feat(monthly-review): multi-month trends, party rankings, and legislative efficiency metrics by Copilot · Pull Request #610 · Hack23/riksdagsmonitor

Copilot · 2026-02-26T21:01:12Z

Original prompt

This section details on the original issue you should resolve

<issue_title>Improve Monthly Review: Add multi-month trends, party rankings, and legislative efficiency metrics</issue_title>
<issue_description>## 📋 Issue Type
Enhancement — Extend Monthly Review with multi-month trend analysis, party performance rankings, and strategic outlook

🎯 Objective

Enhance scripts/news-types/monthly-review.ts to provide comprehensive monthly trend analysis, party performance comparative rankings, legislative efficiency metrics, and a forward-looking strategic outlook. Transform monthly reviews from document summaries into the definitive monthly intelligence brief.

📊 Current State

File: scripts/news-types/monthly-review.ts (335 lines)
REQUIRED_TOOLS: 6 tools — same as weekly review (search_dokument, get_dokument_innehall, search_anforanden, get_betankanden, get_propositioner, get_motioner)
Enrichment pipeline: Same as weekly review but with 30-day lookback
Gap: Monthly reviews don't aggregate weekly patterns into monthly trends, lack party performance rankings, and don't include legislative efficiency metrics (bills passed vs introduced, committee throughput)
Impact: Monthly reviews are essentially longer weekly reviews instead of providing unique strategic monthly intelligence

🚀 Desired State

Multi-month trend analysis (3-month rolling averages for key metrics)
Party performance rankings (legislative output, speech frequency, voting discipline)
Legislative efficiency metrics (bill passage rates, committee throughput, government vs opposition success)
Coalition stability assessment (monthly trajectory of coalition cohesion)
Cross-party collaboration index (bills with multi-party support)
"Month in Numbers" summary statistics section
Strategic outlook section connecting monthly trends to upcoming legislative calendar
Historical comparison with same month in previous parliamentary terms

🔧 Implementation Approach

1. Multi-month trend aggregation (~80 lines)

// Fetch previous months for trend comparison
const previousMonthDocs = await mcpClient.call('search_dokument', {
  from_date: twoMonthsAgo,
  to_date: oneMonthAgo,
  limit: 100
});

Calculate month-over-month change rates
Identify accelerating/decelerating trends
Generate 3-month rolling metrics

2. Party performance rankings (~70 lines)

Rank parties by legislative output (propositions introduced, motions filed)
Rank by debate activity (anföranden frequency, question volume)
Rank by voting discipline (party cohesion percentage)
Create comparative party scorecard

3. Legislative efficiency metrics (~60 lines)

Bill passage rate: betänkanden adopted vs total
Government success rate: propositions reaching committee approval
Committee throughput: average days from referral to report
Opposition effectiveness: motions getting committee attention

4. "Month in Numbers" section (~40 lines)

Total documents processed by type
Total speeches and debate hours
Total votes and their outcomes
Key personnel changes or appointments

5. Enhanced article templates

Add "Month in Numbers" statistical summary
Add "Party Performance Rankings" table
Add "Legislative Efficiency" metrics
Add "Strategic Outlook" forward-looking section
Update all 14 language templates

🤖 Recommended Agent

code-quality-engineer — TypeScript enhancement with data aggregation patterns

✅ Acceptance Criteria

📚 References

File: scripts/news-types/monthly-review.ts
Weekly review pattern: scripts/news-types/weekly-review.ts (base enrichment pipeline)
Risk analysis: scripts/data-transformers/risk-analysis.ts
Policy analysis: scripts/data-transformers/policy-analysis.ts
Document analysis: scripts/data-transformers/document-analysis.ts
CIA methodology: Hack23/cia BUSINESS_PRODUCT_DOCUMENT.md (party performance metrics)
</issue_description>

<agent_instructions>Extend monthly-review articles in scripts/news-types/monthly-review.ts with multi-month trend analysis, party performance rankings, and legislative efficiency metrics. Add "Month in Numbers" and "Party Performance Rankings" template sections. Leverage data-transformers for analysis. Run tests with npx vitest run.</agent_instructions>

Comments on the Issue (you are @copilot in this ...

