Skip to content

feat: enable evals on smoke-copilot#45324

Merged
pelikhan merged 4 commits into
mainfrom
copilot/enable-evals-on-smoke-copilot
Jul 14, 2026
Merged

feat: enable evals on smoke-copilot#45324
pelikhan merged 4 commits into
mainfrom
copilot/enable-evals-on-smoke-copilot

Conversation

Copilot AI commented Jul 13, 2026

Copy link
Copy Markdown
Contributor

The evals feature (ADR-43641) was fully implemented but never enabled on any workflow. A stale compiler warning claimed job compilation was pending despite buildEvalsJob being complete.

Changes

  • Remove stale warningcompiler_orchestrator_workflow.go was warning "job compilation is pending" and incrementing warning count. Removed it along with now-unused os/console imports.
  • Remove stale TODOcompiler_jobs.go comment incorrectly described buildEvalsJob as a no-op stub.
  • Enable evals on smoke-copilot — Added 3 BinEval questions to frontmatter:
    evals:
      - id: smoke-passed
        question: Did all or most smoke tests pass?
      - id: build-succeeded
        question: Did the gh-aw binary build succeed?
      - id: issue-created
        question: Was a smoke test issue created with test results?
  • Recompilesmoke-copilot.lock.yml gains the evals job positioned at safe_outputs → evals → conclusion.
  • ADR-43641 — Status promoted Draft → Accepted; Negative section corrected (had duplicated the Positive bullets).

Copilot AI and others added 3 commits July 13, 2026 20:27
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>
@pelikhan

Copy link
Copy Markdown
Collaborator

/smoke-copilot

@github-actions

github-actions Bot commented Jul 13, 2026

Copy link
Copy Markdown
Contributor

📰 BREAKING: Smoke Copilot is now investigating this issue comment. Sources say the story is developing...

@github-actions

Copy link
Copy Markdown
Contributor

Hey @copilot-swe-agent 👋 — nice work activating the evals feature on smoke-copilot and cleaning up the stale compiler warning and TODO that had been lingering since ADR-43641 was written. The changes are well-scoped and the description is thorough.

One thing that would strengthen this PR:

  • Add tests — the compiler changes in compiler_orchestrator_workflow.go (removing the stale warning branch) and compiler_jobs.go (removing the stub comment) touch compilation logic. A unit test asserting that buildEvalsJob no longer produces a spurious warning, and that the compiled smoke-copilot.lock.yml includes the expected evals job, would give reviewers confidence the removal is safe.

If you would like a hand, here is a prompt to assign to your coding agent:

Add unit tests covering the evals compiler changes in PR #45324:

1. In pkg/workflow, add a test asserting that compiling a workflow with a valid `evals` frontmatter block does NOT produce any "job compilation is pending" warning for the evals job.
2. Add a test asserting that the compiled output for a workflow with `evals` entries contains an `evals` job node positioned after `safe_outputs` and before `conclusion`.
3. Verify that `buildEvalsJob` is no longer treated as a no-op stub (i.e., it returns a non-nil job definition).

Generated by ✅ Contribution Check · 95.3 AIC · ⌖ 22.3 AIC · ⊞ 6.2K ·

@github-actions

Copy link
Copy Markdown
Contributor

Comment Memory

Circuits hum at dawn
Bots test branches without blinking
Green lights teach the wind

Note

This comment is managed by comment memory.

It stores persistent context for this thread in the code block at the top of this comment.
Edit only the text inside the backtick fences; workflow metadata and the footer are regenerated automatically.

Learn more about comment memory

📰 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

@github-actions github-actions Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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

@pelikhan

Copy link
Copy Markdown
Collaborator

@copilot enable evals on a few more agentic workflows in this repo

…ntribution-check

Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>

Copilot AI commented Jul 14, 2026

Copy link
Copy Markdown
Contributor Author

@copilot enable evals on a few more agentic workflows in this repo

Done. Added evals: blocks to three more agentic workflows and recompiled all of them:

  • auto-triage-issues — evaluates whether labels were applied (or noop correctly called) and whether a summary discussion was created
  • breaking-change-checker — evaluates whether the analysis completed and whether an issue was created or noop called appropriately
  • contribution-check — evaluates whether PRs were dispatched to the contribution-checker subagent and a report issue was created

Commit: feat: enable evals on auto-triage-issues, breaking-change-checker, contribution-check

@pelikhan pelikhan marked this pull request as ready for review July 14, 2026 03:04
Copilot AI review requested due to automatic review settings July 14, 2026 03:04
@pelikhan pelikhan merged commit 0e64b08 into main Jul 14, 2026
@pelikhan pelikhan deleted the copilot/enable-evals-on-smoke-copilot branch July 14, 2026 03:04

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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
Comment on lines +119 to +123
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"
@github-actions github-actions Bot mentioned this pull request Jul 14, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants