6 Commits

Author SHA1 Message Date
Rene Fichtmueller
58751b896d blog: calibration v5 — anti-consulting-prose, correct loss budget math, vendor lock-in specifics 2026-03-31 21:26:39 +02:00
Rene Fichtmueller
a2ce024a18 blog: calibration v4 — technical accuracy + structure limits
- Fix SR4/DR4 fiber count: both use 8 fibers (4TX+4RX), difference is MMF vs SMF
- Fix power per port: 400G=10-15W/port, 800G=15-25W/port (not 1kW/port)
- Fix pricing context: always distinguish OEM ($1-5K) vs compatible ($200-600)
- Add HARD RULES 15-21: fiber count, power, pricing, no markdown headers,
  max 6 sections, no repeated topics, flow over format
- Add QA CALIBRATION FAILS 16-21: same rules enforced at QA step
- Add fiber/power reference tables with correct values
- Strip markdown (##/###/####/**) from all output — plain text only
- Add Style B gold example (10/10 validated prose article)
- Update STEP5 reality injection with correct SR4→DR4 description
- Update STEP8 kill-AI-tone to strip markdown headers + merge duplicates
2026-03-31 17:27:51 +02:00
Rene Fichtmueller
68ef15a8fa feat(blog): add Style B prose calibration — 10/10 narrative flow standard
- CALIBRATION_GOLD_STANDARD now covers two validated styles: A (structured) and B (prose)
- Style B: no headers, no bullets, 1-3 sentence paragraphs, reframe ending
- STEP8_KILL_AI_TONE: prose conversion option for over-structured articles
- STEP4_MASTER_DRAFT: explicit style choice instruction (A vs B based on angle)
- Gold standard includes exact prose rhythm patterns from 10/10 human-reviewed article
- Wrong patterns expanded: symmetric sections, checklist endings, transition clichés
2026-03-31 16:48:10 +02:00
Rene Fichtmueller
c7b6351e26 feat(blog): regenerate button, SEO hashtags, calibration engine v2
- POST /api/blog/:id/regenerate — re-runs full 10-step LLM pipeline on existing draft
- Regenerate button visible when quality_issues present or status=review
- SEO keywords now displayed as clickable #hashtags (copy-to-clipboard)
- fo-blog-pipeline: added PoE misuse, DR4 mislabeling, ZR/DR4 conflation as hard QA fails
- fo-blog-pipeline: 14 hard rules in system prompt (was 10)
- fo-blog-pipeline: CALIBRATION_GOLD_STANDARD + withCalibration() from 10/10 human review
- System prompt now includes gold standard example on every pipeline run
2026-03-31 16:46:25 +02:00
Rene Fichtmueller
aa5d03bcf8 fix(blog): harden pipeline prompts based on v0.2.1 blog review feedback
System prompt: 10 HARD RULES (non-negotiable, article fails QA without them)
- Mandatory WHAT BREAKS IN PRODUCTION section (2+ specific failures with symptoms/cause/fix)
- Mandatory HIDDEN COSTS section (cleaning, troubleshooting time, cabling redesign, training)
- Mandatory WHEN NOT TO USE section for every recommendation
- Absolute statement rule: NEVER without conditions/context
- Cabling reality: MPO polarity, SR4→DR4 migration, cleaning requirements
- Brutal hook requirement: not 'If you're still...' but 'You're about to sign a PO. Stop.'
- Minimum 2500 words (was 2000)

Step 5 (Reality Injection): Now checks for ALL mandatory sections and adds if missing
Step 9 (QA Check): Hard fail checks — article is NOT publishable without production failures + hidden costs
Feedback source: Human expert review scoring 7.5/10, targeting 9.5+
2026-03-31 09:24:08 +02:00
Rene Fichtmueller
73ef5766e6 feat(v0.2.1): data confidence tracking + validation + blog feedback system
- Migration 016: data_confidence column (vendor_verified/enriched_estimated/scraped_unverified)
- Migration 015: blog_feedback table with 8 quality scores + free text
- Validation script: 8 physics-based rules (wavelength↔fiber, reach plausibility, power limits)
- Blog feedback API: POST /api/blog/:id/feedback + training data export
- FO Blog Pipeline v3: 10-step Flexoptix Style prompts (Less bullshit. More engineering.)
- Auto-fix: wavelength↔fiber mismatches corrected automatically
2026-03-31 09:12:37 +02:00