diff --git a/.github/dependabot.yml b/.github/dependabot.yml index 5ace4600a..c00c619c4 100644 --- a/.github/dependabot.yml +++ b/.github/dependabot.yml @@ -1,6 +1,8 @@ -version: 2 updates: - - package-ecosystem: "github-actions" - directory: "/" - schedule: - interval: "weekly" +- directory: / + ignore: + - dependency-name: "github/gh-aw-actions/**" # Managed by gh aw compile. Version-locked to the gh-aw compiler; do not bump. + package-ecosystem: github-actions + schedule: + interval: weekly +version: 2 diff --git a/.github/workflows/smtlib-benchmark-finder.lock.yml b/.github/workflows/smtlib-benchmark-finder.lock.yml new file mode 100644 index 000000000..30191b21c --- /dev/null +++ b/.github/workflows/smtlib-benchmark-finder.lock.yml @@ -0,0 +1,1442 @@ +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"7fe62b76e1ec94b221dbb20fe5cd392a7a47a296f9da44c7405c343a2ca3c3e9","compiler_version":"v0.74.8","strict":true,"agent_id":"copilot"} +# 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":"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":"v0.74.8","version":"v0.74.8"}],"containers":[{"image":"ghcr.io/github/gh-aw-firewall/agent:0.25.49"},{"image":"ghcr.io/github/gh-aw-firewall/api-proxy:0.25.49"},{"image":"ghcr.io/github/gh-aw-firewall/squid:0.25.49"},{"image":"ghcr.io/github/gh-aw-mcpg:v0.3.9","digest":"sha256:64828b42a4482f58fab16509d7f8f495a6d97c972a98a68aff20543531ac0388","pinned_image":"ghcr.io/github/gh-aw-mcpg:v0.3.9@sha256:64828b42a4482f58fab16509d7f8f495a6d97c972a98a68aff20543531ac0388"},{"image":"ghcr.io/github/github-mcp-server:v1.0.4"},{"image":"node:lts-alpine","digest":"sha256:d1b3b4da11eefd5941e7f0b9cf17783fc99d9c6fc34884a665f40a06dbdfc94f","pinned_image":"node:lts-alpine@sha256:d1b3b4da11eefd5941e7f0b9cf17783fc99d9c6fc34884a665f40a06dbdfc94f"}]} +# ___ _ _ +# / _ \ | | (_) +# | |_| | __ _ ___ _ __ | |_ _ ___ +# | _ |/ _` |/ _ \ '_ \| __| |/ __| +# | | | | (_| | __/ | | | |_| | (__ +# \_| |_/\__, |\___|_| |_|\__|_|\___| +# __/ | +# _ _ |___/ +# | | | | / _| | +# | | | | ___ _ __ _ __| |_| | _____ ____ +# | |/\| |/ _ \ '__| |/ /| _| |/ _ \ \ /\ / / ___| +# \ /\ / (_) | | | | ( | | | | (_) \ V V /\__ \ +# \/ \/ \___/|_| |_|\_\|_| |_|\___/ \_/\_/ |___/ +# +# This file was automatically generated by gh-aw (v0.74.8). DO NOT EDIT. +# +# 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/ +# +# Monthly SMTLIB Benchmark Finder. Searches GitHub for repositories containing SMT-LIB benchmarks (.smt2 files), excludes repositories that belong to the official SMT-LIB benchmark sets (linked from smtlib.org and hosted on Zenodo), and posts a curated summary of community-contributed benchmark links 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@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@v0.74.8 +# +# Container images used: +# - ghcr.io/github/gh-aw-firewall/agent:0.25.49 +# - ghcr.io/github/gh-aw-firewall/api-proxy:0.25.49 +# - ghcr.io/github/gh-aw-firewall/squid:0.25.49 +# - ghcr.io/github/gh-aw-mcpg:v0.3.9@sha256:64828b42a4482f58fab16509d7f8f495a6d97c972a98a68aff20543531ac0388 +# - ghcr.io/github/github-mcp-server:v1.0.4 +# - node:lts-alpine@sha256:d1b3b4da11eefd5941e7f0b9cf17783fc99d9c6fc34884a665f40a06dbdfc94f + +name: "SMTLIB Benchmark Finder" +on: + schedule: + - cron: "0 8 1 * *" + workflow_dispatch: + inputs: + aw_context: + default: "" + description: "Agent caller context (used internally by Agentic Workflows)." + required: false + type: string + +permissions: {} + +concurrency: + group: "gh-aw-${{ github.workflow }}" + +run-name: "SMTLIB Benchmark Finder" + +jobs: + activation: + runs-on: ubuntu-slim + permissions: + actions: read + contents: read + outputs: + comment_id: "" + comment_repo: "" + 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@v0.74.8 + with: + destination: ${{ runner.temp }}/gh-aw/actions + job-name: ${{ github.job }} + env: + GH_AW_SETUP_WORKFLOW_NAME: "SMTLIB Benchmark Finder" + GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/smtlib-benchmark-finder.lock.yml@${{ github.ref }} + GH_AW_INFO_VERSION: "1.0.48" + 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: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || 'claude-sonnet-4.5' }} + GH_AW_INFO_VERSION: "1.0.48" + GH_AW_INFO_AGENT_VERSION: "1.0.48" + GH_AW_INFO_CLI_VERSION: "v0.74.8" + GH_AW_INFO_WORKFLOW_NAME: "SMTLIB Benchmark Finder" + GH_AW_INFO_EXPERIMENTAL: "false" + GH_AW_INFO_SUPPORTS_TOOLS_ALLOWLIST: "true" + GH_AW_INFO_STAGED: "false" + GH_AW_INFO_ALLOWED_DOMAINS: '["defaults","github","smtlib.cs.uiowa.edu","zenodo.org"]' + GH_AW_INFO_FIREWALL_ENABLED: "true" + GH_AW_INFO_AWF_VERSION: "v0.25.49" + GH_AW_INFO_AWMG_VERSION: "" + GH_AW_INFO_FIREWALL_TYPE: "squid" + GH_AW_COMPILED_STRICT: "true" + uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io, getOctokit); + const { main } = require('${{ runner.temp }}/gh-aw/actions/generate_aw_info.cjs'); + await main(core, context); + - name: Validate COPILOT_GITHUB_TOKEN secret + id: validate-secret + run: bash "${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: ${{ secrets.COPILOT_GITHUB_TOKEN }} + - name: Checkout .github and .agents folders + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + sparse-checkout: | + .github + .agents + .claude + .codex + .crush + .gemini + .opencode + .pi + sparse-checkout-cone-mode: true + fetch-depth: 1 + - name: Save agent config folders for base branch restoration + env: + GH_AW_AGENT_FOLDERS: ".agents .claude .codex .crush .gemini .github .opencode .pi" + GH_AW_AGENT_FILES: ".crush.json AGENTS.md CLAUDE.md GEMINI.md PI.md opencode.jsonc" + # poutine:ignore untrusted_checkout_exec + run: bash "${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: "smtlib-benchmark-finder.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('${{ runner.temp }}/gh-aw/actions/check_workflow_timestamp_api.cjs'); + await main(); + - name: Check compile-agentic version + uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 + env: + GH_AW_COMPILED_VERSION: "v0.74.8" + with: + script: | + const { setupGlobals } = require('${{ 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: 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_04598545a7d250b1_EOF' + + GH_AW_PROMPT_04598545a7d250b1_EOF + cat "${RUNNER_TEMP}/gh-aw/prompts/xpia.md" + cat "${RUNNER_TEMP}/gh-aw/prompts/temp_folder_prompt.md" + cat "${RUNNER_TEMP}/gh-aw/prompts/markdown.md" + cat "${RUNNER_TEMP}/gh-aw/prompts/cache_memory_prompt.md" + cat "${RUNNER_TEMP}/gh-aw/prompts/safe_outputs_prompt.md" + cat << 'GH_AW_PROMPT_04598545a7d250b1_EOF' + + Tools: create_discussion, missing_tool, missing_data, noop + + GH_AW_PROMPT_04598545a7d250b1_EOF + cat "${RUNNER_TEMP}/gh-aw/prompts/mcp_cli_tools_prompt.md" + cat << 'GH_AW_PROMPT_04598545a7d250b1_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_04598545a7d250b1_EOF + cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" + cat << 'GH_AW_PROMPT_04598545a7d250b1_EOF' + + {{#runtime-import .github/workflows/smtlib-benchmark-finder.md}} + GH_AW_PROMPT_04598545a7d250b1_EOF + } > "$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_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_ALLOWED_EXTENSIONS: '' + GH_AW_CACHE_DESCRIPTION: '' + GH_AW_CACHE_DIR: '/tmp/gh-aw/cache-memory/' + GH_AW_EXPR_1A3A194A: ${{ github.event.discussion.