diff --git a/.github/workflows/qf-s-benchmark.lock.yml b/.github/workflows/qf-s-benchmark.lock.yml deleted file mode 100644 index e481c712dc..0000000000 --- a/.github/workflows/qf-s-benchmark.lock.yml +++ /dev/null @@ -1,1572 +0,0 @@ -# gh-aw-metadata: {"schema_version":"v4","frontmatter_hash":"d46f6f1f939df67ce5b7bf1e8073ba03c5631381df51d9711a1c2091400233f7","body_hash":"31e198b5f33dc3ac3830a2e6f90bb70ca3e7947b5ba4ee113ca0fdab61ac0467","compiler_version":"v0.81.6","strict":true,"agent_id":"copilot","engine_versions":{"copilot":"1.0.65"}} -# 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":"27d5ce7f107fe9357f9df03efb73ab90386fccae","version":"v5.0.5"},{"repo":"actions/cache/save","sha":"27d5ce7f107fe9357f9df03efb73ab90386fccae","version":"v5.0.5"},{"repo":"actions/checkout","sha":"9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0","version":"v7.0.0"},{"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":"48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e","version":"v6.4.0"},{"repo":"actions/upload-artifact","sha":"043fb46d1a93c77aae656e7c1c64a875d1fc6a0a","version":"v7.0.1"},{"repo":"github/gh-aw-actions/setup","sha":"ba6380cc6e5be5d21677bebe04d52fb48e3abec7","version":"v0.81.6"}],"containers":[{"image":"ghcr.io/github/gh-aw-firewall/agent:0.27.11","digest":"sha256:979723c628182da7729333f2208bb249fd25ddee579645cf9a3892d681a929c7","pinned_image":"ghcr.io/github/gh-aw-firewall/agent:0.27.11@sha256:979723c628182da7729333f2208bb249fd25ddee579645cf9a3892d681a929c7"},{"image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.27.11","digest":"sha256:807e4831999b44513b0a66e5859d478dc4da7ae74ab1918cec967d513f95bf9d","pinned_image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.27.11@sha256:807e4831999b44513b0a66e5859d478dc4da7ae74ab1918cec967d513f95bf9d"},{"image":"ghcr.io/github/gh-aw-firewall/squid:0.27.11","digest":"sha256:ff27ea0525ad953a6adee28a5fbe9d2e22be47dbec755c15767af4ea3f91df7d","pinned_image":"ghcr.io/github/gh-aw-firewall/squid:0.27.11@sha256:ff27ea0525ad953a6adee28a5fbe9d2e22be47dbec755c15767af4ea3f91df7d"},{"image":"ghcr.io/github/gh-aw-mcpg:v0.3.30","digest":"sha256:35625d1a2269b1238606078c879f59a91cffc4ac33eb54bf39c6418822c1a8be","pinned_image":"ghcr.io/github/gh-aw-mcpg:v0.3.30@sha256:35625d1a2269b1238606078c879f59a91cffc4ac33eb54bf39c6418822c1a8be"},{"image":"ghcr.io/github/gh-aw-node","digest":"sha256:529d02eb970b1161aa25c593a9c3df57fdfad5a8add328cb3b6eccef66f3183b","pinned_image":"ghcr.io/github/gh-aw-node@sha256:529d02eb970b1161aa25c593a9c3df57fdfad5a8add328cb3b6eccef66f3183b"},{"image":"ghcr.io/github/github-mcp-server:v1.4.0","digest":"sha256:2afb26356481d1a350e14544a6e160f7f7ec1561a1ea309b823665abf0309036","pinned_image":"ghcr.io/github/github-mcp-server:v1.4.0@sha256:2afb26356481d1a350e14544a6e160f7f7ec1561a1ea309b823665abf0309036"}]} -# This file was automatically generated by gh-aw (v0.81.6). 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/ -# -# Benchmark Z3 seq vs nseq string solvers on QF_S test suite from 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@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 -# - actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 -# - actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 -# - 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@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0 -# - actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 -# - github/gh-aw-actions/setup@ba6380cc6e5be5d21677bebe04d52fb48e3abec7 # v0.81.6 -# -# Container images used: -# - ghcr.io/github/gh-aw-firewall/agent:0.27.11@sha256:979723c628182da7729333f2208bb249fd25ddee579645cf9a3892d681a929c7 -# - ghcr.io/github/gh-aw-firewall/api-proxy:0.27.11@sha256:807e4831999b44513b0a66e5859d478dc4da7ae74ab1918cec967d513f95bf9d -# - ghcr.io/github/gh-aw-firewall/squid:0.27.11@sha256:ff27ea0525ad953a6adee28a5fbe9d2e22be47dbec755c15767af4ea3f91df7d -# - ghcr.io/github/gh-aw-mcpg:v0.3.30@sha256:35625d1a2269b1238606078c879f59a91cffc4ac33eb54bf39c6418822c1a8be -# - ghcr.io/github/gh-aw-node@sha256:529d02eb970b1161aa25c593a9c3df57fdfad5a8add328cb3b6eccef66f3183b -# - ghcr.io/github/github-mcp-server:v1.4.0@sha256:2afb26356481d1a350e14544a6e160f7f7ec1561a1ea309b823665abf0309036 - -name: "QF_S String Solver Benchmark" -on: - schedule: - - cron: "0 0,12 * * *" - 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: "QF_S String Solver 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 }} - 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@ba6380cc6e5be5d21677bebe04d52fb48e3abec7 # v0.81.6 - 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: "QF_S String Solver Benchmark" - GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/qf-s-benchmark.lock.yml@${{ github.ref }} - GH_AW_INFO_VERSION: "1.0.65" - GH_AW_INFO_AWF_VERSION: "v0.27.11" - 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: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || vars.GH_AW_DEFAULT_MODEL_COPILOT || 'claude-sonnet-4.6' }} - GH_AW_INFO_VERSION: "1.0.65" - GH_AW_INFO_AGENT_VERSION: "1.0.65" - GH_AW_INFO_CLI_VERSION: "v0.81.6" - GH_AW_INFO_WORKFLOW_NAME: "QF_S String Solver Benchmark" - GH_AW_INFO_EXPERIMENTAL: "false" - GH_AW_INFO_SUPPORTS_TOOLS_ALLOWLIST: "true" - GH_AW_INFO_STAGED: "false" - GH_AW_INFO_ALLOWED_DOMAINS: '["defaults"]' - GH_AW_INFO_FIREWALL_ENABLED: "true" - GH_AW_INFO_AWF_VERSION: "v0.27.11" - GH_AW_INFO_AWMG_VERSION: "" - GH_AW_INFO_FIREWALL_TYPE: "squid" - GH_AW_COMPILED_STRICT: "true" - uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 - with: - script: | - const { setupGlobals } = require('${{ 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: ${{ env.GH_AW_MAX_DAILY_AI_CREDITS != '' }} - continue-on-error: true - uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 - with: - key: agentic-workflow-usage-qfsbenchmark-${{ github.run_id }} - restore-keys: agentic-workflow-usage-qfsbenchmark- - 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: "QF_S String Solver Benchmark" - GH_AW_WORKFLOW_ID: "qf-s-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: ${{ secrets.COPILOT_GITHUB_TOKEN }} - - name: Checkout .github and .agents folders - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 - with: - persist-credentials: false - sparse-checkout: | - .github - .agents - .antigravity - .claude - .codex - .crush - .gemini - .opencode - .pi - sparse-checkout-cone-mode: true - fetch-depth: 1 - - name: Save agent config folders for base branch restoration - env: - GH_AW_AGENT_FOLDERS: ".agents .antigravity .claude .codex .crush .gemini .github .opencode .pi" - GH_AW_AGENT_FILES: ".crush.json AGENTS.md ANTIGRAVITY.md CLAUDE.md GEMINI.md PI.md opencode.jsonc" - # poutine:ignore untrusted_checkout_exec - run: bash "${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: "qf-s-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('${{ runner.temp }}/gh-aw/actions/check_workflow_timestamp_api.cjs'); - await main(); - - name: Check compile-agentic version - uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 - env: - GH_AW_COMPILED_VERSION: "v0.81.6" - with: - script: | - const { setupGlobals } = require('${{ 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_5a6a0f70a2d06d17_EOF' - - GH_AW_PROMPT_5a6a0f70a2d06d17_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_5a6a0f70a2d06d17_EOF' - - Tools: create_discussion, missing_tool, missing_data, noop - - GH_AW_PROMPT_5a6a0f70a2d06d17_EOF - cat "${RUNNER_TEMP}/gh-aw/prompts/mcp_cli_tools_prompt.md" - cat << 'GH_AW_PROMPT_5a6a0f70a2d06d17_EOF' - - The following GitHub context information is available for this workflow: - {{#if github.actor}} - - **actor**: __GH_AW_GITHUB_ACTOR__ - {{/if}} - {{#if github.repository}} - - **repository**: __GH_AW_GITHUB_REPOSITORY__ - {{/if}} - {{#if github.workspace}} - - **workspace**: __GH_AW_GITHUB_WORKSPACE__ - {{/if}} - {{#if github.event.issue.number || (github.aw.context.item_type == 'issue' && github.aw.context.item_number)}} - - **issue-number**: #__GH_AW_EXPR_802A9F6A__ - {{/if}} - {{#if github.event.discussion.number || (github.aw.context.item_type == 'discussion' && github.aw.context.item_number)}} - - **discussion-number**: #__GH_AW_EXPR_1A3A194A__ - {{/if}} - {{#if github.event.pull_request.number || (github.aw.context.item_type == 'pull_request' && github.aw.context.item_number)}} - - **pull-request-number**: #__GH_AW_EXPR_463A214A__ - {{/if}} - {{#if github.event.comment.id || github.aw.context.comment_id}} - - **comment-id**: __GH_AW_EXPR_FF1D34CE__ - {{/if}} - {{#if github.run_id}} - - **workflow-run-id**: __GH_AW_GITHUB_RUN_ID__ - {{/if}} - - - GH_AW_PROMPT_5a6a0f70a2d06d17_EOF - cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_5a6a0f70a2d06d17_EOF' - - {{#runtime-import .github/workflows/qf-s-benchmark.md}} - GH_AW_PROMPT_5a6a0f70a2d06d17_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: ${{ github.workflow }} - with: - script: | - const { setupGlobals } = require('${{ 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: ${{ github.workspace }} - GH_AW_MCP_CLI_SERVERS_LIST: '- `safeoutputs` — run `safeoutputs --help` to see available tools' - with: - script: | - const { setupGlobals } = require('${{ 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 "${RUNNER_TEMP}/gh-aw/actions/print_prompt_summary.sh" - - name: Upload activation artifact - if: success() - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 - with: - name: activation - include-hidden-files: true - path: | - /tmp/gh-aw/aw_info.json - /tmp/gh-aw/models.json - /tmp/gh-aw/aw-prompts/prompt.txt - /tmp/gh-aw/aw-prompts/prompt-template.txt - /tmp/gh-aw/aw-prompts/prompt-import-tree.json - /tmp/gh-aw/github_rate_limits.jsonl - /tmp/gh-aw/base - /tmp/gh-aw/.github/agents - /tmp/gh-aw/.github/skills - if-no-files-found: ignore - retention-days: 1 - - agent: - needs: activation - if: needs.activation.outputs.daily_ai_credits_exceeded != 'true' - runs-on: ubuntu-latest - permissions: read-all - concurrency: - group: "gh-aw-copilot-${{ 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: qfsbenchmark - 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 }} - inference_access_error: ${{ steps.detect-agent-errors.outputs.inference_access_error || '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@ba6380cc6e5be5d21677bebe04d52fb48e3abec7 # v0.81.6 - 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: "QF_S String Solver Benchmark" - GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/qf-s-benchmark.lock.yml@${{ github.ref }} - GH_AW_INFO_VERSION: "1.0.65" - GH_AW_INFO_AWF_VERSION: "v0.27.11" - 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: 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" 1.0.65 - env: - GH_HOST: github.com - - name: Install AWF binary - run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.27.11 - - 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: Download activation artifact - uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 - with: - name: activation - path: /tmp/gh-aw - - name: Restore agent config folders from base branch - if: steps.checkout-pr.outcome == 'success' - env: - GH_AW_AGENT_FOLDERS: ".agents .antigravity .claude .codex .crush .gemini .github .opencode .pi" - GH_AW_AGENT_FILES: ".crush.json 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:0.27.11@sha256:979723c628182da7729333f2208bb249fd25ddee579645cf9a3892d681a929c7 ghcr.io/github/gh-aw-firewall/api-proxy:0.27.11@sha256:807e4831999b44513b0a66e5859d478dc4da7ae74ab1918cec967d513f95bf9d ghcr.io/github/gh-aw-firewall/squid:0.27.11@sha256:ff27ea0525ad953a6adee28a5fbe9d2e22be47dbec755c15767af4ea3f91df7d ghcr.io/github/gh-aw-mcpg:v0.3.30@sha256:35625d1a2269b1238606078c879f59a91cffc4ac33eb54bf39c6418822c1a8be ghcr.io/github/gh-aw-node@sha256:529d02eb970b1161aa25c593a9c3df57fdfad5a8add328cb3b6eccef66f3183b ghcr.io/github/github-mcp-server:v1.4.0@sha256:2afb26356481d1a350e14544a6e160f7f7ec1561a1ea309b823665abf0309036 - - 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_1bab4c882b24ea44_EOF' - {"create_discussion":{"category":"agentic workflows","close_older_discussions":true,"expires":168,"fallback_to_issue":true,"max":1,"title_prefix":"[QF_S Benchmark] "},"create_report_incomplete_issue":{},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"false"},"report_incomplete":{}} - GH_AW_SAFE_OUTPUTS_CONFIG_1bab4c882b24ea44_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 \"[QF_S 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="host.docker.internal" - 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=$(id -g 2>/dev/null || echo '0') - case "${DOCKER_HOST:-}" in - unix://* ) DOCKER_SOCK_PATH="${DOCKER_HOST#unix://}" ;; - /* ) DOCKER_SOCK_PATH="$DOCKER_HOST" ;; - * ) DOCKER_SOCK_PATH=/var/run/docker.sock ;; - esac - DOCKER_SOCK_GID=$(stat -c '%g' "$DOCKER_SOCK_PATH" 2>/dev/null || echo '0') - export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host --name awmg-mcpg --add-host host.docker.internal:127.0.0.1 --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:v0.3.30' - - 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_f014db59cae17bc3_EOF | "$GH_AW_NODE" "${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.cjs" - { - "mcpServers": { - "github": { - "type": "stdio", - "container": "ghcr.io/github/github-mcp-server:v1.4.0", - "env": { - "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_TOKEN": "\${GITHUB_TOKEN}", - "GITHUB_WORKSPACE": "\${GITHUB_WORKSPACE}", - "RUNNER_TEMP": "\${RUNNER_TEMP}" - }, - "guard-policies": { - "write-sink": { - "accept": [ - "*" - ] - } - } - } - }, - "gateway": { - "port": $MCP_GATEWAY_PORT, - "domain": "${MCP_GATEWAY_DOMAIN}", - "apiKey": "${MCP_GATEWAY_API_KEY}", - "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" - } - } - GH_AW_MCP_CONFIG_f014db59cae17bc3_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 '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/v0.27.11/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\"]},\"apiProxy\":{\"enabled\":true,\"enableTokenSteering\":true,\"maxRuns\":500,\"maxAiCredits\":${GH_AW_MAX_AI_CREDITS},\"maxCacheMisses\":5,\"models\":{\"agent\":[\"sonnet-6x\",\"gpt-5.5\",\"gpt-5.4\",\"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\"],\"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*\"],\"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-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-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*\"],\"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*\"],\"large\":[\"sonnet\",\"gpt-5-pro\",\"gpt-5\",\"gemini-pro\"],\"mai-code\":[\"copilot/MAI-Code*\",\"copilot/mai-code*\",\"openai/MAI-Code*\"],\"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\"],\"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-4-5-*\",\"anthropic/*sonnet-4-5-*\",\"copilot/*sonnet-4-6*\",\"anthropic/*sonnet-4-6*\"],\"summarization\":[\"haiku\",\"gpt-5-mini\",\"gemini-flash-lite\",\"mini\"],\"vision\":[\"copilot/gemini-*image*\",\"google/gemini-*image*\",\"gemini/gemini-*image*\",\"copilot/gemini-*flash*\",\"google/gemini-*flash*\",\"gemini/gemini-*flash*\"]}},\"container\":{\"imageTag\":\"0.27.11,squid=sha256:ff27ea0525ad953a6adee28a5fbe9d2e22be47dbec755c15767af4ea3f91df7d,agent=sha256:979723c628182da7729333f2208bb249fd25ddee579645cf9a3892d681a929c7,api-proxy=sha256:807e4831999b44513b0a66e5859d478dc4da7ae74ab1918cec967d513f95bf9d\"}}" > "${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="${DOCKER_HOST}" - fi - GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS="" - if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then - GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS="--docker-host-path-prefix /tmp/gh-aw" - GH_AW_CHROOT_BINARIES_SOURCE_PATH=/tmp/gh-aw GH_AW_CHROOT_IDENTITY_HOME=/tmp/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,SC2086 - sudo -E 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"} ${GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS} --env-all --exclude-env COPILOT_GITHUB_TOKEN --exclude-env GITHUB_MCP_SERVER_TOKEN --exclude-env MCP_GATEWAY_API_KEY --log-level info --proxy-logs-dir /tmp/gh-aw/sandbox/firewall/logs --audit-dir /tmp/gh-aw/sandbox/firewall/audit --enable-host-access --allow-host-ports 80,443,8080 --skip-pull \ - -- /bin/bash -c 'set +o histexpand; export PATH="${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:$PATH" || true && GH_AW_NODE_EXEC="${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: 120 - GH_AW_VERSION: v0.81.6 - 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.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('${{ runner.temp }}/gh-aw/actions/collect_ndjson_output.cjs'); - await main(); - - name: Parse agent logs for step summary - if: always() - uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 - env: - GH_AW_AGENT_OUTPUT: /tmp/gh-aw/sandbox/agent/logs/ - with: - script: | - const { setupGlobals } = require('${{ 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('${{ runner.temp }}/gh-aw/actions/parse_mcp_gateway_log.cjs'); - await main(); - - name: Print firewall logs - if: always() - continue-on-error: true - env: - AWF_LOGS_DIR: /tmp/gh-aw/sandbox/firewall/logs - run: | - # Fix permissions on firewall logs/audit dirs so they can be uploaded as artifacts - # AWF runs with sudo, creating files owned by root - sudo chmod -R a+rX /tmp/gh-aw/sandbox/firewall 2>/dev/null || true - # Only run awf logs summary if awf command exists (it may not be installed if workflow failed before install step) - if command -v awf &> /dev/null; then - awf logs summary | tee -a "$GITHUB_STEP_SUMMARY" - else - echo 'AWF binary not installed, skipping firewall log summary' - fi - - 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.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-qf-s-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@ba6380cc6e5be5d21677bebe04d52fb48e3abec7 # v0.81.6 - 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: "QF_S String Solver Benchmark" - GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/qf-s-benchmark.lock.yml@${{ github.ref }} - GH_AW_INFO_VERSION: "1.0.65" - GH_AW_INFO_AWF_VERSION: "v0.27.11" - 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" >> "$GITHUB_OUTPUT" - - name: Collect usage artifact files - if: always() - continue-on-error: true - run: | - mkdir -p /tmp/gh-aw/usage/agent /tmp/gh-aw/usage/detection - echo "Usage artifact source file status:" - for file in /tmp/gh-aw/aw_info.json /tmp/gh-aw/aw-info.jsonl /tmp/gh-aw/agent_usage.json /tmp/gh-aw/agent_usage.jsonl /tmp/gh-aw/detection_usage.jsonl /tmp/gh-aw/github_rate_limits.jsonl /tmp/gh-aw/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall-audit-logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall/logs/api-proxy-logs/token-usage.jsonl /tmp/gh-aw/threat-detection/sandbox/firewall/audit/api-proxy-logs/token-usage.jsonl; do - [ -f "$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/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 ${{ runner.temp }}/gh-aw/actions/generate_usage_activity_summary.cjs - find /tmp/gh-aw/usage -type f -print | sort - - name: Upload usage artifact - if: always() - continue-on-error: true - uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 - with: - name: usage - path: | - /tmp/gh-aw/usage/aw_info.json - /tmp/gh-aw/usage/aw-info.jsonl - /tmp/gh-aw/usage/agent_usage.json - /tmp/gh-aw/usage/agent_usage.jsonl - /tmp/gh-aw/usage/detection_usage.jsonl - /tmp/gh-aw/usage/github_rate_limits.jsonl - /tmp/gh-aw/usage/agent/token_usage.jsonl - /tmp/gh-aw/usage/detection/token_usage.jsonl - /tmp/gh-aw/usage/activity/summary.json - if-no-files-found: ignore - - name: Restore daily AIC usage cache - id: restore-daily-aic-cache-conclusion - if: always() - continue-on-error: true - uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 - with: - key: agentic-workflow-usage-qfsbenchmark-${{ github.run_id }} - restore-keys: agentic-workflow-usage-qfsbenchmark- - 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('${{ runner.temp }}/gh-aw/actions/write_daily_aic_usage_cache.cjs'); - await main(); - - name: Save daily AIC usage cache - id: save-daily-aic-cache - if: always() - continue-on-error: true - uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 - with: - key: agentic-workflow-usage-qfsbenchmark-${{ 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: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }} - GH_AW_NOOP_MAX: "1" - GH_AW_WORKFLOW_NAME: "QF_S String Solver Benchmark" - GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/qf-s-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: "qf-s-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: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }} - GH_AW_WORKFLOW_NAME: "QF_S String Solver Benchmark" - GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/qf-s-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: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }} - GH_AW_MISSING_TOOL_CREATE_ISSUE: "true" - GH_AW_MISSING_TOOL_TITLE_PREFIX: "[missing tool]" - GH_AW_WORKFLOW_NAME: "QF_S String Solver Benchmark" - GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/qf-s-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: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }} - GH_AW_REPORT_INCOMPLETE_CREATE_ISSUE: "true" - GH_AW_WORKFLOW_NAME: "QF_S String Solver Benchmark" - GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/qf-s-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: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }} - GH_AW_WORKFLOW_NAME: "QF_S String Solver Benchmark" - GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/qf-s-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: "qf-s-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_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_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_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" - 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@ba6380cc6e5be5d21677bebe04d52fb48e3abec7 # v0.81.6 - 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: "QF_S String Solver Benchmark" - GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/qf-s-benchmark.lock.yml@${{ github.ref }} - GH_AW_INFO_VERSION: "1.0.65" - GH_AW_INFO_AWF_VERSION: "v0.27.11" - 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" >> "$GITHUB_OUTPUT" - - name: Checkout repository for patch context - if: needs.agent.outputs.has_patch == 'true' - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 - with: - persist-credentials: false - # --- Threat Detection --- - - name: Clean stale firewall files from agent artifact - run: | - rm -rf /tmp/gh-aw/sandbox/firewall/logs - rm -rf /tmp/gh-aw/sandbox/firewall/audit - - name: Download container images - run: bash "${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh" ghcr.io/github/gh-aw-firewall/agent:0.27.11@sha256:979723c628182da7729333f2208bb249fd25ddee579645cf9a3892d681a929c7 ghcr.io/github/gh-aw-firewall/api-proxy:0.27.11@sha256:807e4831999b44513b0a66e5859d478dc4da7ae74ab1918cec967d513f95bf9d ghcr.io/github/gh-aw-firewall/squid:0.27.11@sha256:ff27ea0525ad953a6adee28a5fbe9d2e22be47dbec755c15767af4ea3f91df7d - - 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: "QF_S String Solver Benchmark" - WORKFLOW_DESCRIPTION: "Benchmark Z3 seq vs nseq string solvers on QF_S test suite from 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('${{ runner.temp }}/gh-aw/actions/setup_threat_detection.cjs'); - await main(); - - name: Ensure threat-detection directory and log - if: always() && steps.detection_guard.outputs.run_detection == 'true' - run: | - mkdir -p /tmp/gh-aw/threat-detection - touch /tmp/gh-aw/threat-detection/detection.log - - name: Setup Node.js - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0 - with: - node-version: '24' - package-manager-cache: false - - name: Install GitHub Copilot CLI - run: bash "${RUNNER_TEMP}/gh-aw/actions/install_copilot_cli.sh" 1.0.65 - env: - GH_HOST: github.com - - name: Install AWF binary - run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.27.11 - - name: Execute GitHub Copilot CLI - if: always() && steps.detection_guard.outputs.run_detection == 'true' - continue-on-error: true - id: detection_agentic_execution - # Copilot CLI tool arguments (sorted): - timeout-minutes: 20 - run: | - set -o pipefail - printf '%s' "$(date +%s%3N)" > /tmp/gh-aw/agent_cli_start_ms.txt - trap '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="${GH_AW_MAX_AI_CREDITS:-400}" - printf '%s\n' "{\"\$schema\":\"https://github.com/github/gh-aw-firewall/releases/download/v0.27.11/awf-config.schema.json\",\"network\":{\"allowDomains\":[\"api.business.githubcopilot.com\",\"api.enterprise.githubcopilot.com\",\"api.github.com\",\"api.githubcopilot.com\",\"api.individual.githubcopilot.com\",\"github.com\",\"host.docker.internal\",\"registry.npmjs.org\",\"telemetry.enterprise.githubcopilot.com\"]},\"apiProxy\":{\"enabled\":true,\"enableTokenSteering\":true,\"maxRuns\":500,\"maxAiCredits\":${GH_AW_MAX_AI_CREDITS},\"maxCacheMisses\":5},\"container\":{\"imageTag\":\"0.27.11,squid=sha256:ff27ea0525ad953a6adee28a5fbe9d2e22be47dbec755c15767af4ea3f91df7d,agent=sha256:979723c628182da7729333f2208bb249fd25ddee579645cf9a3892d681a929c7,api-proxy=sha256:807e4831999b44513b0a66e5859d478dc4da7ae74ab1918cec967d513f95bf9d\"}}" > "${RUNNER_TEMP}/gh-aw/awf-config.json" - cp "${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 - GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS="" - if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then - GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS="--docker-host-path-prefix /tmp/gh-aw" - _GH_AW_CHROOT_JSON=$(jq -c --arg src /tmp/gh-aw --arg user "$(id -un)" --argjson uid "$(id -u)" --argjson gid "$(id -g)" --arg home /tmp/gh-aw/home '.chroot={"binariesSourcePath":$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" > "/tmp/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:$GH_AW_TOOL_CACHE:ro" - fi - fi - # shellcheck disable=SC1003,SC2086 - sudo -E awf --config "${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"} ${GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS} --env-all --exclude-env COPILOT_GITHUB_TOKEN --log-level info --proxy-logs-dir /tmp/gh-aw/sandbox/firewall/logs --audit-dir /tmp/gh-aw/sandbox/firewall/audit --enable-host-access --allow-host-ports 80,443,8080 --skip-pull \ - -- /bin/bash -c 'set +o histexpand; : "${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:$PATH" || true && GH_AW_NODE_EXEC="${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: v0.81.6 - 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 }}/qf-s-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: "1.0.65" - GH_AW_RUNTIME_FEATURES: ${{ vars.GH_AW_RUNTIME_FEATURES }} - GH_AW_THREAT_DETECTION_AIC: ${{ needs.detection.outputs.aic }} - GH_AW_WORKFLOW_ID: "qf-s-benchmark" - GH_AW_WORKFLOW_NAME: "QF_S String Solver Benchmark" - GH_AW_WORKFLOW_SOURCE_URL: "${{ github.server_url }}/${{ github.repository }}/blob/${{ github.ref_name }}/.github/workflows/qf-s-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@ba6380cc6e5be5d21677bebe04d52fb48e3abec7 # v0.81.6 - 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: "QF_S String Solver Benchmark" - GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/qf-s-benchmark.lock.yml@${{ github.ref }} - GH_AW_INFO_VERSION: "1.0.65" - GH_AW_INFO_AWF_VERSION: "v0.27.11" - 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\":\"[QF_S 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/safe_output_handler_manager.