Fixes Improve Monthly Review: Add multi-month trends, party rankings, and legislative efficiency metrics #599

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

…islative efficiency metrics - Add MonthlyMetrics interface to data-transformers/types.ts - Add generateMonthlyReviewContent to content-generators.ts with 4 new sections in all 14 languages: Month in Numbers, Party Performance Rankings, Legislative Efficiency, and Strategic Outlook - Route monthly-review type to the new generator in data-transformers/index.ts - Fetch previous 2 months for 3-month rolling trend analysis in monthly-review.ts - Compute party rankings from motion/speech parti fields - Compute legislative efficiency rate (reports / propositions) - Extend MonthlyReviewValidationResult with hasPartyRankings, hasLegislativeEfficiency, hasMonthInNumbers fields and corresponding check functions - Add 6 new tests covering all new sections and features Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

github-actions · 2026-02-27T02:15:20Z

🔍 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 makes monthly-review a distinct, richer intelligence product by adding multi-month trend metrics, party activity rankings, legislative efficiency indicators, and a strategic outlook section, with support across all 14 languages.

Changes:

Add MonthlyMetrics and pass it through the monthly review generation pipeline.
Introduce generateMonthlyReviewContent to append monthly-specific sections after the generic base content.
Extend monthly review validation and tests to cover the new sections and trend-fetch behavior.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
tests/news-types/monthly-review.test.ts	Adds test coverage for the new monthly sections and trend-search behavior.
scripts/news-types/monthly-review.ts	Fetches previous months for trends, computes `MonthlyMetrics`, passes it into article generation, and extends validation fields.
scripts/data-transformers/types.ts	Introduces `MonthlyMetrics` and adds `monthlyMetrics?` to `ArticleContentData`.
scripts/data-transformers/index.ts	Routes `monthly-review` to the new monthly-specific content generator.
scripts/data-transformers/content-generators.ts	Implements localized labels and renders the four new monthly sections.

Copilot · 2026-02-27T02:16:30Z

scripts/news-types/monthly-review.ts

+        .catch(() => [] as RawDocument[]),
+      client.searchDocuments({ from_date: formatDateForSlug(prev2Start), to_date: formatDateForSlug(prevStart), limit: 50 })
+        .catch(() => [] as RawDocument[]),


Step 6 swallows searchDocuments errors with .catch(() => []) and doesn't log, which makes trend metrics silently degrade and harder to debug (unlike Step 2/4 which log errors). Consider logging the caught error (and optionally recording it in mcpCalls) so failures are observable.

Suggested change

.catch(() => [] as RawDocument[]),

client.searchDocuments({ from_date: formatDateForSlug(prev2Start), to_date: formatDateForSlug(prevStart), limit: 50 })

.catch(() => [] as RawDocument[]),

.catch((error) => {

console.error(

'MonthlyReview Step 6 — search_dokument failed for previous month trend window',

{ from_date: formatDateForSlug(prevStart), to_date: fromStr, limit: 50 },

error,

);

return [] as RawDocument[];

}),

client.searchDocuments({ from_date: formatDateForSlug(prev2Start), to_date: formatDateForSlug(prevStart), limit: 50 })

.catch((error) => {

console.error(

'MonthlyReview Step 6 — search_dokument failed for two-months-ago trend window',

{ from_date: formatDateForSlug(prev2Start), to_date: formatDateForSlug(prevStart), limit: 50 },

error,

);

return [] as RawDocument[];

}),

Copilot · 2026-02-27T02:16:31Z

scripts/news-types/monthly-review.ts

+         article.content.includes('partyRankings') ||
+         article.content.toLowerCase().includes('rankings');
+}
+
+function checkLegislativeEfficiency(article: ArticleInput): boolean {
+  if (!article || !article.content) return false;
+  return article.content.includes('Legislative Efficiency') ||
+         article.content.includes('Lagstiftningseffektivitet') ||
+         article.content.toLowerCase().includes('efficiency') ||
+         article.content.toLowerCase().includes('throughput');
+}
+
+function checkMonthInNumbers(article: ArticleInput): boolean {
+  if (!article || !article.content) return false;
+  return article.content.includes('Month in Numbers') ||
+         article.content.includes('Månaden i siffror') ||
+         article.content.toLowerCase().includes('total documents') ||
+         article.content.toLowerCase().includes('committee reports');


The new validation helpers are very permissive and can produce false positives (e.g., any occurrence of the word "rankings", "efficiency", "throughput", or "committee reports" will satisfy the checks even if the dedicated section is missing). Since these flags are used to validate article quality, it would be more reliable to check for the actual section headings/labels that the generator emits (including the emoji-prefixed titles) across supported languages, or a more specific marker unique to each section.