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'discussion' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }} + GH_AW_EXPR_463A214A: ${{ github.event.pull_request.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'pull_request' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }} + GH_AW_EXPR_802A9F6A: ${{ github.event.issue.number || (fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_type == 'issue' && fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').item_number) }} + GH_AW_EXPR_FF1D34CE: ${{ github.event.comment.id || fromJSON(github.event.inputs.aw_context || github.event.client_payload.aw_context || '{}').comment_id }} + GH_AW_GITHUB_ACTOR: ${{ github.actor }} + GH_AW_GITHUB_REPOSITORY: ${{ github.repository }} + GH_AW_GITHUB_RUN_ID: ${{ github.run_id }} + GH_AW_GITHUB_WORKFLOW: ${{ github.workflow }} + GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }} + GH_AW_MCP_CLI_SERVERS_LIST: '- `safeoutputs` — run `safeoutputs --help` to see available tools' + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io, getOctokit); + + const substitutePlaceholders = require('${{ runner.temp }}/gh-aw/actions/substitute_placeholders.cjs'); + + // Call the substitution function + return await substitutePlaceholders({ + file: process.env.GH_AW_PROMPT, + substitutions: { + GH_AW_ALLOWED_EXTENSIONS: process.env.GH_AW_ALLOWED_EXTENSIONS, + GH_AW_CACHE_DESCRIPTION: process.env.GH_AW_CACHE_DESCRIPTION, + GH_AW_CACHE_DIR: process.env.GH_AW_CACHE_DIR, + GH_AW_EXPR_1A3A194A: process.env.GH_AW_EXPR_1A3A194A, + GH_AW_EXPR_463A214A: process.env.GH_AW_EXPR_463A214A, + GH_AW_EXPR_802A9F6A: process.env.GH_AW_EXPR_802A9F6A, + GH_AW_EXPR_FF1D34CE: process.env.GH_AW_EXPR_FF1D34CE, + GH_AW_GITHUB_ACTOR: process.env.GH_AW_GITHUB_ACTOR, + GH_AW_GITHUB_REPOSITORY: process.env.GH_AW_GITHUB_REPOSITORY, + GH_AW_GITHUB_RUN_ID: process.env.GH_AW_GITHUB_RUN_ID, + GH_AW_GITHUB_WORKFLOW: process.env.GH_AW_GITHUB_WORKFLOW, + GH_AW_GITHUB_WORKSPACE: process.env.GH_AW_GITHUB_WORKSPACE, + GH_AW_MCP_CLI_SERVERS_LIST: process.env.GH_AW_MCP_CLI_SERVERS_LIST + } + }); + - name: Validate prompt placeholders + env: + GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt + # poutine:ignore untrusted_checkout_exec + run: bash "${RUNNER_TEMP}/gh-aw/actions/validate_prompt_placeholders.sh" + - name: Print prompt + env: + GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt + # poutine:ignore untrusted_checkout_exec + run: bash "${RUNNER_TEMP}/gh-aw/actions/print_prompt_summary.sh" + - name: Upload activation artifact + if: success() + uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 + with: + name: activation + include-hidden-files: true + path: | + /tmp/gh-aw/aw_info.json + /tmp/gh-aw/aw-prompts/prompt.txt + /tmp/gh-aw/aw-prompts/prompt-template.txt + /tmp/gh-aw/aw-prompts/prompt-import-tree.json + /tmp/gh-aw/github_rate_limits.jsonl + /tmp/gh-aw/base + /tmp/gh-aw/.github/agents + if-no-files-found: ignore + retention-days: 1 + + agent: + needs: activation + runs-on: ubuntu-latest + permissions: read-all + concurrency: + group: "gh-aw-copilot-${{ github.workflow }}" + 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_WORKFLOW_ID_SANITIZED: smtlibbenchmarkfinder + outputs: + agentic_engine_timeout: ${{ steps.detect-copilot-errors.outputs.agentic_engine_timeout || 'false' }} + checkout_pr_success: ${{ steps.checkout-pr.outputs.checkout_pr_success || 'true' }} + effective_tokens: ${{ steps.parse-mcp-gateway.outputs.effective_tokens }} + effective_tokens_rate_limit_error: ${{ steps.parse-mcp-gateway.outputs.effective_tokens_rate_limit_error || 'false' }} + has_patch: ${{ steps.collect_output.outputs.has_patch }} + inference_access_error: ${{ steps.detect-copilot-errors.outputs.inference_access_error || 'false' }} + mcp_policy_error: ${{ steps.detect-copilot-errors.outputs.mcp_policy_error || 'false' }} + model: ${{ needs.activation.outputs.model }} + model_not_supported_error: ${{ steps.detect-copilot-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 }} + steps: + - name: Setup Scripts + id: setup + uses: github/gh-aw-actions/setup@v0.74.8 + 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: "SMTLIB Benchmark Finder" + GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/smtlib-benchmark-finder.lock.yml@${{ github.ref }} + GH_AW_INFO_VERSION: "1.0.48" + 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: Checkout repository + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - 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: ${{ github.token }} + # Cache memory file share configuration from frontmatter processed below + - name: Create cache-memory directory + run: bash "${RUNNER_TEMP}/gh-aw/actions/create_cache_memory_dir.sh" + - name: Restore cache-memory file share data + uses: actions/cache/restore@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 + with: + key: memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}-${{ github.run_id }} + path: /tmp/gh-aw/cache-memory + restore-keys: | + memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}- + - name: Setup cache-memory git repository + env: + GH_AW_CACHE_DIR: /tmp/gh-aw/cache-memory + GH_AW_MIN_INTEGRITY: none + run: bash "${RUNNER_TEMP}/gh-aw/actions/setup_cache_memory_git.sh" + - name: Configure Git credentials + env: + REPO_NAME: ${{ github.repository }} + SERVER_URL: ${{ github.server_url }} + GITHUB_TOKEN: ${{ github.token }} + run: | + git config --global user.email "github-actions[bot]@users.noreply.github.com" + git config --global user.name "github-actions[bot]" + git config --global am.keepcr true + # Re-authenticate git with GitHub token + SERVER_URL_STRIPPED="${SERVER_URL#https://}" + git remote set-url origin "https://x-access-token:${GITHUB_TOKEN}@${SERVER_URL_STRIPPED}/${REPO_NAME}.git" + echo "Git configured with standard GitHub Actions identity" + - name: Checkout PR branch + id: checkout-pr + if: | + github.event.pull_request || github.event.issue.