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 - if-no-files-found: ignore - diff --git a/.github/workflows/qf-s-benchmark.md b/.github/workflows/qf-s-benchmark.md deleted file mode 100644 index e57582d264..0000000000 --- a/.github/workflows/qf-s-benchmark.md +++ /dev/null @@ -1,405 +0,0 @@ ---- -description: Benchmark Z3 seq vs nseq string solvers on QF_S test suite from the c3 branch and post results as a GitHub discussion - -on: - schedule: - - cron: "0 0,12 * * *" - workflow_dispatch: - -permissions: read-all - -network: defaults - -tools: - bash: true - github: - toolsets: [default] - -safe-outputs: - report-failure-as-issue: false - create-discussion: - title-prefix: "[QF_S Benchmark] " - category: "Agentic Workflows" - close-older-discussions: true - missing-tool: - create-issue: true - noop: - report-as-issue: false - -timeout-minutes: 120 - -steps: - - name: Checkout c3 branch - uses: actions/checkout@v6.0.2 - with: - ref: c3 - fetch-depth: 1 - persist-credentials: false - ---- - -# QF_S String Solver Benchmark - -## Job Description - -Your name is ${{ github.workflow }}. You are an expert performance analyst for the Z3 theorem prover, specializing in the string/sequence theory. Your task is to benchmark the `seq` solver (classical string theory) against the `nseq` solver (ZIPT-based string theory) on the QF_S test suite from the `c3` branch, and post a structured report as a GitHub Discussion. - -The workspace already contains the `c3` branch (checked out by the preceding workflow step). - -## Phase 1: Set Up the Build Environment - -Install required build tools: - -```bash -sudo apt-get update -y -sudo apt-get install -y cmake ninja-build python3 python3-pip time -``` - -Verify tools: - -```bash -cmake --version -ninja --version -python3 --version -``` - -## Phase 2: Build Z3 in Release Mode - -Build Z3 in Release mode for accurate benchmark performance numbers and lower memory usage. Running `ninja` in the background with `&` is not allowed — concurrent C++ compilation and LLM inference can exhaust available RAM and kill the agent process. - -```bash -mkdir -p /tmp/z3-build -cd /tmp/z3-build -cmake "$GITHUB_WORKSPACE" \ - -G Ninja \ - -DCMAKE_BUILD_TYPE=Release \ - -DZ3_BUILD_TEST_EXECUTABLES=OFF \ - 2>&1 | tee /tmp/z3-cmake.log -ninja -j2 z3 2>&1 | tee /tmp/z3-build.log -``` - -Verify the binary was built: - -```bash -/tmp/z3-build/z3 --version -``` - -If the build fails, report it immediately and stop. - -Once the binary is confirmed working, call the `noop` safe-output tool with the message `"Z3 built successfully from the c3 branch. Benchmark starting — results will be posted as a GitHub Discussion once complete."` This keepalive call refreshes the safe-output MCP session before the long benchmark run begins, preventing a session timeout. - -## Phase 3: Discover QF_S Benchmark Files - -Find all `.smt2` benchmark files in the workspace that belong to the QF_S logic: - -```bash -# Search for explicit QF_S logic declarations -grep -rl 'QF_S' "$GITHUB_WORKSPACE" --include='*.smt2' 2>/dev/null > /tmp/qf_s_files.txt - -# Also look in dedicated benchmark directories -find "$GITHUB_WORKSPACE" \ - \( -path "*/QF_S/*" -o -path "*/qf_s/*" -o -path "*/benchmarks/*" \) \ - -name '*.smt2' 2>/dev/null >> /tmp/qf_s_files.txt - -# Deduplicate -sort -u /tmp/qf_s_files.txt -o /tmp/qf_s_files.txt - -TOTAL=$(wc -l < /tmp/qf_s_files.txt) -echo "Found $TOTAL QF_S benchmark files" -head -20 /tmp/qf_s_files.txt -``` - -If fewer than 5 files are found, also scan the entire workspace for any `.smt2` file that exercises string constraints: - -```bash -if [ "$TOTAL" -lt 5 ]; then - grep -rl 'declare.*String\|str\.\|seq\.' "$GITHUB_WORKSPACE" \ - --include='*.smt2' 2>/dev/null >> /tmp/qf_s_files.txt - sort -u /tmp/qf_s_files.txt -o /tmp/qf_s_files.txt - TOTAL=$(wc -l < /tmp/qf_s_files.txt) - echo "After extended search: $TOTAL files" -fi -``` - -Cap the benchmark set to keep total runtime under 60 minutes: - -```bash -# Use at most 300 files; take a random sample if more are available -if [ "$TOTAL" -gt 300 ]; then - shuf -n 300 /tmp/qf_s_files.txt > /tmp/qf_s_sample.txt -else - cp /tmp/qf_s_files.txt /tmp/qf_s_sample.txt -fi -SAMPLE=$(wc -l < /tmp/qf_s_sample.txt) -echo "Running benchmarks on $SAMPLE files" -``` - -## Phase 4: Run Benchmarks — seq vs nseq - -Run each benchmark with both solvers. Use a per-file timeout of 5 seconds. Set Z3's internal timeout to 4 seconds so it exits cleanly before the shell timeout fires. - -```bash -Z3=/tmp/z3-build/z3 -TIMEOUT_SEC=5 -Z3_TIMEOUT_SEC=4 -RESULTS=/tmp/benchmark-results.csv - -echo "file,seq_result,seq_time_ms,nseq_result,nseq_time_ms" > "$RESULTS" - -total=0 -done_count=0 -while IFS= read -r smt_file; do - total=$((total + 1)) - - # Run with seq solver; capture both stdout (z3 output) and stderr (time output) - SEQ_OUT=$({ time timeout "$TIMEOUT_SEC" "$Z3" \ - smt.string_solver=seq \ - -T:"$Z3_TIMEOUT_SEC" \ - "$smt_file" 2>/dev/null; } 2>&1) - SEQ_RESULT=$(echo "$SEQ_OUT" | grep -E '^(sat|unsat|unknown)' | head -1) - SEQ_MS=$(echo "$SEQ_OUT" | grep real | awk '{split($2,a,"m"); split(a[2],b,"s"); printf "%d", (a[1]*60+b[1])*1000}') - [ -z "$SEQ_RESULT" ] && SEQ_RESULT="timeout" - [ -z "$SEQ_MS" ] && SEQ_MS=$((TIMEOUT_SEC * 1000)) - - # Run with nseq solver; same structure - NSEQ_OUT=$({ time timeout "$TIMEOUT_SEC" "$Z3" \ - smt.string_solver=nseq \ - -T:"$Z3_TIMEOUT_SEC" \ - "$smt_file" 2>/dev/null; } 2>&1) - NSEQ_RESULT=$(echo "$NSEQ_OUT" | grep -E '^(sat|unsat|unknown)' | head -1) - NSEQ_MS=$(echo "$NSEQ_OUT" | grep real | awk '{split($2,a,"m"); split(a[2],b,"s"); printf "%d", (a[1]*60+b[1])*1000}') - [ -z "$NSEQ_RESULT" ] && NSEQ_RESULT="timeout" - [ -z "$NSEQ_MS" ] && NSEQ_MS=$((TIMEOUT_SEC * 1000)) - - SHORT=$(basename "$smt_file") - echo "$SHORT,$SEQ_RESULT,$SEQ_MS,$NSEQ_RESULT,$NSEQ_MS" >> "$RESULTS" - - done_count=$((done_count + 1)) - if [ $((done_count % 50)) -eq 0 ]; then - echo "Progress: $done_count / $SAMPLE files completed" - fi -done < /tmp/qf_s_sample.txt - -echo "Benchmark run complete: $done_count files" -``` - -## Phase 5: Collect Seq Traces for Interesting Cases - -For benchmarks where `seq` solves in under 2 s but `nseq` times out (seq-fast/nseq-slow cases), collect a brief `seq` trace to understand what algorithm is used: - -```bash -Z3=/tmp/z3-build/z3 -mkdir -p /tmp/traces - -# Find seq-fast / nseq-slow files: seq solved (sat/unsat) in <2000ms AND nseq timed out -awk -F, 'NR>1 && ($2=="sat"||$2=="unsat") && $3<2000 && $4=="timeout" {print $1}' \ - /tmp/benchmark-results.csv > /tmp/seq_fast_nseq_slow.txt -echo "seq-fast / nseq-slow files: $(wc -l < /tmp/seq_fast_nseq_slow.txt)" - -# Collect traces for at most 5 such cases -head -5 /tmp/seq_fast_nseq_slow.txt | while IFS= read -r short; do - # Find the full path - full=$(grep "/$short$" /tmp/qf_s_sample.txt | head -1) - [ -z "$full" ] && continue - timeout 5 "$Z3" \ - smt.string_solver=seq \ - -tr:seq \ - -T:5 \ - "$full" > "/tmp/traces/${short%.smt2}.seq.trace" 2>&1 || true -done -``` - -## Phase 6: Analyze Results - -Compute summary statistics from the CSV. Save the analysis script to a file and run it: - -```bash -cat > /tmp/analyze_benchmark.py << 'PYEOF' -import csv, sys - -results = [] -with open('/tmp/benchmark-results.csv') as f: - reader = csv.DictReader(f) - for row in reader: - results.append(row) - -total = len(results) -if total == 0: - print("No results found.") - sys.exit(0) - -def is_correct(r, solver): - prefix = 'seq' if solver == 'seq' else 'nseq' - return r[f'{prefix}_result'] in ('sat', 'unsat') - -def timed_out(r, solver): - prefix = 'seq' if solver == 'seq' else 'nseq' - return r[f'{prefix}_result'] == 'timeout' - -seq_solved = sum(1 for r in results if is_correct(r, 'seq')) -nseq_solved = sum(1 for r in results if is_correct(r, 'nseq')) -seq_to = sum(1 for r in results if