Suggested change

article.content.includes('partyRankings') ||

article.content.toLowerCase().includes('rankings');

}

function checkLegislativeEfficiency(article: ArticleInput): boolean {

if (!article || !article.content) return false;

return article.content.includes('Legislative Efficiency') ||

article.content.includes('Lagstiftningseffektivitet') ||

article.content.toLowerCase().includes('efficiency') ||

article.content.toLowerCase().includes('throughput');

}

function checkMonthInNumbers(article: ArticleInput): boolean {

if (!article || !article.content) return false;

return article.content.includes('Month in Numbers') ||

article.content.includes('Månaden i siffror') ||

article.content.toLowerCase().includes('total documents') ||

article.content.toLowerCase().includes('committee reports');

article.content.includes('partyRankings');

}

function checkLegislativeEfficiency(article: ArticleInput): boolean {

if (!article || !article.content) return false;

return article.content.includes('Legislative Efficiency') ||

article.content.includes('Lagstiftningseffektivitet');

}

function checkMonthInNumbers(article: ArticleInput): boolean {

if (!article || !article.content) return false;

return article.content.includes('Month in Numbers') ||

article.content.includes('Månaden i siffror');

Copilot · 2026-02-27T02:16:31Z

scripts/data-transformers/types.ts

+  /** Party activity rankings sorted by total activity (motions + speeches) */
+  partyRankings: Array<{ party: string; motionCount: number; speechCount: number }>;
+  /**
+   * Legislative efficiency rate: committee reports divided by propositions (0–1).


legislativeEfficiencyRate is documented as "(0–1)", but reportCount / propositionCount can exceed 1 when there are more reports than propositions in the same window. Either clamp/normalize the metric to a 0–1 range, or update the doc comment to reflect the actual (unbounded) ratio semantics.

Suggested change

* Legislative efficiency rate: committee reports divided by propositions (0–1).

* Legislative efficiency rate: committee reports divided by propositions.

* This is a non-negative ratio (reportCount / propositionCount) and may exceed 1

* when there are more reports than propositions in the same period.

Copilot · 2026-02-27T02:16:31Z

scripts/news-types/monthly-review.ts

+    hasPartyRankings,
+    hasLegislativeEfficiency,
+    hasMonthInNumbers,
    passed: hasMonthlySummary && hasMinimumSources && hasRetrospectiveTone && hasTrendAnalysis


passed is still computed only from the pre-existing checks, so validateMonthlyReview can return passed: true even when the new monthly sections (Month in Numbers / Party Rankings / Legislative Efficiency) are missing. If these sections are now required for a monthly review, include the new booleans in the passed expression (or clearly document why they are informational only).

Suggested change

passed: hasMonthlySummary && hasMinimumSources && hasRetrospectiveTone && hasTrendAnalysis

passed:

hasMonthlySummary &&

hasMinimumSources &&

hasRetrospectiveTone &&

hasTrendAnalysis &&

hasPartyRankings &&

hasLegislativeEfficiency &&

hasMonthInNumbers

pethers · 2026-02-27T06:41:29Z

@copilot apply changes based on the comments in this thread

- Log Step 6 trend-fetch errors with console.error for observability - Tighten check functions to match exact generated section headings only - Include hasPartyRankings/hasLegislativeEfficiency/hasMonthInNumbers in passed - Fix legislativeEfficiencyRate doc comment: ratio is unbounded (may exceed 1) Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-02-27T06:47:37Z

@copilot apply changes based on the comments in this thread

Applied all 4 changes in b990749:

Step 6 error logging — .catch() now calls console.error with the tool name, parameters, and error for both trend-fetch windows.
Tighter check functions — checkPartyRankings, checkLegislativeEfficiency, and checkMonthInNumbers now match only the exact section headings emitted by the generator (e.g. 'Party Performance Rankings' / 'Partiernas prestationsrankning'), removing the loose keyword fallbacks.
passed includes new fields — validateMonthlyReview now requires hasPartyRankings && hasLegislativeEfficiency && hasMonthInNumbers in addition to the pre-existing checks.
legislativeEfficiencyRate doc comment — corrected to state the ratio is non-negative and may exceed 1 when there are more reports than propositions.

