Add deep-inspection analysis: multi-stakeholder SWOT, economic dashboards, newsworthiness scoring by Copilot · Pull Request #914 · Hack23/riksdagsmonitor

Copilot · 2026-03-07T10:41:08Z

🔒 GitHub Advanced Security automatically protects Copilot coding agent pull requests. You can protect all pull requests by enabling Advanced Security for your repositories. Learn more about Advanced Security.

… deep-inspection article type Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

… newsworthiness scoring Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

+  buildEconomicTables,
+} from '../scripts/data-transformers/content-generators/economic-dashboard-section.js';
+import type { EconomicDataPoint } from '../scripts/data-transformers/content-generators/economic-dashboard-section.js';
+import { INDICATOR_IDS, COUNTRY_CODES } from '../scripts/world-bank-client.js';


…ve readability Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

github-actions · 2026-03-07T11:13:27Z

🔍 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 extends the news/article generation codebase with a new “deep-inspection” analysis capability by adding strategic newsworthiness scoring, multi-stakeholder SWOT section generation, and policy-domain-driven World Bank economic dashboard sections, plus workflow/config hooks to request targeted deep inspections.

Changes:

Added new content generators: newsworthiness, stakeholder-swot-section, and economic-dashboard-section (with barrel exports).
Extended CLI/config and workflow dispatch inputs to include a new deep-inspection article type and deep-inspection targeting inputs.
Added unit tests covering structure, i18n surface checks, and key behaviors for the new generators.

Reviewed changes

Copilot reviewed 12 out of 12 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
tests/stakeholder-swot-section.test.ts	Adds tests for multi-stakeholder SWOT section structure, escaping, and basic i18n coverage.
tests/newsworthiness.test.ts	Adds tests for multi-dimension scoring and deep-inspection threshold behavior (with a determinism gap).
tests/economic-dashboard-section.test.ts	Adds tests for indicator matching and dashboard/placeholder rendering behavior.
scripts/types/article.ts	Extends `ArticleType` union with `'deep-inspection'`.
scripts/generate-news-indexes/helpers.ts	Classifies `deep-inspection` filenames as analysis content for indexes.
scripts/generate-news-enhanced/config.ts	Adds deep-inspection CLI args and allows `'deep-inspection'` in `VALID_ARTICLE_TYPES` (but not wired end-to-end).
scripts/data-transformers/content-generators/stakeholder-swot-section.ts	Implements multi-stakeholder SWOT section generator with escaping and localized headings.
scripts/data-transformers/content-generators/newsworthiness.ts	Implements 6-dimension newsworthiness scoring and deep-inspection suggestion logic.
scripts/data-transformers/content-generators/index.ts	Re-exports the newly added content generators and types.
scripts/data-transformers/content-generators/economic-dashboard-section.ts	Implements economic indicator selection and dashboard/table generation (table headers are currently English-only).
.github/workflows/news-article-generator.md	Documents new workflow inputs for deep-inspection targeting (missing `--document-urls` in the “pass flags” rule).
.github/workflows/news-article-generator.lock.yml	Adds workflow_dispatch input descriptions for deep-inspection targeting fields.

Comments suppressed due to low confidence (1)

scripts/generate-news-enhanced/config.ts:88

VALID_ARTICLE_TYPES now includes deep-inspection, but the current generateNews() orchestrator doesn’t appear to handle this type (no case for it), so selecting it will be treated as an unknown type and nothing will be generated. Either implement a deep-inspection generator path (and wire it into the switch) or avoid advertising/allowing this type until it’s supported end-to-end.

export const VALID_ARTICLE_TYPES: readonly string[] = ['week-ahead', 'month-ahead', 'weekly-review', 'monthly-review', 'committee-reports', 'propositions', 'motions', 'breaking', 'deep-inspection'];

export const articleTypes: string[] = typesArg
  ? (typesArg.split('=')[1] ?? '').split(',').map(t => t.trim())
  : ['week-ahead'];

Copilot · 2026-03-07T11:21:43Z

+/** Extract the value after '=' from a CLI argument, or empty string if absent. */
+function parseArgValue(arg: string | undefined): string {
+  return arg ? (arg.split('=')[1] ?? '').trim() : '';
+}


parseArgValue() uses arg.split('=')[1], which truncates values containing additional '=' (common in URLs with query strings). This can break --document-urls= and any future args that may include '='. Consider extracting everything after the first '=' (e.g., arg.slice(arg.indexOf('=') + 1)) instead of splitting and taking index 1.