timed_out(r, 'seq')) -nseq_to = sum(1 for r in results if timed_out(r, 'nseq')) - -seq_times = [int(r['seq_time_ms']) for r in results if is_correct(r, 'seq')] -nseq_times = [int(r['nseq_time_ms']) for r in results if is_correct(r, 'nseq')] - -def median(lst): - s = sorted(lst) - n = len(s) - return s[n//2] if n else 0 - -def mean(lst): - return sum(lst)//len(lst) if lst else 0 - -# Disagreements (sat vs unsat or vice-versa) -disagreements = [ - r for r in results - if r['seq_result'] in ('sat','unsat') - and r['nseq_result'] in ('sat','unsat') - and r['seq_result'] != r['nseq_result'] -] - -# seq-fast / nseq-slow: seq solved in <2s, nseq timed out -seq_fast_nseq_slow = [ - r for r in results - if is_correct(r, 'seq') and int(r['seq_time_ms']) < 2000 and timed_out(r, 'nseq') -] -# nseq-fast / seq-slow: nseq solved in <2s, seq timed out -nseq_fast_seq_slow = [ - r for r in results - if is_correct(r, 'nseq') and int(r['nseq_time_ms']) < 2000 and timed_out(r, 'seq') -] - -print(f"TOTAL={total}") -print(f"SEQ_SOLVED={seq_solved}") -print(f"NSEQ_SOLVED={nseq_solved}") -print(f"SEQ_TIMEOUTS={seq_to}") -print(f"NSEQ_TIMEOUTS={nseq_to}") -print(f"SEQ_MEDIAN_MS={median(seq_times)}") -print(f"NSEQ_MEDIAN_MS={median(nseq_times)}") -print(f"SEQ_MEAN_MS={mean(seq_times)}") -print(f"NSEQ_MEAN_MS={mean(nseq_times)}") -print(f"DISAGREEMENTS={len(disagreements)}") -print(f"SEQ_FAST_NSEQ_SLOW={len(seq_fast_nseq_slow)}") -print(f"NSEQ_FAST_SEQ_SLOW={len(nseq_fast_seq_slow)}") - -# Print top-10 slowest for nseq that seq handles fast -print("\nTOP_SEQ_FAST_NSEQ_SLOW:") -for r in sorted(seq_fast_nseq_slow, key=lambda x: -int(x['nseq_time_ms']))[:10]: - print(f" {r['file']} seq={r['seq_time_ms']}ms nseq={r['nseq_time_ms']}ms seq_result={r['seq_result']} nseq_result={r['nseq_result']}") - -print("\nTOP_NSEQ_FAST_SEQ_SLOW:") -for r in sorted(nseq_fast_seq_slow, key=lambda x: -int(x['seq_time_ms']))[:10]: - print(f" {r['file']} seq={r['seq_time_ms']}ms nseq={r['nseq_time_ms']}ms seq_result={r['seq_result']} nseq_result={r['nseq_result']}") - -if disagreements: - print(f"\nDISAGREEMENTS ({len(disagreements)}):") - for r in disagreements[:10]: - print(f" {r['file']} seq={r['seq_result']} nseq={r['nseq_result']}") -PYEOF - -python3 /tmp/analyze_benchmark.py -``` - -## Phase 7: Create GitHub Discussion - -Use the `create_discussion` safe-output tool to post a structured benchmark report. - -The discussion body should be formatted as follows (fill in real numbers from Phase 6): - -```markdown -# QF_S Benchmark: seq vs nseq - -**Date**: YYYY-MM-DD -**Branch**: c3 -**Commit**: `` -**Workflow Run**: [#](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}) -**Files benchmarked**: N (capped at 300, timeout 5 s per file) - ---- - -## Summary - -| Metric | seq | nseq | -|--------|-----|------| -| Files solved (sat/unsat) | SEQ_SOLVED | NSEQ_SOLVED | -| Timeouts | SEQ_TO | NSEQ_TO | -| Median solve time (solved files) | X ms | Y ms | -| Mean solve time (solved files) | X ms | Y ms | -| **Disagreements (sat≠unsat)** | — | N | - ---- - -## Performance Comparison - -### seq-fast / nseq-slow (seq < 2 s, nseq timed out) - -These are benchmarks where the classical `seq` solver is significantly faster. These represent regression risk for `nseq`. - -| File | seq (ms) | nseq (ms) | seq result | nseq result | -|------|----------|-----------|------------|-------------| -[TOP 10 ENTRIES] - -### nseq-fast / seq-slow (nseq < 2 s, seq timed out) - -These are benchmarks where `nseq` shows a performance advantage. - -| File | seq (ms) | nseq (ms) | seq result | nseq result | -|------|----------|-----------|------------|-------------| -[TOP 10 ENTRIES] - ---- - -## Correctness - -**Disagreements** (files where seq says `sat` but nseq says `unsat` or vice versa): N - -[If disagreements exist, list all of them here with file paths and both results] - ---- - -## seq Trace Analysis (seq-fast / nseq-slow cases) - -
-Click to expand trace snippets for top seq-fast/nseq-slow cases - -[Insert trace snippet for each traced file, or "No traces collected" if section was skipped] - -
- ---- - -## Raw Data - -
-Full results CSV (click to expand) - -```csv -[PASTE FIRST 200 LINES OF /tmp/benchmark-results.csv] -``` - -
- ---- - -*Generated by the QF_S Benchmark workflow. To reproduce: build Z3 from the `c3` branch and run `z3 smt.string_solver=seq|nseq -T:10 `.* -``` - -## Edge Cases - -- If the build fails, call `missing_data` explaining the build error and stop. -- If no benchmark files are found at all, call `missing_data` explaining that no QF_S `.smt2` files were found in the `c3` branch. -- If Z3 crashes (segfault) on a file with either solver, record the result as `crash` and continue. -- If the total benchmark set is very small (< 5 files), note this prominently in the discussion and suggest adding more QF_S benchmarks to the `c3` branch. -- If zero disagreements and both solvers time out on the same files, note that the solvers are in agreement. -- If `create_discussion` fails (e.g., MCP session error), call `report_incomplete` with the reason and include the top-line statistics (files solved, timeouts, disagreement count) in the `details` field. - -## Important Notes - -- **DO NOT** modify any source files or create pull requests. -- **DO NOT** run `ninja` or any build command in the background with `&` — concurrent C++ compilation and LLM inference can exhaust available RAM and kill the agent process. Always wait for build commands to complete before proceeding. -- **DO NOT** run benchmarks for longer than 100 minutes total (leave buffer for posting). -- **DO** always report the commit SHA so results can be correlated with specific code versions. -- **DO** close older QF_S Benchmark discussions automatically (configured via `close-older-discussions: true`). -- **DO** highlight disagreements prominently — these are potential correctness bugs. diff --git a/README.md b/README.md index 35ab011b72..5bb3c5d3a3 100644 --- a/README.md +++ b/README.md @@ -46,9 +46,9 @@ See the [release notes](RELEASE_NOTES.md) for notes on various stable releases o | -------------|-----------------|---------------|---------------------|-------------------| | [![API Coherence Checker](https://github.com/Z3Prover/z3/actions/workflows/api-coherence-checker.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/api-coherence-checker.lock.yml) | [![Code Simplifier](https://github.com/Z3Prover/z3/actions/workflows/code-simplifier.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/code-simplifier.lock.yml) | [![Release Notes Updater](https://github.com/Z3Prover/z3/actions/workflows/release-notes-updater.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/release-notes-updater.lock.yml) | [![Workflow Suggestion Agent](https://github.com/Z3Prover/z3/actions/workflows/workflow-suggestion-agent.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/workflow-suggestion-agent.lock.yml) | [![Academic Citation Tracker](https://github.com/Z3Prover/z3/actions/workflows/academic-citation-tracker.