Copilot

Pull request overview

Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.

Copilot · 2026-02-27T07:03:16Z

scripts/news-types/monthly-review.ts

+      if (rec['doktyp'] === 'mot' && rec['parti']) {
+        const p = String(rec['parti']);
+        partyMotions[p] = (partyMotions[p] ?? 0) + 1;


The party aggregation for motions (lines 239-241) doesn't filter out empty strings after converting rec['parti'] to String, unlike the speech aggregation (lines 245-246) which explicitly checks if (p). If a motion has an empty parti field, it will create a partyRankings entry with an empty party name that would appear in the rendered output. Consider adding if (p) check after line 240 for consistency and to prevent empty party names in rankings.

Suggested change

if (rec['doktyp'] === 'mot' && rec['parti']) {

const p = String(rec['parti']);

partyMotions[p] = (partyMotions[p] ?? 0) + 1;

if (rec['doktyp'] === 'mot') {

const p = String(rec['parti'] ?? '');

if (p) {

partyMotions[p] = (partyMotions[p] ?? 0) + 1;

}

pethers · 2026-02-27T07:13:59Z

@copilot apply changes based on the comments in this thread

Mirror the speech aggregation pattern: use String(rec['parti'] ?? '') and guard with `if (p)` to prevent empty-string party names appearing in partyRankings output. Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-02-27T07:24:28Z

@copilot apply changes based on the comments in this thread

Fixed in 637b7af. The motion aggregation loop now mirrors the speech pattern exactly: const p = String(rec['parti'] ?? '') followed by if (p), preventing empty-string party names from appearing in partyRankings.

Signed-off-by: James Pether Sörling <pethers@users.noreply.github.com>

github-actions · 2026-02-27T14:23:43Z

🔍 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

…er efficiency ratio with toFixed(2) Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-02-27T14:26:01Z

@copilot apply changes based on the comments in this thread

All three issues from the review thread applied in db25d79: efficiency rate rendered as a decimal ratio (toFixed(2)) instead of a percent, and numeric counts in both generateMonthInNumbers and generatePartyRankings are now stringified before escapeHtml to prevent zero values rendering blank. All 20 tests pass.

github-actions · 2026-02-27T14:30:19Z

🔍 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 4 comments.

Copilot · 2026-02-27T14:32:14Z

scripts/data-transformers/content-generators.ts

+  if (metrics.partyRankings.length === 0) return '';
+
+  let html = `\n    <h2>${escapeHtml(ml(lang, 'partyRankings'))}</h2>\n`;


generatePartyRankings returns an empty string when metrics.partyRankings.length === 0, which means the Party Performance Rankings section will be omitted entirely in months where party fields are missing or speech fetch returns empty. Since the monthly review validation now requires hasPartyRankings, this can cause otherwise valid monthly reviews to fail validation. Consider always rendering the section with a localized “insufficient data” placeholder (or relaxing validation to allow the section to be present but empty).

Suggested change

if (metrics.partyRankings.length === 0) return '';

let html = `\n <h2>${escapeHtml(ml(lang, 'partyRankings'))}</h2>\n`;

let html = `\n <h2>${escapeHtml(ml(lang, 'partyRankings'))}</h2>\n`;

// Always render the section; if there is no underlying data, show a localized placeholder

if (!metrics.partyRankings || metrics.partyRankings.length === 0) {

const placeholder = ml(lang, 'insufficientData');

html += ` <div class="context-box">\n`;

html += ` <p>${escapeHtml(placeholder)}</p>\n`;

html += ` </div>\n`;

return html;

}

Fixed in d0e54bd. generatePartyRankings now always renders the 🏆 Party Performance Rankings heading. When partyRankings is empty, a localized "Insufficient party activity data for this period." placeholder is shown inside the context-box instead of returning an empty string — so hasPartyRankings validation passes in all languages.

