From 3c3ba969d78db948114b9521b9e82000adb46022 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Thu, 2 Apr 2026 09:37:52 +0000 Subject: [PATCH] Fix specbot-crash-analyzer: move build to pre-steps to avoid MCP session timeout Agent-Logs-Url: https://github.com/Z3Prover/z3/sessions/add5e714-bc98-44cf-ad6b-5adfbe4668c3 Co-authored-by: NikolajBjorner <3085284+NikolajBjorner@users.noreply.github.com> --- .../workflows/specbot-crash-analyzer.lock.yml | 72 +++++-- .github/workflows/specbot-crash-analyzer.md | 191 ++++++++++-------- 2 files changed, 159 insertions(+), 104 deletions(-) diff --git a/.github/workflows/specbot-crash-analyzer.lock.yml b/.github/workflows/specbot-crash-analyzer.lock.yml index d3fc60e59..f2add345f 100644 --- a/.github/workflows/specbot-crash-analyzer.lock.yml +++ b/.github/workflows/specbot-crash-analyzer.lock.yml @@ -22,7 +22,7 @@ # # Build Z3 in debug mode from the c3 branch, compile and run the specbot tests, identify root causes for any crashes, and post findings as a GitHub Discussion. # -# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"ae9af2e488abb73e7739599aeea03a842d49e4eb00b2a21396e0615142baf1fd","compiler_version":"v0.65.5","strict":true,"agent_id":"copilot"} +# gh-aw-metadata: {"schema_version":"v3","frontmatter_hash":"96d597a3e9425a3a4dc97fd4e1f3bfcc85a157c5ef38a2eaa34dd6837c77bb8d","compiler_version":"v0.65.5","strict":true,"agent_id":"copilot"} name: "Specbot Crash Analyzer" "on": @@ -134,15 +134,15 @@ jobs: run: | bash ${RUNNER_TEMP}/gh-aw/actions/create_prompt_first.sh { - cat << 'GH_AW_PROMPT_8811cf8abce5aeda_EOF' + cat << 'GH_AW_PROMPT_d99201a359739170_EOF' - GH_AW_PROMPT_8811cf8abce5aeda_EOF + GH_AW_PROMPT_d99201a359739170_EOF cat "${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_8811cf8abce5aeda_EOF' + cat << 'GH_AW_PROMPT_d99201a359739170_EOF' Tools: create_discussion, missing_tool, missing_data, noop @@ -174,12 +174,12 @@ jobs: {{/if}} - GH_AW_PROMPT_8811cf8abce5aeda_EOF + GH_AW_PROMPT_d99201a359739170_EOF cat "${RUNNER_TEMP}/gh-aw/prompts/github_mcp_tools_with_safeoutputs_prompt.md" - cat << 'GH_AW_PROMPT_8811cf8abce5aeda_EOF' + cat << 'GH_AW_PROMPT_d99201a359739170_EOF' {{#runtime-import .github/workflows/specbot-crash-analyzer.md}} - GH_AW_PROMPT_8811cf8abce5aeda_EOF + GH_AW_PROMPT_d99201a359739170_EOF } > "$GH_AW_PROMPT" - name: Interpolate variables and render templates uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8 @@ -188,6 +188,7 @@ jobs: GH_AW_GITHUB_REPOSITORY: ${{ github.repository }} GH_AW_GITHUB_RUN_ID: ${{ github.run_id }} GH_AW_GITHUB_WORKFLOW: ${{ github.workflow }} + GH_AW_GITHUB_WORKSPACE: ${{ github.workspace }} with: script: | const { setupGlobals } = require('${{ runner.temp }}/gh-aw/actions/setup_globals.cjs'); @@ -295,6 +296,47 @@ jobs: with: persist-credentials: false ref: c3 + - name: Install build dependencies + run: | + sudo apt-get update -y + sudo apt-get install -y cmake ninja-build python3 gcc g++ 2>&1 | tail -5 + - continue-on-error: true + id: build-z3 + name: Build Z3 in debug mode + run: | + mkdir -p build/debug specbot-results + cd build/debug + cmake -G Ninja -DCMAKE_BUILD_TYPE=Debug ../.. 