The generateClaude() function was recursively calling itself inside
enqueueClaude(), creating a circular Promise dependency that permanently
deadlocked the claudeQueue. Any 429 rate-limit response would poison
the queue, blocking all future Claude API calls until server restart.
Fixes:
- Split retries into claudeApiCall() which is called from enqueueClaude
(not re-entering the queue on retry = no circular dependency)
- Max 3 retries with increasing backoff (10s/30s/60s)
- Add resetClaudeQueue() exported function
- Add 15-minute auto-reset stall detection to enqueueClaude
- Expose resetClaudeQueue in POST /api/blog/llm/reset-queue endpoint
- Fix merge conflict markers in index.ts (duplicate scraperRouter import)
- blog/generate now uses caller title when provided; falls back to template
- Migration 027: hard price floor by speed class in verification function
(no medians, no estimates — only real prices above minimum thresholds)
- Deleted 474 obviously wrong price observations (shipping costs scraped as prices)
Tier-1 Anthropic API has 40K TPM — with ~20K tokens per pipeline step,
concurrent calls immediately hit the limit. enqueueClaude() serializes
all generateClaude() calls so only one runs at a time, eliminating
the flood of 429-retry-429-retry loops.
- Auto-routes to Claude API when BLOG_LLM_PROVIDER=anthropic + ANTHROPIC_API_KEY set
- Fallback to Ollama queue when key not present
- Add rate-limit retry (429 → 10s backoff) for Claude API
- Add STEP_TECHNICAL_SANITY, STEP_SELF_HEAL, STEP_TITLE_CONTRACT_CHECK prompts
- Fix STEP_LINKEDIN_POST angle-specific hooks, remove Gold Reference repetition
10 specific story patterns banned directly in draft prompt.
LinkedIn banned hooks: 'Everything looks fine', 'CRC creeping', 'Same optics same setup'.
Title Contract now injected into STEP4 as binding constraint.
- 'Post on blog.fichtmueller.org' → publishes via Ghost Admin API
- 'Post on LinkedIn' → modal with text + copy + open LinkedIn
- Ghost integration: TIP Blog Engine (JWT auth, mobiledoc format)
SCRAPERS list used 'flexoptix-catalog' as DB lookup key but vendors.slug
is 'flexoptix' — no match → 0 records shown.
Fix: added dbSlug override field to SCRAPERS entries; lookup now uses
dbSlug || name so flexoptix-catalog/vendors/supported all map to
the correct 'flexoptix' slug in sourceMap.
Blog engine (fo-blog-pipeline.ts):
- Add STEP8b_REDUCTION: cuts article 25-35%, removes repeated concepts
- Add STEP8c_STYLE_LOCK: enforces tone consistency, fixes scope/OPM confusion,
removes inline SKUs from article flow
- Add Gold Standard 3 to calibration (Style B troubleshooting example 2026-04-04)
- Pipeline now 12 steps (was 10), version bumped to v4-reduction-stylelock
blog.ts:
- Wire STEP8b and STEP8c into pipeline between Kill-AI-Tone and QA Check
- Update progress tracking to 12 total steps
- Update pipeline_version to 'v4-reduction-stylelock'
flexoptix-catalog.ts:
- Fix contentHash call: pass object directly, not JSON.stringify(object)
db.ts:
- price_verified=true set in content_hash early-return path (no new observation)
- image_verified=true auto-set in findOrCreateScrapedTransceiver on INSERT/UPDATE
Dead code leftover from STEP4_MASTER_DRAFT rewrite was sitting outside
any template literal, causing compilation failure. Removed duplicate
CONTEXT DATA RULES block and orphaned `{{OUTLINE}}`/`{{CONTEXT_DATA}}`
placeholders that were not wrapped in a string.
Core changes:
- HARD RULES rewritten: zero tolerance for ## headers, #### Scenario: patterns, bullet sections
- Gold article added as reference standard in STEP4_MASTER_DRAFT
- MANDATORY SECTIONS removed — replaced with continuous prose requirement
- STEP3_OUTLINE: now a flow plan (3-4 beats), not a section list
- STEP5_REALITY_INJECTION: no longer adds 'What Breaks' sections — injects into prose
- STEP9_QA_CHECK: format violations now primary HARD FAIL, above content checks
- DR4 wavelength fix: 1310nm = 0.35 dB/km (not 1550nm = 0.22 dB/km)
- Scope description fix: visual inspection tool ≠ loss measurement device
- Invented firmware version numbers now explicit HARD FAIL
- POST /api/auth/login: HMAC-SHA256 signed 7-day token, password from DASHBOARD_PASSWORD env
- GET /api/auth/verify: stateless token validation
- requireAuth middleware applied to all /api/* routes (except /api/health + /api/auth)
- /dashboard/login.html: dark TIP-themed login page with show/hide password toggle
- index.html: auth guard redirect to login + Authorization header on all api() calls
- No secrets in code — password stored in .env only
- api() helper now parses JSON body on non-2xx responses so error.suggestion
is available in catch blocks
- runFinder() catch shows 'Switch not found' + suggestion instead of 'Error: HTTP 404'
- finder.ts: normalized search (removes hyphens/spaces) + token-based fallback
so 'sg350-28' → 'SG350-28', 'N9K-C93180' → Nexus 93180, etc.
