diff --git a/CHANGELOG_PENDING.md b/CHANGELOG_PENDING.md
index 3a76731..fae3c6c 100644
--- a/CHANGELOG_PENDING.md
+++ b/CHANGELOG_PENDING.md
@@ -4,6 +4,11 @@ Format: `{"d":"YYYY-MM-DD","t":"TYPE","m":"Description"}`
 {"d":"2026-04-26","t":"DATA","m":"Juniper OEM transceiver seed: 59 PIDs inserted (SFP-1GE/SFPP-10G/SFP-25G/QSFPP-40G/JNP-QSFP-100G/JNP-QSFP56-200G/JNP-QSFPDD-400G/JNP-OSFP-400G+800G + DAC/AOC). Scheduler: daily 04:15."}
 {"d":"2026-04-26","t":"FIX","m":"BlueOptics scraper: force HTTP/1.1 via Node.js https.get() to bypass empty-body HTTP/2 server bug; updated catalog path to /Transceivers_1 (changed 2026)."}
 {"d":"2026-04-26","t":"DATA","m":"Cisco TMG scraper: upsert logic fixed (market_status EOL + temp_range IND normalization). Full run in progress: 300+ switches, 15000+ compat matches written to switch_transceiver_compat."}
+{"d":"2026-04-28","t":"INFRA","m":"Gitea repo tip-training-data created (https://gitea.context-x.org/rene/tip-training-data). Generated full-scope token via gitea admin CLI on 192.168.178.196."}
+{"d":"2026-04-28","t":"AI","m":"crawler-llm/spec-validator.ts: transceiver physical plausibility validator — form factor↔speed matrix, wavelength↔fiber consistency, reach limits, IEEE standard cross-check, DAC/AOC rules. Outputs SpecValidationResult with tier (high/medium/low/rejected) + confidence_delta."}
+{"d":"2026-04-28","t":"AI","m":"crawler-llm/training-data-writer.ts: TIPLLM SFT training data writer — generates spec_qa/crawl_reasoning/validation/discovery JSONL pairs from crawler extractions, git-commits and pushes to Gitea tip-training-data repo in batches of 50."}
+{"d":"2026-04-28","t":"AI","m":"crawler-llm/vendor-discovery-crawler.ts: intelligent PlaywrightCrawler — vendor catalog URL → LLM extraction (core.ts) → spec validation → DB persist (findOrCreateScrapedTransceiver) + Gitea SFT training pairs. 8 vendor configs: Cisco/Juniper/Arista/FS.com/Flexoptix/Nokia/Huawei/II-VI."}
+{"d":"2026-04-28","t":"INFRA","m":"scheduler.ts: 8 weekly vendor discovery jobs registered (discover:vendor:*), staggered Sun 20:00 – Mon 10:00 UTC. Total workers: 102."}
 Types: FEAT · FIX · UI · DATA · AI · INFRA
 
 {"d":"2026-04-25","t":"FEAT","m":"Standards Audit + Form Factors Reference: expanded standards from 40 to 63 (+23 new: full 200G tier SR4/DR4/FR4/LR4/ER4/CR4, PON family GPON/XG-PON1/NG-PON2/25G-PON, copper DAC variants CR4 for 25G/40G/100G/400G, 800G emerging FR4/LR8/CR8, 1.6TBASE-DR16 emerging). All 63 standards have bilingual plain-language descriptions (DE+EN, for non-technical colleagues). New form_factors table (migration 101) with 20 entries: SFP family SFP→SFP112, QSFP family QSFP+→QSFP-DD800, OSFP family OSFP→OSFP224, CFP family, legacy XFP/CXP — with full names, channel count, max speed, hot-swap flag, supersedes chain, status, and bilingual descriptions. New GET /api/form-factors endpoint. Dashboard Standards tab: descriptions shown as table row subtitles, Form Factors grid section with family color coding, speed/channel info, openFormFactorDetail panel."}
@@ -268,3 +273,11 @@ Types: FEAT · FIX · UI · DATA · AI · INFRA
 {"d":"2026-04-21","t":"DATA","m":"Dell N3248TE-ON (networktigers) + S5248F-ON/S5296F-ON (i.dell.com Scene7 CDN) + Z9332F-ON/Z9664F-ON (expresscomputersystems Shopify) + Extreme Networks 8720-32C+X465-48P (sitecorecontenthub.cloud official CDN): migration 070. 7 models, all HTTP 200 verified."}
 {"d":"2026-04-21","t":"DATA","m":"HPE Aruba CX 6300M-48G/8100-48Y6C/8360-32Y4C (blueally.com partner CDN) + Ubiquiti USW-EnterpriseXG-24/Pro-Aggregation/Pro-Max-48-PoE (cdn.ecomm.ui.com official) + Supermicro SSE-C4632SRB/SSE-T7132SR (wiredzone.com): migration 071. 8 models, all HTTP 200 verified."}