2>&1 | tee ../../specbot-results/cmake.log + ninja 2>&1 | tee ../../specbot-results/build.log + BUILD_EXIT=$? + cd ../.. + echo "build_exit=${BUILD_EXIT}" >> specbot-results/build-status.txt + ls -la build/debug/libz3* build/debug/*.so* 2>/dev/null >> specbot-results/build-status.txt || echo "Library not found" >> specbot-results/build-status.txt + exit $BUILD_EXIT + - continue-on-error: true + name: Compile specbot tests + run: "mkdir -p specbot-results\ngcc -g -O0 \\\n -I src/api \\\n specbot/test_specbot_seq.c \\\n -L build/debug \\\n -lz3 \\\n -Wl,-rpath,\"${GITHUB_WORKSPACE}/build/debug\" \\\n -o specbot-results/test_specbot_seq \\\n 2>&1 | tee specbot-results/compile_specbot_seq.log\necho \"compile_specbot_seq_exit=$?\" >> specbot-results/compile-status.txt\n\ngcc -g -O0 \\\n -I src/api \\\n specbot/test_deeptest_seq.c \\\n -L build/debug \\\n -lz3 \\\n -Wl,-rpath,\"${GITHUB_WORKSPACE}/build/debug\" \\\n -o specbot-results/test_deeptest_seq \\\n 2>&1 | tee specbot-results/compile_deeptest_seq.log\necho \"compile_deeptest_seq_exit=$?\" >> specbot-results/compile-status.txt\n" + - continue-on-error: true + name: Run specbot tests + run: |- + mkdir -p specbot-results + if [ -f specbot-results/test_specbot_seq ]; then + LD_LIBRARY_PATH="${GITHUB_WORKSPACE}/build/debug" timeout 120 specbot-results/test_specbot_seq > specbot-results/test_specbot_seq.log 2>&1 + SPECBOT_EXIT=$? + echo "specbot_seq_exit=${SPECBOT_EXIT}" >> specbot-results/test-status.txt + else + echo "Binary not compiled" > specbot-results/test_specbot_seq.log + echo "specbot_seq_exit=127" >> specbot-results/test-status.txt + fi + + if [ -f specbot-results/test_deeptest_seq ]; then + LD_LIBRARY_PATH="${GITHUB_WORKSPACE}/build/debug" timeout 120 specbot-results/test_deeptest_seq > specbot-results/test_deeptest_seq.log 2>&1 + DEEPTEST_EXIT=$? + echo "deeptest_seq_exit=${DEEPTEST_EXIT}" >> specbot-results/test-status.txt + else + echo "Binary not compiled" > specbot-results/test_deeptest_seq.log + echo "deeptest_seq_exit=127" >> specbot-results/test-status.txt + fi # Cache memory file share configuration from frontmatter processed below - name: Create cache-memory directory @@ -358,12 +400,12 @@ jobs: 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_5fe8d0129abde348_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/config.json << 'GH_AW_SAFE_OUTPUTS_CONFIG_9fac06c2633cb7e6_EOF' {"create_discussion":{"category":"agentic workflows","close_older_discussions":true,"expires":168,"fallback_to_issue":true,"max":1,"title_prefix":"[Specbot] "},"missing_data":{},"missing_tool":{},"noop":{"max":1,"report-as-issue":"false"}} - GH_AW_SAFE_OUTPUTS_CONFIG_5fe8d0129abde348_EOF + GH_AW_SAFE_OUTPUTS_CONFIG_9fac06c2633cb7e6_EOF - name: Write Safe Outputs Tools run: | - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_b7ef482a67ec3845_EOF' + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/tools_meta.json << 'GH_AW_SAFE_OUTPUTS_TOOLS_META_55790e26900a41d5_EOF' { "description_suffixes": { "create_discussion": " CONSTRAINTS: Maximum 1 discussion(s) can be created. Title will be prefixed with \"[Specbot] \". Discussions will be created in category \"agentic workflows\"." @@ -371,8 +413,8 @@ jobs: "repo_params": {}, "dynamic_tools": [] } - GH_AW_SAFE_OUTPUTS_TOOLS_META_b7ef482a67ec3845_EOF - cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_8f49b80728c10fc7_EOF' + GH_AW_SAFE_OUTPUTS_TOOLS_META_55790e26900a41d5_EOF + cat > ${RUNNER_TEMP}/gh-aw/safeoutputs/validation.json << 'GH_AW_SAFE_OUTPUTS_VALIDATION_9c92f692de8367d6_EOF' { "create_discussion": { "defaultMax": 1, @@ -458,7 +500,7 @@ jobs: } } } - GH_AW_SAFE_OUTPUTS_VALIDATION_8f49b80728c10fc7_EOF + GH_AW_SAFE_OUTPUTS_VALIDATION_9c92f692de8367d6_EOF node ${RUNNER_TEMP}/gh-aw/actions/generate_safe_outputs_tools.cjs - name: Generate Safe Outputs MCP Server Config id: safe-outputs-config @@ -526,7 +568,7 @@ jobs: export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_GUARD_MIN_INTEGRITY -e GITHUB_MCP_GUARD_REPOS -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -v /tmp/gh-aw/mcp-payloads:/tmp/gh-aw/mcp-payloads:rw -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.2.11' mkdir -p /home/runner/.copilot - cat << GH_AW_MCP_CONFIG_44c4cbc18fb645da_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh + cat << GH_AW_MCP_CONFIG_a39965076f757f6f_EOF | bash ${RUNNER_TEMP}/gh-aw/actions/start_mcp_gateway.sh { "mcpServers": { "github": { @@ -567,7 +609,7 @@ jobs: "payloadDir": "${MCP_GATEWAY_PAYLOAD_DIR}" } } - GH_AW_MCP_CONFIG_44c4cbc18fb645da_EOF + GH_AW_MCP_CONFIG_a39965076f757f6f_EOF - name: Download activation artifact uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1 with: diff --git a/.github/workflows/specbot-crash-analyzer.md b/.github/workflows/specbot-crash-analyzer.md index af589684d..19b45b70d 100644 --- a/.github/workflows/specbot-crash-analyzer.md +++ b/.github/workflows/specbot-crash-analyzer.md @@ -38,6 +38,71 @@ steps: ref: c3 persist-credentials: false + - name: Install build dependencies + run: | + sudo apt-get update -y + sudo apt-get install -y cmake ninja-build python3 gcc g++ 2>&1 | tail -5 + + - name: Build Z3 in debug mode + id: build-z3 + continue-on-error: true + run: | + mkdir -p build/debug specbot-results + cd build/debug + cmake -G Ninja -DCMAKE_BUILD_TYPE=Debug ../.. 2>&1 | tee ../../specbot-results/cmake.log + ninja 2>&1 | tee ../../specbot-results/build.log + BUILD_EXIT=$? + cd ../.. + echo "build_exit=${BUILD_EXIT}" >> specbot-results/build-status.txt + ls -la build/debug/libz3* build/debug/*.so* 2>/dev/null >> specbot-results/build-status.txt || echo "Library not found" >> specbot-results/build-status.txt + exit $BUILD_EXIT + + - name: Compile specbot tests + continue-on-error: true + run: | + mkdir -p specbot-results + gcc -g -O0 \ + -I src/api \ + specbot/test_specbot_seq.c \ + -L build/debug \ + -lz3 \ + -Wl,-rpath,"${GITHUB_WORKSPACE}/build/debug" \ + -o specbot-results/test_specbot_seq \ + 2>&1 | tee specbot-results/compile_specbot_seq.log + echo "compile_specbot_seq_exit=$?" >> specbot-results/compile-status.txt + + gcc -g -O0 \ + -I src/api \ + specbot/test_deeptest_seq.c \ + -L build/debug \ + -lz3 \ + -Wl,-rpath,"${GITHUB_WORKSPACE}/build/debug" \ + -o specbot-results/test_deeptest_seq \ + 2>&1 | tee specbot-results/compile_deeptest_seq.log + echo "compile_deeptest_seq_exit=$?" >> specbot-results/compile-status.txt + + - name: Run specbot tests + continue-on-error: true + run: | + mkdir -p specbot-results + if [ -f specbot-results/test_specbot_seq ]; then + LD_LIBRARY_PATH="${GITHUB_WORKSPACE}/build/debug" timeout 120 specbot-results/test_specbot_seq > specbot-results/test_specbot_seq.log 2>&1 + SPECBOT_EXIT=$? + echo "specbot_seq_exit=${SPECBOT_EXIT}" >> specbot-results/test-status.txt + else + echo "Binary not compiled" > specbot-results/test_specbot_seq.log + echo "specbot_seq_exit=127" >> specbot-results/test-status.txt + fi + + if [ -f specbot-results/test_deeptest_seq ]; then + LD_LIBRARY_PATH="${GITHUB_WORKSPACE}/build/debug" timeout 120 specbot-results/test_deeptest_seq > specbot-results/test_deeptest_seq.log 2>&1 + DEEPTEST_EXIT=$? + echo "deeptest_seq_exit=${DEEPTEST_EXIT}" >> specbot-results/test-status.txt + else + echo "Binary not compiled" > specbot-results/test_deeptest_seq.log + echo "deeptest_seq_exit=127" >> specbot-results/test-status.txt + fi + --- # Specbot Crash Analyzer @@ -45,103 +110,50 @@ steps: ## Job Description Your name is ${{ github.workflow }}. You are an expert C/C++ and SMT solver analyst for the Z3 theorem prover -repository `${{ github.repository }}`. Your task is to build Z3 in debug mode from the `c3` branch, compile and run -the specbot test suite, capture any crashes or assertion failures, diagnose their root causes by reading the -relevant source files, and publish a structured findings report as a GitHub Discussion. +repository `${{ github.repository }}`. The pre-steps above have already built Z3 in debug mode from the `c3` +branch, compiled and run the specbot test suite, and saved all output to the `specbot-results/` directory in +the workspace (`${{ github.workspace }}/specbot-results/`). Your task is to analyze those results, diagnose +any crash root causes by reading the relevant source files, and publish a structured findings report as a +GitHub Discussion. -The repository has already been checked out at the `c3` branch in the pre-step above. +**Do not try to build Z3 or run tests yourself.** All build and test output is already in `specbot-results/`. ## Your Task -### 1. Install Build Dependencies +### 1. Read the Pre-Generated Results -Install the tools needed to build Z3 and compile the C test programs: +All build and test outputs are in `specbot-results/` (relative to the workspace root). Read each file: ```bash -sudo apt-get update -y -sudo apt-get install -y cmake ninja-build python3 gcc g++ 2>&1 | tail -5 +# Build status +cat specbot-results/build-status.txt 2>/dev/null || echo "No build status" + +# Compile status +cat specbot-results/compile-status.txt 2>/dev/null || echo "No compile status" + +# Test status +cat specbot-results/test-status.txt 2>/dev/null || echo "No test status" + +# Test output from test_specbot_seq +cat specbot-results/test_specbot_seq.log 2>/dev/null || echo "No test_specbot_seq output" + +# Test output from test_deeptest_seq +cat specbot-results/test_deeptest_seq.log 2>/dev/null || echo "No test_deeptest_seq output" + +# Last 30 lines of the build log +tail -30 specbot-results/build.log 2>/dev/null || echo "No build log" ``` -### 2. Build Z3 in Debug Mode +If `specbot-results/build-status.txt` shows `build_exit=0`, the build succeeded. +If it shows a non-zero exit, include the last 50 lines of `specbot-results/build.log` in the report +under a "Build Failure" section. -Configure and build Z3 in debug mode. Store the build output in `build/debug`: +If `specbot-results/compile-status.txt` shows a non-zero exit for a test, include the compile error +from `specbot-results/compile_specbot_seq.log` or `specbot-results/compile_deeptest_seq.log`. -```bash -mkdir -p build/debug -cd build/debug -cmake -G Ninja -DCMAKE_BUILD_TYPE=Debug ../.. 