fix: cross-party vote percentage bug, banned subtitle patterns, script-generated analysis metadata, analysis enrichment pipeline by Copilot · Pull Request #1584 · Hack23/riksdagsmonitor

Copilot · 2026-04-07T10:45:30Z

…banned pattern subtitles, add script-generated metadata, meaningful document classification - Fix cross-party voting anomaly detection to use oppositionAlignment instead of raw vote counts (fixes 8853% display bug) - Improve subtitle generation to avoid banned "Analysis of N documents covering" pattern per ai-driven-analysis-guide.md - Add "Produced By: script" metadata and warning banner to all script-generated analysis files - Replace zero-significance stub in analyzeDocuments() with heuristic-based classification using detectPolicyDomainsWithConfidence - Improve SWOT and threat serializers to produce meaningful "no data" messages when AI analysis is needed - Wire synthesis key findings and risk summary into AnalysisEnrichment for article generation - Add domain extraction from keyInsights in classification serializer Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/e3fec942-345b-4828-aa02-11b0e5849838 Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

…article subtitles in generators.ts Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/e3fec942-345b-4828-aa02-11b0e5849838 Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

…document Swedish-only detection Address code review feedback: extract POLICY_DOMAIN_INSIGHT_PREFIX constant shared between pre-article-analysis.ts and markdown-serializer.ts, document why Swedish phrase detection is correct for Riksdag API data, add MOTION_PROPOSITION_RESPONSE_PREFIX constant. Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/e3fec942-345b-4828-aa02-11b0e5849838 Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

github-actions · 2026-04-07T10:46:17Z

🏷️ Automatic Labeling Summary

This PR has been automatically labeled based on the files changed and PR metadata.

Applied Labels: refactor,size-m

Label Categories

🗳️ Content: news, dashboard, visualization, intelligence
💻 Technology: html-css, javascript, workflow, security
📊 Data: cia-data, riksdag-data, data-pipeline, schema
🌍 I18n: i18n, translation, rtl
🔒 ISMS: isms, iso-27001, nist-csf, cis-controls
🏗️ Infrastructure: ci-cd, deployment, performance, monitoring
🔄 Quality: testing, accessibility, documentation, refactor
🤖 AI: agent, skill, agentic-workflow

For more information, see .github/labeler.yml.

github-actions · 2026-04-07T10:46:34Z

🔍 Lighthouse Performance Audit

Category	Score	Status
Performance	85/100	🟡
Accessibility	95/100	🟢
Best Practices	90/100	🟢
SEO	95/100	🟢

📥 Download full Lighthouse report

Budget Compliance: Performance budgets enforced via budget.json

Copilot

Pull request overview

This PR improves the analysis and article-generation pipeline by fixing a cross-party voting anomaly metric bug, removing/avoiding banned subtitle boilerplate, clearly tagging script-generated analysis output, and exposing additional pre-computed analysis fields for article enrichment.

Changes:

Fix cross-party voting anomaly detection by using oppositionAlignment (percentage) instead of crossPartyVotes (raw count).
Add script-generated provenance metadata/banners and improve “no data” messaging for SWOT/threat serializers.
Expand AnalysisEnrichment and populate it from readLatestAnalysis(); update dynamic/en subtitles to avoid banned patterns.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
scripts/pre-article-analysis/markdown-serializer.ts	Adds “Produced By” + warning banner; improves empty SWOT/threat output; extracts policy domains from `keyInsights` when perspectives are missing.
scripts/pre-article-analysis.ts	Replaces stub analysis with heuristic scoring + policy-domain tagging; introduces shared prefixes/constants for downstream consumers.
scripts/generate-news-enhanced/helpers.ts	Extends `AnalysisEnrichment` and wires in synthesis/risk/date fields from the latest analysis snapshot.
scripts/generate-news-enhanced/generators.ts	Updates English subtitles to avoid templated “Analysis of …” phrasing.
scripts/data-transformers/risk-analysis.ts	Corrects anomaly detection to use `oppositionAlignment` (%), keeping `crossPartyVotes` as raw-count context.