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/academic-citation-tracker.lock.yml) | -| Issue Backlog | Memory Safety Report | QF-S Benchmark | Specbot Crash Analyzer | SMTLIB Benchmark Finder | -| --------------|----------------------|----------------|------------------------|-------------------------| -| [![Issue Backlog Processor](https://github.com/Z3Prover/z3/actions/workflows/issue-backlog-processor.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/issue-backlog-processor.lock.yml) | [![Memory Safety Report](https://github.com/Z3Prover/z3/actions/workflows/memory-safety-report.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/memory-safety-report.lock.yml) | [![ZIPT String Solver Benchmark](https://github.com/Z3Prover/z3/actions/workflows/qf-s-benchmark.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/qf-s-benchmark.lock.yml) | [![Specbot Crash Analyzer](https://github.com/Z3Prover/z3/actions/workflows/specbot-crash-analyzer.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/specbot-crash-analyzer.lock.yml) | [![SMTLIB Benchmark Finder](https://github.com/Z3Prover/z3/actions/workflows/smtlib-benchmark-finder.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/smtlib-benchmark-finder.lock.yml) | +| Issue Backlog | Memory Safety Report | Specbot Crash Analyzer | SMTLIB Benchmark Finder | +| --------------|----------------------|------------------------|-------------------------| +| [![Issue Backlog Processor](https://github.com/Z3Prover/z3/actions/workflows/issue-backlog-processor.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/issue-backlog-processor.lock.yml) | [![Memory Safety Report](https://github.com/Z3Prover/z3/actions/workflows/memory-safety-report.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/memory-safety-report.lock.yml) | [![Specbot Crash Analyzer](https://github.com/Z3Prover/z3/actions/workflows/specbot-crash-analyzer.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/specbot-crash-analyzer.lock.yml) | [![SMTLIB Benchmark Finder](https://github.com/Z3Prover/z3/actions/workflows/smtlib-benchmark-finder.lock.yml/badge.svg)](https://github.com/Z3Prover/z3/actions/workflows/smtlib-benchmark-finder.lock.yml) | | TPTP Benchmark | |----------------| diff --git a/agentics/qf-s-benchmark.md b/agentics/qf-s-benchmark.md deleted file mode 100644 index 3ceb8f58e7..0000000000 --- a/agentics/qf-s-benchmark.md +++ /dev/null @@ -1,364 +0,0 @@ -# QF_S String Solver Benchmark - -## Job Description - -Your name is ${{ github.workflow }}. You are an expert performance analyst for the Z3 theorem prover, specializing in the string/sequence theory. Your task is to benchmark the `seq` solver (classical string theory) against the `nseq` solver (ZIPT-based string theory) on the QF_S test suite from the `c3` branch, and post a structured report as a GitHub Discussion. - -The workspace already contains the `c3` branch (checked out by the preceding workflow step). - -## Phase 1: Set Up the Build Environment - -Install required build tools: - -```bash -sudo apt-get update -y -sudo apt-get install -y cmake ninja-build python3 python3-pip time -``` - -Verify tools: - -```bash -cmake --version -ninja --version -python3 --version -``` - -## Phase 2: Build Z3 in Debug Mode with Seq Tracing - -Build Z3 with debug symbols so that tracing and timing data are meaningful. - -```bash -mkdir -p /tmp/z3-build -cd /tmp/z3-build -cmake "$GITHUB_WORKSPACE" \ - -G Ninja \ - -DCMAKE_BUILD_TYPE=Debug \ - -DZ3_BUILD_TEST_EXECUTABLES=OFF \ - 2>&1 | tee /tmp/z3-cmake.log -ninja z3 2>&1 | tee /tmp/z3-build.log -``` - -Verify the binary was built: - -```bash -/tmp/z3-build/z3 --version -``` - -If the build fails, report it immediately and stop. - -## Phase 3: Discover QF_S Benchmark Files - -Find all `.smt2` benchmark files in the workspace that belong to the QF_S logic: - -```bash -# Search for explicit QF_S logic declarations -grep -rl 'QF_S' "$GITHUB_WORKSPACE" --include='*.smt2' 2>/dev/null > /tmp/qf_s_files.txt - -# Also look in dedicated benchmark directories -find "$GITHUB_WORKSPACE" \ - \( -path "*/QF_S/*" -o -path "*/qf_s/*" -o -path "*/benchmarks/*" \) \ - -name '*.smt2' 2>/dev/null >> /tmp/qf_s_files.txt - -# Deduplicate -sort -u /tmp/qf_s_files.txt -o /tmp/qf_s_files.txt - -TOTAL=$(wc -l < /tmp/qf_s_files.txt) -echo "Found $TOTAL QF_S benchmark files" -head -20 /tmp/qf_s_files.txt -``` - -If fewer than 5 files are found, also scan the entire workspace for any `.smt2` file that exercises string constraints: - -```bash -if [ "$TOTAL" -lt 5 ]; then - grep -rl 'declare.*String\|str\.\|seq\.' "$GITHUB_WORKSPACE" \ - --include='*.smt2' 2>/dev/null >> /tmp/qf_s_files.txt - sort -u /tmp/qf_s_files.txt -o /tmp/qf_s_files.txt - TOTAL=$(wc -l < /tmp/qf_s_files.txt) - echo "After extended search: $TOTAL files" -fi -``` - -Cap the benchmark set to keep total runtime under 60 minutes: - -```bash -# Use at most 500 files; take a random sample if more are available -if [ "$TOTAL" -gt 500 ]; then - shuf -n 500 /tmp/qf_s_files.txt > /tmp/qf_s_sample.txt -else - cp /tmp/qf_s_files.txt /tmp/qf_s_sample.txt -fi -SAMPLE=$(wc -l < /tmp/qf_s_sample.txt) -echo "Running benchmarks on $SAMPLE files" -``` - -## Phase 4: Run Benchmarks — seq vs nseq - -Run each benchmark with both solvers. Use a per-file timeout of 10 seconds. Set Z3's internal timeout to 9 seconds so it exits cleanly before the shell timeout fires. - -```bash -Z3=/tmp/z3-build/z3 -TIMEOUT_SEC=10 -Z3_TIMEOUT_SEC=9 -RESULTS=/tmp/benchmark-results.csv - -echo "file,seq_result,seq_time_ms,nseq_result,nseq_time_ms" > "$RESULTS" - -total=0 -done_count=0 -while IFS= read -r smt_file; do - total=$((total + 1)) - - # Run with seq solver; capture both stdout (z3 output) and stderr (time output) - SEQ_OUT=$({ time timeout "$TIMEOUT_SEC" "$Z3" \ - smt.string_solver=seq \ - -T:"$Z3_TIMEOUT_SEC" \ - "$smt_file" 2>/dev/null; } 2>&1) - SEQ_RESULT=$(echo "$SEQ_OUT" | grep -E '^(sat|unsat|unknown)' | head -1) - SEQ_MS=$(echo "$SEQ_OUT" | grep real | awk '{split($2,a,"m"); split(a[2],b,"s"); printf "%d", (a[1]*60+b[1])*1000}') - [ -z "$SEQ_RESULT" ] && SEQ_RESULT="timeout" - [ -z "$SEQ_MS" ] && SEQ_MS=$((TIMEOUT_SEC * 1000)) - - # Run with nseq solver; same structure - NSEQ_OUT=$({ time timeout "$TIMEOUT_SEC" "$Z3" \ - smt.string_solver=nseq \ - -T:"$Z3_TIMEOUT_SEC" \ - "$smt_file" 2>/dev/null; } 2>&1) - NSEQ_RESULT=$(echo "$NSEQ_OUT" | grep -E '^(sat|unsat|unknown)' | head -1) - NSEQ_MS=$(echo "$NSEQ_OUT" | grep real | awk '{split($2,a,"m"); split(a[2],b,"s"); printf "%d", (a[1]*60+b[1])*1000}') - [ -z "$NSEQ_RESULT" ] && NSEQ_RESULT="timeout" - [ -z "$NSEQ_MS" ] && NSEQ_MS=$((TIMEOUT_SEC * 1000)) - - SHORT=$(basename "$smt_file") - echo "$SHORT,$SEQ_RESULT,$SEQ_MS,$NSEQ_RESULT,$NSEQ_MS" >> "$RESULTS" - - done_count=$((done_count + 1)) - if [ $((done_count % 50)) -eq 0 ]; then - echo "Progress: $done_count / $SAMPLE files completed" - fi -done < /tmp/qf_s_sample.txt - -echo "Benchmark run complete: $done_count files" -``` - -## Phase 5: Collect Seq Traces for Interesting Cases - -For benchmarks where `seq` solves in under 2 s but `nseq` times out (seq-fast/nseq-slow