 {"d":"2026-04-21","t":"DATA","m":"Celestica DS3000/DS4000/DS5000 (foleon.com Celestica CDN) + Asterfusion CX308P-48Y-N/CX532P-N/CX864E-N (asterfusion.com WP + cloudswit.ch) + FS.com N8560-32C/S5860-48SC (resource.fs.com) + Edgecore DCS810/EPS203 (edge-core.com WP): migration 072. 10 models, all HTTP 200 verified."}
+{"d":"2026-04-26","t":"DATA","m":"OEM seed scrapers batch 1-20: keysight(25), sycamore(17), ekinops(18), adva(19), coriant(17), casa-systems(22), harmonic(23), solarflare(25), marvell(26), broadcom(23), calix-access(20), ribbon-comms(20), infinera-groove(20), ciena-waveserver(22), commscope(20), teleste(19), tejas-networks(19), ericsson-transport(20), adtran-ta(20), isolan(18). Scheduler daily 20:00-00:45."}
+{"d":"2026-04-26","t":"DATA","m":"OEM seed scrapers batch 21-40: telco-systems(18), rad(20), comtrend(18), packetfront(18), edgewater-networks(16), corning(18), ofs(18), kontron(18), ipinfusion(18), telrad(16), siklu(16), ceragon(16), datang(16), viptela(16), versa-networks(16), vmware(16), cimc(18), qlogic(20), emulex(18), netapp(20). Scheduler daily 01:00-05:45."}
+{"d":"2026-04-26","t":"DATA","m":"OEM seed scrapers batch 41-60: pure-storage(16), hpe-storage(20), ibm-storage(20), dell-storage(18), hitachi-vantara(16), aws(16), azure(16), google-cloud(16), meta(16), nokia-access(20), huawei-access(20), zte-access(18), calix-gigapoint(16), samsung-networks(16), nokia-airscale(16), ericsson-ran(16), mavenir(14), ixia(18), exfo-network(18), cumulus-networks(16). Scheduler daily 06:00-10:45."}
+{"d":"2026-04-26","t":"DATA","m":"OEM seed scrapers batch 61-80: sonic(16), h3c(20), ruijie(17), centec(16), supermicro(18), cisco-meraki(18), cisco-catalyst(20), cisco-nexus(20), cisco-asr(20), juniper-mx(20), juniper-qfx(20), aruba-cx(18), extreme-campus(18), arista-7000(20), pica8(16), pluribus(14), drivenets(15), phoenix-contact(18), beckhoff(16), omron(16). Scheduler daily 11:00-15:45."}
+{"d":"2026-04-26","t":"DATA","m":"OEM seed scrapers batch 81-84: abb(16), siemens-scalance(18), schneider(16), rockwell(16), belden(16). Industrial category. Scheduler daily 16:00-17:00."}
+{"d":"2026-04-26","t":"FEAT","m":"tip-llm-guided.ts: Structured inference engine for tip-llm-v1. Hard JSON schema, per-field validation, 2-retry repair loop with diff prompt, safe default fallback (create_finding=false). Temperature 0.1→0.05 on retry. Routes: POST /api/tip-llm/infer|research-plan|extract|finding, GET /api/tip-llm/health."}
+{"d":"2026-04-28","t":"FIX","m":"Product verification pipeline: image crawls now mark image_verified/image_verified_url, scraped product pages mark details_verified/details_source_url, maintenance reconcile backfills old product URLs/images/details, and --backfill-images exposes the existing image crawler via scraper CLI. Migration 102 reconciles existing data."}
+{"d":"2026-04-28","t":"FIX","m":"Blog Engine Hot Topics: diversified ranking with refresh shuffle/source caps/already-created-topic demotion, plus richer LLM context briefings passed into topic expansion and master-draft context via custom_title/additional_context."}
diff --git a/packages/scraper/src/crawler-llm/spec-validator.ts b/packages/scraper/src/crawler-llm/spec-validator.ts
new file mode 100644
index 0000000..4a18739
--- /dev/null
+++ b/packages/scraper/src/crawler-llm/spec-validator.ts
@@ -0,0 +1,373 @@
+/**
+ * Crawler LLM — Transceiver spec physical plausibility validator.