Copilot · 2026-02-27T14:32:15Z

scripts/data-transformers/content-generators.ts

+    const stabilityLabel = ml(lang, 'coalitionStabilityOutlook');
+    const stabilityScore = cia.coalitionStability.stabilityScore;
+    const riskLevel = cia.coalitionStability.riskLevel;
+    html += `        <li><strong>${escapeHtml(stabilityLabel)}:</strong> ${escapeHtml(stabilityScore)}/100 (${escapeHtml(riskLevel)})</li>\n`;


escapeHtml returns an empty string for falsy values (including numeric 0). Here stabilityScore is a number (0–100) and will render blank if it ever equals 0. Convert numeric values to strings before escaping (e.g., escapeHtml(String(stabilityScore))) to preserve legitimate zero values, consistent with the fixes applied for other numeric metrics.

Suggested change

html += ` <li><strong>${escapeHtml(stabilityLabel)}:</strong> ${escapeHtml(stabilityScore)}/100 (${escapeHtml(riskLevel)})</li>\n`;

html += ` <li><strong>${escapeHtml(stabilityLabel)}:</strong> ${escapeHtml(String(stabilityScore))}/100 (${escapeHtml(riskLevel)})</li>\n`;

Fixed in d0e54bd. stabilityScore is now passed as escapeHtml(String(stabilityScore)) so a legitimate value of 0 renders as "0" rather than blank.

Copilot · 2026-02-27T14:32:15Z

tests/news-types/monthly-review.test.ts

+    it('should fetch previous months for trend analysis (3 searchDocuments calls)', async () => {
+      await monthlyReviewModule.generateMonthlyReview({
+        languages: ['en']
+      });
+
+      // Exactly 3 calls: current month + previous month + 2-months-ago
+      expect(mockClientInstance.searchDocuments.mock.calls.length).toBe(3);


This test asserts an exact searchDocuments call count of 3. That’s brittle and doesn’t verify the important behavior (that the two additional calls target the correct previous windows / limits). Consider asserting on the presence and parameters of the extra calls (e.g., 2 additional calls with limit: 1000 and expected from_date/to_date ranges) rather than enforcing an exact total call count, so the test won’t break if additional document searches are added later for other monthly features.

Suggested change

it('should fetch previous months for trend analysis (3 searchDocuments calls)', async () => {

await monthlyReviewModule.generateMonthlyReview({

languages: ['en']

});

// Exactly 3 calls: current month + previous month + 2-months-ago

expect(mockClientInstance.searchDocuments.mock.calls.length).toBe(3);

it('should fetch previous months for trend analysis using multiple searchDocuments calls', async () => {

await monthlyReviewModule.generateMonthlyReview({

languages: ['en']

});

// At least 3 calls: current month + previous month + 2-months-ago

expect(mockClientInstance.searchDocuments.mock.calls.length).toBeGreaterThanOrEqual(3);

Fixed in d0e54bd. Changed toBe(3) → toBeGreaterThanOrEqual(3) so the assertion won't break if additional document searches are added later.

Copilot · 2026-02-27T14:32:15Z

scripts/news-types/monthly-review.ts

+         article.content.includes('Partiernas prestationsrankning');
+}
+
+function checkLegislativeEfficiency(article: ArticleInput): boolean {
+  if (!article || !article.content) return false;
+  return article.content.includes('Legislative Efficiency') ||
+         article.content.includes('Lagstiftningseffektivitet');
+}
+
+function checkMonthInNumbers(article: ArticleInput): boolean {
+  if (!article || !article.content) return false;
+  return article.content.includes('Month in Numbers') ||
+         article.content.includes('Månaden i siffror');


validateMonthlyReview now requires hasPartyRankings / hasLegislativeEfficiency / hasMonthInNumbers, but the detection helpers only look for English + Swedish headings. When generating monthly reviews in other supported languages (e.g. de, fr, etc.), these checks will return false and passed will fail even though the sections are present with localized headings. Consider either checking for the emoji-prefixed headings (📊/🏆/⚖️) regardless of language, or matching against the full per-language label map used by the content generator (with a fallback to EN/SV).