Copilot · 2026-03-07T11:21:44Z

+    expect(score.overall).toBeGreaterThan(0);
+    // If high enough, should warrant deep inspection
+    if (score.overall >= 65) {
+      expect(score.warrantsDeepInspection).toBe(true);
+      expect(score.suggestedType).toBe('deep-inspection');
+    }
+  });
+


This test is conditional on score.overall >= 65, so it can pass even if the scoring logic never reaches the deep-inspection threshold. Make the assertion deterministic by crafting inputs that are guaranteed to exceed the threshold (and assert warrantsDeepInspection === true / suggestedType === 'deep-inspection'), and add an explicit boundary test around 64/65 to verify the threshold behavior.

Suggested change

expect(score.overall).toBeGreaterThan(0);

// If high enough, should warrant deep inspection

if (score.overall >= 65) {

expect(score.warrantsDeepInspection).toBe(true);

expect(score.suggestedType).toBe('deep-inspection');

}

});

expect(score.overall).toBeGreaterThanOrEqual(65);

expect(score.warrantsDeepInspection).toBe(true);

expect(score.suggestedType).toBe('deep-inspection');

});

it('applies deep inspection threshold around 65 points', () => {

const lowScore = scoreNewsworthiness([makeLowDoc()]);

expect(lowScore.overall).toBeLessThan(65);

expect(lowScore.warrantsDeepInspection).toBe(false);

const highScore = scoreNewsworthiness([makeStrategicDoc()], makeUnstableCIA());

expect(highScore.overall).toBeGreaterThanOrEqual(65);

expect(highScore.warrantsDeepInspection).toBe(true);

expect(highScore.suggestedType).toBe('deep-inspection');

});

Copilot · 2026-03-07T11:21:44Z

+    if (latestPoints.length > 0) {
+      tables.push({
+        caption: `${indicator.name} (${latestYear}) — ${indicator.unit}`,
+        headers: ['Country', indicator.name, 'Unit'],
+        rows: latestPoints.map(p => [
+          NORDIC_COMPARISON.countryNames[p.countryCode] ?? p.countryName,
+          p.value.toFixed(2),
+          indicator.unit,
+        ]),


buildEconomicTables() hard-codes English column headers ('Country', 'Unit'). When generating non-English articles, the accessibility table fallback will remain English, which undermines the module’s stated 14-language support. Consider localizing these headers (e.g., via L(lang, ...) with new label keys) or otherwise deriving translated header labels based on lang.

Copilot · 2026-03-07T11:21:44Z

 3. If **force_generation** is `true`, generate even if recent articles exist.
 4. If **languages** is empty/blank, default to `all` (14 languages).
+5. If **article_types** includes `deep-inspection`, use **document_ids**, **document_urls**, and **focus_topic** for targeted deep analysis.
+6. For `deep-inspection` type: pass `--document-ids` and `--focus-topic` flags to the generation script.


The deep-inspection workflow instructions mention using document_ids, document_urls, and focus_topic (Rule 5), but Rule 6 only mentions passing --document-ids and --focus-topic to the script. This leaves out --document-urls and may cause users to think URLs are unsupported even though config parsing was added. Update the instructions to include --document-urls (and keep flag formatting consistent with the script’s --flag=value parsing).

