feat: enable evals on smoke-copilot#45324
Conversation
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
|
/smoke-copilot |
|
📰 BREAKING: Smoke Copilot is now investigating this issue comment. Sources say the story is developing... |
|
Hey One thing that would strengthen this PR:
If you would like a hand, here is a prompt to assign to your coding agent:
|
Comment MemoryNote This comment is managed by comment memory.It stores persistent context for this thread in the code block at the top of this comment.
|
There was a problem hiding this comment.
Smoke test review comments added.
📰 BREAKING: Report filed by Smoke Copilot · 124.2 AIC · ⌖ 7.89 AIC · ⊞ 19K
Comment /smoke-copilot to run again
Add label smoke to run again
|
@copilot enable evals on a few more agentic workflows in this repo |
…ntribution-check Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Done. Added
Commit: |
There was a problem hiding this comment.
Pull request overview
Activates BinEval evaluation jobs, removes stale compiler messaging, and updates ADR status. The diff enables evals on four workflows, broader than the stated smoke-copilot scope.
Changes:
- Removes obsolete eval warning and TODO.
- Enables and recompiles BinEval jobs across four workflows.
- Marks ADR-43641 Accepted and updates consequences.
Show a summary per file
| File | Description |
|---|---|
pkg/workflow/compiler_orchestrator_workflow.go |
Removes stale warning. |
pkg/workflow/compiler_jobs.go |
Removes obsolete TODO. |
docs/adr/43641-add-bineval-evals-support.md |
Accepts and revises ADR. |
.github/workflows/smoke-copilot.md |
Adds smoke evaluations. |
.github/workflows/smoke-copilot.lock.yml |
Compiles smoke eval job. |
.github/workflows/smoke-call-workflow.lock.yml |
Includes unrelated recompilation changes. |
.github/workflows/contribution-check.md |
Adds contribution evaluations. |
.github/workflows/contribution-check.lock.yml |
Compiles contribution eval job. |
.github/workflows/breaking-change-checker.md |
Adds breaking-change evaluations. |
.github/workflows/breaking-change-checker.lock.yml |
Compiles breaking-change eval job. |
.github/workflows/auto-triage-issues.md |
Adds triage evaluations. |
.github/workflows/auto-triage-issues.lock.yml |
Compiles triage eval job. |
Review details
Tip
Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
- Files reviewed: 12/12 changed files
- Comments generated: 6
- Review effort level: Medium
| uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 | ||
| env: | ||
| GH_AW_EVALS_QUESTIONS: '[{"id":"smoke-passed","question":"Did all or most smoke tests pass? Look for an overall PASS status or the majority of tests showing ✅ in the agent output."},{"id":"build-succeeded","question":"Did the gh-aw binary build succeed? Look for a successful make build step or explicit mention that compilation succeeded."},{"id":"issue-created","question":"Was a smoke test issue created with test results? Look for a create_issue output containing ''Smoke Test'' in the title."}]' | ||
| GH_AW_EVALS_MODEL: "small" |
| uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 | ||
| env: | ||
| GH_AW_EVALS_QUESTIONS: '[{"id":"labels-applied","question":"Did the agent apply at least one label to an unlabeled issue, or correctly call noop when no unlabeled issues were found?"},{"id":"report-created","question":"Was a summary discussion created listing the issues processed and the labels applied?"}]' | ||
| GH_AW_EVALS_MODEL: "small" |
| fi | ||
| # shellcheck disable=SC1003,SC2016,SC2086 | ||
| sudo -E awf --config "${RUNNER_TEMP}/gh-aw/awf-config.json" --container-workdir "${GITHUB_WORKSPACE}" --mount "${RUNNER_TEMP}/gh-aw:${RUNNER_TEMP}/gh-aw:ro" --mount "${RUNNER_TEMP}/gh-aw:/host${RUNNER_TEMP}/gh-aw:ro" ${GH_AW_TOOL_CACHE_MOUNT:+--mount "$GH_AW_TOOL_CACHE_MOUNT"} ${GH_AW_DOCKER_HOST:+--docker-host "$GH_AW_DOCKER_HOST"} --env-all --exclude-env COPILOT_GITHUB_TOKEN --log-level info --enable-host-access --allow-host-ports 80,443,8080 --skip-pull \ | ||
| -- /bin/bash -c 'set +o histexpand; : "${RUNNER_TOOL_CACHE:?RUNNER_TOOL_CACHE must be set}"; GH_AW_TOOL_CACHE="$RUNNER_TOOL_CACHE"; export PATH="$(find "$GH_AW_TOOL_CACHE" -maxdepth 5 -type d -name bin 2>/dev/null | tr '\''\n'\'' '\'':'\'')$PATH"; [ -n "$GOROOT" ] && export PATH="$GOROOT/bin:$PATH" || true; [ -n "$ERLANG_HOME" ] && export PATH="$ERLANG_HOME/bin:$PATH" || true && GH_AW_NODE_EXEC="${GH_AW_NODE_BIN:-}"; if [ -z "$GH_AW_NODE_EXEC" ] || [ ! -x "$GH_AW_NODE_EXEC" ]; then GH_AW_NODE_EXEC="$(command -v node 2>/dev/null || true)"; fi; if [ -z "$GH_AW_NODE_EXEC" ]; then echo "node runtime missing on this runner — check runtimes.node in workflow YAML" >&2; exit 127; fi; GH_AW_NPM_GLOBAL_ROOT="$(npm root -g 2>/dev/null || true)"; if [ -n "$GH_AW_NPM_GLOBAL_ROOT" ]; then export NODE_PATH="${GH_AW_NPM_GLOBAL_ROOT}${NODE_PATH:+:${NODE_PATH}}"; fi; "$GH_AW_NODE_EXEC" ${RUNNER_TEMP}/gh-aw/actions/copilot_harness.cjs /usr/local/bin/copilot --add-dir /tmp/gh-aw/ --log-level all --log-dir /tmp/gh-aw/sandbox/agent/logs/ --disable-builtin-mcps --no-ask-user --agent contribution-checker --allow-all-tools --add-dir "${GITHUB_WORKSPACE}" --prompt-file /tmp/gh-aw/aw-prompts/prompt.txt' 2>&1 | tee -a /tmp/gh-aw/evals/evals.log |
|
|
||
| **Date**: 2026-07-06 | ||
| **Status**: Draft | ||
| **Status**: Accepted |
| evals: | ||
| - id: prs-evaluated | ||
| question: Did the agent dispatch PRs to the contribution-checker subagent and produce evaluation results for each PR? | ||
| - id: report-created | ||
| question: Was a report issue created summarizing PR compliance with the contributing guidelines? |
| uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0 | ||
| env: | ||
| GH_AW_EVALS_QUESTIONS: '[{"id":"analysis-completed","question":"Did the agent complete an analysis of recent commits and merged PRs for breaking CLI changes?"},{"id":"issue-created-or-noop","question":"Was a breaking change issue created when breaking changes were found, or was noop correctly called when no breaking changes were detected?"}]' | ||
| GH_AW_EVALS_MODEL: "small" |
The
evalsfeature (ADR-43641) was fully implemented but never enabled on any workflow. A stale compiler warning claimed job compilation was pending despitebuildEvalsJobbeing complete.Changes
compiler_orchestrator_workflow.gowas warning "job compilation is pending" and incrementing warning count. Removed it along with now-unusedos/consoleimports.compiler_jobs.gocomment incorrectly describedbuildEvalsJobas a no-op stub.smoke-copilot— Added 3 BinEval questions to frontmatter:smoke-copilot.lock.ymlgains theevalsjob positioned atsafe_outputs → evals → conclusion.