Suggested change

article.content.includes('Partiernas prestationsrankning');

}

function checkLegislativeEfficiency(article: ArticleInput): boolean {

if (!article || !article.content) return false;

return article.content.includes('Legislative Efficiency') ||

article.content.includes('Lagstiftningseffektivitet');

}

function checkMonthInNumbers(article: ArticleInput): boolean {

if (!article || !article.content) return false;

return article.content.includes('Month in Numbers') ||

article.content.includes('Månaden i siffror');

article.content.includes('Partiernas prestationsrankning') ||

// Language-agnostic detection via trophy emoji used in headings

article.content.includes('🏆');

}

function checkLegislativeEfficiency(article: ArticleInput): boolean {

if (!article || !article.content) return false;

return article.content.includes('Legislative Efficiency') ||

article.content.includes('Lagstiftningseffektivitet') ||

// Language-agnostic detection via scales emoji used in headings

article.content.includes('⚖️');

}

function checkMonthInNumbers(article: ArticleInput): boolean {

if (!article || !article.content) return false;

return article.content.includes('Month in Numbers') ||

article.content.includes('Månaden i siffror') ||

// Language-agnostic detection via chart emoji used in headings

article.content.includes('📊');

Fixed in d0e54bd. All three helpers now also check for the emoji prefix (📊, 🏆, ⚖️) so they detect the sections in any of the 14 supported languages, not just English and Swedish.

pethers · 2026-02-27T14:42:38Z

@copilot apply changes based on the comments in this thread

…stabilityScore, emoji-based validation, non-brittle test assertion Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-02-27T14:48:13Z

@copilot apply changes based on the comments in this thread

All four review comments applied in d0e54bd. All 2026 tests pass.

github-actions · 2026-02-27T15:20:27Z

🔍 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

Copilot reviewed 6 out of 6 changed files in this pull request and generated 2 comments.

Copilot · 2026-02-27T15:22:27Z

scripts/data-transformers/content-generators.ts

+    html += `        <li><em>${escapeHtml(ml(lang, 'trendVsPrevMonth'))}:</em> ${escapeHtml(prevSign)}${prevDiff}</li>\n`;
+  }
+  if (metrics.twoMonthsAgoDocCount > 0 || metrics.previousMonthDocCount > 0) {
+    html += `        <li><em>${escapeHtml(ml(lang, 'trendVs2MonthsAgo'))}:</em> ${rollingAvg}</li>\n`;


The numeric values prevDiff (line 1436) and rollingAvg (line 1439) are directly interpolated into the HTML without escaping. While these are computed numeric values, they should be consistently escaped like all other interpolated content for defense-in-depth XSS protection. Convert them to strings and apply escapeHtml: escapeHtml(String(prevDiff)) and escapeHtml(String(rollingAvg)).

Suggested change

html += ` <li><em>${escapeHtml(ml(lang, 'trendVsPrevMonth'))}:</em> ${escapeHtml(prevSign)}${prevDiff}</li>\n`;

}

if (metrics.twoMonthsAgoDocCount > 0 || metrics.previousMonthDocCount > 0) {

html += ` <li><em>${escapeHtml(ml(lang, 'trendVs2MonthsAgo'))}:</em> ${rollingAvg}</li>\n`;

html += ` <li><em>${escapeHtml(ml(lang, 'trendVsPrevMonth'))}:</em> ${escapeHtml(prevSign)}${escapeHtml(String(prevDiff))}</li>\n`;

}

if (metrics.twoMonthsAgoDocCount > 0 || metrics.previousMonthDocCount > 0) {

html += ` <li><em>${escapeHtml(ml(lang, 'trendVs2MonthsAgo'))}:</em> ${escapeHtml(String(rollingAvg))}</li>\n`;

Fixed in 770137d. prevDiff and rollingAvg are now wrapped with escapeHtml(String(...)) for consistent defense-in-depth XSS protection.

Copilot · 2026-02-27T15:22:28Z

scripts/data-transformers/content-generators.ts

+
+  if (metrics.propositionCount > 0) {
+    const ratio = metrics.legislativeEfficiencyRate.toFixed(2);
+    html += `        <li><strong>${escapeHtml(ml(lang, 'efficiencyRate'))}:</strong> ${ratio} (${metrics.reportCount} / ${metrics.propositionCount})</li>\n`;


The ratio value (computed from toFixed(2)) and the numeric values metrics.reportCount and metrics.propositionCount are directly interpolated without escaping. Although ratio is a string from toFixed, and reportCount/propositionCount are numeric, they should be consistently escaped for defense-in-depth: ${escapeHtml(ratio)} and ${escapeHtml(String(metrics.reportCount))} / ${escapeHtml(String(metrics.propositionCount))}.