Copilot · 2026-04-07T10:50:56Z

scripts/pre-article-analysis/markdown-serializer.ts

+ * Prefix used by pre-article-analysis.ts to tag policy domain classifications in keyInsights.
+ * Must match {@link POLICY_DOMAIN_INSIGHT_PREFIX} in the parent module.
+ */
+const POLICY_DOMAIN_INSIGHT_PREFIX = 'Policy domain:';
+


POLICY_DOMAIN_INSIGHT_PREFIX is duplicated here and in scripts/pre-article-analysis.ts, which creates a drift risk (the JSDoc even notes it must match). Additionally, the regex used for parsing (/^Policy domain:/...) hard-codes the prefix instead of reusing the constant, so even a small change to the prefix would silently break domain extraction. Consider moving the prefix to a small shared module imported by both producer and serializer, and building the regex from that constant (or parsing based on the constant rather than a literal).

Suggested change

* Prefix used by pre-article-analysis.ts to tag policy domain classifications in keyInsights.

* Must match {@link POLICY_DOMAIN_INSIGHT_PREFIX} in the parent module.

*/

const POLICY_DOMAIN_INSIGHT_PREFIX = 'Policy domain:';

* Prefix used to tag policy domain classifications in keyInsights.

*

* Keep all parsing in this file derived from this constant so a future prefix

* change does not silently drift from regex-based extraction logic.

*/

const POLICY_DOMAIN_INSIGHT_PREFIX = 'Policy domain:';

function escapeRegExp(value: string): string {

return value.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');

}

const POLICY_DOMAIN_INSIGHT_REGEX = new RegExp(

`^${escapeRegExp(POLICY_DOMAIN_INSIGHT_PREFIX)}\\s*(.+?)\\s*$`,

'i',

);

function extractPolicyDomainFromInsight(insight: string): string | null {

const match = POLICY_DOMAIN_INSIGHT_REGEX.exec(insight.trim());

return match?.[1]?.trim() || null;

}

Copilot · 2026-04-07T10:50:56Z

scripts/pre-article-analysis/markdown-serializer.ts

+      if (domainInsight) {
+        const match = domainInsight.match(/^Policy domain:\s*(.+?)\s*\(/);
+        if (match) {
+          domains = match[1].split(',').map(d => d.trim());


When domains are extracted from keyInsights, the resulting array isn’t capped (unlike the perspectives-derived domains which are .slice(0, 3)). Since detectPolicyDomainsWithConfidence() can return multiple matches from keyword heuristics, this can produce very long “Domains” lines in the markdown. Consider applying the same .slice(0, 3) limit (or a dedicated max) after splitting to keep output consistent and readable.

Suggested change

domains = match[1].split(',').map(d => d.trim());

domains = match[1]

.split(',')

.map(d => d.trim())

.slice(0, 3);

pethers · 2026-04-07T11:08:32Z

@copilot apply changes based on the comments in this thread

…REFIX constant, cap domains to 3 Address PR review feedback: - Build POLICY_DOMAIN_INSIGHT_REGEX from POLICY_DOMAIN_INSIGHT_PREFIX constant via escapeRegExp() to prevent silent drift if the prefix changes - Add extractPolicyDomainFromInsight() helper to centralize parsing logic - Cap keyInsights-derived domains with .slice(0, 3) for consistency with perspectives-derived domains Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/218540b7-ad9a-43e0-ac94-01f8de79c0c3 Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-04-07T11:12:02Z

@copilot apply changes based on the comments in this thread

Applied both review comments in 60d0b37:

POLICY_DOMAIN_INSIGHT_REGEX is now built from the POLICY_DOMAIN_INSIGHT_PREFIX constant via escapeRegExp(), with a centralized extractPolicyDomainFromInsight() helper — eliminates the hard-coded regex drift risk.
keyInsights-derived domains are now capped with .slice(0, 3) for consistency with the perspectives-derived path.