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" 1.0.48 + env: + GH_HOST: github.com + - name: Install AWF binary + run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.25.49 + - 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 .claude .codex .crush .gemini .github .opencode .pi" + GH_AW_AGENT_FILES: ".crush.json AGENTS.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: Download container images + run: bash "${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh" ghcr.io/github/gh-aw-firewall/agent:0.25.49 ghcr.io/github/gh-aw-firewall/api-proxy:0.25.49 ghcr.io/github/gh-aw-firewall/squid:0.25.49 ghcr.io/github/gh-aw-mcpg:v0.3.9@sha256:64828b42a4482f58fab16509d7f8f495a6d97c972a98a68aff20543531ac0388 ghcr.io/github/github-mcp-server:v1.0.4 node:lts-alpine@sha256:d1b3b4da11eefd5941e7f0b9cf17783fc99d9c6fc34884a665f40a06dbdfc94f + - name: Generate Safe Outputs Config + run: | + mkdir -p "${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_1c2429a4603946af_EOF' + {"create_discussion":{"category":"agentic workflows","close_older_discussions":true,"expires":2160,"fallback_to_issue":true,"max":1,"title_prefix":"[SMT-LIB Benchmarks] "},"create_report_incomplete_issue":{},"max_bot_mentions":1,"mentions":{"enabled":false},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"false"},"report_incomplete":{}} + GH_AW_SAFE_OUTPUTS_CONFIG_1c2429a4603946af_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 \"[SMT-LIB Benchmarks] \". 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 + }, + "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('${{ runner.temp }}/gh-aw/actions/generate_safe_outputs_tools.cjs'); + await main(); + - name: Generate Safe Outputs MCP Server Config + id: safe-outputs-config + run: | + # Generate a secure random API key (360 bits of entropy, 40+ chars) + # Mask immediately to prevent timing vulnerabilities + API_KEY=$(openssl rand -base64 45 | tr -d '/+=') + echo "::add-mask::${API_KEY}" + + PORT=3001 + + # Set outputs for next steps + { + echo "safe_outputs_api_key=${API_KEY}" + echo "safe_outputs_port=${PORT}" + } >> "$GITHUB_OUTPUT" + + echo "Safe Outputs MCP server will run on port ${PORT}" + + - name: Start Safe Outputs MCP HTTP Server + id: safe-outputs-start + env: + DEBUG: '*' + GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }} + GH_AW_SAFE_OUTPUTS_PORT: ${{ steps.safe-outputs-config.outputs.safe_outputs_port }} + GH_AW_SAFE_OUTPUTS_API_KEY: ${{ steps.safe-outputs-config.outputs.safe_outputs_api_key }} + GH_AW_SAFE_OUTPUTS_TOOLS_PATH: ${{ runner.temp }}/gh-aw/safeoutputs/tools.json + GH_AW_SAFE_OUTPUTS_CONFIG_PATH: ${{ runner.temp }}/gh-aw/safeoutputs/config.json + GH_AW_MCP_LOG_DIR: /tmp/gh-aw/mcp-logs/safeoutputs + run: | + # Environment variables are set above to prevent template injection + export DEBUG + export GH_AW_SAFE_OUTPUTS + export GH_AW_SAFE_OUTPUTS_PORT + export GH_AW_SAFE_OUTPUTS_API_KEY + export GH_AW_SAFE_OUTPUTS_TOOLS_PATH + export GH_AW_SAFE_OUTPUTS_CONFIG_PATH + export GH_AW_MCP_LOG_DIR + + bash "${RUNNER_TEMP}/gh-aw/actions/start_safe_outputs_server.sh" + + - name: Start MCP Gateway + id: start-mcp-gateway + env: + GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }} + GH_AW_SAFE_OUTPUTS_API_KEY: ${{ steps.safe-outputs-start.outputs.api_key }} + GH_AW_SAFE_OUTPUTS_PORT: ${{ steps.safe-outputs-start.outputs.port }} + GITHUB_MCP_GUARD_MIN_INTEGRITY: ${{ steps.determine-automatic-lockdown.outputs.min_integrity }} + GITHUB_MCP_GUARD_REPOS: ${{ steps.determine-automatic-lockdown.outputs.repos }} + GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN || secrets.GH_AW_GITHUB_TOKEN || secrets.GITHUB_TOKEN }} + run: | + set -eo pipefail + mkdir -p "${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 --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_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.3.9' + + mkdir -p /home/runner/.copilot + GH_AW_NODE=$(which node 2>/dev/null || command -v node 2>/dev/null || echo node) + cat << GH_AW_MCP_CONFIG_07d3b8ec96f0806f_EOF | "$GH_AW_NODE" "${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.cjs" + { + "mcpServers": { + "github": { + "type": "stdio", + "container": "ghcr.io/github/github-mcp-server:v1.0.4", + "env": { + "GITHUB_HOST": "\${GITHUB_SERVER_URL}", + "GITHUB_PERSONAL_ACCESS_TOKEN": "\${GITHUB_MCP_SERVER_TOKEN}", + "GITHUB_READ_ONLY": "1", + "GITHUB_TOOLSETS": "context,repos,issues,pull_requests" + }, + "guard-policies": { + "allow-only": { + "min-integrity": "$GITHUB_MCP_GUARD_MIN_INTEGRITY", + "repos": "$GITHUB_MCP_GUARD_REPOS" + } + } + }, + "safeoutputs": { + "type": "http", + "url": "http://host.docker.internal:$GH_AW_SAFE_OUTPUTS_PORT", + "headers": { + "Authorization": "\${GH_AW_SAFE_OUTPUTS_API_KEY}" + }, + "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_07d3b8ec96f0806f_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 "${RUNNER_TEMP}/gh-aw/actions/audit_pre_agent_workspace.sh" + - name: Execute GitHub Copilot CLI + id: agentic_execution + # Copilot CLI tool arguments (sorted): + timeout-minutes: 60 + run: | + set -o pipefail + printf '%s' "$(date +%s%3N)" > /tmp/gh-aw/agent_cli_start_ms.txt + 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) + printf '%s\n' '{"$schema":"https://github.com/github/gh-aw-firewall/releases/download/v0.25.49/awf-config.schema.json","network":{"allowDomains":["*.githubusercontent.com","api.business.githubcopilot.com","api.enterprise.githubcopilot.com","api.github.com","api.githubcopilot.com","api.individual.githubcopilot.com","api.snapcraft.io","archive.ubuntu.com","azure.archive.ubuntu.com","codeload.github.com","crl.geotrust.com","crl.globalsign.com","crl.identrust.com","crl.sectigo.com","crl.thawte.com","crl.usertrust.com","crl.verisign.com","crl3.digicert.com","crl4.digicert.com","crls.ssl.com","docs.github.com","github-cloud.githubusercontent.com","github-cloud.s3.amazonaws.com","github.blog","github.com","github.githubassets.com","host.docker.internal","json-schema.org","json.schemastore.org","keyserver.ubuntu.com","lfs.github.com","objects.githubusercontent.com","ocsp.digicert.com","ocsp.geotrust.com","ocsp.globalsign.com","ocsp.identrust.com","ocsp.sectigo.com","ocsp.ssl.com","ocsp.thawte.com","ocsp.usertrust.com","ocsp.verisign.com","packagecloud.io","packages.cloud.google.com","packages.microsoft.com","patch-diff.githubusercontent.com","ppa.launchpad.net","raw.githubusercontent.com","registry.npmjs.org","s.symcb.com","s.symcd.com","security.ubuntu.com","smtlib.cs.uiowa.edu","telemetry.enterprise.githubcopilot.com","ts-crl.ws.symantec.com","ts-ocsp.ws.symantec.com","www.googleapis.com","zenodo.org"]},"apiProxy":{