Suggested change

html += ` <li><strong>${escapeHtml(ml(lang, 'efficiencyRate'))}:</strong> ${ratio} (${metrics.reportCount} / ${metrics.propositionCount})</li>\n`;

html += ` <li><strong>${escapeHtml(ml(lang, 'efficiencyRate'))}:</strong> ${escapeHtml(ratio)} (${escapeHtml(String(metrics.reportCount))} / ${escapeHtml(String(metrics.propositionCount))})</li>\n`;

Fixed in 770137d. ratio, metrics.reportCount, and metrics.propositionCount are now all wrapped with escapeHtml(...) / escapeHtml(String(...)) for consistent defense-in-depth escaping.

pethers · 2026-02-27T15:30:03Z

@copilot apply changes based on the comments in this thread

…f, rollingAvg, ratio, reportCount, propositionCount Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot · 2026-02-27T15:33:21Z

@copilot apply changes based on the comments in this thread

Applied in 770137d. Both numeric interpolations flagged in the thread are now consistently wrapped with escapeHtml(String(...)). All 20 tests pass.

github-actions · 2026-02-27T15:45:06Z

🔍 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 no new comments.

Initial plan

4cf2fde

Copilot AI assigned Copilot and pethers Feb 26, 2026

Copilot started work on behalf of pethers February 26, 2026 21:01 View session

Copilot AI mentioned this pull request Feb 26, 2026

Analyze remaining gaps after article type improvements; create and assign 4 follow-up issues #594

Draft

Copilot AI changed the title ~~[WIP] Enhance monthly review with multi-month trends and metrics~~ feat(monthly-review): multi-month trends, party rankings, and legislative efficiency metrics Feb 26, 2026

Copilot finished work on behalf of pethers February 26, 2026 21:19

pethers requested a review from Copilot February 27, 2026 02:13

github-actions bot added testing Test coverage refactor Code refactoring size-l Large change (250-1000 lines) labels Feb 27, 2026

Copilot started reviewing on behalf of pethers February 27, 2026 02:14 View session

Copilot AI reviewed Feb 27, 2026

View reviewed changes

Copilot started work on behalf of pethers February 27, 2026 06:44 View session

Copilot finished work on behalf of pethers February 27, 2026 06:49

pethers requested a review from Copilot February 27, 2026 06:57

Copilot started reviewing on behalf of pethers February 27, 2026 06:58 View session

Copilot AI reviewed Feb 27, 2026

View reviewed changes

Copilot started work on behalf of pethers February 27, 2026 07:21 View session

Copilot finished work on behalf of pethers February 27, 2026 07:25

Merge branch 'main' into copilot/enhance-monthly-review-features

7bf6126

Signed-off-by: James Pether Sörling <pethers@users.noreply.github.com>

pethers requested a review from Copilot February 27, 2026 08:27

fix(monthly-review): stringify numeric counts before escapeHtml, rend…

db25d79

…er efficiency ratio with toFixed(2) Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot finished work on behalf of pethers February 27, 2026 14:26

Merge branch 'main' into copilot/enhance-monthly-review-features

2edf7de

pethers requested a review from Copilot February 27, 2026 14:28

Copilot started reviewing on behalf of pethers February 27, 2026 14:29 View session

Copilot AI reviewed Feb 27, 2026

View reviewed changes

Copilot started work on behalf of pethers February 27, 2026 14:42 View session

fix(monthly-review): always render party rankings section, stringify …

d0e54bd

…stabilityScore, emoji-based validation, non-brittle test assertion Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot finished work on behalf of pethers February 27, 2026 14:48

pethers requested a review from Copilot February 27, 2026 15:19

Copilot started reviewing on behalf of pethers February 27, 2026 15:19 View session

Copilot AI reviewed Feb 27, 2026

View reviewed changes

Copilot started work on behalf of pethers February 27, 2026 15:30 View session

fix(content-generators): apply defense-in-depth escapeHtml to prevDif…

770137d

…f, rollingAvg, ratio, reportCount, propositionCount Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot finished work on behalf of pethers February 27, 2026 15:33

pethers requested a review from Copilot February 27, 2026 15:43

Copilot started reviewing on behalf of pethers February 27, 2026 15:44 View session

Copilot AI reviewed Feb 27, 2026

View reviewed changes

pethers marked this pull request as ready for review February 27, 2026 16:30

pethers merged commit 5a8555a into main Feb 27, 2026
20 checks passed

pethers deleted the copilot/enhance-monthly-review-features branch February 27, 2026 16:30

