Conversation
Refactors the benchmark workflow to rely solely on release baselines for performance comparison. This removes the generation of fallback baselines during pull request workflows, streamlining the process and ensuring comparisons are made against accurate, full-setting benchmarks. Updates the reporting to provide clearer guidance on how to enable performance regression testing via release tags. Increases baseline artifact retention from 1 year to 90 days to match repository maximum.
Modifies the workflow to improve the way performance baseline artifacts are located. The workflow now first attempts to find baseline artifacts associated with release tags by searching recent successful workflow runs of 'generate-baseline.yml'. If no release-tagged baseline is found, it falls back to searching for any recent baseline artifact generated by the same workflow, regardless of its origin (e.g., manual trigger). This ensures that a baseline is found even if a tagged release is not available, or the baseline was manually generated. It also changes the failure message if no baseline is found, and provides improved instructions on how to generate a baseline.
|
Note Other AI code review bot(s) detectedCodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review. WalkthroughOverhauled baseline discovery to build a paginated artifact cache (search up to 150 runs), prefer release-matched artifact, fallback to most-recent manual artifact, expose Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor Dev as Developer
participant BW as Benchmarks Workflow
participant GH as GitHub API
participant AC as Artifact Cache
participant RT as Regression Test
Dev->>BW: Trigger benchmarks
BW->>GH: List successful runs of generate-baseline (paginate, up to 150)
GH-->>BW: Runs + artifacts
BW->>AC: Build artifactCache of `performance-baseline-*` artifacts
note right of BW: Derive expectedName from sanitized release tag
alt Exact release baseline found
BW->>BW: emit outputs {found=true, source_type="release", release_tag, artifact_name, run_id}
else Manual fallback found
BW->>BW: emit outputs {found=true, source_type="manual", release_tag="manual-baseline", artifact_name, run_id}
else None found
BW->>BW: set BASELINE_EXISTS=false, BASELINE_SOURCE=none
end
opt If baseline found
BW->>RT: Run full comparison against discovered baseline
RT-->>BW: Results
end
BW-->>Dev: Summary with Baseline Origin and outcome
Estimated code review effort🎯 4 (Complex) | ⏱️ ~40 minutes Poem
✨ Finishing Touches🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
There was a problem hiding this comment.
Pull Request Overview
Updates the performance benchmarking workflow to improve baseline artifact discovery and handling, clarify messaging when baselines are missing, and align artifact retention with repository limits.
- Refactored baseline search to first look for release-tagged artifacts, then fall back to any recent baseline artifacts
- Replaced on-the-fly baseline generation with clearer messaging about enabling performance regression testing
- Reduced artifact retention from 365 to 90 days to match repository maximum
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| .github/workflows/generate-baseline.yml | Updated artifact retention period from 365 to 90 days |
| .github/workflows/benchmarks.yml | Refactored baseline discovery logic, improved fallback handling, and simplified regression testing workflow |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
.github/workflows/benchmarks.yml
Outdated
| core.setOutput('source_type', 'release'); | ||
| return; |
There was a problem hiding this comment.
The return statement exits the entire script block abruptly. Consider using a proper control flow mechanism or setting a flag to break out of nested loops more cleanly, as this makes the code harder to follow and maintain.
.github/workflows/benchmarks.yml
Outdated
| core.setOutput('source_type', 'manual'); | ||
| return; |
There was a problem hiding this comment.
Same issue as above - the return statement exits the script abruptly from within nested loops. This pattern makes the control flow difficult to understand and maintain.
Coverage summary from CodacySee diff coverage on Codacy
Coverage variation details
Coverage variation is the difference between the coverage for the head and common ancestor commits of the pull request branch: Diff coverage details
Diff coverage is the percentage of lines that are covered by tests out of the coverable lines that the pull request added or modified: See your quality gate settings Change summary preferences |
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #59 +/- ##
==========================================
+ Coverage 69.75% 70.11% +0.36%
==========================================
Files 17 17
Lines 2486 2486
==========================================
+ Hits 1734 1743 +9
+ Misses 752 743 -9
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (6)
.github/workflows/generate-baseline.yml (1)
144-146: Avoid asserting “repository maximum” unless enforced; consider making retention configurable.90 days is fine, but “repository maximum” may be plan/settings-dependent. Recommend either softening the comment or wiring retention via an input/env so it can be adjusted without code changes.