github-actions · 2026-04-07T11:12:56Z

🔍 Lighthouse Performance Audit

Category	Score	Status
Performance	85/100	🟡
Accessibility	95/100	🟢
Best Practices	90/100	🟢
SEO	95/100	🟢

📥 Download full Lighthouse report

Budget Compliance: Performance budgets enforced via budget.json

github-actions · 2026-04-07T11:18:46Z

🔍 Lighthouse Performance Audit

Category	Score	Status
Performance	85/100	🟡
Accessibility	95/100	🟢
Best Practices	90/100	🟢
SEO	95/100	🟢

📥 Download full Lighthouse report

Budget Compliance: Performance budgets enforced via budget.json

Copilot

Pull request overview

Copilot reviewed 5 out of 5 changed files in this pull request and generated 2 comments.

Copilot · 2026-04-07T11:21:21Z

scripts/pre-article-analysis/markdown-serializer.ts

+ * Keep all parsing in this file derived from this constant so a future prefix
+ * change does not silently drift from regex-based extraction logic.
+ */
+const POLICY_DOMAIN_INSIGHT_PREFIX = 'Policy domain:';


POLICY_DOMAIN_INSIGHT_PREFIX is defined here but also separately exported in scripts/pre-article-analysis.ts. Keeping two independent copies undermines the stated goal of avoiding silent drift between the producer and the regex-based parser. Consider defining this prefix in a single shared place (e.g., export it from this serializer module and import it in pre-article-analysis.ts, or move it to a small shared constants module) so both sides always stay in sync.

Suggested change

const POLICY_DOMAIN_INSIGHT_PREFIX = 'Policy domain:';

export const POLICY_DOMAIN_INSIGHT_PREFIX = 'Policy domain:';

Copilot · 2026-04-07T11:21:22Z

scripts/pre-article-analysis/markdown-serializer.ts

      .filter((v, i, arr) => arr.indexOf(v) === i)
      .slice(0, 3);
+    if (domains.length === 0 && result.keyInsights.length > 0) {
+      const domainInsight = result.keyInsights.find(i => i.startsWith(POLICY_DOMAIN_INSIGHT_PREFIX));


Domain fallback extraction looks for a matching key insight with startsWith(POLICY_DOMAIN_INSIGHT_PREFIX), which is case-sensitive and doesn't trim leading whitespace. This is inconsistent with the case-insensitive POLICY_DOMAIN_INSIGHT_REGEX used for parsing and can cause domains to be missed if the insight string casing/spacing changes. Prefer matching via the regex (e.g., test POLICY_DOMAIN_INSIGHT_REGEX against insight.trim()) and then parsing, rather than relying on startsWith.

Suggested change

const domainInsight = result.keyInsights.find(i => i.startsWith(POLICY_DOMAIN_INSIGHT_PREFIX));

const domainInsight = result.keyInsights

.map(insight => insight.trim())

.find(insight => POLICY_DOMAIN_INSIGHT_REGEX.test(insight));

pethers · 2026-04-07T11:23:07Z

@copilot apply changes based on the comments in this thread and fix failures in TypeScript & JavaScript Testing / Unit Tests (Vitest) (pull_request)
TypeScript & JavaScript Testing / Unit Tests (Vitest) (pull_request)Failing after 1m