-        .catch(() => [] as RawDocument[]),
-      client.searchDocuments({ from_date: formatDateForSlug(prev2Start), to_date: formatDateForSlug(prevStart), limit: 50 })
-        .catch(() => [] as RawDocument[]),
+        .catch((error) => {
+          console.error(
+            'MonthlyReview Step 6 — search_dokument failed for previous month trend window',
+            { from_date: formatDateForSlug(prevStart), to_date: fromStr, limit: 50 },
+            error,
+          );
+          return [] as RawDocument[];
+        }),
+      client.searchDocuments({ from_date: formatDateForSlug(prev2Start), to_date: formatDateForSlug(prevStart), limit: 50 })
+        .catch((error) => {
+          console.error(
+            'MonthlyReview Step 6 — search_dokument failed for two-months-ago trend window',
+            { from_date: formatDateForSlug(prev2Start), to_date: formatDateForSlug(prevStart), limit: 50 },
+            error,
+          );
+          return [] as RawDocument[];
+        }),

-   * Legislative efficiency rate: committee reports divided by propositions (0–1).
+   * Legislative efficiency rate: committee reports divided by propositions.
+   * This is a non-negative ratio (reportCount / propositionCount) and may exceed 1
+   * when there are more reports than propositions in the same period.

		if (metrics.partyRankings.length === 0) return '';

		let html = `\n <h2>${escapeHtml(ml(lang, 'partyRankings'))}</h2>\n`;

-  if (metrics.partyRankings.length === 0) return '';
-  let html = `\n    <h2>${escapeHtml(ml(lang, 'partyRankings'))}</h2>\n`;
+  let html = `\n    <h2>${escapeHtml(ml(lang, 'partyRankings'))}</h2>\n`;
+  // Always render the section; if there is no underlying data, show a localized placeholder
+  if (!metrics.partyRankings || metrics.partyRankings.length === 0) {
+    const placeholder = ml(lang, 'insufficientData');
+    html += `    <div class="context-box">\n`;
+    html += `      <p>${escapeHtml(placeholder)}</p>\n`;
+    html += `    </div>\n`;
+    return html;
+  }

	html += ` <li><strong>${escapeHtml(stabilityLabel)}:</strong> ${escapeHtml(stabilityScore)}/100 (${escapeHtml(riskLevel)})</li>\n`;
	html += ` <li><strong>${escapeHtml(stabilityLabel)}:</strong> ${escapeHtml(String(stabilityScore))}/100 (${escapeHtml(riskLevel)})</li>\n`;

	html += ` <li><strong>${escapeHtml(ml(lang, 'efficiencyRate'))}:</strong> ${ratio} (${metrics.reportCount} / ${metrics.propositionCount})</li>\n`;
	html += ` <li><strong>${escapeHtml(ml(lang, 'efficiencyRate'))}:</strong> ${escapeHtml(ratio)} (${escapeHtml(String(metrics.reportCount))} / ${escapeHtml(String(metrics.propositionCount))})</li>\n`;

Conversation

Copilot AI commented Feb 26, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🎯 Objective

📊 Current State

🚀 Desired State

🔧 Implementation Approach

1. Multi-month trend aggregation (~80 lines)

2. Party performance rankings (~70 lines)

3. Legislative efficiency metrics (~60 lines)

4. "Month in Numbers" section (~40 lines)

5. Enhanced article templates

🤖 Recommended Agent

✅ Acceptance Criteria

📚 References

Comments on the Issue (you are @copilot in this ...

Uh oh!

github-actions bot commented Feb 27, 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 Feb 27, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 27, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 27, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 27, 2026

Choose a reason for hiding this comment

Uh oh!

pethers commented Feb 27, 2026

Uh oh!

Copilot AI commented Feb 27, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Feb 27, 2026

Choose a reason for hiding this comment

Uh oh!

pethers commented Feb 27, 2026

Uh oh!

Copilot AI commented Feb 27, 2026

Uh oh!

github-actions bot commented Feb 27, 2026

🔍 Lighthouse Performance Audit

Uh oh!

Copilot AI commented Feb 27, 2026

Uh oh!

github-actions bot commented Feb 27, 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 Feb 27, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 27, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 27, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 27, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 27, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 27, 2026

Copilot AI commented Feb 26, 2026 •

edited

Loading