Apply:
- retention-days: 90 # Keep baselines for 90 days (repository maximum) + retention-days: 90 # Keep baselines ~90 days (align with repo settings; adjust if needed).github/workflows/benchmarks.yml (5)
93-96: Keep tag sanitization in lockstep with generate-baseline.Regex mirrors
sedin generate-baseline; add a short comment referencing that file to prevent drift when one changes.Apply:
- const cleanTag = release.tag_name.replace(/[^a-zA-Z0-9._-]/g, '_'); + // Must match sanitize step in .github/workflows/generate-baseline.yml + const cleanTag = release.tag_name.replace(/[^a-zA-Z0-9._-]/g, '_');
190-211: Propagate origin (“release”/“manual”) to the env for later logging.Currently
BASELINE_SOURCEis always set toartifact, losing the newsource_type. Export an additionalBASELINE_ORIGIN.Apply:
- name: Extract baseline from artifact if: steps.find_baseline.outputs.found == 'true' shell: bash env: RELEASE_TAG: ${{ steps.find_baseline.outputs.release_tag }} + SOURCE_TYPE: ${{ steps.find_baseline.outputs.source_type }} run: | set -euo pipefail if [[ -f "baseline-artifact/baseline_results.txt" ]]; then echo "📦 Extracted baseline from artifact for release ${RELEASE_TAG:-unknown}" mkdir -p "benches" cp "baseline-artifact/baseline_results.txt" "benches/baseline_results.txt" echo "BASELINE_EXISTS=true" >> "$GITHUB_ENV" echo "BASELINE_SOURCE=artifact" >> "$GITHUB_ENV" + echo "BASELINE_ORIGIN=${SOURCE_TYPE:-unknown}" >> "$GITHUB_ENV"
213-221: Also set BASELINE_ORIGIN when none found.Keeps summary consistent.
Apply:
- name: Set baseline status if none found if: steps.find_baseline.outputs.found != 'true' shell: bash run: | set -euo pipefail echo "📈 No baseline artifact found for performance comparison" echo "BASELINE_EXISTS=false" >> "$GITHUB_ENV" echo "BASELINE_SOURCE=none" >> "$GITHUB_ENV" + echo "BASELINE_ORIGIN=none" >> "$GITHUB_ENV"
292-299: Fix message: it may be a manual baseline; use origin in logs.Current log says “release baseline” unconditionally.
Apply:
echo "🚀 Running performance regression test..." - echo " Baseline source: ${BASELINE_SOURCE:-unknown}" + echo " Baseline source: ${BASELINE_SOURCE:-unknown}" + echo " Baseline origin: ${BASELINE_ORIGIN:-unknown}" # This will exit with code 1 if significant regressions are found - echo " Using full comparison mode against release baseline" + echo " Using full comparison mode against ${BASELINE_ORIGIN:-unknown} baseline" uv run benchmark-utils compare --baseline benches/baseline_results.txt \ || uv run python -m scripts.benchmark_utils compare --baseline benches/baseline_results.txt
326-333: Include origin in the summary.Surfaces the new
source_typesignal that the PR introduces.Apply:
echo "Baseline source: ${BASELINE_SOURCE:-none}" + echo "Baseline origin: ${BASELINE_ORIGIN:-unknown}" echo "Baseline exists: ${BASELINE_EXISTS:-false}"
📜 Review details
Configuration used: Path: .coderabbit.yml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (2)
.github/workflows/benchmarks.yml(5 hunks).github/workflows/generate-baseline.yml(1 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (5)
- GitHub Check: Codacy Static Code Analysis
- GitHub Check: Code Coverage
- GitHub Check: build (windows-latest)
- GitHub Check: build (macos-latest)
- GitHub Check: Codacy Security Scan
Ensures that expired artifacts are ignored when searching for performance baselines. This prevents the benchmark workflow from erroneously using outdated data. Adds more detailed logging about the baseline source, differentiating between baselines from artifacts and releases. The origin of the baseline (release or artifact) is now included in the comparison output and summary.
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (2)
.github/workflows/benchmarks.yml (2)
124-129: Early returns inside github-script.Previous reviews flagged early returns. Here they’re acceptable for control flow in this isolated script; no action needed unless you prefer a single-exit style.
169-171: Same note about early return.Same rationale as above.