+ *
+ * Runs AFTER LLM extraction to catch technically impossible combinations
+ * (e.g. 100G over SFP, 850nm on SMF, 80km over MMF). Complements
+ * validator.ts which checks stock/price sanity.
+ *
+ * Returns a SpecValidationResult with:
+ *   - passed: false blocks DB write and lowers training data confidence tier
+ *   - warnings: still writes to DB but flags for human review
+ *   - confidence_delta: adjustment applied to the LLM confidence score
+ */
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Type definitions
+// ─────────────────────────────────────────────────────────────────────────────
+
+export interface ExtractedSpec {
+  part_number?: string | null;
+  form_factor?: string | null;
+  speed_gbps?: number | null;
+  reach_meters?: number | null;
+  fiber_type?: string | null;    // "SMF" | "MMF" | "CU" | "DAC" | "AOC"
+  connector?: string | null;
+  wavelengths?: string | null;   // e.g. "850nm" or "1310nm TX / 1490nm RX"
+  ieee_standard?: string | null; // e.g. "100GBASE-SR4"
+  dom_support?: boolean | null;
+}
+
+export interface SpecValidationResult {
+  passed: boolean;
+  errors: string[];
+  warnings: string[];
+  confidence_delta: number;   // negative = reduce LLM confidence score
+  tier: "high" | "medium" | "low" | "rejected";
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Compatibility tables
+// ─────────────────────────────────────────────────────────────────────────────
+
+/** Max rated speed per form factor (Gbps).  DAC/AOC = same form factor shell. */
+const FORM_FACTOR_MAX_SPEED: Record<string, number> = {
+  "GBIC":     1,
+  "SFP":      4.25,   // 4G FC max; 1G Ethernet common
+  "SFP+":     28.05,  // nominally 10G but 16G FC / 25G variants exist
+  "SFP28":    28.05,
+  "SFP56":    56,
+  "SFP-DD":   100,    // dual-lane SFP
+  "QSFP":     40,
+  "QSFP+":    40,
+  "QSFP28":   112,    // 4×25G = 100G; some push 112G
+  "QSFP56":   224,    // 4×56G = 200G
+  "QSFP-DD":  800,    // 8×100G
+  "QSFP112":  800,
+  "OSFP":     800,
+  "OSFP-RHS": 800,
+  "CFP":      100,
+  "CFP2":     400,
+  "CFP4":     100,
+  "CFP8":     400,
+  "XFP":      10,
+  "X2":       10,
+  "XENPAK":   10,
+  "DSFP":     100,
+  "CSFP":     2.5,
+};
+
+/** Min rated speed per form factor (Gbps). Catches wild mismatches. */
+const FORM_FACTOR_MIN_SPEED: Record<string, number> = {
+  "GBIC":    0.1,
+  "SFP":     0.1,
+  "SFP+":    1,
+  "SFP28":   10,
+  "SFP56":   25,
+  "SFP-DD":  50,
+  "QSFP":    4,
+  "QSFP+":   10,
+  "QSFP28":  40,
+  "QSFP56":  100,
+  "QSFP-DD": 100,
+  "QSFP112": 200,
+  "OSFP":    200,
+  "OSFP-RHS":200,
+  "CFP":     10,
+  "CFP2":    40,
+  "CFP4":    10,
+  "CFP8":    100,
+  "XFP":     10,
+  "X2":      10,
+  "XENPAK":  10,
+  "DSFP":    25,
+  "CSFP":    0.1,
+};
+
+/**
+ * Wavelength → expected fiber type.
+ * 850 nm is classically MMF; 1270–1610 nm is SMF.
+ * Exceptions: some 1310nm SFP (1000BASE-LX) work on MMF with mode-conditioning.