"enabled":true,"enableTokenSteering":true,"maxRuns":500,"maxEffectiveTokens":25000000,"models":{"agent":["sonnet-6x","gpt-5.4","gpt-5","gemini-pro","haiku","any"],"any":["copilot/*","anthropic/*","openai/*","google/*","gemini/*"],"auto":["large"],"claude":["agent","sonnet-6x","haiku","any"],"codex":["agent","gpt-5-codex","gpt-5","any"],"coding":["copilot/gpt-5*codex*","openai/gpt-5*codex*","gpt-5-codex"],"copilot":["agent","gpt-5.4","sonnet","gpt-5","any"],"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-pro","gemini-flash","any"],"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-4.1":["copilot/gpt-4.1*","openai/gpt-4.1*"],"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*"],"haiku":["copilot/*haiku*","anthropic/*haiku*"],"large":["sonnet","gpt-5-pro","gpt-5","gemini-pro"],"mini":["haiku","gpt-5-mini","gpt-5-nano","gemini-flash-lite","copilot/raptor*mini*"],"opus":["copilot/*opus*","anthropic/*opus*"],"reasoning":["copilot/o1*","copilot/o3*","copilot/o4*","openai/o1*","openai/o3*","openai/o4*"],"small":["mini"],"sonnet":["copilot/*sonnet*","anthropic/*sonnet*"],"sonnet-6x":["copilot/*sonnet-4.5*","copilot/*sonnet-4-5*","anthropic/*sonnet-4.5*","anthropic/*sonnet-4-5*","copilot/*sonnet-3.7*","copilot/*sonnet-3-7*","anthropic/*sonnet-3.7*","anthropic/*sonnet-3-7*","copilot/*sonnet-3.5*","copilot/*sonnet-3-5*","anthropic/*sonnet-3.5*","anthropic/*sonnet-3-5*"],"vision":["copilot/gemini-*image*","gemini/gemini-*image*","copilot/gemini-*flash*","gemini/gemini-*flash*"]}},"container":{"imageTag":"0.25.49"}}' > "${RUNNER_TEMP}/gh-aw/awf-config.json" + cp "${RUNNER_TEMP}/gh-aw/awf-config.json" /tmp/gh-aw/awf-config.json + GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS="" + if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then + GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS="--docker-host-path-prefix /tmp/gh-aw" + fi + # shellcheck disable=SC1003 + 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" ${GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS} --env-all --exclude-env COPILOT_GITHUB_TOKEN --exclude-env GITHUB_MCP_SERVER_TOKEN --exclude-env MCP_GATEWAY_API_KEY --log-level info --proxy-logs-dir /tmp/gh-aw/sandbox/firewall/logs --audit-dir /tmp/gh-aw/sandbox/firewall/audit --enable-host-access --allow-host-ports 80,443,8080 --skip-pull \ + -- /bin/bash -c 'export PATH="${RUNNER_TEMP}/gh-aw/mcp-cli/bin:$PATH" && export PATH="$(find /opt/hostedtoolcache /home/runner/work/_tool -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_NODE_EXEC" ${RUNNER_TEMP}/gh-aw/actions/copilot_harness.cjs /usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --no-ask-user --allow-all-tools --add-dir /tmp/gh-aw/cache-memory/ --allow-all-paths --add-dir "${GITHUB_WORKSPACE}" --prompt-file /tmp/gh-aw/aw-prompts/prompt.txt' 2>&1 | tee -a /tmp/gh-aw/agent-stdio.log + env: + AWF_REFLECT_ENABLED: 1 + COPILOT_AGENT_RUNNER_TYPE: STANDALONE + COPILOT_DUMMY_BYOK: dummy-byok-key-for-offline-mode + COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }} + COPILOT_MODEL: ${{ vars.GH_AW_MODEL_AGENT_COPILOT || 'claude-sonnet-4.5' }} + GH_AW_MCP_CONFIG: /home/runner/.copilot/mcp-config.json + 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_VERSION: v0.74.8 + 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: ${{ github.workspace }} + GIT_AUTHOR_EMAIL: github-actions[bot]@users.noreply.github.com + GIT_AUTHOR_NAME: github-actions[bot] + GIT_COMMITTER_EMAIL: github-actions[bot]@users.noreply.github.com + GIT_COMMITTER_NAME: github-actions[bot] + XDG_CONFIG_HOME: /home/runner + - name: Detect Copilot errors + id: detect-copilot-errors + if: always() + continue-on-error: true + run: node "${RUNNER_TEMP}/gh-aw/actions/detect_copilot_errors.cjs" + - name: Configure Git credentials + env: + REPO_NAME: ${{ github.repository }} + SERVER_URL: ${{ github.server_url }} + GITHUB_TOKEN: ${{ github.token }} + run: | + git config --global user.email "github-actions[bot]@users.noreply.github.com" + git config --global user.name "github-actions[bot]" + git config --global am.keepcr true + # Re-authenticate git with GitHub token + SERVER_URL_STRIPPED="${SERVER_URL#https://}" + git remote set-url origin "https://x-access-token:${GITHUB_TOKEN}@${SERVER_URL_STRIPPED}/${REPO_NAME}.git" + echo "Git configured with standard GitHub Actions identity" + - name: Copy Copilot session state files to logs + if: always() + continue-on-error: true + run: bash "${RUNNER_TEMP}/gh-aw/actions/copy_copilot_session_state.sh" + - name: Stop MCP Gateway + if: always() + continue-on-error: true + env: + MCP_GATEWAY_PORT: ${{ steps.start-mcp-gateway.outputs.gateway-port }} + MCP_GATEWAY_API_KEY: ${{ steps.start-mcp-gateway.outputs.gateway-api-key }} + GATEWAY_PID: ${{ steps.start-mcp-gateway.outputs.gateway-pid }} + run: | + bash "${RUNNER_TEMP}/gh-aw/actions/stop_mcp_gateway.sh" "$GATEWAY_PID" + - name: Redact secrets in logs + if: always() + uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 + with: + script: | + const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); + setupGlobals(core, github, context, exec, io, getOctokit); + const { main } = require('${{ runner.temp }}/gh-aw/actions/redact_secrets.cjs'); + await main(); + env: + GH_AW_SECRET_NAMES: 'COPILOT_GITHUB_TOKEN,GH_AW_GITHUB_MCP_SERVER_TOKEN,GH_AW_GITHUB_TOKEN,GITHUB_TOKEN' + SECRET_COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }} + SECRET_GH_AW_GITHUB_MCP_SERVER_TOKEN: ${{ secrets.GH_AW_GITHUB_MCP_SERVER_TOKEN }} + SECRET_GH_AW_GITHUB_TOKEN: ${{ secrets.GH_AW_GITHUB_TOKEN }} + SECRET_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} + - name: Append agent step summary + if: always() + run: bash "${RUNNER_TEMP}/gh-aw/actions/append_agent_step_summary.sh" + - name: Copy Safe Outputs + if: always() + env: + GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }} + run: | + mkdir -p /tmp/gh-aw + cp "$GH_AW_SAFE_OUTPUTS" /tmp/gh-aw/safeoutputs.jsonl 2>/dev/null || true + - name: Ingest agent output + id: collect_output + if: always() + uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 + env: + GH_AW_SAFE_OUTPUTS: ${{ steps.set-runtime-paths.outputs.GH_AW_SAFE_OUTPUTS }} + GH_AW_ALLOWED_DOMAINS: "*.githubusercontent.com,api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,codeload.github.com,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,docs.github.com,github-cloud.githubusercontent.com,github-cloud.s3.amazonaws.com,github.blog,github.com,github.githubassets.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,lfs.github.com,objects.githubusercontent.