🧹 Nitpick comments (1)
.github/workflows/benchmarks.yml (1)
97-131: Reduce API calls by caching run artifacts once.Current approach lists artifacts for up to 3×50 runs per release, multiplying API calls by number of releases. Fetch runs and their artifacts once, build a Set/map of artifact names → run_id, then match expectedName per release. This cuts calls from O(releases × runs) to O(runs).
Also applies to: 136-173
📜 Review details
Configuration used: Path: .coderabbit.yml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (2)
.github/workflows/benchmarks.yml(8 hunks).github/workflows/generate-baseline.yml(1 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- .github/workflows/generate-baseline.yml
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (4)
- GitHub Check: Codacy Static Code Analysis
- GitHub Check: build (windows-latest)
- GitHub Check: Code Coverage
- GitHub Check: Codacy Security Scan
🔇 Additional comments (5)
.github/workflows/benchmarks.yml (5)
115-117: Good fix: exclude expired artifacts.Guarding on a.expired !== true prevents 404s when downloading expired artifacts. This addresses prior feedback.
155-158: Good fix in fallback: also exclude expired artifacts.Consistent with the primary search; avoids dead downloads.
192-207: Nice: propagate artifact origin.BASELINE_SOURCE=artifact and BASELINE_ORIGIN={release|manual} improve observability.
217-226: Clear “no baseline” path.Explicitly setting BASELINE_EXISTS=false/SOURCE=none/ORIGIN=none is clean and predictable.
299-300: Consistent origin reporting.Surfacing Baseline origin in run and summary output is helpful for triage.
Also applies to: 335-335
| echo " Using full comparison mode against ${BASELINE_ORIGIN:-unknown} baseline" | ||
| uv run benchmark-utils compare --baseline benches/baseline_results.txt \ | ||
| || uv run python -m scripts.benchmark_utils compare --baseline benches/baseline_results.txt | ||
|
|
There was a problem hiding this comment.
Bug: ‘||’ fallback masks real regressions (exit code 1).
If benchmark-utils correctly exits 1 on regression, the right-hand command runs and can overwrite the outcome. Gate the fallback on command availability, not on exit status.
Apply this diff:
- echo " Using full comparison mode against ${BASELINE_ORIGIN:-unknown} baseline"
- uv run benchmark-utils compare --baseline benches/baseline_results.txt \
- || uv run python -m scripts.benchmark_utils compare --baseline benches/baseline_results.txt
+ echo " Using full comparison mode against ${BASELINE_ORIGIN:-unknown} baseline"
+ if uv run benchmark-utils --help >/dev/null 2>&1; then
+ uv run benchmark-utils compare --baseline benches/baseline_results.txt
+ elif uv run python - <<'PY' >/dev/null 2>&1
+import importlib; importlib.import_module("scripts.benchmark_utils")
+PY
+ then
+ uv run python -m scripts.benchmark_utils compare --baseline benches/baseline_results.txt
+ else
+ echo "❌ benchmark-utils entrypoint and module not found" >&2
+ exit 2
+ fi📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| echo " Using full comparison mode against ${BASELINE_ORIGIN:-unknown} baseline" | |
| uv run benchmark-utils compare --baseline benches/baseline_results.txt \ | |
| || uv run python -m scripts.benchmark_utils compare --baseline benches/baseline_results.txt | |
| echo " Using full comparison mode against ${BASELINE_ORIGIN:-unknown} baseline" | |
| if uv run benchmark-utils --help >/dev/null 2>&1; then | |
| uv run benchmark-utils compare --baseline benches/baseline_results.txt | |
| elif uv run python - <<'PY' >/dev/null 2>&1 | |
| import importlib; importlib.import_module("scripts.benchmark_utils") | |
| PY | |
| then | |
| uv run python -m scripts.benchmark_utils compare --baseline benches/baseline_results.txt | |
| else | |
| echo "❌ benchmark-utils entrypoint and module not found" >&2 | |
| exit 2 | |
| fi |
🤖 Prompt for AI Agents
.github/workflows/benchmarks.yml around lines 302 to 305: the current use of
"||" to fall back to the python runner will execute the python fallback whenever
the first command exits non-zero (including a legitimate regression exit code
1), masking real failures; change the logic to only run the python fallback when
the primary command is unavailable by checking for the presence of the 'uv'
command (or whichever runner you intend) and only invoking the python fallback
if that check fails, ensuring that a non-zero exit from the primary runner is
propagated and not overwritten.