+ */
+function expectedFiberForWavelength(nm: number): "MMF" | "SMF" | "either" {
+  if (nm <= 900) return "MMF";
+  if (nm >= 1260) return "SMF";
+  return "either";
+}
+
+/** Max practical reach per fiber type (meters). Soft sanity limit. */
+const MAX_REACH: Record<string, number> = {
+  MMF: 4000,    // OM5 push ~3.5km; 4km is outer limit for 100M FX
+  SMF: 200_000, // 200km coherent ZR is real
+  CU:  100,
+  DAC: 30,
+  AOC: 200,
+};
+
+/** Known IEEE standards and their canonical speed (Gbps) + form factor hints */
+const IEEE_STANDARDS: Record<string, { speedGbps: number; fiberType?: string; reachKm?: number }> = {
+  "100BASE-FX":    { speedGbps: 0.1,  fiberType: "MMF",  reachKm: 2 },
+  "100BASE-LX10":  { speedGbps: 0.1,  fiberType: "SMF",  reachKm: 10 },
+  "1000BASE-SX":   { speedGbps: 1,    fiberType: "MMF",  reachKm: 0.55 },
+  "1000BASE-LX":   { speedGbps: 1,    fiberType: "SMF",  reachKm: 10 },
+  "1000BASE-EX":   { speedGbps: 1,    fiberType: "SMF",  reachKm: 40 },
+  "1000BASE-ZX":   { speedGbps: 1,    fiberType: "SMF",  reachKm: 80 },
+  "1000BASE-T":    { speedGbps: 1,    fiberType: "CU" },
+  "10GBASE-SR":    { speedGbps: 10,   fiberType: "MMF",  reachKm: 0.3 },
+  "10GBASE-LR":    { speedGbps: 10,   fiberType: "SMF",  reachKm: 10 },
+  "10GBASE-ER":    { speedGbps: 10,   fiberType: "SMF",  reachKm: 40 },
+  "10GBASE-ZR":    { speedGbps: 10,   fiberType: "SMF",  reachKm: 80 },
+  "25GBASE-SR":    { speedGbps: 25,   fiberType: "MMF",  reachKm: 0.1 },
+  "25GBASE-LR":    { speedGbps: 25,   fiberType: "SMF",  reachKm: 10 },
+  "25GBASE-ER":    { speedGbps: 25,   fiberType: "SMF",  reachKm: 40 },
+  "40GBASE-SR4":   { speedGbps: 40,   fiberType: "MMF",  reachKm: 0.15 },
+  "40GBASE-LR4":   { speedGbps: 40,   fiberType: "SMF",  reachKm: 10 },
+  "40GBASE-ER4":   { speedGbps: 40,   fiberType: "SMF",  reachKm: 40 },
+  "100GBASE-SR4":  { speedGbps: 100,  fiberType: "MMF",  reachKm: 0.1 },
+  "100GBASE-SR10": { speedGbps: 100,  fiberType: "MMF",  reachKm: 0.15 },
+  "100GBASE-LR4":  { speedGbps: 100,  fiberType: "SMF",  reachKm: 10 },
+  "100GBASE-ER4":  { speedGbps: 100,  fiberType: "SMF",  reachKm: 40 },
+  "100GBASE-ZR":   { speedGbps: 100,  fiberType: "SMF",  reachKm: 80 },
+  "400GBASE-SR4":  { speedGbps: 400,  fiberType: "MMF",  reachKm: 0.1 },
+  "400GBASE-SR8":  { speedGbps: 400,  fiberType: "MMF",  reachKm: 0.1 },
+  "400GBASE-LR4":  { speedGbps: 400,  fiberType: "SMF",  reachKm: 10 },
+  "400GBASE-LR8":  { speedGbps: 400,  fiberType: "SMF",  reachKm: 10 },
+  "400GBASE-ER8":  { speedGbps: 400,  fiberType: "SMF",  reachKm: 40 },
+  "400GBASE-ZR":   { speedGbps: 400,  fiberType: "SMF",  reachKm: 80 },
+  "400ZR":         { speedGbps: 400,  fiberType: "SMF",  reachKm: 120 },
+  "800GBASE-SR8":  { speedGbps: 800,  fiberType: "MMF",  reachKm: 0.1 },
+  "800GBASE-LR4":  { speedGbps: 800,  fiberType: "SMF",  reachKm: 2 },
+};
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Helpers
+// ─────────────────────────────────────────────────────────────────────────────
+
+/** Parse first numeric wavelength from a string like "850nm" or "1310nm TX / 1490nm RX" */
+function parsePrimaryWavelength(wl: string): number | null {
+  const match = wl.match(/(\d{3,4})\s*nm/);
+  return match ? parseInt(match[1], 10) : null;
+}
+
+function normalizeFormFactor(ff: string): string {
+  return ff.trim().toUpperCase().replace(/\s+/g, "");
+}
+
+function normalizeStandard(s: string): string {