Suggested change

6. For `deep-inspection` type: pass `--document-ids` and `--focus-topic` flags to the generation script.

6. For `deep-inspection` type: pass `--document-ids=<value>`, `--document-urls=<value>`, and `--focus-topic=<value>` flags to the generation script.

pethers · 2026-03-07T11:52:50Z

@copilot apply changes based on the comments in this thread

github-actions · 2026-03-07T11:53:32Z

🔍 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

…stic threshold test, complete workflow docs Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-03-07T12:02:01Z

@copilot apply changes based on the comments in this thread

All 4 review comments addressed in 1f7ef7f:

parseArgValue() URL truncation — Fixed to use arg.slice(arg.indexOf('=') + 1) instead of arg.split('=')[1], preserving = in URLs with query strings.
Conditional threshold test — Made deterministic: low-scoring docs assert < 65 + warrantsDeepInspection === false; high-scoring multi-party+instability docs assert ≥ 65 + suggestedType === 'deep-inspection'.
Hard-coded English table headers — Added country and unit keys to EconomicSectionHeadings with translations for all 14 languages. buildEconomicTables() now accepts a lang parameter and uses getEconomicHeading() for localized headers.
Missing --document-urls — Updated Rule 6 to: pass --document-ids=<value>, --document-urls=<value>, and --focus-topic=<value> flags.

All 2739 tests passing, build succeeds.

pethers · 2026-03-07T19:35:18Z

@copilot apply changes based on the comments in this thread

- Replace hard-coded English "Policy Analysis" with per-language defaultTopicLabels map (14 languages) so no-focusTopic titles are fully localized (e.g. "Policyanalys" for sv, "Politikanalyse" for de) - Narrow document_urls workflow input description to "Riksdag documents" to match actual extractDocIdFromUrl() implementation scope - Updated lock.yml description to match Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-03-07T19:42:50Z

@copilot apply changes based on the comments in this thread

Addressed in fb687ea: extracted sanitizeSlugSegment() helper, fallback chain uses allDocIds[0] (includes URL-derived IDs) instead of documentIds[0], and empty ASCII slug gets 'analysis' fallback. All 2761 tests passing.

@copilot apply changes based on the comments in this thread

Both review comments addressed in 471e4b6:

document_urls description too broad — Narrowed to 'Comma-separated URLs to specific Riksdag documents for deep analysis' in both .md and .lock.yml.
Hard-coded English "Policy Analysis" fallback — Added defaultTopicLabels map with localized labels for all 14 languages. Each title entry now uses sanitizedTopic || defaultTopicLabels.xx so unfocused deep-inspection articles get fully localized headings (e.g. Djupanalys: Policyanalys for sv, Tiefenanalyse: Politikanalyse for de).

All 2761 tests passing, CodeQL: 0 alerts.

github-actions · 2026-03-07T19:51:37Z

🔍 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 17 out of 17 changed files in this pull request and generated 2 comments.

Copilot · 2026-03-07T19:55:31Z

+export const articleTypes: string[] = rawArticleTypes.length > 0
+  ? rawArticleTypes.filter(t => VALID_ARTICLE_TYPES.includes(t))


articleTypes can become an empty array when --types is provided but all values are invalid (because invalid types are filtered out). In that case, generateNews() will do nothing without failing, which is easy to miss in workflows. Consider either (a) falling back to the default schedule/type when the filtered result is empty, or (b) exiting with a non-zero code / explicit error so the caller can detect misconfiguration.

Suggested change

export const articleTypes: string[] = rawArticleTypes.length > 0

? rawArticleTypes.filter(t => VALID_ARTICLE_TYPES.includes(t))

const filteredArticleTypes: string[] = rawArticleTypes.filter(t => VALID_ARTICLE_TYPES.includes(t));

if (rawArticleTypes.length > 0 && filteredArticleTypes.length === 0) {

throw new Error(

`No valid article types specified via --types. Valid types are: ${VALID_ARTICLE_TYPES.join(', ')}`

);

}

export const articleTypes: string[] = filteredArticleTypes.length > 0

? filteredArticleTypes

Copilot · 2026-03-07T19:55:31Z

+      const sanitizedTopic: string | null = focusTopic ? sanitizePlainText(focusTopic) : null;
+      const defaultTopicLabels: Record<Language, string> = {
+        en: 'Policy Analysis',
+        sv: 'Policyanalys',
+        da: 'Politisk analyse',
+        no: 'Politisk analyse',
+        fi: 'Politiikka-analyysi',


defaultTopicLabels is a constant map but it is re-created on every iteration of the for (const lang of languages) loop. Moving it (and potentially the titles template) outside the loop would reduce repeated allocations and keep the per-language loop focused on generation logic.

