Enforce 15-min analysis minimum, quality gate, and template compliance across all agentic workflows by Copilot · Pull Request #1453 · Hack23/riksdagsmonitor

Copilot · 2026-03-30T00:53:36Z

PR #1452 produced plain-prose SWOT analysis with no structured tables, no Mermaid diagrams, no dok_id citations, and no template structure. Root cause: workflows allocated only 10 min for analysis, defaulted to standard depth (1-2 iterations), and had no blocking quality gate.

SHARED_PROMPT_PATTERNS.md

Added mandatory 15-minute minimum analysis time with enforcement rationale
Added quality gate bash script that blocks commit if analysis files lack Mermaid diagrams, color-coded style directives, or contain [REQUIRED] placeholders
Updated Standardised Analysis Depth Gate default from standard → deep

ai-driven-analysis-guide.md (v1.0 → v1.1)

Added "Mandatory Quality Requirements" section with output format table
Added concrete anti-pattern from PR 🔴 Breaking: KU Scrutiny Hearings — Carlson/Lantmäteriet & Northvolt — 2026-03-30 #1452 (plain prose SWOT) alongside good example showing proper template structure with Context table, evidence tables, and color-coded Mermaid

All 11 news workflows

analysis_depth default: standard → deep across all workflows
Time budgets restructured: separate Download (3 min) from AI Analysis (15 min minimum) phases
30-minute workflows (week-ahead, month-ahead, monthly-review) get 10-min minimum

All 8 analysis templates

Added anti-pattern warning block to each template referencing the methodology guide

Example quality gate check added to SHARED_PROMPT_PATTERNS:

# Check: Every analysis file must contain at least 1 Mermaid diagram
for f in "$ANALYSIS_DIR"/*.md; do
  MERMAID_COUNT=$(grep -c '```mermaid' "$f" 2>/dev/null || echo 0)
  if [ "$MERMAID_COUNT" -eq 0 ]; then
    echo "❌ FAIL: $f has NO Mermaid diagrams (minimum: 1)"
    QUALITY_PASS=false
  fi
done

🔒 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.

github-actions · 2026-03-30T00:54:09Z

🏷️ Automatic Labeling Summary

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

Applied Labels: size-xs

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 · 2026-03-30T00:54:41Z

🔍 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

…ements in SHARED_PROMPT_PATTERNS, ai-driven-analysis-guide, and news-realtime-monitor Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/d9709bf9-e994-4bc9-9bc5-1d498d61da9c Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

github-actions · 2026-03-30T01:03:00Z

🔍 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

…sis_depth default to deep, quality gate enforcement Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/d9709bf9-e994-4bc9-9bc5-1d498d61da9c Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

github-actions · 2026-03-30T01:06:59Z

🔍 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

…1452 quality failures Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/d9709bf9-e994-4bc9-9bc5-1d498d61da9c Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

github-actions · 2026-03-30T01:08:20Z

🔍 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 strengthens the agentic news-analysis workflow guidance to prevent low-quality “plain prose” outputs by requiring longer analysis time, deeper default analysis depth, template compliance, and a pre-commit quality gate.

Changes:

Added anti-pattern warnings to all analysis templates and expanded the AI-driven analysis methodology with mandatory quality requirements and good/bad examples.
Updated news workflows to default analysis_depth to deep and restructured time budgets to reserve explicit analysis time.
Introduced a reusable “quality gate” bash check in SHARED_PROMPT_PATTERNS.md intended to block committing non-compliant analysis artifacts.

Reviewed changes

Copilot reviewed 21 out of 21 changed files in this pull request and generated 18 comments.

