_AW_NODE_EXEC" ${RUNNER_TEMP}/gh-aw/actions/copilot_harness.cjs /usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --no-ask-user --allow-all-tools --add-dir "${GITHUB_WORKSPACE}" --prompt-file /tmp/gh-aw/aw-prompts/prompt.txt' 2>&1 | tee -a /tmp/gh-aw/threat-detection/detection.log
- env:
- AWF_REFLECT_ENABLED: 1
- COPILOT_AGENT_RUNNER_TYPE: STANDALONE
- COPILOT_DUMMY_BYOK: dummy-byok-key-for-offline-mode
- COPILOT_GITHUB_TOKEN: ${{ github.token }}
- COPILOT_MODEL: ${{ vars.GH_AW_MODEL_DETECTION_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_LLM_PROVIDER: github
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_DETECTION_MAX_AI_CREDITS || '400' }}
- GH_AW_MAX_TURNS: ${{ vars.GH_AW_DEFAULT_MAX_TURNS || '' }}
- GH_AW_PHASE: detection
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_TIMEOUT_MINUTES: 20
- GH_AW_VERSION: v0.83.4
- GITHUB_API_URL: ${{ github.api_url }}
- GITHUB_AW: true
- GITHUB_COPILOT_INTEGRATION_ID: agentic-workflows
- GITHUB_HEAD_REF: ${{ github.head_ref }}
- GITHUB_REF_NAME: ${{ github.ref_name }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_STEP_SUMMARY: /tmp/gh-aw/agent-step-summary.md
- GITHUB_WORKSPACE: ${{ github.workspace }}
- GIT_AUTHOR_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_AUTHOR_NAME: github-actions[bot]
- GIT_COMMITTER_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_COMMITTER_NAME: github-actions[bot]
- RUNNER_TEMP: ${{ runner.temp }}
- S2STOKENS: true
- TRACEPARENT: ${{ env.GITHUB_AW_OTEL_TRACE_ID != '' && env.GITHUB_AW_OTEL_PARENT_SPAN_ID != '' && format('00-{0}-{1}-01', env.GITHUB_AW_OTEL_TRACE_ID, env.GITHUB_AW_OTEL_PARENT_SPAN_ID) || '' }}
- - name: Parse threat detection token usage for step summary
- id: parse_detection_token_usage
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_TOKEN_USAGE_SUMMARY_TITLE: Threat Detection Token Usage
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_token_usage.cjs');
- await main();
- - name: Upload threat detection log
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: detection
- path: /tmp/gh-aw/threat-detection/detection.log
- if-no-files-found: ignore
- - name: Parse and conclude threat detection
- id: detection_conclusion
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- RUN_DETECTION: ${{ steps.detection_guard.outputs.run_detection }}
- DETECTION_AGENTIC_EXECUTION_OUTCOME: ${{ steps.detection_agentic_execution.outcome }}
- GH_AW_DETECTION_CONTINUE_ON_ERROR: "true"
- with:
- script: |
- try {
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_threat_detection_results.cjs');
- await main();
- } catch (loadErr) {
- const continueOnError = process.env.GH_AW_DETECTION_CONTINUE_ON_ERROR !== 'false';
- const detectionExecutionFailed = process.env.DETECTION_AGENTIC_EXECUTION_OUTCOME === 'failure';
- const msg = 'ERR_SYSTEM: \u274C Unexpected error loading threat detection module: ' + (loadErr && loadErr.message ? loadErr.message : String(loadErr));
- core.error(msg);
- core.setOutput('reason', 'parse_error');
- if (continueOnError && !detectionExecutionFailed) {
- core.warning('\u26A0\uFE0F ' + msg);
- core.setOutput('conclusion', 'warning');
- core.setOutput('success', 'false');
- } else {
- core.setOutput('conclusion', 'failure');
- core.setOutput('success', 'false');
- core.setFailed(msg);
- }
- }
-
- safe_outputs:
- needs:
- - activation
- - agent
- - detection
- if: (!cancelled()) && needs.agent.result != 'skipped' && needs.detection.result == 'success'
- runs-on: ubuntu-slim
- permissions:
- contents: read
- discussions: write
- issues: write
- timeout-minutes: 45
- env:
- GH_AW_AGENT_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_AMBIENT_CONTEXT: ${{ needs.agent.outputs.ambient_context }}
- GH_AW_CALLER_WORKFLOW_ID: "${{ github.repository }}/tptp-benchmark"
- GH_AW_DETECTION_CONCLUSION: ${{ needs.detection.outputs.detection_conclusion }}
- GH_AW_DETECTION_REASON: ${{ needs.detection.outputs.detection_reason }}
- GH_AW_EFFECTIVE_TOKENS: ${{ needs.agent.outputs.effective_tokens }}
- GH_AW_ENGINE_ID: "copilot"
- GH_AW_ENGINE_MODEL: ${{ needs.agent.outputs.model }}
- GH_AW_ENGINE_VERSION: "1.0.75"
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_WORKFLOW_ID: "tptp-benchmark"
- GH_AW_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/tptp-benchmark.md"
- 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 }}
- create_discussion_error_count: ${{ steps.process_safe_outputs.outputs.create_discussion_error_count }}
- create_discussion_errors: ${{ steps.process_safe_outputs.outputs.create_discussion_errors }}
- process_safe_outputs_processed_count: ${{ steps.process_safe_outputs.outputs.processed_count }}
- process_safe_outputs_temporary_id_map: ${{ steps.process_safe_outputs.outputs.temporary_id_map }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "TPTP Front-End Benchmark"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/tptp-benchmark.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Configure GH_HOST for enterprise compatibility
- id: ghes-host-config
- shell: bash
- run: | # zizmor: ignore[github-env] - GITHUB_SERVER_URL is set by GitHub Actions, not user input.
- # Derive GH_HOST from GITHUB_SERVER_URL so the gh CLI targets the correct
- # GitHub instance (GHES/GHEC). On github.com this is a harmless no-op.
- GH_HOST="${GITHUB_SERVER_URL#https://}"
- GH_HOST="${GH_HOST#http://}"
- echo "GH_HOST=${GH_HOST}" >> "$GITHUB_ENV"
- - name: Process Safe Outputs
- id: process_safe_outputs
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_COMMENT_ID: ${{ needs.activation.outputs.comment_id }}
- 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,tptp.org,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com,www.googleapis.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\":336,\"fallback_to_issue\":true,\"max\":1,\"title_prefix\":\"[TPTP Benchmark] \"},\"create_report_incomplete_issue\":{},\"missing_data\":{},\"missing_tool\":{},\"noop\":{\"max\":1,\"report-as-issue\":\"false\"},\"report_incomplete\":{}}"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/process_safe_outputs.cjs');
- await main();
- - name: Upload Safe Outputs Items
- if: always()
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: safe-outputs-items
- path: |
- /tmp/gh-aw/safe-output-items.jsonl
- /tmp/gh-aw/temporary-id-map.json
- /tmp/gh-aw/process-safe-outputs.stdout.log
- /tmp/gh-aw/process-safe-outputs.stderr.log
- if-no-files-found: ignore
diff --git a/.github/workflows/tptp-benchmark.md b/.github/workflows/tptp-benchmark.md
deleted file mode 100644
index 134d0e7009..0000000000
--- a/.github/workflows/tptp-benchmark.md
+++ /dev/null
@@ -1,551 +0,0 @@
----
-description: >
- Weekly benchmark of Z3's TPTP front-end against 500 random TPTP problems.
- Downloads TPTP benchmarks from tptp.org, resolves axiom dependencies,
- skips large problems, runs each with a 5-second timeout, and posts a
- discrepancy/crash report as a GitHub discussion.
-
-on:
- schedule:
- - cron: "0 6 * * 1"
- workflow_dispatch:
-
-permissions:
- contents: read
- issues: read
- pull-requests: read
- copilot-requests: write
-
-network:
- allowed:
- - defaults
- - tptp.org
-
-tools:
- bash: true
- github:
- toolsets: [default]
-
-safe-outputs:
- report-failure-as-issue: false
- create-discussion:
- title-prefix: "[TPTP Benchmark] "
- category: "Agentic Workflows"
- close-older-discussions: true
- expires: 14d
- missing-tool:
- create-issue: true
- noop:
- report-as-issue: false
-
-timeout-minutes: 300
-
-steps:
- - name: Checkout repository
- uses: actions/checkout@v6.0.2
- with:
- persist-credentials: false
-
- - name: Install build dependencies
- run: |
- sudo apt-get update -y -q
- sudo apt-get install -y cmake ninja-build python3 wget curl bc
-
- - name: Build Z3
- run: |
- mkdir -p /tmp/z3-build
- cd /tmp/z3-build
- cmake "$GITHUB_WORKSPACE" \
- -G Ninja \
- -DCMAKE_BUILD_TYPE=Release \
- -DZ3_BUILD_TEST_EXECUTABLES=OFF
- ninja -j$(nproc) z3
- ./z3 --version
-
----
-
-# TPTP Front-End Benchmark
-
-## Job Description
-
-Your name is ${{ github.workflow }}. You are an expert testing engineer for the Z3 theorem prover. Your task is to:
-
-1. Verify the Z3 binary built by the pre-flight step is available
-2. Download the TPTP benchmark library from tptp.org
-3. Select 500 random small-to-medium problems (with their axiom dependencies)
-4. Run each problem through Z3's TPTP front-end with a 5-second timeout
-5. Compare Z3's output against the expected SZS status declared in each problem file
-6. Post a detailed report as a GitHub Discussion summarising discrepancies and crashes
-
-**Repository**: ${{ github.repository }}
-**Workspace**: ${{ github.workspace }}
-
-## Phase 1: Verify Z3 Binary
-
-Z3 was built by the workflow pre-flight step and is available at `/tmp/z3-build/z3`.
-Confirm the binary is present and functional:
-
-```bash
-/tmp/z3-build/z3 --version
-```
-
-If the binary is missing or returns an error, call the `noop` safe-output with a message describing the problem and stop.
-
-Once confirmed, call `noop` with `"Z3 binary verified. Downloading TPTP benchmark library — this may take a few minutes."` to keep the safe-output session alive.
-
-## Phase 2: Download the TPTP Problem Library
-
-Find the latest TPTP release and download the full archive.
-
-```bash
-# Find the latest TPTP distribution version by fetching the directory listing
-TPTP_DIST_URL="https://tptp.org/TPTP/Distribution/"
-LATEST_TGZ=$(curl -sL "$TPTP_DIST_URL" \
- | grep -oP 'TPTP-v[0-9]+\.[0-9]+\.[0-9]+\.tgz' \
- | sort -V | tail -1)
-
-if [ -z "$LATEST_TGZ" ]; then
- echo "ERROR: Could not determine latest TPTP version from $TPTP_DIST_URL"
- # Fall back to a known stable version
- LATEST_TGZ="TPTP-v9.0.0.tgz"
-fi
-
-echo "Downloading $LATEST_TGZ ..."
-mkdir -p /tmp/tptp_download
-wget -q --show-progress \
- "${TPTP_DIST_URL}${LATEST_TGZ}" \
- -O /tmp/tptp_download/tptp.tgz
-
-echo "Extracting TPTP library..."
-mkdir -p /tmp/tptp
-tar -xzf /tmp/tptp_download/tptp.tgz -C /tmp/tptp --strip-components=1 2>&1 | tail -5
-
-# Verify extraction
-if [ ! -d /tmp/tptp/Problems ] || [ ! -d /tmp/tptp/Axioms ]; then
- echo "ERROR: TPTP extraction failed — Problems/ or Axioms/ directory not found"
- ls /tmp/tptp/
- exit 1
-fi
-
-TPTP_ROOT=/tmp/tptp
-echo "TPTP library extracted to $TPTP_ROOT"
-echo "Problem domains available:"
-ls "$TPTP_ROOT/Problems/" | wc -l
-echo "Axiom files available:"
-ls "$TPTP_ROOT/Axioms/" | wc -l
-```
-
-If the download or extraction fails, call `noop` with the error details and stop.
-
-Call `noop` with `"TPTP library downloaded and extracted. Selecting 500 benchmark problems — filtering by size."` to keep the session alive.
-
-## Phase 3: Select 500 Benchmark Problems
-
-Filter out large problems and problems that depend on large axiom files, then take a random sample of 500.
-
-Save this script to `/tmp/select_benchmarks.py` and run it:
-
-```python
-#!/usr/bin/env python3
-"""
-Select 500 random TPTP problems that:
- - Have a known, conclusive expected status (Theorem, Unsatisfiable,
- CounterSatisfiable, Satisfiable) OR Unknown/Open status.
- - Are not "large" (problem file <= 50 KB).
- - Do not include any axiom file larger than 100 KB.
-"""
-import os
-import re
-import random
-import sys
-
-TPTP_ROOT = "/tmp/tptp"
-PROBLEMS_DIR = os.path.join(TPTP_ROOT, "Problems")
-AXIOMS_DIR = os.path.join(TPTP_ROOT, "Axioms")
-MAX_PROBLEM_SIZE = 50 * 1024 # 50 KB
-MAX_AXIOM_SIZE = 100 * 1024 # 100 KB
-SAMPLE_SIZE = 500
-OUTPUT_FILE = "/tmp/selected_benchmarks.txt"
-
-include_re = re.compile(r"include\s*\(\s*['\"]([^'\"]+)['\"]", re.IGNORECASE)
-status_re = re.compile(r"%\s*Status\s*:\s*(\S+)", re.IGNORECASE)
-
-def axiom_sizes_ok(problem_path):
- """Return True if all included axiom files exist and are <= MAX_AXIOM_SIZE."""
- try:
- with open(problem_path, encoding="utf-8", errors="replace") as f:
- content = f.read(4096) # header is in first few KB
- except OSError:
- return False
- for m in include_re.finditer(content):
- axiom_rel = m.group(1) # e.g. "Axioms/AGT001+0.ax"
- axiom_path = os.path.join(TPTP_ROOT, axiom_rel)
- if not os.path.exists(axiom_path):
- return False # axiom missing — skip
- if os.path.getsize(axiom_path) > MAX_AXIOM_SIZE:
- return False # axiom too large — skip
- return True
-
-candidates = []
-skipped_size = 0
-skipped_axiom = 0
-
-for domain in sorted(os.listdir(PROBLEMS_DIR)):
- domain_dir = os.path.join(PROBLEMS_DIR, domain)
- if not os.path.isdir(domain_dir):
- continue
- for fname in os.listdir(domain_dir):
- if not fname.endswith(".p"):
- continue
- fpath = os.path.join(domain_dir, fname)
- size = os.path.getsize(fpath)
- if size > MAX_PROBLEM_SIZE:
- skipped_size += 1
- continue
- if not axiom_sizes_ok(fpath):
- skipped_axiom += 1
- continue
- candidates.append(fpath)
-
-print(f"Total candidates (after filtering): {len(candidates)}", flush=True)
-print(f" Skipped — problem too large : {skipped_size}", flush=True)
-print(f" Skipped — axiom too large : {skipped_axiom}", flush=True)
-
-if len(candidates) == 0:
- print("ERROR: No suitable benchmark problems found.", file=sys.stderr)
- sys.exit(1)
-
-if len(candidates) > SAMPLE_SIZE:
- random.seed(42)
- selected = random.sample(candidates, SAMPLE_SIZE)
-else:
- selected = candidates
-
-selected.sort()
-with open(OUTPUT_FILE, "w") as f:
- f.write("\n".join(selected) + "\n")
-
-print(f"Selected {len(selected)} problems → {OUTPUT_FILE}", flush=True)
-```
-
-Run the script:
-
-```bash
-python3 /tmp/select_benchmarks.py
-SELECTED=$(wc -l < /tmp/selected_benchmarks.txt)
-echo "Benchmark set: $SELECTED problems"
-```
-
-If no problems are found, call `noop` with an error message and stop.
-
-Call `noop` with `"$SELECTED problems selected. Starting benchmark run with 5-second timeout per problem — this will take approximately $(( SELECTED * 7 / 60 )) minutes."` to keep the session alive.
-
-## Phase 4: Run Benchmarks
-
-Save the following script to `/tmp/run_tptp_benchmarks.sh`, make it executable, and run it.