pethers · 2026-03-07T20:11:31Z

@copilot apply changes based on the comments in this thread

…language loop Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-03-07T20:23:09Z

@copilot apply changes based on the comments in this thread

Both review comments addressed in 978c86c:

Empty articleTypes after filtering — Added filteredArticleTypes intermediate + throws Error with valid-types listing when --types was provided but all entries were invalid, so misconfiguration is immediately visible.
defaultTopicLabels re-created per loop iteration — Moved sanitizedTopic, defaultTopicLabels, and titles outside the for (const lang of languages) loop. Only computed once per deep-inspection run.

All 2761 tests passing, CodeQL: 0 alerts.

github-actions · 2026-03-07T21:19:43Z

🔍 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 17 out of 17 changed files in this pull request and generated 3 comments.

Copilot · 2026-03-07T21:25:15Z

+      const contentData = { reports: enrichedDocs as Parameters<typeof generateArticleContent>[0]['reports'] };
+      const content: string = generateArticleContent(contentData, 'deep-inspection', lang);
+      const watchPoints = extractWatchPoints(contentData, lang);
+      const metadata = generateMetadata(contentData, 'deep-inspection', lang);
+      const readTime: string = calculateReadTime(content);


In generateDeepInspection(), contentData is built with reports: enrichedDocs, but generateArticleContent('deep-inspection', ...) falls through to generateGenericContent(), which reads from data.documents (not data.reports). This will produce the generic “no documents” placeholder instead of rendering the enriched documents. Populate contentData.documents (and adjust watchPoints/metadata inputs accordingly) so deep-inspection articles actually include the target documents.

Copilot · 2026-03-07T21:25:16Z

+/**
+ * Strip HTML tags from a user-supplied string to prevent XSS.
+ * Uses defense-in-depth: first strips tag patterns in a loop to handle nested
+ * reconstruction (e.g. `<scr<script>ipt>`), then HTML-escapes any remaining
+ * special characters via escapeHtml() as a safety net.
+ */
+export function sanitizePlainText(text: string): string {
+  let cleaned = text;
+  let prev: string;
+  do {
+    prev = cleaned;
+    cleaned = cleaned.replace(/<[^>]*>/g, '');
+  } while (cleaned !== prev);
+  return escapeHtml(cleaned);
+}


sanitizePlainText() returns an HTML-escaped string via escapeHtml(). When that escaped string is later passed as title/subtitle into generateArticleHTML(), the template escapes title/subtitle again in meta tags and JSON-LD, resulting in double-escaped entities (e.g. & → &amp;) in structured data/SEO fields. Consider making sanitizePlainText() return plain text (tag-stripped) and fix escaping at render sites (ideally escape title/subtitle in the <title>, <h1>, and lede output), so escaping happens exactly once.

Copilot · 2026-03-07T21:25:16Z

+export { generateStakeholderSwotSection } from './stakeholder-swot-section.js';
+export type { StakeholderSwotSectionOptions, StakeholderSwot } from './stakeholder-swot-section.js';
+export { generateEconomicDashboardSection, findIndicatorsForDomains, buildEconomicCharts, buildEconomicTables } from './economic-dashboard-section.js';
+export type { EconomicDashboardOptions, EconomicDataPoint } from './economic-dashboard-section.js';
+export { scoreNewsworthiness } from './newsworthiness.js';
+export type { NewsworthinessScore, NewsworthinessDimension } from './newsworthiness.js';


This file exports the new generators/types, but the stable barrel (scripts/data-transformers/content-generators.ts, which is what scripts/data-transformers/index.ts re-exports) still only re-exports generateSwotSection/generateDashboardSection. As a result, consumers importing from ../data-transformers.js or ./content-generators.js won’t be able to access generateStakeholderSwotSection, generateEconomicDashboardSection, or scoreNewsworthiness. Add the corresponding exports/types to the stable barrel so the public API matches the documentation here.