Optimizes the benchmark workflow by caching baseline artifacts from recent successful workflow runs. This significantly reduces the number of API calls required to locate the correct baseline, particularly for release baselines. It also falls back to the most recent baseline artifact if no release baseline is found. Also, the `compare` command is executed using an `if` statement that determines whether the benchmark utils is installed as a module or an entrypoint to avoid errors.
There was a problem hiding this comment.
Actionable comments posted: 2
📜 Review details
Configuration used: Path: .coderabbit.yml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
.github/workflows/benchmarks.yml(7 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (5)
- GitHub Check: Codacy Static Code Analysis
- GitHub Check: build (windows-latest)
- GitHub Check: build (ubuntu-latest)
- GitHub Check: Code Coverage
- GitHub Check: Codacy Security Scan
🔇 Additional comments (3)
.github/workflows/benchmarks.yml (3)
142-145: Confirm tag sanitization matches generate-baseline.The regex must be identical to the producer to avoid misses. Please verify
.github/workflows/generate-baseline.ymluses the same/[^a-zA-Z0-9._-]/greplacement.
152-158: Early returns are appropriate here.Exiting after setting outputs keeps control flow simple in
actions/github-script. No change needed.Also applies to: 182-188
319-327: Good fix: don’t mask regressions with “||” fallback.Tool detection before invocation preserves non-zero exit codes from real regressions. Solid.
Limits the number of workflow runs fetched to avoid excessive API calls and ensures that only unique, non-expired baseline artifacts are cached, enhancing the reliability and efficiency of the benchmark workflow. Fixes a bug where oldest benchmarks were used - GitHub lists newest first, so first one should be preferred.
There was a problem hiding this comment.
Actionable comments posted: 0
♻️ Duplicate comments (1)
.github/workflows/benchmarks.yml (1)
320-329: Fix preserves true regression exit codes (no ‘||’ masking).Availability-gated fallback addresses the prior concern about masking exit code 1 on regressions.
🧹 Nitpick comments (3)
.github/workflows/benchmarks.yml (3)
91-96: Cap pagination to exactly 150 items (avoid overshooting).Currently you may collect >150 runs from the last page. Slice the current page to the remaining budget and update the counter from the slice length.
- (response, done) => { - // Limit to 150 runs total across pages - count += response.data.length; - if (count >= 150) done(); - return response.data; - } + (response, done) => { + // Limit to 150 runs total across pages (no overshoot) + const remaining = Math.max(0, 150 - count); + if (remaining === 0) { done(); return []; } + const slice = response.data.slice(0, remaining); + count += slice.length; + if (count >= 150) done(); + return slice; + }
218-225: Surface the baseline tag in the Summary.Persist the release tag into GITHUB_ENV when present and show it in the summary.
cp "baseline-artifact/baseline_results.txt" "benches/baseline_results.txt" echo "BASELINE_EXISTS=true" >> "$GITHUB_ENV" echo "BASELINE_SOURCE=artifact" >> "$GITHUB_ENV" echo "BASELINE_ORIGIN=${SOURCE_TYPE:-unknown}" >> "$GITHUB_ENV" + if [[ -n "${RELEASE_TAG:-}" ]]; then + echo "BASELINE_TAG=${RELEASE_TAG}" >> "$GITHUB_ENV" + fi- echo "Baseline origin: ${BASELINE_ORIGIN:-unknown}" + echo "Baseline origin: ${BASELINE_ORIGIN:-unknown}" + echo "Baseline tag: ${BASELINE_TAG:-n/a}"Also applies to: 359-361
76-99: Optional: reduce API calls by early-hit strategy.Precompute a Set of expected baseline names from releases, then stop artifact enumeration as soon as you cache any exact match. This can short-circuit before walking all runs.
📜 Review details
Configuration used: Path: .coderabbit.yml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
.github/workflows/benchmarks.yml(7 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (4)
- GitHub Check: Codacy Static Code Analysis
- GitHub Check: Code Coverage
- GitHub Check: Codacy Security Scan
- GitHub Check: build (windows-latest)
🔇 Additional comments (3)
.github/workflows/benchmarks.yml (3)
110-118: Good: filters expired artifacts and preserves newest cache entry.The
expired !== trueguard plus “set-if-absent” avoids 404s and prevents older runs from overwriting newer ones.
148-160: Release-first match logic looks solid.Tag sanitization mirrors the generator, outputs are complete, and early exit is appropriate here.
165-189: Sane fallback: most-recent non-expired baseline.Clear logging and outputs; good tie-break via run_created_at.