-
-```bash
-#!/usr/bin/env bash
-set -euo pipefail
-
-Z3=/tmp/z3-build/z3
-TPTP_ROOT=/tmp/tptp
-TIMEOUT_HARD=8 # outer OS-level guard (seconds; 3 s beyond Z3's -T:5)
-Z3_TIMEOUT=5 # Z3 internal timeout: -T:N sets N-second limit (uppercase -T is seconds)
-
-RESULTS=/tmp/tptp_results.tsv
-PROBLEM_LIST=/tmp/selected_benchmarks.txt
-
-echo -e "file\texpected\tactual\ttime_s\tnotes" > "$RESULTS"
-
-# Helper: extract the expected SZS status from the TPTP problem header.
-get_expected_status() {
- local file="$1"
- # Look for lines like: "% Status : Theorem"
- grep -m1 -iP '%\s*Status\s*:\s*\K\S+' "$file" 2>/dev/null || echo "Unknown"
-}
-
-# Helper: run z3 on a single TPTP problem with timeout.
-run_benchmark() {
- local file="$1"
- local start end elapsed output exit_code verdict
-
- start=$(date +%s%3N) # milliseconds since epoch
- output=$(TPTP="$TPTP_ROOT" timeout "$TIMEOUT_HARD" \
- "$Z3" -tptp -T:"$Z3_TIMEOUT" "$file" 2>&1) || exit_code=$?
- exit_code=${exit_code:-0}
- end=$(date +%s%3N)
- elapsed=$(echo "scale=3; ($end - $start) / 1000" | bc)
-
- # Extract SZS status line from output
- szs_line=$(echo "$output" | grep -m1 "% SZS status" || true)
-
- if [ -n "$szs_line" ]; then
- # Parse the status keyword (e.g. "Theorem", "CounterSatisfiable", "GaveUp")
- verdict=$(echo "$szs_line" | grep -oP '% SZS status \K\S+' || echo "Unknown")
- elif [ "$exit_code" -eq 124 ]; then
- verdict="Timeout"
- elif [ "$exit_code" -ne 0 ]; then
- verdict="Crash"
- else
- verdict="NoOutput"
- fi
-
- echo "$verdict $elapsed"
-}
-
-COUNTER=0
-TOTAL=$(wc -l < "$PROBLEM_LIST")
-
-while IFS= read -r problem_file; do
- COUNTER=$((COUNTER + 1))
-
- expected=$(get_expected_status "$problem_file")
- result_line=$(run_benchmark "$problem_file")
- actual=$(echo "$result_line" | cut -d' ' -f1)
- elapsed=$(echo "$result_line" | cut -d' ' -f2)
- fname=$(basename "$problem_file")
-
- # Classify notes
- notes=""
- # Soundness discrepancy: both answers are conclusive but conflict
- conclusive_expected=false
- conclusive_actual=false
- case "$expected" in
- Theorem|Unsatisfiable) conclusive_expected=true ;;
- Satisfiable|CounterSatisfiable) conclusive_expected=true ;;
- esac
- case "$actual" in
- Theorem|Unsatisfiable) conclusive_actual=true ;;
- Satisfiable|CounterSatisfiable) conclusive_actual=true ;;
- esac
-
- if $conclusive_expected && $conclusive_actual; then
- # Map expected to the Z3 output equivalents for comparison
- # Theorem (has-conjecture unsat) matches "Theorem"
- # Unsatisfiable (no-conjecture unsat) matches "Unsatisfiable"
- # Satisfiable (no-conjecture sat) matches "Satisfiable"
- # CounterSatisfiable (has-conjecture sat) matches "CounterSatisfiable"
- if [ "$expected" != "$actual" ]; then
- # Check for sat/unsat polarity conflict
- sat_expected=false; sat_actual=false
- case "$expected" in Satisfiable|CounterSatisfiable) sat_expected=true ;; esac
- case "$actual" in Satisfiable|CounterSatisfiable) sat_actual=true ;; esac
- if [ "$sat_expected" != "$sat_actual" ]; then
- notes="SOUNDNESS_ERROR"
- else
- notes="STATUS_MISMATCH"
- fi
- fi
- fi
-
- if [ "$actual" = "Crash" ]; then
- notes="CRASH"
- fi
-
- echo -e "$fname\t$expected\t$actual\t$elapsed\t$notes" >> "$RESULTS"
-
- if [ -n "$notes" ]; then
- echo "[$COUNTER/$TOTAL] $fname expected=$expected actual=$actual time=${elapsed}s *** $notes ***"
- elif [ $((COUNTER % 50)) -eq 0 ]; then
- echo "[$COUNTER/$TOTAL] Progress checkpoint last=$fname actual=$actual time=${elapsed}s"
- fi
-
-done < "$PROBLEM_LIST"
-
-echo "Benchmark run complete: $COUNTER problems processed. Results → $RESULTS"
-```
-
-Run it:
-
-```bash
-chmod +x /tmp/run_tptp_benchmarks.sh
-/tmp/run_tptp_benchmarks.sh
-```
-
-Do not skip any file in the list.
-
-## Phase 5: Analyze Results
-
-Save the following script to `/tmp/analyze_tptp.py` and run it:
-
-```python
-#!/usr/bin/env python3
-"""Compute summary statistics from the TPTP benchmark TSV."""
-import csv
-
-RESULTS_FILE = "/tmp/tptp_results.tsv"
-
-rows = []
-with open(RESULTS_FILE, newline="") as f:
- reader = csv.DictReader(f, delimiter="\t")
- for row in reader:
- rows.append(row)
-
-total = len(rows)
-
-# Verdict counts
-from collections import Counter, defaultdict
-actual_counts = Counter(r["actual"] for r in rows)
-expected_counts = Counter(r["expected"] for r in rows)
-
-# Flagged rows
-soundness_errors = [r for r in rows if r["notes"] == "SOUNDNESS_ERROR"]
-status_mismatches = [r for r in rows if r["notes"] == "STATUS_MISMATCH"]
-crashes = [r for r in rows if r["notes"] == "CRASH"]
-timeouts = [r for r in rows if r["actual"] == "Timeout"]
-gave_up = [r for r in rows if r["actual"] == "GaveUp"]
-
-# Solved correctly (expected matches actual for conclusive verdicts)
-conclusive_expected = {"Theorem", "Unsatisfiable", "Satisfiable", "CounterSatisfiable"}
-correct = [r for r in rows
- if r["expected"] in conclusive_expected
- and r["actual"] == r["expected"]]
-
-print(f"TOTAL={total}")
-print(f"CORRECT={len(correct)}")
-print(f"TIMEOUTS={len(timeouts)}")
-print(f"GAVE_UP={len(gave_up)}")
-print(f"CRASHES={len(crashes)}")
-print(f"SOUNDNESS_ERRORS={len(soundness_errors)}")
-print(f"STATUS_MISMATCHES={len(status_mismatches)}")
-
-print("\n--- Actual verdict breakdown ---")
-for v, c in sorted(actual_counts.items()):
- print(f" {v}: {c}")
-
-print("\n--- Expected status breakdown ---")
-for v, c in sorted(expected_counts.items()):
- print(f" {v}: {c}")
-
-if soundness_errors:
- print(f"\n--- SOUNDNESS ERRORS ({len(soundness_errors)}) ---")
- for r in soundness_errors:
- print(f" {r['file']} expected={r['expected']} actual={r['actual']}")
-
-if crashes:
- print(f"\n--- CRASHES ({len(crashes)}) ---")
- for r in crashes:
- print(f" {r['file']} expected={r['expected']}")
-
-if status_mismatches:
- print(f"\n--- STATUS MISMATCHES ({len(status_mismatches)}) ---")
- for r in status_mismatches[:20]:
- print(f" {r['file']} expected={r['expected']} actual={r['actual']}")
-```
-
-Run the analysis:
-
-```bash
-python3 /tmp/analyze_tptp.py
-```
-
-## Phase 6: Generate and Post the Discussion Report
-
-Read the TSV at `/tmp/tptp_results.tsv` and the analysis output, then compose a Markdown report and call `create_discussion`.
-
-The report should use `###` or lower for all headers (never `#` or `##`). Use collapsible `` sections for large tables.
-
-Use this structure:
-
-```markdown
-**Date**:
-**Branch**: master
-**Commit**: `` (run `git rev-parse --short HEAD` in ${{ github.workspace }} to get the SHA)
-**Workflow Run**: [${{ github.run_id }}](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }})
-**TPTP version**:
-**Problems benchmarked**: (random sample, timeout 5 s per problem)
-
----
-
-### Summary
-
-| Metric | Count |
-|--------|-------|
-| Total problems run | N |
-| Correct (expected = actual) | N |
-| Timeouts | N |
-| GaveUp (within time budget) | N |
-| Crashes / errors | N |
-| Soundness errors (sat↔unsat conflict) | N |
-| Status mismatches (Theorem vs Unsatisfiable etc.) | N |
-
-### Expected Status Distribution
-
-| Expected Status | Count |
-|----------------|-------|
-| Theorem | N |
-| Unsatisfiable | N |
-| Satisfiable | N |
-| CounterSatisfiable | N |
-| Unknown / Open | N |
-
----
-
-### ⚠️ Critical: Soundness Errors
-
-[List ALL files where Z3 returned a conclusive answer that contradicts the expected answer
-(e.g., expected Theorem but got CounterSatisfiable). If none, write "None detected."]
-
-### 💥 Crashes
-
-[List ALL files where Z3 crashed (non-zero exit, no SZS output, not a timeout).
-Include filename and expected status. If none, write "None detected."]
-
-### Status Mismatches
-
-[Files where both answers are conclusive but differ in Theorem vs Unsatisfiable polarity
-(e.g., expected Theorem but actual Unsatisfiable). These may indicate conjecture-handling
-differences rather than soundness bugs. If none, write "None detected."]
-
----
-
-
-View all Timeouts (problems where Z3 exceeded the 5-second limit)
-
-| # | File | Expected Status |
-|---|------|----------------|
-[First 100 timeout rows]
-
-
-
-
-View full per-problem results table
-
-| # | File | Expected | Actual | Time (s) | Notes |
-|---|------|----------|--------|----------|-------|
-[All rows, or first 500 if over limit]
-
-
-
----
-
-### Recommendations
-
-[Based on the findings, list actionable items. E.g.: investigate soundness errors,
-file crash bugs, note domains where Z3 consistently times out.]
-```
-
-Post the discussion using the `create_discussion` safe output. The title should be
-`[TPTP Benchmark] master — `.
-
-## Safe Output Guarantee
-
-You **MUST** call either `create_discussion` or `noop` before the workflow ends:
-
-- **Full success**: Call `create_discussion` with the complete report.
-- **Partial results** (some problems ran): Call `create_discussion` with whatever results are available and a note about incomplete execution.
-- **Download failure**: Call `noop` with the download error details.
-- **No problems selected**: Call `noop` explaining why no problems were found.
-- **Binary missing**: If `/tmp/z3-build/z3` is unexpectedly absent, call `noop` with that detail and stop.
-
-## Important Notes
-
-- **Build failure handling**: Z3 was built before the agent loaded. If the binary is missing or non-functional, call `noop` with the error and stop.
-- **TPTP environment variable**: Set `TPTP=/tmp/tptp` when invoking `z3 -tptp` so that `include()` directives in problem files resolve correctly against the downloaded Axioms directory.
-- **Timeout detection**: Use `timeout 8` as the outer OS-level guard (3 seconds beyond Z3's `-T:5`) to allow Z3 to exit cleanly before the shell kills it. If the exit code from `timeout` is 124, record the verdict as `Timeout`.
-- **Crash detection**: A crash is a non-zero exit code with no `% SZS status` line in the output and no timeout. Record it separately from `GaveUp`.
-- **SZS status semantics**: Z3 outputs `Theorem` (not `Unsatisfiable`) when it proves a conjecture; `CounterSatisfiable` (not `Satisfiable`) when it finds a counterexample to a conjecture. A status mismatch between `Theorem` and `Unsatisfiable` for the same problem may be innocuous and depends on whether the problem file uses a conjecture formula.
-- **Report soundness bugs prominently**: Any case where the polarity of the answer conflicts (expected Theorem/Unsatisfiable but got CounterSatisfiable/Satisfiable, or vice versa) is a potential soundness bug and must be highlighted as critical.
-- **Keep progress log**: Print a line for every flagged result and every 50th problem so the workflow log shows progress.
-- **Close older discussions**: Configured via `close-older-discussions: true`. Only the latest weekly report remains open.
diff --git a/.github/workflows/zipt-code-reviewer.lock.yml b/.github/workflows/zipt-code-reviewer.lock.yml
deleted file mode 100644
index 2e8039a13d..0000000000
--- a/.github/workflows/zipt-code-reviewer.lock.yml
+++ /dev/null
@@ -1,1706 +0,0 @@
-# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"90eb42871609810a52a4978e4b7466c07df8df2436b147dc3c7a90af001cae8b","body_hash":"8d42996a836cf572c7768349b6475e3d79f2631d070a31d31ac4f7522d617e33","compiler_version":"v0.83.4","strict":true,"agent_id":"copilot","engine_versions":{"copilot":"1.0.75"}}
-# gh-aw-manifest: {"version":1,"secrets":["COPILOT_GITHUB_TOKEN","GH_AW_GITHUB_MCP_SERVER_TOKEN","GH_AW_GITHUB_TOKEN","GITHUB_TOKEN"],"actions":[{"repo":"actions/cache/restore","sha":"55cc8345863c7cc4c66a329aec7e433d2d1c52a9","version":"v6.1.0"},{"repo":"actions/cache/save","sha":"55cc8345863c7cc4c66a329aec7e433d2d1c52a9","version":"v6.1.0"},{"repo":"actions/checkout","sha":"3d3c42e5aac5ba805825da76410c181273ba90b1","version":"v7.0.1"},{"repo":"actions/checkout","sha":"de0fac2e4500dabe0009e67214ff5f5447ce83dd","version":"v6.0.2"},{"repo":"actions/download-artifact","sha":"3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c","version":"v8.0.1"},{"repo":"actions/github-script","sha":"3a2844b7e9c422d3c10d287c895573f7108da1b3","version":"v9.0.0"},{"repo":"actions/setup-node","sha":"820762786026740c76f36085b0efc47a31fe5020","version":"v7.0.0"},{"repo":"actions/upload-artifact","sha":"043fb46d1a93c77aae656e7c1c64a875d1fc6a0a","version":"v7.0.1"},{"repo":"github/gh-aw-actions/setup","sha":"v0.83.4","version":"v0.83.4"}],"containers":[{"image":"ghcr.io/github/gh-aw-firewall/agent:0.27.42","digest":"sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b","pinned_image":"ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b"},{"image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42","digest":"sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607","pinned_image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607"},{"image":"ghcr.io/github/gh-aw-firewall/squid:0.27.42","digest":"sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0","pinned_image":"ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0"},{"image":"ghcr.io/github/gh-aw-mcpg:v0.4.6","digest":"sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c","pinned_image":"ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c"},{"image":"ghcr.io/github/gh-aw-node","digest":"sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748","pinned_image":"ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748"},{"image":"ghcr.io/github/github-mcp-server:v1.7.0","digest":"sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308","pinned_image":"ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308"}]}
-# This file was automatically generated by gh-aw (v0.83.4). DO NOT EDIT. To debug this workflow, load the skill at https://github.com/github/gh-aw/blob/main/debug.md
-#
-# ___ _ _
-# / _ \ | | (_)
-# | |_| | __ _ ___ _ __ | |_ _ ___
-# | _ |/ _` |/ _ \ '_ \| __| |/ __|
-# | | | | (_| | __/ | | | |_| | (__
-# \_| |_/\__, |\___|_| |_|\__|_|\___|
-# __/ |
-# _ _ |___/
-# | | | | / _| |
-# | | | | ___ _ __ _ __| |_| | _____ ____
-# | |/\| |/ _ \ '__| |/ /| _| |/ _ \ \ /\ / / ___|
-# \ /\ / (_) | | | | ( | | | | (_) \ V V /\__ \
-# \/ \/ \___/|_| |_|\_\|_| |_|\___/ \_/\_/ |___/
-#
-#
-# To update this file, edit the corresponding .md file and run:
-# gh aw compile
-# Not all edits will cause changes to this file.