Show a summary per file

File	Description
`analysis/templates/threat-analysis.md`	Adds anti-pattern warning requiring structured evidence, Mermaid, and template compliance.
`analysis/templates/synthesis-summary.md`	Adds anti-pattern warning to enforce template-structured synthesis output.
`analysis/templates/swot-analysis.md`	Adds detailed anti-pattern warning and points to `SWOT.md` exemplar.
`analysis/templates/stakeholder-impact.md`	Adds anti-pattern warning to prevent plain-prose stakeholder output.
`analysis/templates/significance-scoring.md`	Adds anti-pattern warning emphasizing tables/diagrams/evidence.
`analysis/templates/risk-assessment.md`	Adds anti-pattern warning to enforce structured risk output.
`analysis/templates/political-classification.md`	Adds anti-pattern warning to enforce classification template compliance.
`analysis/templates/per-file-political-intelligence.md`	Adds anti-pattern warning for per-file analyses.
`analysis/methodologies/ai-driven-analysis-guide.md`	Adds “Mandatory Quality Requirements” and expands bad-vs-good examples.
`.github/workflows/news-weekly-review.md`	Sets default depth to `deep`, reworks time budget, and reinforces quality requirements.
`.github/workflows/news-week-ahead.md`	Sets default depth to `deep`, reworks time budget, and updates depth gate table.
`.github/workflows/news-realtime-monitor.md`	Sets default depth to `deep`, reworks phases to allocate 15 min analysis, and strengthens instructions.
`.github/workflows/news-propositions.md`	Sets default depth to `deep`, reworks time budget, and updates depth gate table.
`.github/workflows/news-motions.md`	Sets default depth to `deep`, reworks time budget, and updates depth gate table.
`.github/workflows/news-monthly-review.md`	Reworks time budget and updates depth gate table/requirements.
`.github/workflows/news-month-ahead.md`	Sets default depth to `deep`, reworks time budget, and updates depth gate table.
`.github/workflows/news-interpellations.md`	Sets default depth to `deep`, reworks time budget, and updates depth gate table.
`.github/workflows/news-evening-analysis.md`	Sets default depth to `deep`, reworks phases for 15 min analysis, and updates depth gate table.
`.github/workflows/news-committee-reports.md`	Sets default depth to `deep`, reworks time budget, and updates depth gate table.
`.github/workflows/news-article-generator.md`	Sets default depth to `deep`, reworks phases for 15 min analysis, and updates depth gate table.
`.github/workflows/SHARED_PROMPT_PATTERNS.md`	Updates shared depth gate defaults and adds the reusable quality-gate bash check.

Copilot · 2026-03-30T01:17:52Z

.github/workflows/news-interpellations.md

        description: 'Analysis depth for AI iterations (standard=1-2 iterations, deep=2-3 iterations, comprehensive=3+ iterations). Controls SWOT complexity, stakeholder count, and dashboard charts.'
        required: false
-        default: standard
+        default: deep


This workflow source .md sets analysis_depth default to deep, but the compiled .lock.yml still has analysis_depth.default: standard (so GitHub Actions will keep using standard). Regenerate and commit the updated lock file via gh aw compile so the new default (and any other frontmatter changes) actually take effect.

Suggested change

default: deep

default: standard

Copilot · 2026-03-30T01:17:52Z

analysis/methodologies/ai-driven-analysis-guide.md

+| S1 | Coalition maintains working majority — AU10 vote showed standard party alignment with SD support | AU10 vote record (dok_id: H901AU10) | H | H | 2026-03-30 |
+| S2 | Strong legislative output — 20+ propositions in March covering criminal justice and defense | Prop 2025/26:227, 213, 210 (criminal justice), Prop 2025/26:205 (food stockpile) | H | M | 2026-03-30 |
+
+### ⚠️ Weaknesses — Government Coalition
+
+| # | Weakness Statement | Evidence (dok_id) | Confidence | Impact | Entry Date |
+|---|-------------------|-------------------|:----------:|:------:|:----------:|
+| W1 | MP Marléne Lund Kopparklint leaving M party group signals internal dissent — narrows parliamentary arithmetic | Riksdag MP registry, party group change notice | H | M | 2026-03-30 |
+| W2 | Minister Andreas Carlson (KD) under KU scrutiny for Lantmäteriet security failures — G7-8 complaint dockets | KU hearing agenda, dockets G7, G8 | H | H | 2026-03-30 |


This guide states confidence labels should be [HIGH]/[MEDIUM]/[LOW], but the “GOOD” example evidence tables use H/M (e.g., | ... | H | H |). Either update the requirement wording to allow H/M/L in tables (and define the mapping), or update the example to use the same confidence-label format the guide mandates.