cases), collect a brief `seq` trace to understand what algorithm is used: - -```bash -Z3=/tmp/z3-build/z3 -mkdir -p /tmp/traces - -# Find seq-fast / nseq-slow files: seq solved (sat/unsat) in <2000ms AND nseq timed out -awk -F, 'NR>1 && ($2=="sat"||$2=="unsat") && $3<2000 && $4=="timeout" {print $1}' \ - /tmp/benchmark-results.csv > /tmp/seq_fast_nseq_slow.txt -echo "seq-fast / nseq-slow files: $(wc -l < /tmp/seq_fast_nseq_slow.txt)" - -# Collect traces for at most 5 such cases -head -5 /tmp/seq_fast_nseq_slow.txt | while IFS= read -r short; do - # Find the full path - full=$(grep "/$short$" /tmp/qf_s_sample.txt | head -1) - [ -z "$full" ] && continue - timeout 5 "$Z3" \ - smt.string_solver=seq \ - -tr:seq \ - -T:5 \ - "$full" > "/tmp/traces/${short%.smt2}.seq.trace" 2>&1 || true -done -``` - -## Phase 6: Analyze Results - -Compute summary statistics from the CSV: - -```bash -Save the analysis script to a file and run it: - -```bash -cat > /tmp/analyze_benchmark.py << 'PYEOF' -import csv, sys - -results = [] -with open('/tmp/benchmark-results.csv') as f: - reader = csv.DictReader(f) - for row in reader: - results.append(row) - -total = len(results) -if total == 0: - print("No results found.") - sys.exit(0) - -def is_correct(r, solver): - prefix = 'seq' if solver == 'seq' else 'nseq' - return r[f'{prefix}_result'] in ('sat', 'unsat') - -def timed_out(r, solver): - prefix = 'seq' if solver == 'seq' else 'nseq' - return r[f'{prefix}_result'] == 'timeout' - -seq_solved = sum(1 for r in results if is_correct(r, 'seq')) -nseq_solved = sum(1 for r in results if is_correct(r, 'nseq')) -seq_to = sum(1 for r in results if timed_out(r, 'seq')) -nseq_to = sum(1 for r in results if timed_out(r, 'nseq')) - -seq_times = [int(r['seq_time_ms']) for r in results if is_correct(r, 'seq')] -nseq_times = [int(r['nseq_time_ms']) for r in results if is_correct(r, 'nseq')] - -def median(lst): - s = sorted(lst) - n = len(s) - return s[n//2] if n else 0 - -def mean(lst): - return sum(lst)//len(lst) if lst else 0 - -# Disagreements (sat vs unsat or vice-versa) -disagreements = [ - r for r in results - if r['seq_result'] in ('sat','unsat') - and r['nseq_result'] in ('sat','unsat') - and r['seq_result'] != r['nseq_result'] -] - -# seq-fast / nseq-slow: seq solved in <2s, nseq timed out -seq_fast_nseq_slow = [ - r for r in results - if is_correct(r, 'seq') and int(r['seq_time_ms']) < 2000 and timed_out(r, 'nseq') -] -# nseq-fast / seq-slow: nseq solved in <2s, seq timed out -nseq_fast_seq_slow = [ - r for r in results - if is_correct(r, 'nseq') and int(r['nseq_time_ms']) < 2000 and timed_out(r, 'seq') -] - -print(f"TOTAL={total}") -print(f"SEQ_SOLVED={seq_solved}") -print(f"NSEQ_SOLVED={nseq_solved}") -print(f"SEQ_TIMEOUTS={seq_to}") -print(f"NSEQ_TIMEOUTS={nseq_to}") -print(f"SEQ_MEDIAN_MS={median(seq_times)}") -print(f"NSEQ_MEDIAN_MS={median(nseq_times)}") -print(f"SEQ_MEAN_MS={mean(seq_times)}") -print(f"NSEQ_MEAN_MS={mean(nseq_times)}") -print(f"DISAGREEMENTS={len(disagreements)}") -print(f"SEQ_FAST_NSEQ_SLOW={len(seq_fast_nseq_slow)}") -print(f"NSEQ_FAST_SEQ_SLOW={len(nseq_fast_seq_slow)}") - -# Print top-10 slowest for nseq that seq handles fast -print("\nTOP_SEQ_FAST_NSEQ_SLOW:") -for r in sorted(seq_fast_nseq_slow, key=lambda x: -int(x['nseq_time_ms']))[:10]: - print(f" {r['file']} seq={r['seq_time_ms']}ms nseq={r['nseq_time_ms']}ms seq_result={r['seq_result']} nseq_result={r['nseq_result']}") - -print("\nTOP_NSEQ_FAST_SEQ_SLOW:") -for r in sorted(nseq_fast_seq_slow, key=lambda x: -int(x['seq_time_ms']))[:10]: - print(f" {r['file']} seq={r['seq_time_ms']}ms nseq={r['nseq_time_ms']}ms seq_result={r['seq_result']} nseq_result={r['nseq_result']}") - -if disagreements: - print(f"\nDISAGREEMENTS ({len(disagreements)}):") - for r in disagreements[:10]: - print(f" {r['file']} seq={r['seq_result']} nseq={r['nseq_result']}") -PYEOF - -python3 /tmp/analyze_benchmark.py -``` - -## Phase 7: Create GitHub Discussion - -Use the `create_discussion` safe-output tool to post a structured benchmark report. - -The discussion body should be formatted as follows (fill in real numbers from Phase 6): - -```markdown -# QF_S Benchmark: seq vs nseq - -**Date**: YYYY-MM-DD -**Branch**: c3 -**Commit**: `` -**Workflow Run**: [#](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}) -**Files benchmarked**: N (capped at 500, timeout 10 s per file) - ---- - -## Summary - -| Metric | seq | nseq | -|--------|-----|------| -| Files solved (sat/unsat) | SEQ_SOLVED | NSEQ_SOLVED | -| Timeouts | SEQ_TO | NSEQ_TO | -| Median solve time (solved files) | X ms | Y ms | -| Mean solve time (solved files) | X ms | Y ms | -| **Disagreements (sat≠unsat)** | — | N | - ---- - -## Performance Comparison - -### seq-fast / nseq-slow (seq < 2 s, nseq timed out) - -These are benchmarks where the classical `seq` solver is significantly faster. These represent regression risk for `nseq`. - -| File | seq (ms) | nseq (ms) | seq result | nseq result | -|------|----------|-----------|------------|-------------| -[TOP 10 ENTRIES] - -### nseq-fast / seq-slow (nseq < 2 s, seq timed out) - -These are benchmarks where `nseq` shows a performance advantage. - -| File | seq (ms) | nseq (ms) | seq result | nseq result | -|------|----------|-----------|------------|-------------| -[TOP 10 ENTRIES] - ---- - -## Correctness - -**Disagreements** (files where seq says `sat` but nseq says `unsat` or vice versa): N - -[If disagreements exist, list all of them here with file paths and both results] - ---- - -## seq Trace Analysis (seq-fast / nseq-slow cases) - -
-Click to expand trace snippets for top seq-fast/nseq-slow cases - -[Insert trace snippet for each traced file, or "No traces collected" if section was skipped] - -
- ---- - -## Raw Data - -
-Full results CSV (click to expand) - -```csv -[PASTE FIRST 200 LINES OF /tmp/benchmark-results.csv] -``` - -
- ---- - -*Generated by the QF_S Benchmark workflow. To reproduce: build Z3 from the `c3` branch and run `z3 smt.string_solver=seq|nseq -T:10 `.* -``` - -## Edge Cases - -- If the build fails, call `missing_data` explaining the build error and stop. -- If no benchmark files are found at all, call `missing_data` explaining that no QF_S `.smt2` files were found in the `c3` branch. -- If Z3 crashes (segfault) on a file with either solver, record the result as `crash` and continue. -- If the total benchmark set is very small (< 5 files), note this prominently in the discussion and suggest adding more QF_S benchmarks to the `c3` branch. -- If zero disagreements and both solvers time out on the same files, note that the solvers are in agreement. - -## Important Notes - -- **DO NOT** modify any source files or create pull requests. -- **DO NOT** run benchmarks for longer than 80 minutes total (leave buffer for posting). -- **DO** always report the commit SHA so results can be correlated with specific code versions. -- **DO** close older ZIPT Benchmark discussions automatically (configured via `close-older-discussions: true`). -- **DO** highlight disagreements prominently — these are potential correctness bugs.