-#
-# For more information: https://github.github.com/gh-aw/introduction/overview/
-#
-# Reviews Z3 string/sequence graph implementation (euf_sgraph, euf_seq_plugin, src/smt/seq) by comparing with the ZIPT reference implementation and reporting improvements as git diffs in GitHub issues
-#
-# Secrets used:
-# - COPILOT_GITHUB_TOKEN
-# - GH_AW_GITHUB_MCP_SERVER_TOKEN
-# - GH_AW_GITHUB_TOKEN
-# - GITHUB_TOKEN
-#
-# Custom actions used:
-# - actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-# - actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
-# - actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-# - actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
-# - actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
-# - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
-# - actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 (source v9)
-# - actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
-# - actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
-# - github/gh-aw-actions/setup@v0.83.4
-#
-# Container images used:
-# - ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b
-# - ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607
-# - ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0
-# - ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c
-# - ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748
-# - ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308
-
-name: "ZIPT Code Reviewer"
-on:
- schedule:
- - cron: "34 6 * * *" # Friendly format: daily (scattered)
- workflow_dispatch:
- inputs:
- aw_context:
- default: ""
- description: "Agent caller context (used internally by Agentic Workflows)."
- required: false
- type: string
-
-permissions: {}
-
-concurrency:
- group: "gh-aw-${{ github.workflow }}"
-
-run-name: "ZIPT Code Reviewer"
-
-jobs:
- activation:
- runs-on: ubuntu-slim
- permissions:
- actions: read
- contents: read
- env:
- GH_AW_MAX_DAILY_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_DAILY_AI_CREDITS || '5000' }}
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- comment_id: ""
- comment_repo: ""
- daily_ai_credits_exceeded: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_exceeded == 'true' }}
- daily_ai_credits_threshold: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_threshold || '' }}
- daily_ai_credits_total_effective_tokens: ${{ steps.daily-effective-workflow-guardrail.outputs.daily_ai_credits_total_effective_tokens || '' }}
- engine_id: ${{ steps.generate_aw_info.outputs.engine_id }}
- lockdown_check_failed: ${{ steps.generate_aw_info.outputs.lockdown_check_failed == 'true' }}
- model: ${{ steps.generate_aw_info.outputs.model }}
- oauth_token_check_failed: ${{ steps.check-oauth-tokens.outputs.oauth_token_check_failed == 'true' }}
- secret_verification_result: ${{ steps.validate-secret.outputs.verification_result }}
- setup-parent-span-id: ${{ steps.setup.outputs.parent-span-id || steps.setup.outputs.span-id }}
- setup-span-id: ${{ steps.setup.outputs.span-id }}
- setup-trace-id: ${{ steps.setup.outputs.trace-id }}
- stale_lock_file_failed: ${{ steps.check-lock-file.outputs.stale_lock_file_failed == 'true' }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- safe-output-artifact-client: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/zipt-code-reviewer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Generate agentic run info
- id: generate_aw_info
- env:
- GH_AW_INFO_ENGINE_ID: "copilot"
- GH_AW_INFO_ENGINE_NAME: "GitHub Copilot CLI"
- GH_AW_INFO_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AGENT_VERSION: "1.0.75"
- GH_AW_INFO_CLI_VERSION: "v0.83.4"
- GH_AW_INFO_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_INFO_EXPERIMENTAL: "false"
- GH_AW_INFO_SUPPORTS_TOOLS_ALLOWLIST: "true"
- GH_AW_INFO_STAGED: "false"
- GH_AW_INFO_ALLOWED_DOMAINS: '["defaults","github"]'
- GH_AW_INFO_FIREWALL_ENABLED: "true"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_AWMG_VERSION: ""
- GH_AW_INFO_FIREWALL_TYPE: "squid"
- GH_AW_COMPILED_STRICT: "true"
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/generate_aw_info.cjs');
- await main(core, context);
- - name: Restore daily AIC usage cache
- id: restore-daily-aic-cache
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- continue-on-error: true
- uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-ziptcodereviewer-${{ github.run_id }}
- restore-keys: agentic-workflow-usage-ziptcodereviewer-
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Restore daily AIC usage cache (artifact fallback)
- id: restore-daily-aic-cache-fallback
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_RESTORE_DAILY_AIC_CACHE_HIT: ${{ steps.restore-daily-aic-cache.outputs.cache-hit }}
- GH_AW_RESTORE_DAILY_AIC_CACHE_MATCHED_KEY: ${{ steps.restore-daily-aic-cache.outputs.cache-matched-key }}
- with:
- github-token: ${{ secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/restore_aic_usage_cache_fallback.cjs');
- await main();
- - name: Check daily workflow token guardrail
- id: daily-effective-workflow-guardrail
- if: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }}
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_WORKFLOW_ID: "zipt-code-reviewer"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_WORKFLOW_DISPATCH_AW_CONTEXT: ${{ github.event.inputs.aw_context || '' }}
- GH_AW_HAS_SLASH_COMMAND: "false"
- GH_AW_HAS_LABEL_COMMAND: "false"
- GH_AW_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- GH_AW_MAX_DAILY_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_DAILY_AI_CREDITS || '5000' }}
- with:
- github-token: ${{ secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_daily_aic_workflow_guardrail.cjs');
- await main();
- - name: Validate COPILOT_GITHUB_TOKEN secret
- id: validate-secret
- run: bash "${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
- env:
- COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- - name: Check for OAuth tokens
- id: check-oauth-tokens
- run: bash "${RUNNER_TEMP}/gh-aw/actions/check_oauth_tokens.sh"
- env:
- COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }}
- - name: Checkout .github and .agents folders
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- with:
- persist-credentials: false
- sparse-checkout: |
- .github
- .agents
- .antigravity
- .claude
- .codex
- .gemini
- .opencode
- .pi
- sparse-checkout-cone-mode: true
- fetch-depth: 1
- - name: Save agent config folders for base branch restoration
- env:
- GH_AW_AGENT_FOLDERS: ".agents .antigravity .claude .codex .gemini .github .opencode .pi"
- GH_AW_AGENT_FILES: "AGENTS.md ANTIGRAVITY.md CLAUDE.md GEMINI.md PI.md opencode.jsonc"
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/save_base_github_folders.sh"
- - name: Check workflow lock file
- id: check-lock-file
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_WORKFLOW_FILE: "zipt-code-reviewer.lock.yml"
- GH_AW_CONTEXT_WORKFLOW_REF: "${{ github.workflow_ref }}"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_workflow_timestamp_api.cjs');
- await main();
- - name: Check compile-agentic version
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_COMPILED_VERSION: "v0.83.4"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/check_version_updates.cjs');
- await main();
- - name: Log runtime features
- if: ${{ contains(toJSON(vars), '"GH_AW_RUNTIME_FEATURES":') }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/log_runtime_features_summary.sh"
- - name: Create prompt with built-in context
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_SAFE_OUTPUTS: ${{ runner.temp }}/gh-aw/safeoutputs/outputs.jsonl
- GH_AW_EXPR_1A3A194A: ${{ github.event.discussion.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'discussion' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_463A214A: ${{ github.event.pull_request.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'pull_request' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_802A9F6A: ${{ github.event.issue.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'issue' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_FF1D34CE: ${{ github.event.comment.id || fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').comment_id }}
- GH_AW_GITHUB_ACTOR: ${{ github.actor }}
- GH_AW_GITHUB_REPOSITORY: ${{ github.repository }}
- GH_AW_GITHUB_RUN_ID: ${{ github.run_id }}
- GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
- # poutine:ignore untrusted_checkout_exec
- run: |
- bash "${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh"
- {
- cat << 'GH_AW_PROMPT_b225e3779bc1701a_EOF'
-
- GH_AW_PROMPT_b225e3779bc1701a_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/cache_memory_prompt.md"
- cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md"
- cat << 'GH_AW_PROMPT_b225e3779bc1701a_EOF'
-
- Tools: create_issue(max:3), missing_tool, missing_data, noop
-
- GH_AW_PROMPT_b225e3779bc1701a_EOF
- cat "${RUNNER_TEMP}/gh-aw/prompts/mcp_cli_tools_prompt.md"
- cat << 'GH_AW_PROMPT_b225e3779bc1701a_EOF'
-
- The following GitHub context information is available for this workflow:
- {{#if github.actor}}
- - **actor**: __GH_AW_GITHUB_ACTOR__
- {{/if}}
- {{#if github.repository}}
- - **repository**: __GH_AW_GITHUB_REPOSITORY__
- {{/if}}
- {{#if github.workspace}}
- - **workspace**: __GH_AW_GITHUB_WORKSPACE__
- {{/if}}
- {{#if github.event.issue.number || (github.aw.context.item_type == 'issue' && github.aw.context.item_number)}}
- - **issue-number**: #__GH_AW_EXPR_802A9F6A__
- {{/if}}
- {{#if github.event.discussion.number || (github.aw.context.item_type == 'discussion' && github.aw.context.item_number)}}
- - **discussion-number**: #__GH_AW_EXPR_1A3A194A__
- {{/if}}
- {{#if github.event.pull_request.number || (github.aw.context.item_type == 'pull_request' && github.aw.context.item_number)}}
- - **pull-request-number**: #__GH_AW_EXPR_463A214A__
- {{/if}}
- {{#if github.event.comment.id || github.aw.context.comment_id}}
- - **comment-id**: __GH_AW_EXPR_FF1D34CE__
- {{/if}}
- {{#if github.run_id}}
- - **workflow-run-id**: __GH_AW_GITHUB_RUN_ID__
- {{/if}}
-
-
- GH_AW_PROMPT_b225e3779bc1701a_EOF
- cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md"
- cat << 'GH_AW_PROMPT_b225e3779bc1701a_EOF'
-
- {{#runtime-import .github/workflows/zipt-code-reviewer.md}}
- GH_AW_PROMPT_b225e3779bc1701a_EOF
- } > "$GH_AW_PROMPT"
- - name: Interpolate variables and render templates
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_ENGINE_ID: "copilot"
- 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');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/interpolate_prompt.cjs');
- await main();
- - name: Substitute placeholders
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_ALLOWED_EXTENSIONS: ''
- GH_AW_CACHE_DESCRIPTION: ''
- GH_AW_CACHE_DIR: '/tmp/gh-aw/cache-memory/'
- GH_AW_EXPR_1A3A194A: ${{ github.event.discussion.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'discussion' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_463A214A: ${{ github.event.pull_request.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'pull_request' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_802A9F6A: ${{ github.event.issue.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'issue' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }}
- GH_AW_EXPR_FF1D34CE: ${{ github.event.comment.id || fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').comment_id }}
- GH_AW_GITHUB_ACTOR: ${{ github.actor }}
- GH_AW_GITHUB_REPOSITORY: ${{ github.repository }}
- GH_AW_GITHUB_RUN_ID: ${{ github.run_id }}
- GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }}
- GH_AW_MCP_CLI_SERVERS_LIST: "- `github` — run `github --help` to see available tools\n- `safeoutputs` — run `safeoutputs --help` to see available tools"
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
-
- const substitutePlaceholders = require('${{ runner.temp }}/gh-aw/actions/substitute_placeholders.cjs');
-
- // Call the substitution function
- return await substitutePlaceholders({
- file: process.env.GH_AW_PROMPT,
- substitutions: {
- GH_AW_ALLOWED_EXTENSIONS: process.env.GH_AW_ALLOWED_EXTENSIONS,
- GH_AW_CACHE_DESCRIPTION: process.env.GH_AW_CACHE_DESCRIPTION,
- GH_AW_CACHE_DIR: process.env.GH_AW_CACHE_DIR,
- GH_AW_EXPR_1A3A194A: process.env.GH_AW_EXPR_1A3A194A,
- GH_AW_EXPR_463A214A: process.env.GH_AW_EXPR_463A214A,
- GH_AW_EXPR_802A9F6A: process.env.GH_AW_EXPR_802A9F6A,
- GH_AW_EXPR_FF1D34CE: process.env.GH_AW_EXPR_FF1D34CE,
- GH_AW_GITHUB_ACTOR: process.env.GH_AW_GITHUB_ACTOR,
- GH_AW_GITHUB_REPOSITORY: process.env.GH_AW_GITHUB_REPOSITORY,
- GH_AW_GITHUB_RUN_ID: process.env.GH_AW_GITHUB_RUN_ID,
- GH_AW_GITHUB_WORKSPACE: process.env.GH_AW_GITHUB_WORKSPACE,
- GH_AW_MCP_CLI_SERVERS_LIST: process.env.GH_AW_MCP_CLI_SERVERS_LIST
- }
- });
- - name: Validate prompt placeholders
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/validate_prompt_placeholders.sh"
- - name: Print prompt
- env:
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- # poutine:ignore untrusted_checkout_exec
- run: bash "${RUNNER_TEMP}/gh-aw/actions/print_prompt_summary.sh"
- - name: Upload activation artifact
- if: success()
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: activation
- include-hidden-files: true
- path: |
- /tmp/gh-aw/aw_info.json
- /tmp/gh-aw/models.json
- /tmp/gh-aw/aw-prompts/prompt.txt
- /tmp/gh-aw/aw-prompts/prompt-template.txt
- /tmp/gh-aw/aw-prompts/prompt-import-tree.json
- /tmp/gh-aw/github_rate_limits.jsonl
- /tmp/gh-aw/base
- /tmp/gh-aw/.github/agents
- /tmp/gh-aw/.github/skills
- if-no-files-found: ignore
- retention-days: 1
-
- agent:
- needs: activation
- if: needs.activation.outputs.daily_ai_credits_exceeded != 'true'
- runs-on: ubuntu-latest
- permissions: read-all
- concurrency:
- group: "gh-aw-copilot-${{ github.workflow }}"
- queue: max
- env:
- DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
- GH_AW_ASSETS_ALLOWED_EXTS: ""
- GH_AW_ASSETS_BRANCH: ""
- GH_AW_ASSETS_MAX_SIZE_KB: 0
- GH_AW_MCP_LOG_DIR: /tmp/gh-aw/mcp-logs/safeoutputs
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- GH_AW_WORKFLOW_ID_SANITIZED: ziptcodereviewer