pethers · 2026-03-07T21:37:39Z

@copilot apply changes based on the comments in this thread

… double-escaping, and barrel exports Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-03-07T21:48:12Z

@copilot apply changes based on the comments in this thread

All 3 review comments addressed in e2f89ad:

contentData uses reports but generateGenericContent() reads documents — Changed to documents: enrichedDocs so deep-inspection articles render the enriched docs instead of falling through to the "no documents" placeholder.
sanitizePlainText() double-escaping — Removed escapeHtml() from sanitizePlainText() so it returns tag-stripped plain text. Added escapeHtml() to template.ts render sites (<title>, <h1>, lede <p>) so escaping happens exactly once. Prevents &amp; in JSON-LD/meta tags.
Missing barrel exports — Added generateStakeholderSwotSection, generateEconomicDashboardSection, findIndicatorsForDomains, buildEconomicCharts, buildEconomicTables, scoreNewsworthiness and their types to both content-generators.ts and data-transformers/index.ts.

All 2761 tests passing, CodeQL: 0 alerts.

github-actions · 2026-03-07T22:18:17Z

🔍 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 20 out of 20 changed files in this pull request and generated 1 comment.

Copilot · 2026-03-07T22:26:42Z

  <meta name="description" content="${escapeHtml(subtitle).substring(0, 160)}">
  <meta name="keywords" content="${keywords.join(', ')}">
  <meta name="author" content="James Pether Sörling, CISSP, CISM">


keywords are interpolated into the <meta name="keywords"> attribute without escaping. If any keyword contains ", <, or & (e.g., coming from document titles or user-provided topics in future), this can break the HTML or enable injection. Escape each keyword (or the joined string) before inserting into the attribute, consistent with how title, subtitle, and tags are handled.

Initial plan

56c30c5

Copilot AI assigned Copilot and pethers Mar 7, 2026

Copilot started work on behalf of pethers March 7, 2026 10:41 View session

Copilot AI and others added 2 commits March 7, 2026 10:53

Add stakeholder SWOT, economic dashboard, newsworthiness scoring, and…

f09a8e5

… deep-inspection article type Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Add comprehensive tests for stakeholder SWOT, economic dashboard, and…

5ba775a

… newsworthiness scoring Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

github-code-quality Bot found potential problems Mar 7, 2026

View reviewed changes

Address code review feedback: extract helpers, fix duplication, impro…

a62319c

…ve readability Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot AI changed the title ~~[WIP] Add deep inspection analysis for article types~~ Add deep-inspection analysis: multi-stakeholder SWOT, economic dashboards, newsworthiness scoring Mar 7, 2026

Copilot finished work on behalf of pethers March 7, 2026 11:03

pethers requested a review from Copilot March 7, 2026 11:12

Copilot started reviewing on behalf of pethers March 7, 2026 11:13 View session

Copilot AI reviewed Mar 7, 2026

View reviewed changes

Merge branch 'main' into copilot/add-deep-inspection-analysis

721d3f1

Copilot started work on behalf of pethers March 7, 2026 11:52 View session

Address PR review: fix URL parsing, localize table headers, determini…

1f7ef7f

…stic threshold test, complete workflow docs Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

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

Merge branch 'main' into copilot/add-deep-inspection-analysis

32c9060

Copilot started work on behalf of pethers March 7, 2026 19:35 View session

Copilot finished work on behalf of pethers March 7, 2026 19:43

pethers requested a review from Copilot March 7, 2026 19:50

Copilot started reviewing on behalf of pethers March 7, 2026 19:51 View session

Copilot AI reviewed Mar 7, 2026

View reviewed changes

Copilot started work on behalf of pethers March 7, 2026 20:11 View session

Throw on all-invalid --types; move defaultTopicLabels/titles outside …

978c86c

…language loop Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot finished work on behalf of pethers March 7, 2026 20:23