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,patch-diff.githubusercontent.com,ppa.launchpad.net,raw.githubusercontent.com,registry.npmjs.org,s.symcb.com,s.symcd.com,security.ubuntu.com,smtlib.cs.uiowa.edu,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com,www.googleapis.com,zenodo.org" + GH_AW_ALLOWED_GITHUB_REFS: "" + 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: Commit cache-memory changes + if: always() + env: + GH_AW_CACHE_DIR: /tmp/gh-aw/cache-memory + run: bash "${RUNNER_TEMP}/gh-aw/actions/commit_cache_memory_git.sh" + - name: Upload cache-memory data as artifact + uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 + if: always() + with: + name: cache-memory + include-hidden-files: true + path: /tmp/gh-aw/cache-memory + - name: Upload agent artifacts + if: always() + continue-on-error: true + uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1 + with: + name: agent + path: | + /tmp/gh-aw/aw-prompts/prompt.txt + /tmp/gh-aw/sandbox/agent/logs/ + /tmp/gh-aw/redacted-urls.log + /tmp/gh-aw/mcp-logs/ + /tmp/gh-aw/agent_usage.json + /tmp/gh-aw/agent-stdio.log + /tmp/gh-aw/pre-agent-audit.txt + /tmp/gh-aw/agent/ + /tmp/gh-aw/github_rate_limits.jsonl + /tmp/gh-aw/safeoutputs.jsonl + /tmp/gh-aw/agent_output.json + /tmp/gh-aw/aw-*.patch + /tmp/gh-aw/aw-*.bundle + /tmp/gh-aw/awf-config.json + /tmp/gh-aw/sandbox/firewall/logs/ + /tmp/gh-aw/sandbox/firewall/audit/ + /tmp/gh-aw/sandbox/firewall/awf-reflect.json + if-no-files-found: ignore + + conclusion: + needs: + - activation + - agent + - detection + - safe_outputs + - update_cache_memory + if: > + always() && (needs.agent.result != 'skipped' || needs.activation.outputs.lockdown_check_failed == 'true' || + needs.activation.outputs.stale_lock_file_failed == 'true') + runs-on: ubuntu-slim + permissions: + contents: read + discussions: write + issues: write + concurrency: + group: "gh-aw-conclusion-smtlib-benchmark-finder" + cancel-in-progress: false + queue: max + outputs: + incomplete_count: ${{ steps.report_incomplete.outputs.incomplete_count }} + noop_message: ${{ steps.noop.outputs.noop_message }} + tools_reported: ${{ steps.missing_tool.outputs.tools_reported }} + total_count: ${{ steps.missing_tool.outputs.total_count }} + steps: + - name: Setup Scripts + id: setup + uses: github/gh-aw-actions/setup@v0.74.8 + 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: "SMTLIB Benchmark Finder" + GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/smtlib-benchmark-finder.lock.yml@${{ github.ref }} + GH_AW_INFO_VERSION: "1.0.48" + 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: 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: "SMTLIB Benchmark Finder" + 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" + 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: "SMTLIB Benchmark Finder" + 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: "SMTLIB Benchmark Finder" + 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: "SMTLIB Benchmark Finder" + 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: "SMTLIB Benchmark Finder" + 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: "smtlib-benchmark-finder" + 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_EFFECTIVE_TOKENS_RATE_LIMIT_ERROR: ${{ needs.agent.outputs.effective_tokens_rate_limit_error || 'false' }} + 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_GROUP_REPORTS: "false" + GH_AW_FAILURE_REPORT_AS_ISSUE: "true" + GH_AW_MISSING_TOOL_REPORT_AS_FAILURE: "true" + GH_AW_MISSING_DATA_REPORT_AS_FAILURE: "true" + GH_AW_TIMEOUT_MINUTES: "60" + GH_AW_MAX_EFFECTIVE_TOKENS: "25000000" + GH_AW_CACHE_MEMORY_ENABLED: "true" + 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' && (needs.agent.outputs.output_types != '' || needs.agent.outputs.has_patch == 'true') + runs-on: ubuntu-latest + permissions: + contents: read + outputs: + detection_conclusion: ${{ steps.detection_conclusion.outputs.conclusion }} + detection_reason: ${{ steps.detection_conclusion.outputs.reason }} + detection_success: ${{ steps.detection_conclusion.outputs.success }} + steps: + - name: Setup Scripts + id: setup + uses: github/gh-aw-actions/setup@v0.74.8 + 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: "SMTLIB Benchmark Finder" + GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/smtlib-benchmark-finder.lock.yml@${{ github.ref }} + GH_AW_INFO_VERSION: "1.0.48" + 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" >> "$GITHUB_OUTPUT" + - name: Checkout repository for patch context + if: needs.agent.outputs.has_patch == 'true' + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + # --- Threat Detection --- + - name: Clean stale firewall files from agent artifact + run: | + rm -rf /tmp/gh-aw/sandbox/firewall/logs + rm -rf /tmp/gh-aw/sandbox/firewall/audit + - name: Download container images + run: bash "${RUNNER_TEMP}/gh-aw/actions/download_docker_images.sh" ghcr.io/github/gh-aw-firewall/agent:0.25.49 ghcr.io/github/gh-aw-firewall/api-proxy:0.25.49 ghcr.io/github/gh-aw-firewall/squid:0.25.49 + - 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/runner/.copilot/mcp-config.json + rm -f "$GITHUB_WORKSPACE/.gemini/settings.json" + - name: Prepare threat detection files + if: always() && steps.detection_guard.outputs.run_detection == 'true' + run: | + mkdir -p /tmp/gh-aw/threat-detection/aw-prompts + cp /tmp/gh-aw/aw-prompts/prompt.txt /tmp/gh-aw/threat-detection/aw-prompts/prompt.txt 2>/dev/null || true + cp /tmp/gh-aw/agent_output.json /tmp/gh-aw/threat-detection/agent_output.json 2>/dev/null || true + for f in /tmp/gh-aw/aw-*.patch; do + [ -f "$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: "SMTLIB Benchmark Finder" + WORKFLOW_DESCRIPTION: "Monthly SMTLIB Benchmark Finder. Searches GitHub for repositories containing SMT-LIB benchmarks (.smt2 files), excludes repositories that belong to the official SMT-LIB benchmark sets (linked from smtlib.org and hosted on Zenodo), and posts a curated summary of community-contributed benchmark links 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" 1.0.48 + env: + GH_HOST: github.com + - name: Install AWF binary + run: bash "${RUNNER_TEMP}/gh-aw/actions/install_awf_binary.sh" v0.25.49 + - name: Execute GitHub Copilot CLI + if: always() && steps.detection_guard.outputs.run_detection == 'true' + continue-on-error: true + id: detection_agentic_execution + # Copilot CLI tool arguments (sorted): + timeout-minutes: 20 + run: | + set -o pipefail + printf '%s' "$(date +%s%3N)" > /tmp/gh-aw/agent_cli_start_ms.txt + 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) + printf '%s\n' '{"$schema":"https://github.com/github/gh-aw-firewall/releases/download/v0.25.49/awf-config.schema.json","network":{"allowDomains":["api.business.githubcopilot.com","api.enterprise.githubcopilot.com","api.github.com","api.githubcopilot.com","api.individual.githubcopilot.com","github.com","host.docker.internal","telemetry.enterprise.githubcopilot.com"]},"apiProxy":{"enabled":true,"enableTokenSteering":true,"maxRuns":500,"maxEffectiveTokens":25000000},"container":{"imageTag":"0.25.49"}}' > "${RUNNER_TEMP}/gh-aw/awf-config.json" + cp "${RUNNER_TEMP}/gh-aw/awf-config.json" /tmp/gh-aw/awf-config.json + GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS="" + if [[ "${DOCKER_HOST:-}" =~ ^tcp:// ]]; then + GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS="--docker-host-path-prefix /tmp/gh-aw" + fi + # shellcheck disable=SC1003 + 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" ${GH_AW_DOCKER_HOST_PATH_PREFIX_ARGS} --env-all --exclude-env COPILOT_GITHUB_TOKEN --log-level info --proxy-logs-dir /tmp/gh-aw/sandbox/firewall/logs --audit-dir /tmp/gh-aw/sandbox/firewall/audit --enable-host-access --allow-host-ports 80,443,8080 --skip-pull \ + -- /bin/bash -c 'export PATH="$(find /opt/hostedtoolcache /home/runner/work/_tool -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_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 || 'claude-sonnet-4.5' }} + GH_AW_PHASE: detection + GH_AW_PROMPT: /tmp/gh-aw/aw-prompts/prompt.txt + GH_AW_VERSION: v0.74.8 + 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] + XDG_CONFIG_HOME: /home/runner + - 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('${{ runner.temp }}/gh-aw/actions/parse_threat_detection_results.cjs'); + await main(); + } catch (loadErr) { + const continueOnError = process.env.GH_AW_DETECTION_CONTINUE_ON_ERROR !== 'false'; + const detectionExecutionFailed = process.env.DETECTION_AGENTIC_EXECUTION_OUTCOME === 'failure'; + const msg = 'ERR_SYSTEM: \u274C Unexpected error loading threat detection module: ' + (loadErr && loadErr.message ? loadErr.message : String(loadErr)); + core.error(msg); + core.setOutput('reason', 'parse_error'); + if (continueOnError && !detectionExecutionFailed) { + core.warning('\u26A0\uFE0F ' + msg); + core.setOutput('conclusion', 'warning'); + core.setOutput('success', 'false'); + } else { + core.setOutput('conclusion', 'failure'); + core.setOutput('success', 'false'); + core.setFailed(msg); + } + } + + safe_outputs: + needs: + - activation + - agent + - detection + if: (!cancelled()) && needs.agent.result != 'skipped' && needs.detection.result == 'success' + runs-on: ubuntu-slim + permissions: + contents: read + discussions: write + issues: write + timeout-minutes: 15 + env: + GH_AW_CALLER_WORKFLOW_ID: "${{ github.repository }}/smtlib-benchmark-finder" + 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: "1.0.48" + GH_AW_WORKFLOW_ID: "smtlib-benchmark-finder" + GH_AW_WORKFLOW_NAME: "SMTLIB Benchmark Finder" + outputs: + code_push_failure_count: ${{ steps.process_safe_outputs.outputs.code_push_failure_count }} + code_push_failure_errors: ${{ steps.process_safe_outputs.outputs.code_push_failure_errors }} + create_discussion_error_count: ${{ steps.process_safe_outputs.outputs.create_discussion_error_count }} + create_discussion_errors: ${{ steps.process_safe_outputs.outputs.create_discussion_errors }} + process_safe_outputs_processed_count: ${{ steps.process_safe_outputs.outputs.processed_count }} + process_safe_outputs_temporary_id_map: ${{ steps.process_safe_outputs.outputs.temporary_id_map }} + steps: + - name: Setup Scripts + id: setup + uses: github/gh-aw-actions/setup@v0.74.8 + 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: "SMTLIB Benchmark Finder" + GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/smtlib-benchmark-finder.lock.yml@${{ github.ref }} + GH_AW_INFO_VERSION: "1.0.48" + 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" >> "$GITHUB_OUTPUT" + - name: Configure GH_HOST for enterprise compatibility + id: ghes-host-config + shell: bash + run: | + # Derive GH_HOST from GITHUB_SERVER_URL so the gh CLI targets the correct + # GitHub instance (GHES/GHEC). On github.com this is a harmless no-op. + GH_HOST="${GITHUB_SERVER_URL#https://}" + GH_HOST="${GH_HOST#http://}" + echo "GH_HOST=${GH_HOST}" >> "$GITHUB_ENV" + - name: Process Safe Outputs + id: process_safe_outputs + uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 + env: + GH_AW_AGENT_OUTPUT: ${{ steps.setup-agent-output-env.outputs.GH_AW_AGENT_OUTPUT }} + GH_AW_COMMENT_ID: ${{ needs.activation.outputs.comment_id }} + GH_AW_ALLOWED_DOMAINS: "*.githubusercontent.com,api.business.githubcopilot.com,api.enterprise.githubcopilot.com,api.github.com,api.githubcopilot.com,api.individual.githubcopilot.com,api.snapcraft.io,archive.ubuntu.com,azure.archive.ubuntu.com,codeload.github.com,crl.geotrust.com,crl.globalsign.com,crl.identrust.com,crl.sectigo.com,crl.thawte.com,crl.usertrust.com,crl.verisign.com,crl3.digicert.com,crl4.digicert.com,crls.ssl.com,docs.github.com,github-cloud.githubusercontent.com,github-cloud.s3.amazonaws.com,github.blog,github.com,github.githubassets.com,host.docker.internal,json-schema.org,json.schemastore.org,keyserver.ubuntu.com,lfs.github.com,objects.githubusercontent.com,ocsp.digicert.com,ocsp.geotrust.com,ocsp.globalsign.com,ocsp.identrust.com,ocsp.sectigo.com,ocsp.ssl.com,ocsp.thawte.com,ocsp.usertrust.com,ocsp.verisign.com,packagecloud.io,packages.cloud.google.com,packages.microsoft.com,patch-diff.githubusercontent.com,ppa.launchpad.net,raw.githubusercontent.com,registry.npmjs.org,s.symcb.com,s.symcd.com,security.ubuntu.com,smtlib.cs.uiowa.edu,telemetry.enterprise.githubcopilot.com,ts-crl.ws.symantec.com,ts-ocsp.ws.symantec.com,www.googleapis.com,zenodo.org" + 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\":2160,\"fallback_to_issue\":true,\"max\":1,\"title_prefix\":\"[SMT-LIB Benchmarks] \"},\"create_report_incomplete_issue\":{},\"mentions\":{\"enabled\":false},\"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 + + update_cache_memory: + needs: + - activation + - agent + - detection + if: > + always() && (needs.detection.result == 'success' || needs.detection.result == 'skipped') && + needs.agent.result == 'success' + runs-on: ubuntu-slim + permissions: {} + env: + GH_AW_WORKFLOW_ID_SANITIZED: smtlibbenchmarkfinder + steps: + - name: Setup Scripts + id: setup + uses: github/gh-aw-actions/setup@v0.74.8 + 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: "SMTLIB Benchmark Finder" + GH_AW_CURRENT_WORKFLOW_REF: ${{ github.repository }}/.github/workflows/smtlib-benchmark-finder.lock.yml@${{ github.ref }} + GH_AW_INFO_VERSION: "1.0.48" + GH_AW_INFO_ENGINE_ID: "copilot" + - name: Download