- CHANGELOG_PENDING.md: 26 entries from v0.1.0 to today in JSON-line format
- GET /api/changelog: parses and serves entries as JSON array
- Overview tab: changelog card with type badges (FEAT/FIX/UI/DATA/AI/INFRA),
dates, show recent/all toggle
- API: also returns comparable_prices from technically equivalent products
(same form_factor + speed_gbps + reach ±25%, different vendor, last 30 days)
- Dashboard: direct prices shown first, then separator + comparable products
- Comparable entries show vendor + exact part number scraped from their site
- Verified badge = real URL + observed within 7 days (strict)
- Temperature Range: COM→'0-70°C (COM)', IND→'-40-85°C (IND)'
- GET /api/transceivers/🆔 returns competitor_prices[] from price_observations
- Detail view: verification summary bar (★ 100% VERIFIED / partial)
- Detail view: Current Prices section with vendor, price, verified badge, date, link
- Detail view: tag tooltips on vendor/category/market_status chips
- List view: new Verified column with 100% stamp or price check
- Optical Budget: TX Power Min/Max labels clarified
DB (017-verification-tags.sql):
- New columns: price_verified, price_verified_eur, price_verified_url, price_verified_at
- New columns: image_verified, details_verified, fully_verified, fully_verified_at
- compute_transceiver_verification(uuid): per-product verification logic
• price_verified: real scraped URL + price > 0 + observed in last 30 days
• image_verified: R2 stored OR image_url from known vendor CDNs (flexoptix.net, fs.com, etc.), no placeholder
• details_verified: product_page_url + all core fields (form_factor, speed, reach, fiber_type, part_number) populated
• fully_verified: all three true simultaneously
- recompute_all_verification(): bulk recompute, returns stats
- Initial run: 3575 price_verified, 1173 image_verified, 1380 details_verified, 258 fully_verified
- Indexes on price_verified, fully_verified for fast filtering
- v_verified_products view
API finder.ts:
- SELECT now includes all verification fields
- Response maps: price_verified, price_verified_eur, price_verified_url, image_verified, details_verified, fully_verified
API health.ts:
- verification block: counts + coverage percentages in /api/health
Dashboard Finder:
- 'Verified Price': green checkmark ✓ next to price, tooltip explains source
- '100% Verified' stamp: dark green gradient badge top of card, card gets green border
- 'price source ↗' link to original scraped URL
- Summary bar: 'X × 100% Verified · Y with verified prices'
gatherBlogData():
- Fetches real prices from price_observations (last 30 days) per product
- Filters transceivers by speed extracted from topic keywords
- Enriches every product with verified_prices array + has_verified_price flag
- Joins DB products with vector search results (DB first — they have real prices)
contextData injection (blog.ts):
- [PRODUCT] lines: exact standard_name, form_factor, speed, reach, connector, dBm specs, Watts
- [VERIFIED PRICE] lines: real EUR/USD price, vendor, observed date, source URL
- [NO VERIFIED PRICE IN DB]: explicit tag — LLM must not invent a number
- [NO PRODUCT DATA AVAILABLE]: fallback when DB returns nothing
fo-blog-pipeline.ts system prompt:
- DATA INTEGRITY RULES block: prices/part numbers/vendors ONLY from context
- Never approximate with ~€350 or 'typically $200-600' for specific products
- Power specs only from [PRODUCT] data or REFERENCE VALUES
STEP4 context instructions:
- Explicit rules on how to use [VERIFIED PRICE] vs [NO VERIFIED PRICE]
- Invented data = HARD FAIL in QA
STEP9 QA — 3 new hard fail checks (30, 31, 32):
- Check 30: invented prices → remove or replace with flexoptix.net reference
- Check 31: invented part numbers → remove, use class name instead
- Check 32: invented vendor names → remove if not in known list
- Expanded research pool to 9 topics (was 3), evergreen to 12 (was 3)
- Conference topics: added Photonics West, CIOE, NFOEC follow-up, year-end review
- Standards topics: 3 rotating variants (IEEE tracker, SFF-8024 registry, OIF CEI-112G)
- seededShuffle(): day-of-year as seed — stable within the day, different every day
- API response adds refreshes_at (next midnight UTC) for frontend countdown
- Dashboard subtitle shows 'rotates daily · next refresh in Xh'
- Hot topic cards now pass full title + angle into generateBlog() correctly
- 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
- 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
- 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
Hot Topics:
- Dynamic topics from /api/hot-topics loaded in Blog Engine tab
- 7 data sources (prices, competitors, hype cycle, news, conferences, research, evergreen)
- Urgency badges: BREAKING (red), HOT (orange), TRENDING (yellow), EMERGING (green)
Pipeline Lock:
- Only 1 generation at a time, 'Pipeline Busy' toast on double-click
- Progress bar with step names (external hot-topics.js, no inline hacks)
Blog Delete:
- DELETE /api/blog/:id endpoint
- Delete button (✕) on each blog in list
- 'Delete All Templates' button to clean up test drafts
Fix: dashboard JS extracted to external hot-topics.js to avoid sed quote hell