Optimizes the retrieval of baseline artifacts by pre-computing expected release baseline names and short-circuiting the search when a release baseline is found. This significantly reduces the number of API calls and speeds up the process, especially when release baselines are available. Also exports the `BASELINE_TAG` to the environment, making it available for subsequent steps.
There was a problem hiding this comment.
Actionable comments posted: 0
♻️ Duplicate comments (2)
.github/workflows/benchmarks.yml (2)
170-182: Early return from github-script is acceptable here.Setting outputs then
return;is the right way to short-circuit in actions/github-script despite prior comments.
344-354: Great fix: no ‘||’ fallback masking regressions.Capability checks gate the fallback runner, preserving exit code 1 on real regressions as intended.
🧹 Nitpick comments (2)
.github/workflows/benchmarks.yml (2)
246-249: Only set BASELINE_TAG for release-sourced baselines.Avoid writing a synthetic tag like “manual-baseline” into BASELINE_TAG; reserve it for actual release tags.
Apply:
- echo "BASELINE_ORIGIN=${SOURCE_TYPE:-unknown}" >> "$GITHUB_ENV" - if [[ -n "${RELEASE_TAG:-}" ]]; then - echo "BASELINE_TAG=${RELEASE_TAG}" >> "$GITHUB_ENV" - fi + echo "BASELINE_ORIGIN=${SOURCE_TYPE:-unknown}" >> "$GITHUB_ENV" + if [[ "${SOURCE_TYPE:-}" == "release" && -n "${RELEASE_TAG:-}" ]]; then + echo "BASELINE_TAG=${RELEASE_TAG}" >> "$GITHUB_ENV" + fi
326-334: Clarify retention window in guidance.Mention 90-day artifact retention to explain why older baselines might be missing.
Apply:
echo "⚠️ No performance baseline available for comparison." echo " - No baseline artifacts found in recent workflow runs" echo " - Performance regression testing requires a baseline" echo "" echo "💡 To enable performance regression testing:" echo " 1. Create a release tag (e.g., v0.4.3), or" echo " 2. Manually trigger the 'Generate Performance Baseline' workflow" echo " 3. Future PRs and pushes will use that baseline for comparison" - echo " 4. Baselines use full benchmark settings for accurate comparisons" + echo " 4. Baselines use full benchmark settings for accurate comparisons" + echo " 5. Baseline artifacts are retained for ~90 days; older ones may expire"
📜 Review details
Configuration used: Path: .coderabbit.yml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
.github/workflows/benchmarks.yml(7 hunks)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (5)
- GitHub Check: Codacy Static Code Analysis
- GitHub Check: build (windows-latest)
- GitHub Check: build (ubuntu-latest)
- GitHub Check: Codacy Security Scan
- GitHub Check: Code Coverage
🔇 Additional comments (5)
.github/workflows/benchmarks.yml (5)
48-49: Confirm macOS 15 runner availability or use macos-latest.macos-15 may not be available in all orgs/tiers. Consider macos-latest to avoid queued failures.
Apply if desired:
- runs-on: macos-15 + runs-on: macos-latest
94-114: Good pagination cap fix.The aggregate counter with slice prevents over-fetching and keeps API calls bounded. Nicely done.
129-148: Artifact cache logic looks solid.Filtering expired artifacts and only setting when absent (to preserve newest) prevents 404s and stale hits. Early-hit flag plus outer-loop break is clean.
201-212: Sane fallback to most-recent manual baseline.Selecting by run_created_at gives deterministic behavior when no release-tagged baseline exists.
283-307: Skip logic reads correctly and is safe under set -euo pipefail.Covers unknown baseline, identical commit, missing commit, and relevant-change detection without false exits in conditionals.
This pull request updates the performance benchmarking workflow to improve how baseline artifacts are found and handled, and clarifies the messaging and artifact retention policy. The workflow now more reliably locates baseline artifacts, provides clearer instructions when no baseline is found, and aligns artifact retention with repository limits.
Improvements to baseline artifact discovery and handling:
.github/workflows/benchmarks.ymlwas refactored to first look for release-tagged baseline artifacts, and if none are found, to search for any recent baseline artifacts from manual or other workflow runs. The search is now more robust and logs the source type of the found artifact (releaseormanual). [1] [2] [3]Messaging and instructions:
Artifact retention policy:
.github/workflows/generate-baseline.ymlwas reduced from 365 days to 90 days to match the repository maximum.