cache-memory artifact (default) + id: download_cache_default + uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 + continue-on-error: true + with: + name: cache-memory + path: /tmp/gh-aw/cache-memory + - name: Check if cache-memory folder has content (default) + id: check_cache_default + shell: bash + run: | + if [ -d "/tmp/gh-aw/cache-memory" ] && [ "$(ls -A /tmp/gh-aw/cache-memory 2>/dev/null)" ]; then + echo "has_content=true" >> "$GITHUB_OUTPUT" + else + echo "has_content=false" >> "$GITHUB_OUTPUT" + fi + - name: Save cache-memory to cache (default) + if: steps.check_cache_default.outputs.has_content == 'true' + uses: actions/cache/save@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5 + with: + key: memory-none-nopolicy-${{ env.GH_AW_WORKFLOW_ID_SANITIZED }}-${{ github.run_id }} + path: /tmp/gh-aw/cache-memory + diff --git a/.github/workflows/smtlib-benchmark-finder.md b/.github/workflows/smtlib-benchmark-finder.md new file mode 100644 index 000000000..19c615493 --- /dev/null +++ b/.github/workflows/smtlib-benchmark-finder.md @@ -0,0 +1,342 @@ +--- +description: > + Monthly SMTLIB Benchmark Finder. + Searches GitHub for repositories containing SMT-LIB benchmarks (.smt2 files), + excludes repositories that belong to the official SMT-LIB benchmark sets + (linked from smtlib.org and hosted on Zenodo), and posts a curated summary + of community-contributed benchmark links as a GitHub Discussion. + +on: + schedule: + - cron: "0 8 1 * *" + workflow_dispatch: + +timeout-minutes: 60 + +permissions: read-all + +network: + allowed: + - defaults + - github + - smtlib.cs.uiowa.edu + - zenodo.org + +tools: + cache-memory: true + web-fetch: {} + github: + toolsets: [default, repos] + bash: [":*"] + +safe-outputs: + mentions: false + allowed-github-references: [] + max-bot-mentions: 1 + create-discussion: + title-prefix: "[SMT-LIB Benchmarks] " + category: "Agentic Workflows" + close-older-discussions: true + expires: 90d + missing-tool: + create-issue: true + noop: + report-as-issue: false + +--- + +# SMTLIB Benchmark Finder + +## Job Description + +Your name is ${{ github.workflow }}. You are a research analyst for the Z3 theorem +prover repository `${{ github.repository }}`. Your mission is to discover GitHub +repositories that host SMT-LIB benchmarks, exclude the ones that are already part +of the official SMT-LIB benchmark distribution (linked from smtlib.org and published +on Zenodo), and post a curated summary of community-contributed benchmark links as a +GitHub Discussion. + +## Step 1: Load Cache and Determine Run Mode + +Check cache memory for: +- `official_repos`: set of GitHub repository full names (`owner/repo`) and Zenodo + record IDs already identified as official SMT-LIB benchmark sets +- `known_community_repos`: set of repo full names already listed in a previous report +- `last_run_date`: ISO-8601 date string of the previous run + +Use the cache to skip repos already classified. On the very first run (no cache), +perform a full discovery pass. On subsequent runs focus on repos pushed or created +since `last_run_date`. + +## Step 2: Collect Official SMT-LIB Benchmark Sets to Exclude + +### 2.1 Scrape smtlib.org + +Fetch the SMT-LIB benchmarks page and extract all linked Zenodo DOIs and GitHub URLs: + +```bash +curl -s "https://smtlib.cs.uiowa.edu/benchmarks.shtml" -o /tmp/smtlib-benchmarks.html +# Also try the main page and any mirror +curl -s "https://smtlib.cs.uiowa.edu/" -o /tmp/smtlib-home.html +``` + +Parse both files for: +- Zenodo DOI links (`doi.org/10.5281/zenodo.*` or `zenodo.org/record/*`) +- GitHub repository URLs (`github.com/...`) +- Any other hosted benchmark archive links + +### 2.2 Enumerate Zenodo SMT-LIB Community Records + +Query the Zenodo API for all records in the SMT-LIB community: + +```bash +curl -s "https://zenodo.org/api/records?communities=smt-lib&size=100&page=1" \ + -o /tmp/zenodo-smtlib-page1.json + +# Check if there are more pages (paginate until empty) +curl -s "https://zenodo.org/api/records?communities=smt-lib&size=100&page=2" \ + -o /tmp/zenodo-smtlib-page2.json 2>/dev/null || true + +curl -s "https://zenodo.org/api/records?communities=smt-lib&size=100&page=3" \ + -o /tmp/zenodo-smtlib-page3.json 2>/dev/null || true +``` + +For each Zenodo record extract: +- Record ID (e.g. `5827900`) +- Title +- Any GitHub repository URLs listed in the description or related identifiers + +```bash +python3 - <<'PYEOF' +import json, re + +def extract_github_repos(text): + pattern = r'github\.com/([A-Za-z0-9_.-]+/[A-Za-z0-9_.-]+)' + return set(re.findall(pattern, text or '')) + +official_repos = set() +official_zenodo_ids = set() + +for fname in ['/tmp/zenodo-smtlib-page1.json', '/tmp/zenodo-smtlib-page2.json', + '/tmp/zenodo-smtlib-page3.json']: + try: + data = json.load(open(fname)) + except Exception: + continue + for hit in data.get('hits', {}).get('hits', []): + rid = str(hit.get('id', '')) + official_zenodo_ids.add(rid) + metadata = hit.get('metadata', {}) + description = metadata.get('description', '') + related = ' '.join( + r.get('identifier', '') + for r in metadata.get('related_identifiers', []) + ) + title = metadata.get('title', '') + for repo in extract_github_repos(description + ' ' + related + ' ' + title): + official_repos.add(repo.lower().rstrip('.')) + +with open('/tmp/smtlib-benchmarks.html') as f: + html = f.read() +for repo in extract_github_repos(html): + official_repos.add(repo.lower().rstrip('.')) + +print("OFFICIAL_ZENODO_IDS:", ','.join(sorted(official_zenodo_ids)) or '(none)') +print("OFFICIAL_GITHUB_REPOS:", ','.join(sorted(official_repos)) or '(none)') +PYEOF +``` + +### 2.3 Well-Known Official Repository Patterns + +Regardless of the above scrape, always exclude: +- Any repo under the `SMT-LIB` GitHub organization (`SMT-LIB/*`) +- Any repo whose name matches `smt-comp-*` that is under `SMT-Competition` org +- The Z3 repo itself (`Z3Prover/z3`) and its forks + +Combine all official sources into a single exclusion set stored at +`/tmp/official_exclusions.txt` (one `owner/repo` pattern per line, lowercase). + +## Step 3: Search GitHub for Community SMT-LIB Benchmark Repositories + +Use multiple GitHub search strategies to find repos containing `.smt2` benchmark +files that are NOT part of the official distribution. Search for repos updated +since the last run date (or the last 90 days for the initial run). + +Compute the cutoff date first: +```bash +CUTOFF=$(date -d "90 days ago" +%Y-%m-%d 2>/dev/null || date -v-90d +%Y-%m-%d) +echo "Using cutoff date: $CUTOFF" +``` + +### Search Strategies + +Use the GitHub MCP server tools to run these