2>&1 | tail -10 -ninja 2>&1 | tail -20 -cd ../.. -``` +Collect every line containing `CRASH` or `ABORT` from the test log files — these are the crashes to analyze. -Verify the build succeeded by checking that `build/debug/libz3.so` (or `build/debug/libz3.a`) exists: - -```bash -ls build/debug/libz3* 2>/dev/null || ls build/debug/*.so* 2>/dev/null || echo "Library not found" -``` - -If the build fails, capture the last 50 lines of ninja output and include them in the report under a -"Build Failure" section, then stop. - -### 3. Compile the Specbot Tests - -The `specbot/` directory at the root of the repository contains two C test programs: - -- `specbot/test_specbot_seq.c` — basic specbot invariant tests for the Z3 seq/Nielsen solver -- `specbot/test_deeptest_seq.c` — deep-coverage tests targeting under-exercised code paths - -Compile each test, linking against the debug build of Z3. Use the Z3 public C API header from `src/api/z3.h`: - -```bash -# Compile test_specbot_seq -gcc -g -O0 \ - -I src/api \ - specbot/test_specbot_seq.c \ - -L build/debug \ - -lz3 \ - -Wl,-rpath,build/debug \ - -o /tmp/test_specbot_seq \ - 2>&1 -echo "test_specbot_seq compile exit: $?" - -# Compile test_deeptest_seq -gcc -g -O0 \ - -I src/api \ - specbot/test_deeptest_seq.c \ - -L build/debug \ - -lz3 \ - -Wl,-rpath,build/debug \ - -o /tmp/test_deeptest_seq \ - 2>&1 -echo "test_deeptest_seq compile exit: $?" -``` - -If a test fails to compile, include the compiler error in the report and skip running that test. - -### 4. Run the Tests and Capture Output - -Run each compiled test binary. Capture stdout and stderr. The test harness prints lines like: - -- `[TEST] Running ` — test started -- `[TEST] PASS ` — test passed -- `[TEST] CRASH (exception 0x...)` — SEH exception caught (Windows only; on Linux the process aborts) -- `[TEST] ABORT (caught SIGABRT)` — assertion failure caught via SIGABRT + longjmp - -On Linux, wrap each run with a timeout and capture the exit code and any signal: - -```bash -LD_LIBRARY_PATH=build/debug timeout 120 /tmp/test_specbot_seq > /tmp/specbot_out.txt 2>&1 -echo "specbot exit: $?" -cat /tmp/specbot_out.txt - -LD_LIBRARY_PATH=build/debug timeout 120 /tmp/test_deeptest_seq > /tmp/deeptest_out.txt 2>&1 -echo "deeptest exit: $?" -cat /tmp/deeptest_out.txt -``` - -Collect every line that contains `CRASH` or `ABORT` from both output files — these are the crashes to analyze. - -### 5. Diagnose Each Crash +### 2. Diagnose Each Crash For each crashed test function, perform the following analysis: @@ -170,7 +182,7 @@ For each crashed test function, perform the following analysis: 4. **Suggest a fix**: propose a minimal, concrete fix — e.g., a guard condition, an additional lemma, a missing reference-count increment, or a missing case in a switch/match. -### 6. Generate the Report +### 3. Generate the Report After analyzing all crashes, produce a structured GitHub Discussion in the "Agentic Workflows" category using `create-discussion`. @@ -231,6 +243,7 @@ Format workflow run references as: `[§${{ github.run_id }}](https://github.com/ ## Usage -Trigger via **Actions → Specbot Crash Analyzer → Run workflow** on any branch; the pre-step -always checks out the `c3` branch where `specbot/test_specbot_seq.c` and -`specbot/test_deeptest_seq.c` live. The discussion is posted to the "Agentic Workflows" category. +Trigger via **Actions → Specbot Crash Analyzer → Run workflow** on any branch. The pre-steps +always check out the `c3` branch where `specbot/test_specbot_seq.c` and +`specbot/test_deeptest_seq.c` live, build Z3, run the tests, and save results to `specbot-results/`. +The agent then analyzes the results and posts a discussion to the "Agentic Workflows" category.