+  return s.trim().toUpperCase().replace(/\s+/g, "").replace("BASE-", "BASE-");
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Main validator
+// ─────────────────────────────────────────────────────────────────────────────
+
+export function validateTransceiverSpec(spec: ExtractedSpec): SpecValidationResult {
+  const errors: string[] = [];
+  const warnings: string[] = [];
+  let confidenceDelta = 0;
+
+  const ff = spec.form_factor ? normalizeFormFactor(spec.form_factor) : null;
+  const speedGbps = spec.speed_gbps ?? null;
+  const fiberType = spec.fiber_type?.toUpperCase().trim() ?? null;
+  const reachM = spec.reach_meters ?? null;
+  const wavelengths = spec.wavelengths ?? null;
+
+  // ── 1. Form factor ↔ speed compatibility ──────────────────────────────────
+  if (ff && speedGbps !== null) {
+    const maxSpeed = FORM_FACTOR_MAX_SPEED[ff];
+    const minSpeed = FORM_FACTOR_MIN_SPEED[ff];
+
+    if (maxSpeed !== undefined && speedGbps > maxSpeed * 1.15) {
+      errors.push(
+        `Speed ${speedGbps}G exceeds ${ff} maximum (${maxSpeed}G). Physically impossible.`
+      );
+      confidenceDelta -= 0.4;
+    }
+
+    if (minSpeed !== undefined && speedGbps < minSpeed * 0.5) {
+      warnings.push(
+        `Speed ${speedGbps}G is unusually low for ${ff} (typical min ${minSpeed}G). Verify.`
+      );
+      confidenceDelta -= 0.1;
+    }
+  }
+
+  // ── 2. Wavelength ↔ fiber type consistency ────────────────────────────────
+  if (wavelengths && fiberType && fiberType !== "DAC" && fiberType !== "AOC" && fiberType !== "CU") {
+    const primaryNm = parsePrimaryWavelength(wavelengths);
+    if (primaryNm !== null) {
+      const expectedFiber = expectedFiberForWavelength(primaryNm);
+
+      if (expectedFiber === "MMF" && fiberType === "SMF") {
+        errors.push(
+          `${primaryNm}nm is a multi-mode wavelength but fiber_type is SMF. Check the source.`
+        );
+        confidenceDelta -= 0.3;
+      }
+
+      if (expectedFiber === "SMF" && fiberType === "MMF") {
+        // 1310nm LX on MMF with mode-conditioning cable is a real thing — warn, not error
+        if (primaryNm >= 1260 && primaryNm <= 1360) {
+          warnings.push(
+            `${primaryNm}nm on MMF is unusual. Possible mode-conditioning cable — verify.`
+          );
+          confidenceDelta -= 0.05;
+        } else {
+          errors.push(
+            `${primaryNm}nm (SMF wavelength) cannot work on MMF fiber at this reach.`
+          );
+          confidenceDelta -= 0.35;
+        }
+      }
+    }
+  }
+
+  // ── 3. Reach ↔ fiber type sanity ─────────────────────────────────────────
+  if (reachM !== null && fiberType && fiberType in MAX_REACH) {
+    const maxReach = MAX_REACH[fiberType];
+    if (reachM > maxReach) {
+      errors.push(
+        `Reach ${reachM}m exceeds physical maximum for ${fiberType} (${maxReach}m). Data error.`
+      );
+      confidenceDelta -= 0.4;
+    }
+  }
+
+  if (reachM !== null && fiberType === "MMF" && reachM > 2000) {
+    warnings.push(
+      `MMF reach ${reachM}m is very high (rare). OM5 max ~3.5km, earlier OM4 max 400m at 10G+.`
+    );
+    confidenceDelta -= 0.1;
+  }
+
+  // ── 4. IEEE standard cross-check ─────────────────────────────────────────
+  if (spec.ieee_standard) {
+    const stdKey = Object.keys(IEEE_STANDARDS).find(
+      (k) => normalizeStandard(k) === normalizeStandard(spec.ieee_standard!)