- outputs:
- agentic_engine_timeout: ${{ steps.detect-agent-errors.outputs.agentic_engine_timeout || 'false' }}
- ai_credits_rate_limit_error: ${{ steps.parse-mcp-gateway.outputs.ai_credits_rate_limit_error || 'false' }}
- aic: ${{ steps.parse-mcp-gateway.outputs.aic }}
- ambient_context: ${{ steps.parse-mcp-gateway.outputs.ambient_context }}
- cache_memory_restore_0_cache_hit: ${{ steps.restore_cache_memory_0.outputs.cache-hit || 'false' }}
- cache_memory_restore_0_matched_key: ${{ steps.restore_cache_memory_0.outputs.cache-matched-key || '' }}
- checkout_pr_success: ${{ steps.checkout-pr.outputs.checkout_pr_success || 'true' }}
- effective_tokens: ${{ steps.parse-mcp-gateway.outputs.effective_tokens }}
- has_patch: ${{ steps.collect_output.outputs.has_patch }}
- http_400_response_error: ${{ steps.detect-agent-errors.outputs.http_400_response_error || 'false' }}
- inference_access_error: ${{ steps.detect-agent-errors.outputs.inference_access_error || 'false' }}
- invocation_cap_exceeded: ${{ steps.detect-agent-errors.outputs.invocation_cap_exceeded || 'false' }}
- mcp_policy_error: ${{ steps.detect-agent-errors.outputs.mcp_policy_error || 'false' }}
- model: ${{ needs.activation.outputs.model }}
- model_not_supported_error: ${{ steps.detect-agent-errors.outputs.model_not_supported_error || 'false' }}
- output: ${{ steps.collect_output.outputs.output }}
- output_types: ${{ steps.collect_output.outputs.output_types }}
- setup-parent-span-id: ${{ steps.setup.outputs.parent-span-id || steps.setup.outputs.span-id }}
- setup-span-id: ${{ steps.setup.outputs.span-id }}
- setup-trace-id: ${{ steps.setup.outputs.trace-id }}
- unknown_model_ai_credits: ${{ steps.parse-mcp-gateway.outputs.unknown_model_ai_credits || 'false' }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/zipt-code-reviewer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Set runtime paths
- id: set-runtime-paths
- run: |
- {
- echo "GH_AW_SAFE_OUTPUTS=${RUNNER_TEMP}/gh-aw/safeoutputs/outputs.jsonl"
- echo "GH_AW_SAFE_OUTPUTS_CONFIG_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/config.json"
- echo "GH_AW_SAFE_OUTPUTS_TOOLS_PATH=${RUNNER_TEMP}/gh-aw/safeoutputs/tools.json"
- } >> "$GITHUB_OUTPUT"
- - 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: ${{ github.token }}
- - name: Download activation artifact
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: activation
- path: /tmp/gh-aw
- # Cache memory file share configuration from frontmatter processed below
- - name: Create cache-memory directory
- run: bash "${RUNNER_TEMP}/gh-aw/actions/create_cache_memory_dir.sh"
- - name: Restore cache-memory file share data
- id: restore_cache_memory_0
- uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}-${{ github.run_id }}
- path: /tmp/gh-aw/cache-memory
- restore-keys: |
- memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}-
- - name: Setup cache-memory git repository
- env:
- GH_AW_CACHE_DIR: /tmp/gh-aw/cache-memory
- GH_AW_MIN_INTEGRITY: none
- run: bash "${RUNNER_TEMP}/gh-aw/actions/setup_cache_memory_git.sh"
- - name: Checkout repository
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- with:
- persist-credentials: false
-
- - name: Configure Git credentials
- env:
- GITHUB_REPOSITORY: ${{ github.repository }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_TOKEN: ${{ github.token }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/configure_git_credentials.sh"
- - name: Checkout PR branch
- id: checkout-pr
- if: |
- github.event.pull_request || github.event.issue.pull_request || github.event_name == 'workflow_dispatch' && fromJSON(github.event.inputs.aw_context || '{}').item_type == 'pull_request'
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- 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');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/checkout_pr_branch.cjs');
- await main();
- - name: Install GitHub Copilot CLI
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh" 1.0.75
- env:
- GH_HOST: github.com
- - name: Install AWF binary
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.27.42 --rootless
- - name: Determine automatic lockdown mode for GitHub MCP Server
- id: determine-automatic-lockdown
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 (source v9)
- env:
- GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- 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');
- await determineAutomaticLockdown(github, context, core);
- - name: Restore agent config folders from base branch
- if: steps.checkout-pr.outcome == 'success'
- env:
- GH_AW_AGENT_FOLDERS: ".agents .antigravity .claude .codex .gemini .github .opencode .pi"
- GH_AW_AGENT_FILES: "AGENTS.md ANTIGRAVITY.md CLAUDE.md GEMINI.md PI.md opencode.jsonc"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_base_github_folders.sh"
- - name: Restore inline sub-agents from activation artifact
- env:
- GH_AW_SUB_AGENT_DIR: ".github/agents"
- GH_AW_SUB_AGENT_EXT: ".agent.md"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_inline_sub_agents.sh"
- - name: Restore inline skills from activation artifact
- env:
- GH_AW_SKILL_DIR: ".github/skills"
- run: bash "${RUNNER_TEMP}/gh-aw/actions/restore_inline_skills.sh"
- - name: Download container images
- run: bash "${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh" ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607 ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0 ghcr.io/github/gh-aw-mcpg:v0.4.6@sha256:fecabec51bbc41f2ad61076d6bcd9a36ef23b142e672a444e054d37fc29de93c ghcr.io/github/gh-aw-node@sha256:a8082161d7dceda14b68f32eb39d0eaa96b825d07f5895b096afab9d9e0c7748 ghcr.io/github/github-mcp-server:v1.7.0@sha256:c491ffdf6f4c85cb5397021bc655edb8ab825c6f5f568e7597d77a1bd7c4d308
- - name: Generate Safe Outputs Config
- run: |
- mkdir -p "${RUNNER_TEMP}/gh-aw/safeoutputs"
- mkdir -p /tmp/gh-aw/safeoutputs
- mkdir -p /tmp/gh-aw/mcp-logs/safeoutputs
- cat > "${RUNNER_TEMP}/gh-aw/safeoutputs/config.json" << 'GH_AW_SAFE_OUTPUTS_CONFIG_f579d8ba423d2ca7_EOF'
- {"create_issue":{"labels":["code-quality","automated","string-solver"],"max":3,"title_prefix":"[zipt-review] "},"create_report_incomplete_issue":{},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"false"},"report_incomplete":{}}
- GH_AW_SAFE_OUTPUTS_CONFIG_f579d8ba423d2ca7_EOF
- - name: Generate Safe Outputs Tools
- env:
- GH_AW_TOOLS_META_JSON: |
- {
- "description_suffixes": {
- "create_issue": " CONSTRAINTS: Maximum 3 issue(s) can be created. Title will be prefixed with \"[zipt-review] \". Labels [\"code-quality\" \"automated\" \"string-solver\"] will be automatically added."
- },
- "repo_params": {},
- "dynamic_tools": []
- }
- GH_AW_VALIDATION_JSON: |
- {
- "create_issue": {
- "defaultMax": 1,
- "fields": {
- "body": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 65000,
- "minLength": 20
- },
- "fields": {
- "type": "array"
- },
- "labels": {
- "type": "array",
- "itemType": "string",
- "itemSanitize": true,
- "itemMaxLength": 128
- },
- "parent": {
- "issueOrPRNumber": true
- },
- "repo": {
- "type": "string",
- "maxLength": 256
- },
- "temporary_id": {
- "type": "string"
- },
- "title": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- }
- }
- },
- "missing_data": {
- "defaultMax": 20,
- "fields": {
- "alternatives": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "context": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "data_type": {
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- },
- "reason": {
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- }
- }
- },
- "missing_tool": {
- "defaultMax": 20,
- "fields": {
- "alternatives": {
- "type": "string",
- "sanitize": true,
- "maxLength": 512
- },
- "reason": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 256
- },
- "tool": {
- "type": "string",
- "sanitize": true,
- "maxLength": 128
- }
- }
- },
- "noop": {
- "defaultMax": 1,
- "fields": {
- "message": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 65000
- }
- }
- },
- "report_incomplete": {
- "defaultMax": 5,
- "fields": {
- "details": {
- "type": "string",
- "sanitize": true,
- "maxLength": 65000
- },
- "reason": {
- "required": true,
- "type": "string",
- "sanitize": true,
- "maxLength": 1024
- }
- }
- }
- }
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/generate_safe_outputs_tools.cjs');
- await main();
- - name: Start MCP Gateway
- id: start-mcp-gateway
- env:
- GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST: ${{ vars.GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST || 'true' }}
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- GH_AW_SAFE_OUTPUTS_CONFIG_PATH: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS_CONFIG_PATH }}
- GH_AW_SAFE_OUTPUTS_TOOLS_PATH: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS_TOOLS_PATH }}
- GITHUB_MCP_GUARD_MIN_INTEGRITY: ${{ steps.determine-automatic-lockdown.outputs.min_integrity }}
- GITHUB_MCP_GUARD_REPOS: ${{ steps.determine-automatic-lockdown.outputs.repos }}
- GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- run: |
- set -eo pipefail
- mkdir -p "${RUNNER_TEMP}/gh-aw/mcp-config"
-
- # Export gateway environment variables for MCP config and gateway script
- export MCP_GATEWAY_PORT="8080"
- export MCP_GATEWAY_DOMAIN="awmg-mcpg"
- export MCP_GATEWAY_HOST_DOMAIN="localhost"
- MCP_GATEWAY_API_KEY=$(openssl rand -base64 45 | tr -d '/+=')
- echo "::add-mask::${MCP_GATEWAY_API_KEY}"
- export MCP_GATEWAY_API_KEY
- export MCP_GATEWAY_PAYLOAD_DIR="/tmp/gh-aw/mcp-payloads"
- mkdir -p "${MCP_GATEWAY_PAYLOAD_DIR}"
- export MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD="524288"
- export DEBUG="*"
-
- export GH_AW_ENGINE="copilot"
- MCP_GATEWAY_UID=$(id -u 2>/dev/null || echo '0')
- MCP_GATEWAY_GID=$(id -g 2>/dev/null || echo '0')
- source "${RUNNER_TEMP}/gh-aw/actions/resolve_docker_socket_gid.sh"
- export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network bridge -p 127.0.0.1:'"${MCP_GATEWAY_PORT}"':'"${MCP_GATEWAY_PORT}"' --name awmg-mcpg --add-host host.docker.internal:host-gateway --user '"${MCP_GATEWAY_UID}"':'"${MCP_GATEWAY_GID}"' --group-add '"${DOCKER_SOCK_GID}"' -v '"${DOCKER_SOCK_PATH}"':/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 DOCKER_HOST=unix:///var/run/docker.sock -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_POLICY_ALLOW_CREATE_PULL_REQUEST -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 RUNNER_TEMP -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 -v '"${RUNNER_TEMP}"'/gh-aw/safeoutputs:'"${RUNNER_TEMP}"'/gh-aw/safeoutputs:rw ghcr.io/github/gh-aw-mcpg:v0.4.6'
-
- mkdir -p "$HOME/.copilot"
- GH_AW_NODE=$(which node 2>/dev/null || command -v node 2>/dev/null || echo node)
- cat << GH_AW_MCP_CONFIG_4dd92588edb04041_EOF | "$GH_AW_NODE" "${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.cjs"
- {
- "mcpServers": {
- "github": {
- "type": "stdio",
- "container": "ghcr.io/github/github-mcp-server:v1.7.0",
- "env": {
- "GITHUB_FEATURES": "fields_param",
- "GITHUB_HOST": "${GITHUB_SERVER_URL}",
- "GITHUB_PERSONAL_ACCESS_TOKEN": "${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": {
- "type": "stdio",
- "container": "ghcr.io/github/gh-aw-node",
- "mounts": ["\${GITHUB_WORKSPACE}:\${GITHUB_WORKSPACE}:rw", "${RUNNER_TEMP}/gh-aw/safeoutputs:${RUNNER_TEMP}/gh-aw/safeoutputs:rw", "/tmp/gh-aw:/tmp/gh-aw:rw"],
- "args": ["-w", "\${GITHUB_WORKSPACE}"],
- "entrypoint": "sh",
- "entrypointArgs": ["-c", "sh ${RUNNER_TEMP}/gh-aw/safeoutputs/start_safe_outputs_mcp.sh"],
- "env": {
- "DEBUG": "*",
- "DEFAULT_BRANCH": "\${DEFAULT_BRANCH}",
- "GH_AW_ASSETS_ALLOWED_EXTS": "\${GH_AW_ASSETS_ALLOWED_EXTS}",
- "GH_AW_ASSETS_BRANCH": "\${GH_AW_ASSETS_BRANCH}",
- "GH_AW_ASSETS_MAX_SIZE_KB": "\${GH_AW_ASSETS_MAX_SIZE_KB}",
- "GH_AW_MCP_LOG_DIR": "\${GH_AW_MCP_LOG_DIR}",
- "GH_AW_SAFE_OUTPUTS": "\${GH_AW_SAFE_OUTPUTS}",
- "GH_AW_SAFE_OUTPUTS_CONFIG_PATH": "\${GH_AW_SAFE_OUTPUTS_CONFIG_PATH}",
- "GH_AW_SAFE_OUTPUTS_TOOLS_PATH": "\${GH_AW_SAFE_OUTPUTS_TOOLS_PATH}",
- "GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST": "\${GH_AW_POLICY_ALLOW_CREATE_PULL_REQUEST}",
- "GITHUB_REPOSITORY": "\${GITHUB_REPOSITORY}",
- "GITHUB_SHA": "\${GITHUB_SHA}",
- "GITHUB_TOKEN": "\${GITHUB_TOKEN}",
- "GITHUB_WORKSPACE": "\${GITHUB_WORKSPACE}",
- "RUNNER_TEMP": "\${RUNNER_TEMP}"
- },
- "guard-policies": {
- "write-sink": {
- "accept": [
- "*"
- ],
- "sink-visibility": ${{ toJSON(steps.determine-automatic-lockdown.outputs.visibility) }}
- }
- }
- }
- },
- "gateway": {
- "port": $MCP_GATEWAY_PORT,
- "domain": "${MCP_GATEWAY_DOMAIN}",
- "apiKey": "${MCP_GATEWAY_API_KEY}",
- "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}",
- "startupTimeout": 120
- }
- }
- GH_AW_MCP_CONFIG_4dd92588edb04041_EOF
- - name: Mount MCP servers as CLIs
- id: mount-mcp-clis
- continue-on-error: true
- env:
- MCP_GATEWAY_API_KEY: ${{ steps.start-mcp-gateway.outputs.gateway-api-key }}
- MCP_GATEWAY_DOMAIN: ${{ steps.start-mcp-gateway.outputs.gateway-domain }}
- MCP_GATEWAY_PORT: ${{ steps.start-mcp-gateway.outputs.gateway-port }}
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/mount_mcp_as_cli.cjs');
- await main();
- - name: Clean credentials
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/clean_git_credentials.sh"
- - name: Audit pre-agent workspace
- id: pre_agent_audit
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/audit_pre_agent_workspace.sh"
- - name: Execute GitHub Copilot CLI
- id: agentic_execution
- # Copilot CLI tool arguments (sorted):
- # --allow-tool github
- # --allow-tool safeoutputs
- # --allow-tool shell(cat)
- # --allow-tool shell(clang-format:*)
- # --allow-tool shell(date)
- # --allow-tool shell(echo)
- # --allow-tool shell(git diff:*)
- # --allow-tool shell(git log:*)
- # --allow-tool shell(git show:*)
- # --allow-tool shell(git status)
- # --allow-tool shell(github:*)
- # --allow-tool shell(grep)
- # --allow-tool shell(head)
- # --allow-tool shell(ls)
- # --allow-tool shell(printf)
- # --allow-tool shell(pwd)
- # --allow-tool shell(safeoutputs:*)
- # --allow-tool shell(sort)
- # --allow-tool shell(tail)