pethers requested a review from Copilot March 7, 2026 21:18

Copilot started reviewing on behalf of pethers March 7, 2026 21:20 View session

Copilot AI reviewed Mar 7, 2026

View reviewed changes

Copilot started work on behalf of pethers March 7, 2026 21:37 View session

Address review round 12: fix contentData.documents, sanitizePlainText…

e2f89ad

… double-escaping, and barrel exports Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot finished work on behalf of pethers March 7, 2026 21:48

pethers requested a review from Copilot March 7, 2026 22:17

Copilot started reviewing on behalf of pethers March 7, 2026 22:18 View session

Copilot AI reviewed Mar 7, 2026

View reviewed changes

pethers marked this pull request as ready for review March 7, 2026 23:21

pethers merged commit 1267257 into main Mar 7, 2026
20 checks passed

pethers deleted the copilot/add-deep-inspection-analysis branch March 21, 2026 19:50

-    expect(score.overall).toBeGreaterThan(0);
-    // If high enough, should warrant deep inspection
-    if (score.overall >= 65) {
-      expect(score.warrantsDeepInspection).toBe(true);
-      expect(score.suggestedType).toBe('deep-inspection');
-    }
-  });
+    expect(score.overall).toBeGreaterThanOrEqual(65);
+    expect(score.warrantsDeepInspection).toBe(true);
+    expect(score.suggestedType).toBe('deep-inspection');
+  });
+  it('applies deep inspection threshold around 65 points', () => {
+    const lowScore = scoreNewsworthiness([makeLowDoc()]);
+    expect(lowScore.overall).toBeLessThan(65);
+    expect(lowScore.warrantsDeepInspection).toBe(false);
+    const highScore = scoreNewsworthiness([makeStrategicDoc()], makeUnstableCIA());
+    expect(highScore.overall).toBeGreaterThanOrEqual(65);
+    expect(highScore.warrantsDeepInspection).toBe(true);
+    expect(highScore.suggestedType).toBe('deep-inspection');
+  });

	6. For `deep-inspection` type: pass `--document-ids` and `--focus-topic` flags to the generation script.
	6. For `deep-inspection` type: pass `--document-ids=<value>`, `--document-urls=<value>`, and `--focus-topic=<value>` flags to the generation script.

		export const articleTypes: string[] = rawArticleTypes.length > 0
		? rawArticleTypes.filter(t => VALID_ARTICLE_TYPES.includes(t))

-export const articleTypes: string[] = rawArticleTypes.length > 0
-  ? rawArticleTypes.filter(t => VALID_ARTICLE_TYPES.includes(t))
+const filteredArticleTypes: string[] = rawArticleTypes.filter(t => VALID_ARTICLE_TYPES.includes(t));
+if (rawArticleTypes.length > 0 && filteredArticleTypes.length === 0) {
+  throw new Error(
+    `No valid article types specified via --types. Valid types are: ${VALID_ARTICLE_TYPES.join(', ')}`
+  );
+}
+export const articleTypes: string[] = filteredArticleTypes.length > 0
+  ? filteredArticleTypes

Uh oh!

Uh oh!

Conversation

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

Uh oh!

Uh oh!

github-actions Bot commented Mar 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 Mar 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 7, 2026

Choose a reason for hiding this comment

Uh oh!

pethers commented Mar 7, 2026

Uh oh!

github-actions Bot commented Mar 7, 2026

🔍 Lighthouse Performance Audit

Uh oh!

Copilot AI commented Mar 7, 2026

Uh oh!

pethers commented Mar 7, 2026

Uh oh!

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

Uh oh!

Uh oh!

github-actions Bot commented Mar 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 Mar 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 7, 2026

Choose a reason for hiding this comment

Uh oh!

pethers commented Mar 7, 2026

Uh oh!

Copilot AI commented Mar 7, 2026

Uh oh!

github-actions Bot commented Mar 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 Mar 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 7, 2026

Choose a reason for hiding this comment

Uh oh!

pethers commented Mar 7, 2026

Uh oh!

Copilot AI commented Mar 7, 2026

Uh oh!

github-actions Bot commented Mar 7, 2026

🔍 Lighthouse Performance Audit

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Copilot AI commented Mar 7, 2026 •

edited

Loading

Copilot AI commented Mar 7, 2026 •

edited

Loading