+    );
+
+    if (stdKey) {
+      const stdDef = IEEE_STANDARDS[stdKey];
+
+      // Speed mismatch
+      if (speedGbps !== null && Math.abs(speedGbps - stdDef.speedGbps) / stdDef.speedGbps > 0.15) {
+        errors.push(
+          `${spec.ieee_standard} requires ${stdDef.speedGbps}G but extracted speed is ${speedGbps}G.`
+        );
+        confidenceDelta -= 0.35;
+      }
+
+      // Fiber type mismatch (soft — standard may have variants)
+      if (fiberType && stdDef.fiberType && fiberType !== stdDef.fiberType) {
+        warnings.push(
+          `${spec.ieee_standard} expects ${stdDef.fiberType} but fiber_type is ${fiberType}.`
+        );
+        confidenceDelta -= 0.1;
+      }
+
+      // Reach mismatch: more than 3× the defined reach is suspicious
+      if (reachM !== null && stdDef.reachKm !== undefined) {
+        const stdReachM = stdDef.reachKm * 1000;
+        if (reachM > stdReachM * 3) {
+          warnings.push(
+            `Reach ${reachM}m is >3× the ${spec.ieee_standard} defined reach (${stdReachM}m). Verify — may be a proprietary extended reach variant.`
+          );
+          confidenceDelta -= 0.05;
+        }
+      }
+    } else {
+      // Standard not in table — not an error, just warn for unknown standards
+      warnings.push(`IEEE standard "${spec.ieee_standard}" not in reference table. Accepted as-is.`);
+    }
+  }
+
+  // ── 5. DAC/AOC special rules ──────────────────────────────────────────────
+  if (fiberType === "DAC" || fiberType === "AOC") {
+    if (reachM !== null && reachM > 30 && fiberType === "DAC") {
+      warnings.push(`DAC cables > 30m are unusual (passive DAC max ~7m). Verify if active DAC or AOC.`);
+      confidenceDelta -= 0.1;
+    }
+    if (wavelengths) {
+      warnings.push(`DAC/AOC have no wavelength. Extracted wavelength "${wavelengths}" may be wrong.`);
+      confidenceDelta -= 0.05;
+    }
+  }
+
+  // ── 6. Connector ↔ form factor ────────────────────────────────────────────
+  if (spec.connector && ff) {
+    const connector = spec.connector.toUpperCase();
+    const mpoBased = ["QSFP", "QSFP+", "QSFP28", "QSFP56", "QSFP-DD", "OSFP", "CFP8"];
+    const scBased  = ["GBIC", "CSFP"];
+
+    if (mpoBased.includes(ff) && connector === "SC") {
+      warnings.push(`${ff} modules rarely use SC connectors. LC or MPO expected. Verify.`);
+      confidenceDelta -= 0.1;
+    }
+    if (scBased.includes(ff) && connector === "LC") {
+      // GBIC can use LC — soft warning only
+      warnings.push(`${ff} with LC connector is unusual. SC more common for this form factor.`);
+      confidenceDelta -= 0.05;
+    }
+  }
+
+  // ── Tier assignment ───────────────────────────────────────────────────────
+  const passed = errors.length === 0;
+  let tier: SpecValidationResult["tier"];
+
+  if (!passed) {
+    tier = "rejected";
+  } else if (warnings.length === 0 && confidenceDelta >= 0) {
+    tier = "high";
+  } else if (warnings.length <= 2 && confidenceDelta >= -0.15) {
+    tier = "medium";
+  } else {
+    tier = "low";
+  }
+
+  return {
+    passed,
+    errors,
+    warnings,
+    confidence_delta: Math.max(confidenceDelta, -0.9),
+    tier,
+  };
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Convenience: combine with stock validation result
+// ─────────────────────────────────────────────────────────────────────────────
+
+export interface CombinedValidationResult {
+  passed: boolean;
+  spec_errors: string[];
+  spec_warnings: string[];
+  tier: SpecValidationResult["tier"];
+  adjusted_confidence: number;
+}
+
+export function combineValidations(
+  specResult: SpecValidationResult,
+  baseLlmConfidence: number
+): CombinedValidationResult {
+  const adjusted = Math.min(
+    1.0,
+    Math.max(0.0, baseLlmConfidence + specResult.confidence_delta)
+  );
+
+  return {
+    passed: specResult.passed,
+    spec_errors: specResult.errors,
+    spec_warnings: specResult.warnings,
+    tier: specResult.tier,
+    adjusted_confidence: adjusted,
+  };
+}
diff --git a/packages/scraper/src/crawler-llm/training-data-writer.ts b/packages/scraper/src/crawler-llm/training-data-writer.ts
new file mode 100644
index 0000000..2ebabf6
--- /dev/null
+++ b/packages/scraper/src/crawler-llm/training-data-writer.ts
@@ -0,0 +1,364 @@
+/**
+ * Crawler LLM — TIPLLM Training Data Writer.