- # --allow-tool shell(uniq)
- # --allow-tool shell(wc)
- # --allow-tool shell(yq)
- # --allow-tool web_fetch
- # --allow-tool write
- timeout-minutes: 30
- run: |
- set -o pipefail
- printf '%s' "$(date +%s%3N)" > /tmp/gh-aw/agent_cli_start_ms.txt
- trap 'gh_aw_exit_code=$?; mkdir -p /tmp/gh-aw >/dev/null 2>&1 || true; printf "%s" "$gh_aw_exit_code" > /tmp/gh-aw/agent_execution_exit_code.txt || true; rm -f "$HOME/.copilot/settings.json"' EXIT
- mkdir -p "$HOME/.copilot"
- printf '%s' '{"builtInAgents":{"rubberDuck":false}}' > "$HOME/.copilot/settings.json"
- export XDG_CONFIG_HOME="$HOME"
- export GH_AW_MCP_CONFIG="$HOME/.copilot/mcp-config.json"
- touch /tmp/gh-aw/agent-step-summary.md
- GH_AW_NODE_BIN=$(command -v node 2>/dev/null || true)
- export GH_AW_NODE_BIN
- export COPILOT_API_KEY="$COPILOT_DUMMY_BYOK"
- (umask 177 && touch /tmp/gh-aw/agent-stdio.log)
- GH_AW_MAX_AI_CREDITS="${GH_AW_MAX_AI_CREDITS:-1000}"
- printf '%s\n' "{\"\$schema\":\"https://github.com/github/gh-aw-firewall/releases/download/v0.27.42/awf-config.schema.json\",\"network\":{\"allowDomains\":[\"*.githubusercontent.com\",\"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\",\"codeload.github.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\",\"docs.github.com\",\"github-cloud.githubusercontent.com\",\"github-cloud.s3.amazonaws.com\",\"github.blog\",\"github.com\",\"github.githubassets.com\",\"host.docker.internal\",\"json-schema.org\",\"json.schemastore.org\",\"keyserver.ubuntu.com\",\"lfs.github.com\",\"objects.githubusercontent.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\",\"patch-diff.githubusercontent.com\",\"patchdiff.githubusercontent.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\"],\"isolation\":true,\"topologyAttach\":[\"awmg-mcpg\"]},\"apiProxy\":{\"enabled\":true,\"enableTokenSteering\":true,\"maxRuns\":500,\"maxAiCredits\":${GH_AW_MAX_AI_CREDITS},\"maxCacheMisses\":5,\"models\":{\"agent\":[\"sonnet-6x\",\"gpt-5.4\",\"gpt-5.5\",\"gpt-5.6\",\"gpt-5.3\",\"gemini-pro\",\"any\"],\"antigravity\":[\"copilot/antigravity*\",\"google/antigravity*\",\"gemini/antigravity*\"],\"any\":[\"copilot/*\",\"anthropic/*\",\"openai/*\",\"google/*\",\"gemini/*\"],\"claude\":[\"agent\"],\"codex\":[\"agent\"],\"coding\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\",\"gpt-5-codex\",\"kimi\"],\"computer-use\":[\"copilot/*computer-use*\",\"google/*computer-use*\",\"gemini/*computer-use*\",\"openai/*computer-use*\"],\"copilot\":[\"agent\"],\"deep-research\":[\"copilot/deep-research*\",\"copilot/o3-deep-research*\",\"copilot/o4-mini-deep-research*\",\"google/deep-research*\",\"gemini/deep-research*\",\"openai/o3-deep-research*\",\"openai/o4-mini-deep-research*\"],\"fable\":[\"copilot/*fable*\",\"anthropic/*fable*\"],\"gemini\":[\"agent\"],\"gemini-3-flash\":[\"copilot/gemini-3*flash*\",\"google/gemini-3*flash*\",\"gemini/gemini-3*flash*\"],\"gemini-3-pro\":[\"copilot/gemini-3*pro*\",\"google/gemini-3*pro*\",\"google/nano-banana*\",\"gemini/gemini-3*pro*\"],\"gemini-3.1-flash\":[\"copilot/gemini-3.1*flash*\",\"google/gemini-3.1*flash*\",\"gemini/gemini-3.1*flash*\"],\"gemini-3.1-pro\":[\"copilot/gemini-3.1*pro*\",\"google/gemini-3.1*pro*\",\"gemini/gemini-3.1*pro*\"],\"gemini-3.5-flash\":[\"copilot/gemini-3.5*flash*\",\"google/gemini-3.5*flash*\",\"gemini/gemini-3.5*flash*\"],\"gemini-3.6-flash\":[\"copilot/gemini-3.6*flash*\",\"google/gemini-3.6*flash*\",\"gemini/gemini-3.6*flash*\"],\"gemini-flash\":[\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"],\"gemini-flash-lite\":[\"copilot/gemini-*flash*lite*\",\"google/gemini-*flash*lite*\",\"gemini/gemini-*flash*lite*\"],\"gemini-omni\":[\"copilot/gemini-omni*\",\"google/gemini-omni*\",\"gemini/gemini-omni*\"],\"gemini-pro\":[\"copilot/gemini-*pro*\",\"google/gemini-*pro*\",\"gemini/gemini-*pro*\"],\"gemma\":[\"copilot/gemma*\",\"google/gemma*\",\"gemini/gemma*\"],\"gpt-5\":[\"copilot/gpt-5*\",\"openai/gpt-5*\"],\"gpt-5-codex\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\"],\"gpt-5-mini\":[\"copilot/gpt-5*mini*\",\"openai/gpt-5*mini*\"],\"gpt-5-nano\":[\"copilot/gpt-5*nano*\",\"openai/gpt-5*nano*\"],\"gpt-5-pro\":[\"copilot/gpt-5*pro*\",\"openai/gpt-5*pro*\"],\"gpt-5.1\":[\"copilot/gpt-5.1*\",\"openai/gpt-5.1*\"],\"gpt-5.2\":[\"copilot/gpt-5.2*\",\"openai/gpt-5.2*\"],\"gpt-5.3\":[\"copilot/gpt-5.3*\",\"openai/gpt-5.3*\"],\"gpt-5.4\":[\"copilot/gpt-5.4*\",\"openai/gpt-5.4*\"],\"gpt-5.5\":[\"copilot/gpt-5.5*\",\"openai/gpt-5.5*\"],\"gpt-5.6\":[\"copilot/gpt-5.6*\",\"openai/gpt-5.6*\"],\"haiku\":[\"copilot/*haiku*\",\"anthropic/*haiku*\"],\"image-generation\":[\"copilot/gpt-image*\",\"openai/gpt-image*\",\"openai/chatgpt-image*\",\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"google/imagen*\"],\"kimi\":[\"copilot/kimi*\",\"openai/kimi*\"],\"kiwi\":[\"copilot/kiwi*\",\"openai/kiwi*\"],\"large\":[\"fable\",\"sonnet\",\"gpt-5-pro\",\"gpt-5\",\"gemini-pro\"],\"lyria\":[\"google/lyria*\",\"gemini/lyria*\",\"copilot/lyria*\"],\"mai-code\":[\"copilot/MAI-Code*\",\"copilot/mai-code*\",\"openai/MAI-Code*\"],\"mai-code-1-flash-picker\":[\"copilot/MAI-Code-1-Flash-picker*\",\"copilot/mai-code-1-flash-picker*\",\"openai/MAI-Code-1-Flash-picker*\"],\"mini\":[\"haiku\",\"gpt-5-mini\",\"gpt-5-nano\",\"gemini-flash-lite\"],\"nano-banana\":[\"copilot/nano-banana*\",\"google/nano-banana*\",\"gemini/nano-banana*\"],\"opus\":[\"copilot/*opus*\",\"anthropic/*opus*\"],\"opusplan\":[\"opus?effort=high\"],\"raptor-mini\":[\"copilot/raptor*\",\"openai/raptor*\"],\"reasoning\":[\"copilot/o1*\",\"copilot/o3*\",\"copilot/o4*\",\"openai/o1*\",\"openai/o3*\",\"openai/o4*\"],\"robotics\":[\"copilot/*robotics*\",\"google/*robotics*\",\"gemini/*robotics*\"],\"small\":[\"mini\"],\"small-agent\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash\"],\"sonnet\":[\"copilot/*sonnet*\",\"anthropic/*sonnet*\"],\"sonnet-6x\":[\"copilot/*sonnet-4.5*\",\"copilot/*sonnet-4.6*\",\"copilot/*sonnet-5*\",\"copilot/*sonnet-4-5-*\",\"anthropic/*sonnet-4-5-*\",\"copilot/*sonnet-4-6*\",\"anthropic/*sonnet-4-6*\",\"anthropic/*sonnet-5*\"],\"summarization\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash-lite\",\"mini\"],\"veo\":[\"google/veo*\",\"gemini/veo*\"],\"vision\":[\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"]}},\"container\":{\"imageTag\":\"0.27.42,squid=sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0,agent=sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b,agent-act=sha256:a14ad974484aa518aab83d40f3f141175dfd171d3745e01c092375b970f73a20,api-proxy=sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607,cli-proxy=sha256:da006bf96d2d246dd269d57b233c1798d2ad63d6cd64ca02f7bf71045028781f\"},\"logging\":{\"proxyLogsDir\":\"/tmp/gh-aw/sandbox/firewall/logs\",\"auditDir\":\"/tmp/gh-aw/sandbox/firewall/audit\"}}" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- cp "${RUNNER_TEMP}/gh-aw/awf-config.json" /tmp/gh-aw/awf-config.json
- export GH_AW_MODELS_JSON_PATH="/tmp/gh-aw/models.json"
- GH_AW_DOCKER_HOST=""
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_DOCKER_HOST="${DOCKER_HOST}"
- fi
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_CHROOT_BINARIES_SOURCE_PATH="${RUNNER_TEMP}/gh-aw" GH_AW_CHROOT_IDENTITY_HOME="${RUNNER_TEMP}/gh-aw/home" node "${RUNNER_TEMP}/gh-aw/actions/patch_awf_chroot_config.cjs"
- fi
- GH_AW_TOOL_CACHE_MOUNT=""
- GH_AW_TOOL_CACHE="${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"
- if [ -d "$GH_AW_TOOL_CACHE" ]; then
- if [[ "$GH_AW_TOOL_CACHE" != /opt/* ]]; then
- GH_AW_TOOL_CACHE_MOUNT="$GH_AW_TOOL_CACHE:$GH_AW_TOOL_CACHE:ro"
- fi
- fi
- # shellcheck disable=SC1003,SC2016,SC2086
- awf --config "${RUNNER_TEMP}/gh-aw/awf-config.json" --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" ${GH_AW_TOOL_CACHE_MOUNT:+--mount "$GH_AW_TOOL_CACHE_MOUNT"} ${GH_AW_DOCKER_HOST:+--docker-host "$GH_AW_DOCKER_HOST"} --env-all --exclude-env COPILOT_GITHUB_TOKEN --exclude-env GITHUB_MCP_SERVER_TOKEN --exclude-env MCP_GATEWAY_API_KEY --log-level info --skip-pull \
- -- /bin/bash -c 'set +o histexpand; export PATH="${RUNNER_TEMP}/gh-aw/mcp-cli/bin:$PATH" && : "${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"; GH_AW_TOOL_CACHE="$RUNNER_TOOL_CACHE"; export PATH="$(find "$GH_AW_TOOL_CACHE" -maxdepth 5 -type d -name bin 2>/dev/null | tr '\''\n'\'' '\'':'\'')$PATH"; [ -n "$GOROOT" ] && export PATH="$GOROOT/bin:$PATH" || true; [ -n "$ERLANG_HOME" ] && export PATH="$ERLANG_HOME/bin:$PATH" || true && GH_AW_NODE_EXEC="${GH_AW_NODE_BIN:-}"; if [ -z "$GH_AW_NODE_EXEC" ] || [ ! -x "$GH_AW_NODE_EXEC" ]; then GH_AW_NODE_EXEC="$(command -v node 2>/dev/null || true)"; fi; if [ -z "$GH_AW_NODE_EXEC" ]; then echo "node runtime missing on this runner — check runtimes.node in workflow YAML" >&2; exit 127; fi; GH_AW_NPM_GLOBAL_ROOT="$(npm root -g 2>/dev/null || true)"; if [ -n "$GH_AW_NPM_GLOBAL_ROOT" ]; then export NODE_PATH="${GH_AW_NPM_GLOBAL_ROOT}${NODE_PATH:+:${NODE_PATH}}"; fi; "$GH_AW_NODE_EXEC" ${RUNNER_TEMP}/gh-aw/actions/copilot_harness.cjs /usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --no-ask-user --allow-tool github --allow-tool safeoutputs --allow-tool '\''shell(cat)'\'' --allow-tool '\''shell(clang-format:*)'\'' --allow-tool '\''shell(date)'\'' --allow-tool '\''shell(echo)'\'' --allow-tool '\''shell(git diff:*)'\'' --allow-tool '\''shell(git log:*)'\'' --allow-tool '\''shell(git show:*)'\'' --allow-tool '\''shell(git status)'\'' --allow-tool '\''shell(github:*)'\'' --allow-tool '\''shell(grep)'\'' --allow-tool '\''shell(head)'\'' --allow-tool '\''shell(ls)'\'' --allow-tool '\''shell(printf)'\'' --allow-tool '\''shell(pwd)'\'' --allow-tool '\''shell(safeoutputs:*)'\'' --allow-tool '\''shell(sort)'\'' --allow-tool '\''shell(tail)'\'' --allow-tool '\''shell(uniq)'\'' --allow-tool '\''shell(wc)'\'' --allow-tool '\''shell(yq)'\'' --allow-tool web_fetch --allow-tool write --add-dir /tmp/gh-aw/cache-memory/ --allow-all-paths --add-dir "${GITHUB_WORKSPACE}" --prompt-file /tmp/gh-aw/aw-prompts/prompt.txt' 2>&1 | tee -a /tmp/gh-aw/agent-stdio.log
- env:
- AWF_REFLECT_ENABLED: 1
- COPILOT_AGENT_RUNNER_TYPE: STANDALONE
- COPILOT_DUMMY_BYOK: dummy-byok-key-for-offline-mode
- COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- COPILOT_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_LLM_PROVIDER: github
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }}
- GH_AW_MAX_TURNS: ${{ vars.GH_AW_DEFAULT_MAX_TURNS || '' }}
- GH_AW_PHASE: agent
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- GH_AW_TIMEOUT_MINUTES: 30
- GH_AW_VERSION: v0.83.4
- GITHUB_API_URL: ${{ github.api_url }}
- GITHUB_AW: true
- GITHUB_COPILOT_INTEGRATION_ID: agentic-workflows
- GITHUB_HEAD_REF: ${{ github.head_ref }}
- GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- GITHUB_REF_NAME: ${{ github.ref_name }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_STEP_SUMMARY: /tmp/gh-aw/agent-step-summary.md
- GITHUB_WORKSPACE: ${{ github.workspace }}
- GIT_AUTHOR_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_AUTHOR_NAME: github-actions[bot]
- GIT_COMMITTER_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_COMMITTER_NAME: github-actions[bot]
- RUNNER_TEMP: ${{ runner.temp }}
- TRACEPARENT: ${{ env.GITHUB_AW_OTEL_TRACE_ID != '' && env.GITHUB_AW_OTEL_PARENT_SPAN_ID != '' && format('00-{0}-{1}-01', env.GITHUB_AW_OTEL_TRACE_ID, env.GITHUB_AW_OTEL_PARENT_SPAN_ID) || '' }}
- - name: Detect agent errors
- if: always()
- id: detect-agent-errors
- continue-on-error: true
- run: node "${RUNNER_TEMP}/gh-aw/actions/detect_agent_errors.cjs"
- - name: Configure Git credentials
- env:
- GITHUB_REPOSITORY: ${{ github.repository }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_TOKEN: ${{ github.token }}
- run: bash "${RUNNER_TEMP}/gh-aw/actions/configure_git_credentials.sh"
- - name: Copy Copilot session state files to logs
- if: always()
- continue-on-error: true
- run: bash "${RUNNER_TEMP}/gh-aw/actions/copy_copilot_session_state.sh"
- - name: Stop MCP Gateway
- if: always()
- continue-on-error: true
- env:
- MCP_GATEWAY_PORT: ${{ steps.start-mcp-gateway.outputs.gateway-port }}
- 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" "$GATEWAY_PID"
- - name: Redact secrets in logs
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/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'
- SECRET_COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- SECRET_GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }}
- SECRET_GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }}
- 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
- if: always()
- env:
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- run: |
- mkdir -p /tmp/gh-aw
- cp "$GH_AW_SAFE_OUTPUTS" /tmp/gh-aw/safeoutputs.jsonl 2>/dev/null || true
- - name: Ingest agent output
- id: collect_output
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- GH_AW_ALLOWED_DOMAINS: "*.githubusercontent.com,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,codeload.github.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,docs.github.com,github-cloud.githubusercontent.com,github-cloud.s3.amazonaws.com,github.blog,github.com,github.githubassets.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,lfs.github.com,objects.githubusercontent.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,patch-diff.githubusercontent.com,patchdiff.githubusercontent.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"
- 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');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/collect_ndjson_output.cjs');
- await main();
- - name: Parse agent logs for step summary
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: /tmp/gh-aw/sandbox/agent/logs/
- GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }}
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_copilot_log.cjs');
- await main();
- - name: Parse MCP Gateway logs for step summary
- if: always()
- id: parse-mcp-gateway
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_mcp_gateway_log.cjs');
- await main();
- - name: Print firewall logs
- if: always()
- continue-on-error: true