…fix CI test failures Address second round of review feedback: - Export POLICY_DOMAIN_INSIGHT_PREFIX from markdown-serializer.ts and import in pre-article-analysis.ts (eliminates duplication drift risk) - Use POLICY_DOMAIN_INSIGHT_REGEX.test() instead of case-sensitive startsWith() for domain insight matching (consistent with regex-based extraction) Fix CI test failures in analysis-quality-validation: - Add per-file isStrictV2Format() checks in Mermaid, evidence density, and scoring tests — script-generated (v1) files in mixed-format directories are no longer subject to strict-v2 quality requirements - Broaden LXI_SCORING_PATTERN to match Likelihood/Impact table headers and inline L:N × I:N patterns used in Mermaid diagrams - Add COMMITTEE_CODE_PATTERN to countDokIds() so committee report abbreviations (FöU12, JuU15) count as valid document references alongside full dok_ids All 4060 tests pass across 99 test files. Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/96fe0c5f-1545-45ed-9a9f-082ba8fff464 Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

github-actions · 2026-04-07T11:35:58Z

🔍 Lighthouse Performance Audit

Category	Score	Status
Performance	85/100	🟡
Accessibility	95/100	🟢
Best Practices	90/100	🟢
SEO	95/100	🟢

📥 Download full Lighthouse report

Budget Compliance: Performance budgets enforced via budget.json

Copilot · 2026-04-07T11:37:57Z

@copilot apply changes based on the comments in this thread and fix failures in [TypeScript & JavaSc...

Applied both review comments and fixed CI failures in 1bc415c:

Review feedback:

POLICY_DOMAIN_INSIGHT_PREFIX is now exported from markdown-serializer.ts and imported in pre-article-analysis.ts — single source of truth, no duplication.
Domain insight matching uses POLICY_DOMAIN_INSIGHT_REGEX.test() instead of case-sensitive startsWith().

CI fixes:

Added per-file isStrictV2Format() checks in Mermaid, evidence density, and scoring tests — script-generated (v1) files in mixed-format directories are no longer subject to strict-v2 requirements.
Broadened LXI_SCORING_PATTERN to match Likelihood (1-5) | Impact (1-5) table headers and inline L:N × I:N Mermaid patterns.
Added COMMITTEE_CODE_PATTERN so committee abbreviations (FöU12, JuU15) count as valid document references in synthesis files.

All 4060 tests pass, TypeScript clean, CodeQL 0 alerts.

Copilot

Pull request overview

Copilot reviewed 6 out of 6 changed files in this pull request and generated 1 comment.

Copilot · 2026-04-07T11:55:55Z

scripts/pre-article-analysis.ts

+      const organ = d.organ || d.committee || '';
+
+      // Domain classification using committee→domain mapping
+      const domainResult = detectPolicyDomainsWithConfidence(d, 'en');


analyzeDocuments() takes a _lang parameter but hardcodes 'en' when calling detectPolicyDomainsWithConfidence(). This makes the function signature misleading and prevents policy-domain labels from being localised if the script is ever run for non-English output. Use the _lang argument (or remove it entirely) so the language selection is consistent end-to-end.

Suggested change

const domainResult = detectPolicyDomainsWithConfidence(d, 'en');

const domainResult = detectPolicyDomainsWithConfidence(d, _lang);

pethers · 2026-04-07T11:59:04Z

@copilot apply changes based on the comments in this thread

github-actions · 2026-04-07T11:59:55Z

🔍 Lighthouse Performance Audit

Category	Score	Status
Performance	85/100	🟡
Accessibility	95/100	🟢
Best Practices	90/100	🟢
SEO	95/100	🟢

📥 Download full Lighthouse report

Budget Compliance: Performance budgets enforced via budget.json

Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/a8775231-40ce-4641-b44b-4cd1e9a036f8 Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-04-07T12:02:11Z

@copilot apply changes based on the comments in this thread

Fixed in 6564970: detectPolicyDomainsWithConfidence(d, 'en') now uses the _lang parameter — detectPolicyDomainsWithConfidence(d, _lang). TypeScript compiles clean, all tests pass.

github-actions · 2026-04-07T12:03:14Z

🔍 Lighthouse Performance Audit

Category	Score	Status
Performance	85/100	🟡
Accessibility	95/100	🟢
Best Practices	90/100	🟢
SEO	95/100	🟢

📥 Download full Lighthouse report

Budget Compliance: Performance budgets enforced via budget.json

Copilot

Pull request overview

Copilot reviewed 6 out of 6 changed files in this pull request and generated 1 comment.