Suggested change

| S1 | Coalition maintains working majority — AU10 vote showed standard party alignment with SD support | AU10 vote record (dok_id: H901AU10) | H | H | 2026-03-30 |

| S2 | Strong legislative output — 20+ propositions in March covering criminal justice and defense | Prop 2025/26:227, 213, 210 (criminal justice), Prop 2025/26:205 (food stockpile) | H | M | 2026-03-30 |

### ⚠️ Weaknesses — Government Coalition

| # | Weakness Statement | Evidence (dok_id) | Confidence | Impact | Entry Date |

|---|-------------------|-------------------|:----------:|:------:|:----------:|

| W1 | MP Marléne Lund Kopparklint leaving M party group signals internal dissent — narrows parliamentary arithmetic | Riksdag MP registry, party group change notice | H | M | 2026-03-30 |

| W2 | Minister Andreas Carlson (KD) under KU scrutiny for Lantmäteriet security failures — G7-8 complaint dockets | KU hearing agenda, dockets G7, G8 | H | H | 2026-03-30 |

| S1 | Coalition maintains working majority — AU10 vote showed standard party alignment with SD support | AU10 vote record (dok_id: H901AU10) | [HIGH] | [HIGH] | 2026-03-30 |

| S2 | Strong legislative output — 20+ propositions in March covering criminal justice and defense | Prop 2025/26:227, 213, 210 (criminal justice), Prop 2025/26:205 (food stockpile) | [HIGH] | [MEDIUM] | 2026-03-30 |

### ⚠️ Weaknesses — Government Coalition

| # | Weakness Statement | Evidence (dok_id) | Confidence | Impact | Entry Date |

|---|-------------------|-------------------|:----------:|:------:|:----------:|

| W1 | MP Marléne Lund Kopparklint leaving M party group signals internal dissent — narrows parliamentary arithmetic | Riksdag MP registry, party group change notice | [HIGH] | [MEDIUM] | 2026-03-30 |

| W2 | Minister Andreas Carlson (KD) under KU scrutiny for Lantmäteriet security failures — G7-8 complaint dockets | KU hearing agenda, dockets G7, G8 | [HIGH] | [HIGH] | 2026-03-30 |

Copilot · 2026-03-30T01:17:52Z

.github/workflows/news-weekly-review.md

        description: 'Analysis depth for AI iterations (standard=1-2 iterations, deep=2-3 iterations, comprehensive=3+ iterations). Controls SWOT complexity, stakeholder count, and dashboard charts.'
        required: false
-        default: standard
+        default: deep


This workflow source .md sets analysis_depth default to deep, but the compiled .lock.yml still has analysis_depth.default: standard (so GitHub Actions will keep using standard). Regenerate and commit the updated lock file via gh aw compile so the new default (and any other frontmatter changes) actually take effect.

Suggested change

default: deep

default: standard

Copilot · 2026-03-30T01:17:53Z

.github/workflows/news-article-generator.md

        description: 'Analysis depth for AI iterations (standard=1-2 iterations, deep=2-3 iterations, comprehensive=3+ iterations). Controls SWOT complexity, stakeholder count, and dashboard charts.'
        required: false
-        default: standard
+        default: deep


This workflow source .md sets analysis_depth default to deep, but the compiled .lock.yml still has analysis_depth.default: standard (so GitHub Actions will keep using standard). Regenerate and commit the updated lock file via gh aw compile so the new default (and any other frontmatter changes) actually take effect.