- env:
- AWF_LOGS_DIR: /tmp/gh-aw/sandbox/firewall/logs
- run: bash "${RUNNER_TEMP}/gh-aw/actions/print_firewall_logs.sh" --rootless
- - name: Parse token usage for step summary
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_token_usage.cjs');
- await main();
- - name: Print AWF reflect summary
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/awf_reflect_summary.cjs');
- await main();
- - name: Write agent output placeholder if missing
- if: always()
- run: |
- if [ ! -f /tmp/gh-aw/agent_output.json ]; then
- echo '{"items":[]}' > /tmp/gh-aw/agent_output.json
- fi
- - name: Commit cache-memory changes
- if: always()
- env:
- GH_AW_CACHE_DIR: /tmp/gh-aw/cache-memory
- run: bash "${RUNNER_TEMP}/gh-aw/actions/commit_cache_memory_git.sh"
- - name: Check cache-memory git integrity
- if: always()
- continue-on-error: true
- env:
- GH_AW_CACHE_DIR: /tmp/gh-aw/cache-memory
- run: bash "${RUNNER_TEMP}/gh-aw/actions/check_cache_memory_git_integrity.sh"
- - name: Upload cache-memory data as artifact
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- if: always()
- with:
- name: cache-memory
- include-hidden-files: true
- path: /tmp/gh-aw/cache-memory
- - name: Upload agent artifacts
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: agent
- 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/agent_usage.json
- /tmp/gh-aw/agent-stdio.log
- /tmp/gh-aw/pre-agent-audit.txt
- /tmp/gh-aw/agent/
- /tmp/gh-aw/github_rate_limits.jsonl
- /tmp/gh-aw/safeoutputs.jsonl
- /tmp/gh-aw/agent_output.json
- /tmp/gh-aw/aw-*.patch
- /tmp/gh-aw/aw-*.bundle
- /tmp/gh-aw/awf-config.json
- /tmp/gh-aw/sandbox/firewall/logs/
- /tmp/gh-aw/sandbox/firewall/audit/
- /tmp/gh-aw/sandbox/firewall/awf-reflect.json
- if-no-files-found: ignore
-
- conclusion:
- needs:
- - activation
- - agent
- - detection
- - safe_outputs
- - update_cache_memory
- if: >
- always() && (needs.agent.result != 'skipped' || needs.activation.outputs.lockdown_check_failed == 'true' ||
- needs.activation.outputs.oauth_token_check_failed == 'true' || needs.activation.outputs.stale_lock_file_failed == 'true' ||
- needs.activation.outputs.secret_verification_result == 'failed' || needs.activation.outputs.daily_ai_credits_exceeded == 'true')
- runs-on: ubuntu-slim
- permissions:
- contents: read
- issues: write
- concurrency:
- group: "gh-aw-conclusion-zipt-code-reviewer"
- cancel-in-progress: false
- queue: max
- env:
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- incomplete_count: ${{ steps.report_incomplete.outputs.incomplete_count }}
- noop_message: ${{ steps.noop.outputs.noop_message }}
- tools_reported: ${{ steps.missing_tool.outputs.tools_reported }}
- total_count: ${{ steps.missing_tool.outputs.total_count }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/zipt-code-reviewer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Download safe outputs items manifest
- id: download-safe-outputs-manifest
- if: always()
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: safe-outputs-items
- path: /tmp/gh-aw/
- - name: Collect usage artifact files
- if: always()
- continue-on-error: true
- run: |
- mkdir -p /tmp/gh-aw/usage/agent /tmp/gh-aw/usage/detection
- echo "Usage artifact source file status:"
- for file in /tmp/gh-aw/aw_info.json /tmp/gh-aw/aw-info.jsonl /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/detection_usage.jsonl /tmp/gh-aw/evals/evals.jsonl /tmp/gh-aw/github_rate_limits.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl; do
- [ -f "$file" ] && echo "FOUND: $file" || echo "MISSING: $file"
- done
- [ -f /tmp/gh-aw/aw_info.json ] && cp /tmp/gh-aw/aw_info.json /tmp/gh-aw/usage/aw_info.json || true
- [ -f /tmp/gh-aw/aw-info.jsonl ] && cp /tmp/gh-aw/aw-info.jsonl /tmp/gh-aw/usage/aw-info.jsonl || true
- [ -f /tmp/gh-aw/agent_usage.json ] && cp /tmp/gh-aw/agent_usage.json /tmp/gh-aw/usage/agent_usage.json || true
- [ -f /tmp/gh-aw/agent_usage.jsonl ] && cp /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/usage/agent_usage.jsonl || true
- [ -f /tmp/gh-aw/detection_usage.jsonl ] && cp /tmp/gh-aw/detection_usage.jsonl /tmp/gh-aw/usage/detection_usage.jsonl || true
- [ -f /tmp/gh-aw/evals/evals.jsonl ] && cp /tmp/gh-aw/evals/evals.jsonl /tmp/gh-aw/usage/evals.jsonl || true
- [ -f /tmp/gh-aw/github_rate_limits.jsonl ] && cp /tmp/gh-aw/github_rate_limits.jsonl /tmp/gh-aw/usage/github_rate_limits.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/agent/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -s /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl ] && cp /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/usage/detection/token_usage.jsonl || true
- [ -f /tmp/gh-aw/usage/agent/token_usage.jsonl ] || : > /tmp/gh-aw/usage/agent/token_usage.jsonl
- [ -f /tmp/gh-aw/usage/detection/token_usage.jsonl ] || : > /tmp/gh-aw/usage/detection/token_usage.jsonl
- mkdir -p /tmp/gh-aw/usage/activity
- node "${RUNNER_TEMP}/gh-aw/actions/generate_usage_activity_summary.cjs"
- find /tmp/gh-aw/usage -type f -print | sort
- - name: Upload usage artifact
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: usage
- path: |
- /tmp/gh-aw/usage/aw_info.json
- /tmp/gh-aw/usage/aw-info.jsonl
- /tmp/gh-aw/usage/agent_usage.json
- /tmp/gh-aw/usage/agent_usage.jsonl
- /tmp/gh-aw/usage/detection_usage.jsonl
- /tmp/gh-aw/usage/evals.jsonl
- /tmp/gh-aw/usage/github_rate_limits.jsonl
- /tmp/gh-aw/usage/agent/token_usage.jsonl
- /tmp/gh-aw/usage/detection/token_usage.jsonl
- /tmp/gh-aw/usage/activity/summary.json
- if-no-files-found: ignore
- - name: Restore daily AIC usage cache
- id: restore-daily-aic-cache-conclusion
- if: always()
- continue-on-error: true
- uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-ziptcodereviewer-${{ github.run_id }}
- restore-keys: agentic-workflow-usage-ziptcodereviewer-
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Write daily AIC usage cache entry
- id: write-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- with:
- github-token: ${{ github.token }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/write_daily_aic_usage_cache.cjs');
- await main();
- - name: Save daily AIC usage cache
- id: save-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: agentic-workflow-usage-ziptcodereviewer-${{ github.run_id }}
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- - name: Upload daily AIC usage cache artifact
- id: upload-daily-aic-cache
- if: always()
- continue-on-error: true
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: aic-usage-cache
- path: /tmp/gh-aw/agentic-workflow-usage-cache.jsonl
- if-no-files-found: ignore
- retention-days: 7
- - name: Process no-op messages
- id: noop
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_NOOP_MAX: "1"
- GH_AW_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/zipt-code-reviewer.md"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_AGENT_CONCLUSION: ${{ needs.agent.result }}
- GH_AW_NOOP_REPORT_AS_ISSUE: "false"
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_AMBIENT_CONTEXT: ${{ needs.agent.outputs.ambient_context }}
- GH_AW_WORKFLOW_ID: "zipt-code-reviewer"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_noop_message.cjs');
- await main();
- - name: Log detection run
- id: detection_runs
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/zipt-code-reviewer.md"
- GH_AW_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
- GH_AW_DETECTION_CONCLUSION: ${{ needs.detection.outputs.detection_conclusion }}
- GH_AW_DETECTION_REASON: ${{ needs.detection.outputs.detection_reason }}
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_detection_runs.cjs');
- await main();
- - name: Record missing tool
- id: missing_tool
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_MISSING_TOOL_CREATE_ISSUE: "true"
- GH_AW_MISSING_TOOL_TITLE_PREFIX: "[missing tool]"
- GH_AW_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/zipt-code-reviewer.md"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/missing_tool.cjs');
- await main();
- - name: Record incomplete
- id: report_incomplete
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_REPORT_INCOMPLETE_CREATE_ISSUE: "true"
- GH_AW_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/zipt-code-reviewer.md"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/report_incomplete_handler.cjs');
- await main();
- - name: Handle agent failure
- id: handle_agent_failure
- if: always()
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/zipt-code-reviewer.md"
- 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: "zipt-code-reviewer"
- GH_AW_ACTION_FAILURE_ISSUE_EXPIRES_HOURS: "168"
- GH_AW_ENGINE_ID: "copilot"
- GH_AW_SECRET_VERIFICATION_RESULT: ${{ needs.activation.outputs.secret_verification_result }}
- GH_AW_ENGINE_SECRET_FAILURE_MESSAGE: "**Alternative**: If your organization has a Copilot subscription, you can avoid the need for a personal access token by adding a top-level `permissions` block to your workflow file. This enables Copilot inference through the org using the built-in GitHub Actions token.\n\n```yaml\npermissions:\n copilot-requests: write\n```\n\nSee: https://github.github.com/gh-aw/reference/engines/#github-copilot-default"
- GH_AW_CHECKOUT_PR_SUCCESS: ${{ needs.agent.outputs.checkout_pr_success }}
- GH_AW_EFFECTIVE_TOKENS: ${{ needs.agent.outputs.effective_tokens || '' }}
- GH_AW_AI_CREDITS_RATE_LIMIT_ERROR: ${{ needs.agent.outputs.ai_credits_rate_limit_error || 'false' }}
- GH_AW_UNKNOWN_MODEL_AI_CREDITS: ${{ needs.agent.outputs.unknown_model_ai_credits || 'false' }}
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_MAX_AI_CREDITS || '1000' }}
- GH_AW_INFERENCE_ACCESS_ERROR: ${{ needs.agent.outputs.inference_access_error }}
- GH_AW_MCP_POLICY_ERROR: ${{ needs.agent.outputs.mcp_policy_error }}
- GH_AW_AGENTIC_ENGINE_TIMEOUT: ${{ needs.agent.outputs.agentic_engine_timeout }}
- GH_AW_MODEL_NOT_SUPPORTED_ERROR: ${{ needs.agent.outputs.model_not_supported_error }}
- GH_AW_HTTP_400_RESPONSE_ERROR: ${{ needs.agent.outputs.http_400_response_error }}
- GH_AW_ENGINE_API_HOSTS: "api.enterprise.githubcopilot.com,api.githubcopilot.com,api.business.githubcopilot.com,api.individual.githubcopilot.com"
- GH_AW_LOCKDOWN_CHECK_FAILED: ${{ needs.activation.outputs.lockdown_check_failed }}
- GH_AW_OAUTH_TOKEN_CHECK_FAILED: ${{ needs.activation.outputs.oauth_token_check_failed }}
- GH_AW_STALE_LOCK_FILE_FAILED: ${{ needs.activation.outputs.stale_lock_file_failed }}
- GH_AW_DAILY_AI_CREDITS_EXCEEDED: ${{ needs.activation.outputs.daily_ai_credits_exceeded }}
- GH_AW_DAILY_AI_CREDITS_TOTAL_EFFECTIVE_TOKENS: ${{ needs.activation.outputs.daily_ai_credits_total_effective_tokens }}
- GH_AW_DAILY_AI_CREDITS_THRESHOLD: ${{ needs.activation.outputs.daily_ai_credits_threshold }}
- GH_AW_GROUP_REPORTS: "false"
- GH_AW_FAILURE_REPORT_AS_ISSUE: "false"
- GH_AW_MISSING_TOOL_REPORT_AS_FAILURE: "true"
- GH_AW_MISSING_DATA_REPORT_AS_FAILURE: "true"
- GH_AW_TIMEOUT_MINUTES: "30"
- GH_AW_CACHE_MEMORY_ENABLED: "true"
- GH_AW_CACHE_MEMORY_RESTORE_0_MATCHED_KEY: ${{ needs.agent.outputs.cache_memory_restore_0_matched_key || '' }}
- GH_AW_CACHE_MEMORY_RESTORE_0_CACHE_HIT: ${{ needs.agent.outputs.cache_memory_restore_0_cache_hit || 'false' }}
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/handle_agent_failure.cjs');
- await main();
-
- detection:
- needs:
- - activation
- - agent
- if: always() && needs.agent.result != 'skipped'
- runs-on: ubuntu-latest
- permissions:
- contents: read
- env:
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- outputs:
- aic: ${{ steps.parse_detection_token_usage.outputs.aic }}
- detection_conclusion: ${{ steps.detection_conclusion.outputs.conclusion }}
- detection_reason: ${{ steps.detection_conclusion.outputs.reason }}
- detection_success: ${{ steps.detection_conclusion.outputs.success }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/zipt-code-reviewer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Checkout repository for patch context
- if: needs.agent.outputs.has_patch == 'true'
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- with:
- persist-credentials: false
- # --- Threat Detection ---
- - name: Clean stale firewall files from agent artifact
- run: |
- rm -rf /tmp/gh-aw/sandbox/firewall/logs
- rm -rf /tmp/gh-aw/sandbox/firewall/audit
- - name: Download container images
- run: bash "${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh" ghcr.io/github/gh-aw-firewall/agent:0.27.42@sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b ghcr.io/github/gh-aw-firewall/api-proxy:0.27.42@sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607 ghcr.io/github/gh-aw-firewall/squid:0.27.42@sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0
- - name: Check if detection needed
- id: detection_guard
- if: always()
- env:
- OUTPUT_TYPES: ${{ needs.agent.outputs.output_types }}
- HAS_PATCH: ${{ needs.agent.outputs.has_patch }}
- run: |
- if [[ -n "$OUTPUT_TYPES" || "$HAS_PATCH" == "true" ]]; then
- echo "run_detection=true" >> "$GITHUB_OUTPUT"
- echo "Detection will run: output_types=$OUTPUT_TYPES, has_patch=$HAS_PATCH"
- else
- echo "run_detection=false" >> "$GITHUB_OUTPUT"
- echo "Detection skipped: no agent outputs or patches to analyze"
- fi
- - name: Clear MCP Config for detection
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- rm -f "${RUNNER_TEMP}/gh-aw/mcp-config/mcp-servers.json"
- rm -f "$HOME/.copilot/mcp-config.json"
- rm -f "$GITHUB_WORKSPACE/.gemini/settings.json"
- - name: Prepare threat detection files
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- mkdir -p /tmp/gh-aw/threat-detection/aw-prompts
- rm -f /tmp/gh-aw/agent_usage.json
- cp /tmp/gh-aw/aw-prompts/prompt.txt /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt 2>/dev/null || true
- if [ ! -s /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt ]; then
- echo "::warning::ERR_VALIDATION: Missing or empty detection context prompt at /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt. Ensure the agent artifact includes /tmp/gh-aw/aw-prompts/prompt.txt. Detection will continue with fallback workflow context."