Copilot · 2026-04-07T12:21:59Z

scripts/generate-news-enhanced/helpers.ts

+  /** Key findings from pre-computed synthesis analysis (for article enrichment) */
+  synthesisKeyFindings?: string[];
+  /** Aggregate risk summary from pre-computed risk assessment */
+  riskSummary?: string;
+  /** Date of the analysis data (may differ from article date due to lookback) */
+  analysisDate?: string;


synthesisKeyFindings is populated from analysis.synthesis.keyThemes, but the name/JSDoc imply these are “key findings”. This is misleading for consumers and log output. Consider renaming the field to something like synthesisKeyThemes (and update the log label), or alternatively populate it with actual “findings” if that exists in the parsed analysis model.

pethers · 2026-04-07T12:26:48Z

@copilot apply changes based on the comments in this thread

Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/69e90da8-c2c2-4782-9b18-9368ad97e842 Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-04-07T12:34:22Z

@copilot apply changes based on the comments in this thread

Renamed synthesisKeyFindings → synthesisKeyThemes (field, JSDoc, and log label) in a43782c. The field now accurately reflects that it's populated from analysis.synthesis.keyThemes.

github-actions · 2026-04-07T12:35:16Z

🔍 Lighthouse Performance Audit

Category	Score	Status
Performance	85/100	🟡
Accessibility	95/100	🟢
Best Practices	90/100	🟢
SEO	95/100	🟢

📥 Download full Lighthouse report

Budget Compliance: Performance budgets enforced via budget.json

Copilot AI and others added 3 commits April 7, 2026 10:26

fix: remove remaining "Analysis of N documents" banned patterns from …

29813c4

…article subtitles in generators.ts Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/e3fec942-345b-4828-aa02-11b0e5849838 Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot AI assigned Copilot and pethers Apr 7, 2026

Copilot created this pull request from a session on behalf of pethers April 7, 2026 10:45 View session

pethers marked this pull request as ready for review April 7, 2026 10:45

Copilot AI review requested due to automatic review settings April 7, 2026 10:45

github-actions bot added refactor Code refactoring size-m Medium change (50-250 lines) labels Apr 7, 2026

Copilot started reviewing on behalf of pethers April 7, 2026 10:47 View session

Copilot AI reviewed Apr 7, 2026

View reviewed changes

Copilot started work on behalf of pethers April 7, 2026 11:08 View session

Copilot AI requested a review from pethers April 7, 2026 11:13

Copilot finished work on behalf of pethers April 7, 2026 11:13

Merge branch 'main' into copilot/improve-quality-of-ai-analysis

65a4007

pethers requested a review from Copilot April 7, 2026 11:17

Copilot started reviewing on behalf of pethers April 7, 2026 11:18 View session

Copilot AI reviewed Apr 7, 2026

View reviewed changes

Copilot started work on behalf of pethers April 7, 2026 11:23 View session

github-actions bot added the testing Test coverage label Apr 7, 2026

github-actions bot added the size-l Large change (250-1000 lines) label Apr 7, 2026

Copilot finished work on behalf of pethers April 7, 2026 11:40

pethers requested a review from Copilot April 7, 2026 11:50

Copilot started reviewing on behalf of pethers April 7, 2026 11:51 View session

Copilot AI reviewed Apr 7, 2026

View reviewed changes

Merge branch 'main' into copilot/improve-quality-of-ai-analysis

5ea2a8d

Copilot started work on behalf of pethers April 7, 2026 11:59 View session

fix: use _lang parameter instead of hardcoded 'en' in analyzeDocuments()