Suggested change

default: deep

default: standard

Copilot · 2026-03-30T01:17:53Z

.github/workflows/news-realtime-monitor.md

      analysis_depth:
-        description: 'Analysis depth for AI iterations (standard=1-2 iterations, deep=2-3 iterations, comprehensive=3+ iterations). Controls SWOT complexity, stakeholder count, and dashboard charts.'
+        description: 'Analysis depth for AI iterations (standard=1-2 iterations, deep=2-3 iterations, comprehensive=3+ iterations). Controls SWOT complexity, stakeholder count, and dashboard charts. Default: deep (minimum 15 min analysis, Mermaid diagrams required).'
        required: false
-        default: standard
+        default: deep


This workflow source .md sets analysis_depth default to deep, but the compiled .lock.yml still has analysis_depth.default: standard (so GitHub Actions will keep using standard). Regenerate and commit the updated lock file via gh aw compile so the new default (and any other frontmatter changes) actually take effect.

Copilot · 2026-03-30T01:17:55Z

.github/workflows/news-evening-analysis.md

        description: 'Analysis depth for AI iterations (standard=1-2 iterations, deep=2-3 iterations, comprehensive=3+ iterations). Controls SWOT complexity, stakeholder count, and dashboard charts.'
        required: false
-        default: standard
+        default: deep


This workflow source .md sets analysis_depth default to deep, but the compiled .lock.yml still has analysis_depth.default: standard (so GitHub Actions will keep using standard). Regenerate and commit the updated lock file via gh aw compile so the new default (and any other frontmatter changes) actually take effect.

Suggested change

default: deep

default: standard

Copilot · 2026-03-30T01:17:55Z

.github/workflows/news-motions.md

        description: 'Analysis depth for AI iterations (standard=1-2 iterations, deep=2-3 iterations, comprehensive=3+ iterations). Controls SWOT complexity, stakeholder count, and dashboard charts.'
        required: false
-        default: standard
+        default: deep


This workflow source .md sets analysis_depth default to deep, but the compiled .lock.yml still has analysis_depth.default: standard (so GitHub Actions will keep using standard). Regenerate and commit the updated lock file via gh aw compile so the new default (and any other frontmatter changes) actually take effect.

Suggested change

default: deep

default: standard

Copilot · 2026-03-30T01:17:55Z

.github/workflows/SHARED_PROMPT_PATTERNS.md

+# Check 3: No [REQUIRED] placeholders remaining
+for f in "$ANALYSIS_DIR"/*.md; do
+  [ ! -f "$f" ] && continue
+  REQ_COUNT=$(grep -c '\[REQUIRED\]' "$f" 2>/dev/null || echo 0)
+  if [ "$REQ_COUNT" -gt 0 ]; then
+    echo "❌ FAIL: $f has $REQ_COUNT unfilled [REQUIRED] placeholders"
+    QUALITY_PASS=false
+  fi


Quality requirements mention zero placeholders, but the quality gate only checks for [REQUIRED] and never flags remaining [OPTIONAL] placeholders. Consider adding a corresponding [OPTIONAL] check so the gate enforces the stated “No placeholders” rule consistently.

Suggested change

# Check 3: No [REQUIRED] placeholders remaining

for f in "$ANALYSIS_DIR"/*.md; do

[ ! -f "$f" ] && continue

REQ_COUNT=$(grep -c '\[REQUIRED\]' "$f" 2>/dev/null || echo 0)

if [ "$REQ_COUNT" -gt 0 ]; then

echo "❌ FAIL: $f has $REQ_COUNT unfilled [REQUIRED] placeholders"

QUALITY_PASS=false

fi

# Check 3: No [REQUIRED] or [OPTIONAL] placeholders remaining

for f in "$ANALYSIS_DIR"/*.md; do

[ ! -f "$f" ] && continue

REQ_COUNT=$(grep -c '\[REQUIRED\]' "$f" 2>/dev/null || echo 0)

OPT_COUNT=$(grep -c '\[OPTIONAL\]' "$f" 2>/dev/null || echo 0)

if [ "$REQ_COUNT" -gt 0 ]; then

echo "❌ FAIL: $f has $REQ_COUNT unfilled [REQUIRED] placeholders"