- fi
- cp /tmp/gh-aw/agent_output.json /tmp/gh-aw/threat-detection/agent_output.json 2>/dev/null || true
- for f in /tmp/gh-aw/aw-*.patch; do
- [ -f "$f" ] && cp "$f" /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- done
- for f in /tmp/gh-aw/aw-*.bundle; do
- [ -f "$f" ] && cp "$f" /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- done
- echo "Prepared threat detection files:"
- ls -la /tmp/gh-aw/threat-detection/ 2>/dev/null || true
- - name: Setup threat detection
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- WORKFLOW_NAME: "ZIPT Code Reviewer"
- WORKFLOW_DESCRIPTION: "Reviews Z3 string/sequence graph implementation (euf_sgraph, euf_seq_plugin, src/smt/seq) by comparing with the ZIPT reference implementation and reporting improvements as git diffs in GitHub issues"
- HAS_PATCH: ${{ needs.agent.outputs.has_patch }}
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/setup_threat_detection.cjs');
- await main();
- - name: Ensure threat-detection directory and log
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- run: |
- mkdir -p /tmp/gh-aw/threat-detection
- touch /tmp/gh-aw/threat-detection/detection.log
- - name: Setup Node.js
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
- with:
- node-version: '24'
- package-manager-cache: false
- - name: Install GitHub Copilot CLI
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh" 1.0.75
- env:
- GH_HOST: github.com
- - name: Install AWF binary
- run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.27.42
- - name: Execute GitHub Copilot CLI
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- continue-on-error: true
- id: detection_agentic_execution
- # Copilot CLI tool arguments (sorted):
- timeout-minutes: 20
- run: |
- set -o pipefail
- printf '%s' "$(date +%s%3N)" > /tmp/gh-aw/agent_cli_start_ms.txt
- trap 'gh_aw_exit_code=$?; mkdir -p /tmp/gh-aw >/dev/null 2>&1 || true; printf "%s" "$gh_aw_exit_code" > /tmp/gh-aw/agent_execution_exit_code.txt || true; rm -f "$HOME/.copilot/settings.json"' EXIT
- mkdir -p "$HOME/.copilot"
- printf '%s' '{"builtInAgents":{"rubberDuck":false}}' > "$HOME/.copilot/settings.json"
- export XDG_CONFIG_HOME="$HOME"
- touch /tmp/gh-aw/agent-step-summary.md
- GH_AW_NODE_BIN=$(command -v node 2>/dev/null || true)
- export GH_AW_NODE_BIN
- export COPILOT_API_KEY="$COPILOT_DUMMY_BYOK"
- (umask 177 && touch /tmp/gh-aw/threat-detection/detection.log)
- GH_AW_MAX_AI_CREDITS="${GH_AW_MAX_AI_CREDITS:-400}"
- printf '%s\n' "{\"\$schema\":\"https://github.com/github/gh-aw-firewall/releases/download/v0.27.42/awf-config.schema.json\",\"network\":{\"allowDomains\":[\"api.business.githubcopilot.com\",\"api.enterprise.githubcopilot.com\",\"api.github.com\",\"api.githubcopilot.com\",\"api.individual.githubcopilot.com\",\"github.com\",\"host.docker.internal\",\"registry.npmjs.org\",\"telemetry.enterprise.githubcopilot.com\"]},\"apiProxy\":{\"enabled\":true,\"enableTokenSteering\":true,\"maxRuns\":500,\"maxAiCredits\":${GH_AW_MAX_AI_CREDITS},\"maxCacheMisses\":5,\"models\":{\"agent\":[\"sonnet-6x\",\"gpt-5.4\",\"gpt-5.5\",\"gpt-5.6\",\"gpt-5.3\",\"gemini-pro\",\"any\"],\"antigravity\":[\"copilot/antigravity*\",\"google/antigravity*\",\"gemini/antigravity*\"],\"any\":[\"copilot/*\",\"anthropic/*\",\"openai/*\",\"google/*\",\"gemini/*\"],\"claude\":[\"agent\"],\"codex\":[\"agent\"],\"coding\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\",\"gpt-5-codex\",\"kimi\"],\"computer-use\":[\"copilot/*computer-use*\",\"google/*computer-use*\",\"gemini/*computer-use*\",\"openai/*computer-use*\"],\"copilot\":[\"agent\"],\"deep-research\":[\"copilot/deep-research*\",\"copilot/o3-deep-research*\",\"copilot/o4-mini-deep-research*\",\"google/deep-research*\",\"gemini/deep-research*\",\"openai/o3-deep-research*\",\"openai/o4-mini-deep-research*\"],\"fable\":[\"copilot/*fable*\",\"anthropic/*fable*\"],\"gemini\":[\"agent\"],\"gemini-3-flash\":[\"copilot/gemini-3*flash*\",\"google/gemini-3*flash*\",\"gemini/gemini-3*flash*\"],\"gemini-3-pro\":[\"copilot/gemini-3*pro*\",\"google/gemini-3*pro*\",\"google/nano-banana*\",\"gemini/gemini-3*pro*\"],\"gemini-3.1-flash\":[\"copilot/gemini-3.1*flash*\",\"google/gemini-3.1*flash*\",\"gemini/gemini-3.1*flash*\"],\"gemini-3.1-pro\":[\"copilot/gemini-3.1*pro*\",\"google/gemini-3.1*pro*\",\"gemini/gemini-3.1*pro*\"],\"gemini-3.5-flash\":[\"copilot/gemini-3.5*flash*\",\"google/gemini-3.5*flash*\",\"gemini/gemini-3.5*flash*\"],\"gemini-3.6-flash\":[\"copilot/gemini-3.6*flash*\",\"google/gemini-3.6*flash*\",\"gemini/gemini-3.6*flash*\"],\"gemini-flash\":[\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"],\"gemini-flash-lite\":[\"copilot/gemini-*flash*lite*\",\"google/gemini-*flash*lite*\",\"gemini/gemini-*flash*lite*\"],\"gemini-omni\":[\"copilot/gemini-omni*\",\"google/gemini-omni*\",\"gemini/gemini-omni*\"],\"gemini-pro\":[\"copilot/gemini-*pro*\",\"google/gemini-*pro*\",\"gemini/gemini-*pro*\"],\"gemma\":[\"copilot/gemma*\",\"google/gemma*\",\"gemini/gemma*\"],\"gpt-5\":[\"copilot/gpt-5*\",\"openai/gpt-5*\"],\"gpt-5-codex\":[\"copilot/gpt-5*codex*\",\"openai/gpt-5*codex*\"],\"gpt-5-mini\":[\"copilot/gpt-5*mini*\",\"openai/gpt-5*mini*\"],\"gpt-5-nano\":[\"copilot/gpt-5*nano*\",\"openai/gpt-5*nano*\"],\"gpt-5-pro\":[\"copilot/gpt-5*pro*\",\"openai/gpt-5*pro*\"],\"gpt-5.1\":[\"copilot/gpt-5.1*\",\"openai/gpt-5.1*\"],\"gpt-5.2\":[\"copilot/gpt-5.2*\",\"openai/gpt-5.2*\"],\"gpt-5.3\":[\"copilot/gpt-5.3*\",\"openai/gpt-5.3*\"],\"gpt-5.4\":[\"copilot/gpt-5.4*\",\"openai/gpt-5.4*\"],\"gpt-5.5\":[\"copilot/gpt-5.5*\",\"openai/gpt-5.5*\"],\"gpt-5.6\":[\"copilot/gpt-5.6*\",\"openai/gpt-5.6*\"],\"haiku\":[\"copilot/*haiku*\",\"anthropic/*haiku*\"],\"image-generation\":[\"copilot/gpt-image*\",\"openai/gpt-image*\",\"openai/chatgpt-image*\",\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"google/imagen*\"],\"kimi\":[\"copilot/kimi*\",\"openai/kimi*\"],\"kiwi\":[\"copilot/kiwi*\",\"openai/kiwi*\"],\"large\":[\"fable\",\"sonnet\",\"gpt-5-pro\",\"gpt-5\",\"gemini-pro\"],\"lyria\":[\"google/lyria*\",\"gemini/lyria*\",\"copilot/lyria*\"],\"mai-code\":[\"copilot/MAI-Code*\",\"copilot/mai-code*\",\"openai/MAI-Code*\"],\"mai-code-1-flash-picker\":[\"copilot/MAI-Code-1-Flash-picker*\",\"copilot/mai-code-1-flash-picker*\",\"openai/MAI-Code-1-Flash-picker*\"],\"mini\":[\"haiku\",\"gpt-5-mini\",\"gpt-5-nano\",\"gemini-flash-lite\"],\"nano-banana\":[\"copilot/nano-banana*\",\"google/nano-banana*\",\"gemini/nano-banana*\"],\"opus\":[\"copilot/*opus*\",\"anthropic/*opus*\"],\"opusplan\":[\"opus?effort=high\"],\"raptor-mini\":[\"copilot/raptor*\",\"openai/raptor*\"],\"reasoning\":[\"copilot/o1*\",\"copilot/o3*\",\"copilot/o4*\",\"openai/o1*\",\"openai/o3*\",\"openai/o4*\"],\"robotics\":[\"copilot/*robotics*\",\"google/*robotics*\",\"gemini/*robotics*\"],\"small\":[\"mini\"],\"small-agent\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash\"],\"sonnet\":[\"copilot/*sonnet*\",\"anthropic/*sonnet*\"],\"sonnet-6x\":[\"copilot/*sonnet-4.5*\",\"copilot/*sonnet-4.6*\",\"copilot/*sonnet-5*\",\"copilot/*sonnet-4-5-*\",\"anthropic/*sonnet-4-5-*\",\"copilot/*sonnet-4-6*\",\"anthropic/*sonnet-4-6*\",\"anthropic/*sonnet-5*\"],\"summarization\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash-lite\",\"mini\"],\"veo\":[\"google/veo*\",\"gemini/veo*\"],\"vision\":[\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"]}},\"container\":{\"imageTag\":\"0.27.42,squid=sha256:42dfeb649c680a8558cd5423dbc530b653a69413e35ffbe5e71da5d48c94bdf0,agent=sha256:26a8af4e5566485b02f52af59ee03803ae798271a9619d4767e94d07806deb9b,agent-act=sha256:a14ad974484aa518aab83d40f3f141175dfd171d3745e01c092375b970f73a20,api-proxy=sha256:944f2686c9ab9bec338fd14b662461662f77cd12cd0ea8a3e7cb8c0987cd1607,cli-proxy=sha256:da006bf96d2d246dd269d57b233c1798d2ad63d6cd64ca02f7bf71045028781f\"},\"logging\":{\"proxyLogsDir\":\"/tmp/gh-aw/sandbox/firewall/logs\",\"auditDir\":\"/tmp/gh-aw/sandbox/firewall/audit\"}}" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- cp "${RUNNER_TEMP}/gh-aw/awf-config.json" /tmp/gh-aw/awf-config.json
- export GH_AW_MODELS_JSON_PATH="/tmp/gh-aw/models.json"
- GH_AW_DOCKER_HOST=""
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- GH_AW_DOCKER_HOST="${DOCKER_HOST}"
- fi
- if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then
- _GH_AW_CHROOT_JSON=$(jq -c --arg src "${RUNNER_TEMP}/gh-aw" --arg user "$(id -un)" --argjson uid "$(id -u)" --argjson gid "$(id -g)" --arg home "${RUNNER_TEMP}/gh-aw/home" '.chroot={"binariesSourcePath":$src,"identity":{"user":$user,"uid":$uid,"gid":$gid,"home":$home}}' "${RUNNER_TEMP}/gh-aw/awf-config.json") || { echo "chroot config patch failed" >&2; exit 1; }
- printf '%s\n' "$_GH_AW_CHROOT_JSON" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- printf '%s\n' "$_GH_AW_CHROOT_JSON" > "${RUNNER_TEMP}/gh-aw/awf-config.json"
- fi
- GH_AW_TOOL_CACHE_MOUNT=""
- GH_AW_TOOL_CACHE="${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"
- if [ -d "$GH_AW_TOOL_CACHE" ]; then
- if [[ "$GH_AW_TOOL_CACHE" != /opt/* ]]; then
- GH_AW_TOOL_CACHE_MOUNT="$GH_AW_TOOL_CACHE:$GH_AW_TOOL_CACHE:ro"
- fi
- fi
- # shellcheck disable=SC1003,SC2016,SC2086
- awf --config "${RUNNER_TEMP}/gh-aw/awf-config.json" --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" ${GH_AW_TOOL_CACHE_MOUNT:+--mount "$GH_AW_TOOL_CACHE_MOUNT"} ${GH_AW_DOCKER_HOST:+--docker-host "$GH_AW_DOCKER_HOST"} --env-all --exclude-env COPILOT_GITHUB_TOKEN --log-level info --skip-pull \
- -- /bin/bash -c 'set +o histexpand; : "${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"; GH_AW_TOOL_CACHE="$RUNNER_TOOL_CACHE"; export PATH="$(find "$GH_AW_TOOL_CACHE" -maxdepth 5 -type d -name bin 2>/dev/null | tr '\''\n'\'' '\'':'\'')$PATH"; [ -n "$GOROOT" ] && export PATH="$GOROOT/bin:$PATH" || true; [ -n "$ERLANG_HOME" ] && export PATH="$ERLANG_HOME/bin:$PATH" || true && GH_AW_NODE_EXEC="${GH_AW_NODE_BIN:-}"; if [ -z "$GH_AW_NODE_EXEC" ] || [ ! -x "$GH_AW_NODE_EXEC" ]; then GH_AW_NODE_EXEC="$(command -v node 2>/dev/null || true)"; fi; if [ -z "$GH_AW_NODE_EXEC" ]; then echo "node runtime missing on this runner — check runtimes.node in workflow YAML" >&2; exit 127; fi; GH_AW_NPM_GLOBAL_ROOT="$(npm root -g 2>/dev/null || true)"; if [ -n "$GH_AW_NPM_GLOBAL_ROOT" ]; then export NODE_PATH="${GH_AW_NPM_GLOBAL_ROOT}${NODE_PATH:+:${NODE_PATH}}"; fi; "$GH_AW_NODE_EXEC" ${RUNNER_TEMP}/gh-aw/actions/copilot_harness.cjs /usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --no-ask-user --allow-all-tools --add-dir "${GITHUB_WORKSPACE}" --prompt-file /tmp/gh-aw/aw-prompts/prompt.txt' 2>&1 | tee -a /tmp/gh-aw/threat-detection/detection.log
- env:
- AWF_REFLECT_ENABLED: 1
- COPILOT_AGENT_RUNNER_TYPE: STANDALONE
- COPILOT_DUMMY_BYOK: dummy-byok-key-for-offline-mode
- COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}
- COPILOT_MODEL: ${{ vars.GH_AW_MODEL_DETECTION_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }}
- GH_AW_LLM_PROVIDER: github
- GH_AW_MAX_AI_CREDITS: ${{ vars.GH_AW_DEFAULT_DETECTION_MAX_AI_CREDITS || '400' }}
- GH_AW_MAX_TURNS: ${{ vars.GH_AW_DEFAULT_MAX_TURNS || '' }}
- GH_AW_PHASE: detection
- GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt
- GH_AW_TIMEOUT_MINUTES: 20
- GH_AW_VERSION: v0.83.4
- GITHUB_API_URL: ${{ github.api_url }}
- GITHUB_AW: true
- GITHUB_COPILOT_INTEGRATION_ID: agentic-workflows
- GITHUB_HEAD_REF: ${{ github.head_ref }}
- GITHUB_REF_NAME: ${{ github.ref_name }}
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_STEP_SUMMARY: /tmp/gh-aw/agent-step-summary.md
- GITHUB_WORKSPACE: ${{ github.workspace }}
- GIT_AUTHOR_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_AUTHOR_NAME: github-actions[bot]
- GIT_COMMITTER_EMAIL: github-actions[bot]@users.noreply.github.com
- GIT_COMMITTER_NAME: github-actions[bot]
- RUNNER_TEMP: ${{ runner.temp }}
- TRACEPARENT: ${{ env.GITHUB_AW_OTEL_TRACE_ID != '' && env.GITHUB_AW_OTEL_PARENT_SPAN_ID != '' && format('00-{0}-{1}-01', env.GITHUB_AW_OTEL_TRACE_ID, env.GITHUB_AW_OTEL_PARENT_SPAN_ID) || '' }}
- - name: Parse threat detection token usage for step summary
- id: parse_detection_token_usage
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_TOKEN_USAGE_SUMMARY_TITLE: Threat Detection Token Usage
- with:
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_token_usage.cjs');
- await main();
- - name: Upload threat detection log
- if: always() && steps.detection_guard.outputs.run_detection == 'true'
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: detection
- path: /tmp/gh-aw/threat-detection/detection.log
- if-no-files-found: ignore
- - name: Parse and conclude threat detection
- id: detection_conclusion
- if: always()
- continue-on-error: true
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- RUN_DETECTION: ${{ steps.detection_guard.outputs.run_detection }}
- DETECTION_AGENTIC_EXECUTION_OUTCOME: ${{ steps.detection_agentic_execution.outcome }}
- GH_AW_DETECTION_CONTINUE_ON_ERROR: "true"
- with:
- script: |
- try {
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/parse_threat_detection_results.cjs');
- await main();
- } catch (loadErr) {
- const continueOnError = process.env.GH_AW_DETECTION_CONTINUE_ON_ERROR !== 'false';
- const detectionExecutionFailed = process.env.DETECTION_AGENTIC_EXECUTION_OUTCOME === 'failure';
- const msg = 'ERR_SYSTEM: \u274C Unexpected error loading threat detection module: ' + (loadErr && loadErr.message ? loadErr.message : String(loadErr));
- core.error(msg);
- core.setOutput('reason', 'parse_error');
- if (continueOnError && !detectionExecutionFailed) {
- core.warning('\u26A0\uFE0F ' + msg);
- core.setOutput('conclusion', 'warning');
- core.setOutput('success', 'false');
- } else {
- core.setOutput('conclusion', 'failure');
- core.setOutput('success', 'false');
- core.setFailed(msg);
- }
- }
-
- safe_outputs:
- needs:
- - activation
- - agent
- - detection
- if: (!cancelled()) && needs.agent.result != 'skipped' && needs.detection.result == 'success'
- runs-on: ubuntu-slim
- permissions:
- contents: read
- issues: write
- timeout-minutes: 45
- env:
- GH_AW_AGENT_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_AIC: ${{ needs.agent.outputs.aic }}
- GH_AW_AMBIENT_CONTEXT: ${{ needs.agent.outputs.ambient_context }}
- GH_AW_CALLER_WORKFLOW_ID: "${{ github.repository }}/zipt-code-reviewer"
- GH_AW_DETECTION_CONCLUSION: ${{ needs.detection.outputs.detection_conclusion }}
- GH_AW_DETECTION_REASON: ${{ needs.detection.outputs.detection_reason }}
- GH_AW_EFFECTIVE_TOKENS: ${{ needs.agent.outputs.effective_tokens }}
- GH_AW_ENGINE_ID: "copilot"
- GH_AW_ENGINE_MODEL: ${{ needs.agent.outputs.model }}
- GH_AW_ENGINE_VERSION: "1.0.75"
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }}
- GH_AW_WORKFLOW_ID: "zipt-code-reviewer"
- GH_AW_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/zipt-code-reviewer.md"
- 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 }}
- create_discussion_error_count: ${{ steps.process_safe_outputs.outputs.create_discussion_error_count }}
- create_discussion_errors: ${{ steps.process_safe_outputs.outputs.create_discussion_errors }}
- created_issue_number: ${{ steps.process_safe_outputs.outputs.created_issue_number }}
- created_issue_url: ${{ steps.process_safe_outputs.outputs.created_issue_url }}
- process_safe_outputs_processed_count: ${{ steps.process_safe_outputs.outputs.processed_count }}
- process_safe_outputs_temporary_id_map: ${{ steps.process_safe_outputs.outputs.temporary_id_map }}
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/zipt-code-reviewer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download agent output artifact
- id: download-agent-output
- continue-on-error: true
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- with:
- name: agent
- path: /tmp/gh-aw/
- - name: Setup agent output environment variable
- id: setup-agent-output-env
- 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" >> "$GITHUB_OUTPUT"
- - name: Configure GH_HOST for enterprise compatibility
- id: ghes-host-config
- shell: bash
- run: | # zizmor: ignore[github-env] - GITHUB_SERVER_URL is set by GitHub Actions, not user input.