+ *
+ * Converts validated transceiver extractions and crawl events into SFT training
+ * pairs, appends them to JSONL files in the local tip-training-data git clone,
+ * and pushes to Gitea after each batch.
+ *
+ * Training pair types generated:
+ *   spec_qa         — "What are the specs of [PID]?" → structured answer
+ *   crawl_reasoning — "How did you extract X from this HTML?" → CoT trace
+ *   validation      — "Is this spec physically plausible?" → yes/no + reasoning
+ *   discovery       — "Where can I find [vendor]'s transceiver catalog?" → nav guidance
+ *
+ * Gitea repo: http://192.168.178.196:3000/rene/tip-training-data
+ * Local clone: /tmp/tip-training-data (pre-cloned with token auth remote)
+ */
+
+import { execSync } from "child_process";
+import { appendFileSync, mkdirSync, existsSync } from "fs";
+import { join } from "path";
+import { createHash } from "crypto";
+
+import type { ExtractedSpec } from "./spec-validator";
+import type { CombinedValidationResult } from "./spec-validator";
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Config
+// ─────────────────────────────────────────────────────────────────────────────
+
+const REPO_DIR = process.env.TIP_TRAINING_REPO || "/tmp/tip-training-data";
+const GITEA_TOKEN = process.env.GITEA_TOKEN || "0e758f30abf86ffb49b2d7bb5b1f0be12c7f0b46";
+const GITEA_BASE = "http://192.168.178.196:3000";
+
+// Minimum confidence for a spec to enter the high-quality training set
+const MIN_CONFIDENCE_HIGH = 0.75;
+const MIN_CONFIDENCE_LOW = 0.50;
+
+const SYSTEM_PROMPT = `You are TIPLLM, an expert AI assistant for the Transceiver Intelligence Platform (TIP). \
+You have deep knowledge of optical transceiver specifications, form factors, IEEE standards, \
+vendor product catalogs, and fiber optic networking. You help engineers select, source, and \
+validate transceivers. You provide precise, structured answers with confidence scores and \
+always cite your reasoning.`;
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Types
+// ─────────────────────────────────────────────────────────────────────────────
+
+export interface SftMessage {
+  role: "system" | "user" | "assistant";
+  content: string;
+}
+
+export interface SftRecord {
+  id: string;
+  source: string;
+  kind: "sft-jsonl";
+  messages: SftMessage[];
+}
+
+export interface CrawlExtraction {
+  url: string;
+  vendor_slug: string;
+  vendor_name: string;
+  spec: ExtractedSpec;
+  validation: CombinedValidationResult;
+  raw_html_snippet?: string;   // first 2000 chars of cleaned HTML for CoT training
+  crawled_at: string;          // ISO timestamp
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Helpers
+// ─────────────────────────────────────────────────────────────────────────────
+
+function makeId(prefix: string, input: string): string {
+  const hash = createHash("sha256").update(input).digest("hex").slice(0, 12);
+  return `${prefix}-${hash}`;
+}
+
+function specToMarkdown(spec: ExtractedSpec): string {
+  const lines: string[] = [];
+  if (spec.part_number)   lines.push(`- **Part Number**: ${spec.part_number}`);
+  if (spec.form_factor)   lines.push(`- **Form Factor**: ${spec.form_factor}`);
+  if (spec.speed_gbps)    lines.push(`- **Speed**: ${spec.speed_gbps}G`);
+  if (spec.fiber_type)    lines.push(`- **Fiber Type**: ${spec.fiber_type}`);
+  if (spec.connector)     lines.push(`- **Connector**: ${spec.connector}`);
