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

packages/api/src/llm/fo-blog-pipeline.ts

@@ -199,7 +199,14 @@ STYLE:
 - Specific transceiver types (SR4, DR4, LR4, FR4, ZR) with REAL problems, not just specs
 - Real numbers (dBm, watts, $/port, €/Gbit, $/year power cost)
 
-MINIMUM 2500 words. No placeholders. No TODO markers. Complete article.
+STYLE CHOICE:
+Two valid output formats — pick based on the outline's angle and audience:
+- STYLE A (structured): Use headers, specific failure scenarios, bullet lists where needed. Best for troubleshooting guides, migration how-tos, deep dives.
+- STYLE B (prose narrative): No headers after the title, no bullet points, pure flowing paragraphs (1-3 sentences each). Best for roundups, opinion pieces, "state of the technology" takes. The ending MUST be a single reframe sentence, not a list.
+
+Both styles are 10/10 valid. Choose the one that fits the angle selected in the outline.
+
+MINIMUM 2000 words. No placeholders. No TODO markers. Complete article.
 
 Outline:
 {{OUTLINE}}
@@ -302,6 +309,8 @@ REMOVE:
 - Lists that all follow identical format
 - Perfect grammar everywhere — add occasional conversational shortcuts
 - Phrases like "it is important to note", "one should consider"
+- Any section that ends with a tidy 4-item bullet list
+- Perfectly symmetrical sections (same length = AI fingerprint)
 
 REPLACE WITH:
 - Natural, slightly imperfect flow
@@ -310,6 +319,15 @@ REPLACE WITH:
 - Direct address ("You know this is true if...")
 - Specific instead of generic ("the Nexus 93180 in rack 14" not "your network switch")
 
+PROSE STYLE OPTION (use when article currently feels too structured/sectioned):
+If the article has many headers and bullet points and reads like a slide deck, consider
+converting major sections to flowing prose paragraphs instead.
+A validated 10/10 prose rhythm:
+  - 1-3 sentences per paragraph, then line break
+  - Short punchy sentences after a buildup: "It isn't.", "It usually does that at the worst possible time."
+  - No bullet points — everything as prose
+  - Ending is a one-liner reframe: "Because 400G itself isn't the risk. Your assumptions are."
+
 The article should read like a human engineer wrote it during a long flight.
 Keep it clear and professional, but natural.
 
@@ -488,37 +506,53 @@ export function buildFeedbackContext(feedback: Array<{ score: number; feedback_t
 // ═══════════════════════════════════════════════════════
 
 export const CALIBRATION_GOLD_STANDARD = `
---- GOLD STANDARD REFERENCE (10/10 — calibrate your output to this level) ---
+--- GOLD STANDARD REFERENCE (10/10 — two validated styles) ---
 
-KEY STRUCTURAL PATTERNS from a 10/10 article:
+TWO VALID WRITING STYLES — choose based on topic complexity:
 
-HOOK (correct):
+━━━ STYLE A: STRUCTURED (sections, some bullets, headers) ━━━
-"You're sitting in front of a quote for a few hundred 400G optics. Everything looks clean on paper. Bandwidth solved. Future-proof. Done.
+Use for: deep dives, migration guides, troubleshooting tutorials
-That's usually the moment where things start going wrong."
+Key patterns:
+  HOOK: "You're about to sign a PO for 200 optics. The vendor quote is on your desk. Before you sign — read this."
+  WHAT BREAKS: short scenario blocks — "Cause: wrong MPO polarity. Fix: flip the key on one end."
+  ENDING: "400G doesn't fail in design. It fails in production. Fast."
+  HIDDEN COSTS (raw): "That $350 optic turned into a multi-thousand-dollar problem because someone skipped the connector cleaning."
+  CABLING: "SR4 to DR4 migration is where budgets go to die. Wrong patch panels, wrong polarity, wrong assumptions."
 
-WHAT BREAKS (correct — short, direct, no padding):
+━━━ STYLE B: PROSE (no headers, no bullets, pure narrative flow) ━━━
-"Works in lab, fails in production
+Use for: opinion pieces, roundups, market analysis, "state of the technology" articles
-Classic.
+This style was 10/10 rated with this exact structure:
-Lab: single vendor, short patch, clean environment.
-Production: mixed optics, different firmware, real distances.
-Result: CRC errors, unstable links, weird flaps."
 
-HIDDEN COSTS (correct — raw, not sanitized):
+  "You're sitting there, staring at a quote for a couple hundred 400G optics. Pricing looks decent, vendor says it's all production-ready, future-proof, industry standard — the usual story.
-"That 'cheap' optic? Turns into a multi-thousand-euro problem because someone didn't clean a connector. At 400G, contamination isn't a quality issue. It's a service outage."
+  And to be fair: they're not wrong.
+  400G works. It's stable. It's deployed everywhere.
+  But that's also exactly where people get burned — because they assume 'works' means 'easy'.
+  It's not."
 
-CABLING REALITY (correct):
+  Key rhythm: very short paragraphs (1-3 sentences). Line breaks as breathing room.
-"SR4 to DR4 migration is where budgets go to die. Wrong patch panels, wrong polarity, wrong assumptions. You end up re-cabling things you thought were ready."
+  No bullet points anywhere. No numbered sections.
+  Conversational asides that set up the next thought: "And that's usually the moment where deployments slow down."
+  Reframe at the end — not a summary, a shift in perspective:
+    "None of this means you shouldn't deploy it. Quite the opposite."
+    [builds to...]
+    "Because 400G itself isn't the risk. Your assumptions are."
 
-ENDING (correct — hits and stops):
+STYLE B RHYTHM RULES:
-"400G is not risky because it's new. It's risky because people underestimate what actually changes.
+- One thought per paragraph
-If your design only works on paper, it will fail in production. And 400G fails fast."
+- Never more than 3 sentences in a row without a break
+- Short declarative sentences after a build-up: "It isn't.", "And it usually does that at the worst possible time."
+- The ending is a one-liner that reframes everything: not a conclusion, a punch
+- NEVER end Style B with a list or action items — just the thought that sticks
 
-WRONG PATTERNS (do not produce these):
+WRONG PATTERNS (both styles — never produce):
 ❌ "Thoroughly Test Your PoE Budget:" (PoE = wrong context, checklist = wrong format)
-❌ "QSFP-DD DR4 (Direct Attach)" (DR4 ≠ Direct Attach)
+❌ "QSFP-DD DR4 (Direct Attach)" (DR4 ≠ Direct Attach — DAC is Direct Attach Copper)
-❌ "DR4 and ZR both push boundaries..." (they serve completely different use cases)
+❌ "DR4 and ZR both push boundaries..." (completely different use cases, always separate)
 ❌ "Don't be swayed by shiny new toys" (marketing speak, not engineer voice)
-❌ 4-item bullet recommendation at end (too clean, too AI)
+❌ 4-item bullet recommendation at end of any article
+❌ Ending with "consider your options carefully" or any variant of that
+❌ Starting a new paragraph with "Furthermore", "Additionally", "It's worth noting"
+❌ Perfectly symmetrical sections (every section same length = AI fingerprint)
 
 --- END GOLD STANDARD ---
 `;