6564970

Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/a8775231-40ce-4641-b44b-4cd1e9a036f8 Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot finished work on behalf of pethers April 7, 2026 12:03

pethers requested a review from Copilot April 7, 2026 12:16

Copilot started reviewing on behalf of pethers April 7, 2026 12:18 View session

Copilot AI reviewed Apr 7, 2026

View reviewed changes

Copilot started work on behalf of pethers April 7, 2026 12:29 View session

refactor: rename synthesisKeyFindings to synthesisKeyThemes for clarity

a43782c

Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/69e90da8-c2c2-4782-9b18-9368ad97e842 Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot finished work on behalf of pethers April 7, 2026 12:36

pethers merged commit b1b18e4 into main Apr 7, 2026
17 checks passed

pethers deleted the copilot/improve-quality-of-ai-analysis branch April 7, 2026 12:49

- * Prefix used by pre-article-analysis.ts to tag policy domain classifications in keyInsights.
- * Must match {@link POLICY_DOMAIN_INSIGHT_PREFIX} in the parent module.
- */
-const POLICY_DOMAIN_INSIGHT_PREFIX = 'Policy domain:';
+ * Prefix used to tag policy domain classifications in keyInsights.
+ *
+ * Keep all parsing in this file derived from this constant so a future prefix
+ * change does not silently drift from regex-based extraction logic.
+ */
+const POLICY_DOMAIN_INSIGHT_PREFIX = 'Policy domain:';
+function escapeRegExp(value: string): string {
+  return value.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
+}
+const POLICY_DOMAIN_INSIGHT_REGEX = new RegExp(
+  `^${escapeRegExp(POLICY_DOMAIN_INSIGHT_PREFIX)}\\s*(.+?)\\s*$`,
+  'i',
+);
+function extractPolicyDomainFromInsight(insight: string): string | null {
+  const match = POLICY_DOMAIN_INSIGHT_REGEX.exec(insight.trim());
+  return match?.[1]?.trim() || null;
+}

	const POLICY_DOMAIN_INSIGHT_PREFIX = 'Policy domain:';
	export const POLICY_DOMAIN_INSIGHT_PREFIX = 'Policy domain:';

	const domainResult = detectPolicyDomainsWithConfidence(d, 'en');
	const domainResult = detectPolicyDomainsWithConfidence(d, _lang);

Conversation

Copilot AI commented Apr 7, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions bot commented Apr 7, 2026

🏷️ Automatic Labeling Summary

Label Categories

Uh oh!

github-actions bot commented Apr 7, 2026

🔍 Lighthouse Performance Audit

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Apr 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 7, 2026

Choose a reason for hiding this comment

Uh oh!

pethers commented Apr 7, 2026

Uh oh!

Copilot AI commented Apr 7, 2026

Uh oh!

github-actions bot commented Apr 7, 2026

🔍 Lighthouse Performance Audit

Uh oh!

github-actions bot commented Apr 7, 2026

🔍 Lighthouse Performance Audit

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Apr 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 7, 2026

Choose a reason for hiding this comment

Uh oh!

pethers commented Apr 7, 2026

Uh oh!

github-actions bot commented Apr 7, 2026

🔍 Lighthouse Performance Audit

Uh oh!

Copilot AI commented Apr 7, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Apr 7, 2026

Choose a reason for hiding this comment

Uh oh!

pethers commented Apr 7, 2026

Uh oh!

github-actions bot commented Apr 7, 2026

🔍 Lighthouse Performance Audit

Uh oh!

Copilot AI commented Apr 7, 2026

Uh oh!

github-actions bot commented Apr 7, 2026

🔍 Lighthouse Performance Audit

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Apr 7, 2026

Choose a reason for hiding this comment

Uh oh!

pethers commented Apr 7, 2026

Uh oh!

Copilot AI commented Apr 7, 2026

Uh oh!

github-actions bot commented Apr 7, 2026

🔍 Lighthouse Performance Audit

Uh oh!

Copilot AI commented Apr 7, 2026 •

edited

Loading