searches: + +1. **Topic search**: `topic:smtlib pushed:>$CUTOFF` +2. **Topic search variant**: `topic:smt-lib pushed:>$CUTOFF` +3. **Topic search variant**: `topic:smt2 pushed:>$CUTOFF` +4. **Benchmark filename pattern**: `filename:*.smt2 pushed:>$CUTOFF` (limit to top results) +5. **Benchmarks directory pattern**: `path:benchmarks *.smt2 in:path pushed:>$CUTOFF` +6. **README mention**: `SMT-LIB benchmarks in:readme stars:>2 pushed:>$CUTOFF` +7. **Organization-level search**: repos under `SMT-Competition` org, if any are not already excluded + +For each search, collect: `full_name`, `html_url`, `description`, `stargazers_count`, +`updated_at`, `pushed_at`, `default_branch`, `topics`. + +Deduplicate by `full_name`. Limit to 200 total candidates before filtering. + +## Step 4: Filter Out Official Benchmark Sets + +For each candidate repo: + +1. Check if `full_name.lower()` is in the exclusion set from Step 2. +2. Check if the repo is owned by `SMT-LIB` or `SMT-Competition` org (case-insensitive). +3. Check if the repo is a fork of a known official repo (if `fork: true` and parent is + in the exclusion set). + +Discard repos that match any of the above. Keep the rest as community benchmarks. + +Also apply quality filters to reduce noise — skip repos that: +- Have 0 stars and fewer than 3 `.smt2` files (likely a student homework or test repo + with minimal public value); use your judgement — if the repo description clearly + describes a research benchmark, keep it regardless of star count. +- Were created but never pushed after creation (empty repos). +- Have names that are clearly course assignment repositories + (e.g. contain `homework`, `assignment`, `hw[0-9]`, `cs[0-9]{3}`). + +## Step 5: Classify Remaining Repos + +For each repo that survives filtering, classify it into one of these categories: + +| Category | Description | +|----------|-------------| +| **Solver evaluation** | Benchmarks used to evaluate or compare SMT solvers | +| **Verification** | Benchmarks from program verification or model checking | +| **Security / CTF** | Benchmarks from security research or CTF challenges | +| **Theory / logic** | Benchmarks exploring specific SMT theories or logics | +| **Tool output** | Benchmarks generated by another tool (e.g. a compiler, fuzzer) | +| **Education** | Course materials or tutorials with benchmark examples | +| **Other / unknown** | Does not fit another category | + +Base the classification on: repo description, README (fetch if web-fetch is available), +topics, and directory structure. A single brief `web-fetch` of the repo's README is +sufficient; do not fetch individual `.smt2` files. + +Note the dominant SMT logic(s) present, if discernible from the description or topics +(e.g. QF_BV, QF_LIA, QF_S, NIA, …). + +## Step 6: Generate the Discussion Report + +Create a GitHub Discussion. Use heading level 3 or deeper (`###`, `####`, …) for all +section headers; never use `##` or `#` in the body. +Wrap long tables in `
` tags to keep the report scannable. + +Title: `[SMT-LIB Benchmarks] Community Benchmark Repository Survey — [Month YYYY]` + +Structure the report as follows: + +```markdown +**Period covered**: [cutoff date] – [today's date] +**Repositories found**: N community repos (after excluding M official sets) +**New this run**: N (not listed in previous report) + +### Overview + +1–2 sentences summarising the breadth of community SMT-LIB benchmarks found. + +### Community Benchmark Repositories + +Use `###` for category headers. Within each category, list repos as a markdown table. +For each repo include: +- Repo link (`[owner/repo](html_url)`) +- Stars +- Last pushed date +- Dominant logic(s) (if known) +- Brief description (from repo description or README, max 120 chars) + +#### Solver Evaluation + +| Repository | ⭐ | Last pushed | Logic(s) | Description | +|------------|-----|------------|---------|-------------| +| [owner/repo](url) | N | YYYY-MM-DD | QF_BV, QF_LIA | … | + +#### Verification + +[same table structure] + +#### Security / CTF + +[same table structure] + +#### Theory / Logic + +[same table structure] + +#### Tool Output + +[same table structure] + +#### Education + +[same table structure] + +#### Other / Unknown + +[same table structure] + +--- + +### Exclusions Applied + +
+Official SMT-LIB sets excluded from this report + +List Zenodo record IDs and GitHub repos identified as official distributions. + +| Source | Identifier | Notes | +|--------|-----------|-------| +| Zenodo | [10.5281/zenodo.XXXXXXX](https://zenodo.org/record/XXXXXXX) | Official QF_BV benchmark set | +| GitHub | [SMT-LIB/benchmarks-non-incremental](https://github.com/SMT-LIB/benchmarks-non-incremental) | | + +
+ +--- + +### Methodology + +Brief note on search queries used, cutoff date, and any quality filters applied. +``` + +## Step 7: Update Cache Memory + +After posting the discussion, update cache memory with: +- `official_repos`: updated exclusion set (union of previous + newly found) +- `known_community_repos`: union of previous + repos listed in this report +- `last_run_date`: today's ISO-8601 date +- `report_url`: URL of the GitHub Discussion created + +## Guidelines + +- **Be conservative with exclusions**: when in doubt whether a repo is "official", + keep it in the community list rather than silently dropping it. +- **Be accurate**: only include repos that genuinely contain SMT-LIB `.smt2` files + or clearly describe themselves as SMT-LIB benchmark collections. +- **Avoid noise**: student homework repos and trivially small repos add clutter; + apply the quality filters from Step 4 judiciously. +- **No source code changes**: DO NOT create pull requests or modify any source files. +- **No copyrighted content**: DO NOT reproduce benchmark file contents; only post + links and metadata. +- **Always cite sources**: include the full GitHub URL for every listed repository. +- **Use cache**: skip repos already classified in a previous run to keep runtime short. +- **Fail gracefully**: if GitHub search rate-limits the workflow, post whatever was + collected so far with a note that the search was incomplete. + +## Important Notes + +- DO NOT create pull requests or modify source files. +- DO close older SMT-LIB Benchmarks discussions automatically (configured). +- DO always call `create_discussion` or `noop` before the workflow ends. + Failing to produce any safe output triggers an automatic failure issue. +- DO use cache memory to avoid re-processing repos already surveyed. +- DO limit individual `web-fetch` calls (README fetches) to repos where the + description alone is insufficient for classification.