- # Derive GH_HOST from GITHUB_SERVER_URL so the gh CLI targets the correct
- # GitHub instance (GHES/GHEC). On github.com this is a harmless no-op.
- GH_HOST="${GITHUB_SERVER_URL#https://}"
- GH_HOST="${GH_HOST#http://}"
- echo "GH_HOST=${GH_HOST}" >> "$GITHUB_ENV"
- - name: Process Safe Outputs
- id: process_safe_outputs
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
- env:
- GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }}
- GH_AW_COMMENT_ID: ${{ needs.activation.outputs.comment_id }}
- GH_AW_ALLOWED_DOMAINS: "*.githubusercontent.com,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,codeload.github.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,docs.github.com,github-cloud.githubusercontent.com,github-cloud.s3.amazonaws.com,github.blog,github.com,github.githubassets.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,lfs.github.com,objects.githubusercontent.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,patch-diff.githubusercontent.com,patchdiff.githubusercontent.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"
- GITHUB_SERVER_URL: ${{ github.server_url }}
- GITHUB_API_URL: ${{ github.api_url }}
- GH_AW_SAFE_OUTPUTS_HANDLER_CONFIG: "{\"create_issue\":{\"labels\":[\"code-quality\",\"automated\",\"string-solver\"],\"max\":3,\"title_prefix\":\"[zipt-review] \"},\"create_report_incomplete_issue\":{},\"missing_data\":{},\"missing_tool\":{},\"noop\":{\"max\":1,\"report-as-issue\":\"false\"},\"report_incomplete\":{}}"
- with:
- github-token: ${{ secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }}
- script: |
- const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs');
- setupGlobals(core, github, context, exec, io, getOctokit);
- const { main } = require('${{ runner.temp }}/gh-aw/actions/process_safe_outputs.cjs');
- await main();
- - name: Upload Safe Outputs Items
- if: always()
- uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
- with:
- name: safe-outputs-items
- path: |
- /tmp/gh-aw/safe-output-items.jsonl
- /tmp/gh-aw/temporary-id-map.json
- /tmp/gh-aw/process-safe-outputs.stdout.log
- /tmp/gh-aw/process-safe-outputs.stderr.log
- if-no-files-found: ignore
-
- update_cache_memory:
- needs:
- - activation
- - agent
- - detection
- if: always() && needs.detection.result == 'success' && needs.agent.result == 'success'
- runs-on: ubuntu-slim
- permissions:
- actions: write
- env:
- GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }}
- GH_AW_WORKFLOW_ID_SANITIZED: ziptcodereviewer
- steps:
- - name: Setup Scripts
- id: setup
- uses: github/gh-aw-actions/setup@v0.83.4
- with:
- destination: ${{ runner.temp }}/gh-aw/actions
- job-name: ${{ github.job }}
- trace-id: ${{ needs.activation.outputs.setup-trace-id }}
- parent-span-id: ${{ needs.activation.outputs.setup-parent-span-id || needs.activation.outputs.setup-span-id }}
- env:
- GH_AW_SETUP_WORKFLOW_NAME: "ZIPT Code Reviewer"
- GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/zipt-code-reviewer.lock.yml@${{ github.ref }}
- GH_AW_INFO_VERSION: "1.0.75"
- GH_AW_INFO_AWF_VERSION: "v0.27.42"
- GH_AW_INFO_ENGINE_ID: "copilot"
- - name: Download cache-memory artifact (default)
- id: download_cache_default
- uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
- continue-on-error: true
- with:
- name: cache-memory
- path: /tmp/gh-aw/cache-memory
- - name: Check if cache-memory folder has content (default)
- id: check_cache_default
- shell: bash
- run: |
- if [ -d "/tmp/gh-aw/cache-memory" ] && [ "$(ls -A /tmp/gh-aw/cache-memory 2>/dev/null)" ]; then
- echo "has_content=true" >> "$GITHUB_OUTPUT"
- else
- echo "has_content=false" >> "$GITHUB_OUTPUT"
- fi
- - name: Save cache-memory to cache (default)
- if: steps.check_cache_default.outputs.has_content == 'true'
- uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
- with:
- key: memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}-${{ github.run_id }}
- path: /tmp/gh-aw/cache-memory
diff --git a/.github/workflows/zipt-code-reviewer.md b/.github/workflows/zipt-code-reviewer.md
deleted file mode 100644
index 1ec51eb49f..0000000000
--- a/.github/workflows/zipt-code-reviewer.md
+++ /dev/null
@@ -1,261 +0,0 @@
----
-description: Reviews Z3 string/sequence graph implementation (euf_sgraph, euf_seq_plugin, src/smt/seq) by comparing with the ZIPT reference implementation and reporting improvements as git diffs in GitHub issues
-
-on:
- schedule: daily
- workflow_dispatch:
-
-permissions: read-all
-
-network:
- allowed:
- - defaults
- - github
-
-tools:
- cache-memory: true
- github:
- toolsets: [default]
- edit: {}
- web-fetch: {}
- bash:
- - "git diff:*"
- - "git log:*"
- - "git show:*"
- - "git status"
- - "clang-format:*"
-
-safe-outputs:
- report-failure-as-issue: false
- create-issue:
- title-prefix: "[zipt-review] "
- labels: [code-quality, automated, string-solver]
- max: 3
- missing-tool:
- create-issue: true
- noop:
- report-as-issue: false
-
-timeout-minutes: 30
-
-steps:
- - name: Checkout repository
- uses: actions/checkout@v6.0.2
- with:
- persist-credentials: false
-
----
-
-# ZIPT Code Reviewer
-
-You are an expert C++ code reviewer specializing in string constraint solvers and the Z3 theorem prover. Your mission is to compare Z3's string/sequence graph implementation with the reference ZIPT implementation, identify concrete code improvements, and present them as git diffs in a GitHub issue.
-
-## Current Context
-
-- **Repository**: ${{ github.repository }}
-- **Workspace**: ${{ github.workspace }}
-- **ZIPT Reference**: https://github.com/CEisenhofer/ZIPT/tree/parikh/ZIPT
-
-## Phase 1: Read Z3 Source Files
-
-Read each of the following Z3 source files in full:
-
-### String Graph (euf_sgraph / euf_snode)
-- `src/ast/euf/euf_snode.h`
-- `src/ast/euf/euf_sgraph.h`
-- `src/ast/euf/euf_sgraph.cpp`
-
-### Sequence Plugin (euf_seq_plugin)
-- `src/ast/euf/euf_seq_plugin.h`
-- `src/ast/euf/euf_seq_plugin.cpp`
-
-### SMT Sequence Theory (src/smt/seq*)
-Use the glob tool to find all relevant files:
-```
-src/smt/seq*.h
-src/smt/seq*.cpp
-```
-Read each matched file.
-
-## Phase 2: Fetch ZIPT Reference Implementation
-
-The ZIPT project (https://github.com/CEisenhofer/ZIPT/tree/parikh/ZIPT) is the reference C# implementation that the Z3 string solver is ported from. Fetch the relevant source files to understand the reference algorithms.
-
-### Step 2.1: Discover ZIPT File Structure
-
-Fetch the ZIPT repository tree to understand the structure:
-
-```
-https://raw.githubusercontent.com/CEisenhofer/ZIPT/parikh/ZIPT/
-```
-
-Try fetching these likely ZIPT source directories and files:
-
-1. Repository root listing: `https://api.github.com/repos/CEisenhofer/ZIPT/git/trees/parikh?recursive=1`
-2. Key ZIPT source files (fetch the ones you find relevant from the tree):
- - Look for files related to: string graphs, sequence plugins, Nielsen graph, Parikh constraints, polynomial hashing, substitution caching
- - The ZIPT project is written in C#; the Z3 implementation is a C++ port
-
-When fetching files, use the raw content URL pattern:
-```
-https://raw.githubusercontent.com/CEisenhofer/ZIPT/parikh/ZIPT/
-```
-
-### Step 2.2: Identify Corresponding ZIPT Files
-
-For each Z3 file you read in Phase 1, identify the ZIPT file(s) that implement the same functionality. Focus on:
-- String/sequence graph data structures (snode, sgraph equivalents)
-- Concat associativity propagation
-- Nullable computation
-- Kleene star / regex handling
-- Polynomial hash matrix computation
-- Substitution caching
-
-## Phase 3: Analyze and Identify Improvements
-
-Compare the Z3 C++ implementation against the ZIPT C# reference. For each file pair, look for:
-
-### 3.1 Algorithmic Improvements
-- Missing algorithms or edge cases present in ZIPT but absent from Z3
-- More efficient data structures used in ZIPT
-- Better asymptotic complexity in ZIPT for key operations
-- Missing optimizations (e.g., short-circuit evaluations, caching strategies)
-
-### 3.2 Correctness Issues
-- Logic discrepancies between Z3 and ZIPT for the same algorithm
-- Missing null/empty checks present in ZIPT
-- Incorrect handling of edge cases (empty strings, epsilon, absorbing elements)
-- Off-by-one errors or boundary condition mistakes
-
-### 3.3 Code Quality Improvements
-- Functions in ZIPT that are cleaner or more modular than the Z3 port
-- Missing early-exit conditions
-- Redundant computations that ZIPT avoids
-- Better naming or structure in ZIPT that could improve Z3 readability
-
-### 3.4 Missing Features
-- ZIPT functionality not yet ported to Z3
-- Incomplete ports where only part of the ZIPT logic was transferred
-
-## Phase 4: Implement Improvements as Code Changes
-
-For each improvement identified in Phase 3:
-
-1. **Assess feasibility**: Only implement improvements that are:
- - Self-contained (don't require large architectural changes)
- - Verifiable (you can confirm correctness by reading the code)
- - Safe (don't change public API signatures)
-
-2. **Apply the change** using the edit tool to modify the Z3 source file
-
-3. **Track each change**: Note the file, line range, and rationale
-
-Focus on at most **5 concrete, high-value improvements** per run to keep changes focused and reviewable.
-
-## Phase 5: Generate Git Diff
-
-After applying all changes:
-
-```bash
-# Check what was modified
-git status
-
-# Generate a unified diff of all changes
-git diff > /tmp/zipt-improvements.diff
-
-# Read the diff
-cat /tmp/zipt-improvements.diff
-```
-
-If no changes were made because no improvements were found or all were too risky, call the `noop` safe-output tool:
-
-```
-noop: "ZIPT code review complete. No concrete improvements found in this run. Files examined: [list files]. ZIPT files compared: [list files]."
-```
-
-## Phase 6: Create GitHub Issue
-
-If improvements were found and changes were applied, create a GitHub issue using the safe-outputs configuration.
-
-Structure the issue body as follows:
-
-```markdown
-## ZIPT Code Review: Improvements from Reference Implementation
-
-**Date**: [today's date]
-**Files Reviewed**: [list of Z3 files examined]
-**ZIPT Reference**: https://github.com/CEisenhofer/ZIPT/tree/parikh/ZIPT
-
-### Summary
-
-[2-3 sentence summary of what was found and changed]
-
-### Improvements Applied
-
-For each improvement:
-
-#### Improvement N: [Short title]
-
-**File**: `path/to/z3/file.cpp`
-**Rationale**: [Why this improves the code, with reference to the ZIPT equivalent]
-**ZIPT Reference**: [URL or file path of the corresponding ZIPT code]
-
-### Git Diff
-
-The following diff can be applied with `git apply`:
-
-```diff
-[FULL GIT DIFF OUTPUT HERE]
-```
-
-To apply:
-```bash
-git apply - << 'EOF'
-[FULL GIT DIFF OUTPUT HERE]
-EOF
-```
-
-### Testing
-
-After applying this diff, build and test with:
-```bash
-mkdir -p build && cd build
-cmake ..
-make -j$(nproc)
-make test-z3
-./test-z3 euf_sgraph
-./test-z3 euf_seq_plugin
-```
-
----
-*Generated by ZIPT Code Reviewer agent — comparing Z3 implementation with CEisenhofer/ZIPT@parikh*
-```
-
-## Important: Always Call a Safe Output Tool
-
-**You MUST always call at least one safe-output tool before finishing.** Failing to do so is reported as a workflow failure.
-
-- If you found and applied improvements → call `create_issue`
-- If ZIPT is unreachable, no improvements were found, or all improvements are out of scope → call `noop` with a brief explanation
-
-### Scope
-- **Only** examine the files listed in Phase 1
-- **Only** compare against the ZIPT reference at https://github.com/CEisenhofer/ZIPT/tree/parikh/ZIPT
-- Do **not** modify test files
-- Do **not** change public API signatures
-
-### Quality Bar
-- Every change must be demonstrably better than the current code
-- Cite the specific ZIPT file and function for each improvement
-- Prefer small, surgical changes over large refactors
-
-### Exit Conditions
-Call `noop` (instead of creating an issue) if:
-- ZIPT repository is unreachable
-- No concrete, safe improvements can be identified
-- All identified improvements require architectural changes beyond the scope of a single diff
-
-Example noop call:
-```
-noop: "ZIPT code review complete. No improvements applied: [brief reason, e.g. ZIPT unreachable / no safe changes identified]. Files reviewed: [list]."
-```