QUALITY_PASS=false

fi

if [ "$OPT_COUNT" -gt 0 ]; then

echo "❌ FAIL: $f has $OPT_COUNT unfilled [OPTIONAL] placeholders"

QUALITY_PASS=false

fi

Copilot · 2026-03-30T01:17:56Z

.github/workflows/news-month-ahead.md

        description: 'Analysis depth for AI iterations (standard=1-2 iterations, deep=2-3 iterations, comprehensive=3+ iterations). Controls SWOT complexity, stakeholder count, and dashboard charts.'
        required: false
-        default: standard
+        default: deep


This workflow source .md sets analysis_depth default to deep, but the compiled .lock.yml still has analysis_depth.default: standard (so GitHub Actions will keep using standard). Regenerate and commit the updated lock file via gh aw compile so the new default (and any other frontmatter changes) actually take effect.

Suggested change

default: deep

default: standard

Copilot · 2026-03-30T01:17:56Z

.github/workflows/news-committee-reports.md

        description: 'Analysis depth for AI iterations (standard=1-2 iterations, deep=2-3 iterations, comprehensive=3+ iterations). Controls SWOT complexity, stakeholder count, and dashboard charts.'
        required: false
-        default: standard
+        default: deep


This workflow source .md sets analysis_depth default to deep, but the compiled .lock.yml still has analysis_depth.default: standard (so GitHub Actions will keep using standard). Regenerate and commit the updated lock file via gh aw compile so the new default (and any other frontmatter changes) actually take effect.

Suggested change

default: deep

default: standard

Initial plan

cdb1faf

Copilot AI assigned Copilot and pethers Mar 30, 2026

Copilot started work on behalf of pethers March 30, 2026 00:53 View session

github-actions bot added the size-xs Extra small change (< 10 lines) label Mar 30, 2026

github-actions bot added documentation Documentation updates workflow GitHub Actions workflows ci-cd CI/CD pipeline changes news News articles and content generation agentic-workflow Agentic workflow changes size-l Large change (250-1000 lines) labels Mar 30, 2026

Add anti-pattern warnings to all 8 analysis templates referencing PR #…

728885e

…1452 quality failures Agent-Logs-Url: https://github.com/Hack23/riksdagsmonitor/sessions/d9709bf9-e994-4bc9-9bc5-1d498d61da9c Co-authored-by: pethers <1726836+pethers@users.noreply.github.com>

Copilot AI changed the title ~~[WIP] Update analysis methods and templates for better compliance~~ Enforce 15-min analysis minimum, quality gate, and template compliance across all agentic workflows Mar 30, 2026

Copilot finished work on behalf of pethers March 30, 2026 01:10

Copilot AI requested a review from pethers March 30, 2026 01:10

pethers marked this pull request as ready for review March 30, 2026 01:10

Copilot AI review requested due to automatic review settings March 30, 2026 01:10

pethers merged commit 7438a98 into main Mar 30, 2026
14 checks passed

pethers deleted the copilot/improve-analysis-methods-templates branch March 30, 2026 01:10

Copilot started reviewing on behalf of pethers March 30, 2026 01:11 View session

Copilot AI reviewed Mar 30, 2026

View reviewed changes

Conversation

Copilot AI commented Mar 30, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

SHARED_PROMPT_PATTERNS.md

ai-driven-analysis-guide.md (v1.0 → v1.1)

All 11 news workflows

All 8 analysis templates

Uh oh!

github-actions bot commented Mar 30, 2026

🏷️ Automatic Labeling Summary

Label Categories

Uh oh!

github-actions bot commented Mar 30, 2026

🔍 Lighthouse Performance Audit

Uh oh!

github-actions bot commented Mar 30, 2026

🔍 Lighthouse Performance Audit

Uh oh!

github-actions bot commented Mar 30, 2026

🔍 Lighthouse Performance Audit

Uh oh!

github-actions bot commented Mar 30, 2026

🔍 Lighthouse Performance Audit

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Mar 30, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Copilot AI commented Mar 30, 2026 •

edited

Loading