+  if (spec.wavelengths)   lines.push(`- **Wavelengths**: ${spec.wavelengths}`);
+  if (spec.reach_meters)  lines.push(`- **Reach**: ${spec.reach_meters >= 1000 ? `${spec.reach_meters / 1000}km` : `${spec.reach_meters}m`}`);
+  if (spec.ieee_standard) lines.push(`- **IEEE Standard**: ${spec.ieee_standard}`);
+  if (spec.dom_support != null) lines.push(`- **DOM**: ${spec.dom_support ? "Yes" : "No"}`);
+  return lines.join("\n");
+}
+
+function ensureDir(dir: string): void {
+  if (!existsSync(dir)) mkdirSync(dir, { recursive: true });
+}
+
+function appendRecord(filePath: string, record: SftRecord): void {
+  appendFileSync(filePath, JSON.stringify(record) + "\n", "utf8");
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Training pair generators
+// ─────────────────────────────────────────────────────────────────────────────
+
+function makeSpecQaPair(extraction: CrawlExtraction): SftRecord | null {
+  const { spec, vendor_name, url, validation } = extraction;
+  if (!spec.part_number) return null;
+
+  const specMd = specToMarkdown(spec);
+  if (!specMd) return null;
+
+  const confNote = validation.adjusted_confidence >= MIN_CONFIDENCE_HIGH
+    ? "high confidence"
+    : `confidence ${validation.adjusted_confidence.toFixed(2)}`;
+
+  return {
+    id: makeId("spec-qa", spec.part_number + url),
+    source: `crawl:${extraction.vendor_slug}:${url}`,
+    kind: "sft-jsonl",
+    messages: [
+      { role: "system", content: SYSTEM_PROMPT },
+      {
+        role: "user",
+        content: `What are the technical specifications for transceiver ${spec.part_number}?`,
+      },
+      {
+        role: "assistant",
+        content: `**${spec.part_number}** (${vendor_name})\n\n${specMd}\n\n*Source: [${vendor_name} product page](${url}) — ${confNote}*`,
+      },
+    ],
+  };
+}
+
+function makeCrawlReasoningPair(extraction: CrawlExtraction): SftRecord | null {
+  const { spec, url, validation, raw_html_snippet } = extraction;
+  if (!raw_html_snippet || !spec.part_number) return null;
+
+  const issues = [
+    ...validation.spec_errors.map((e) => `ERROR: ${e}`),
+    ...validation.spec_warnings.map((w) => `WARN: ${w}`),
+  ];
+
+  return {
+    id: makeId("crawl-cot", url),
+    source: `crawl-reasoning:${extraction.vendor_slug}:${url}`,
+    kind: "sft-jsonl",
+    messages: [
+      { role: "system", content: SYSTEM_PROMPT },
+      {
+        role: "user",
+        content: `I have this HTML snippet from ${url}:\n\n---\n${raw_html_snippet.slice(0, 1500)}\n---\n\nExtract the transceiver part number, form factor, speed, fiber type, wavelength, and reach.`,
+      },
+      {
+        role: "assistant",
+        content: `From the HTML I can extract:\n\n${specToMarkdown(spec)}\n\n**Validation** (confidence: ${validation.adjusted_confidence.toFixed(2)}, tier: ${validation.tier}):\n${issues.length > 0 ? issues.map((i) => `- ${i}`).join("\n") : "- All checks passed."}\n\n**Source evidence**: The part number "${spec.part_number}" appears in a product header or SKU field. Speed and form factor are confirmed by the specification table.`,
+      },
+    ],
+  };
+}
+
+function makeValidationPair(extraction: CrawlExtraction): SftRecord {
+  const { spec, validation, url } = extraction;
+
+  const question = `Is the following transceiver specification physically plausible?\n\n${specToMarkdown(spec)}\n\nSource: ${url}`;
+
+  let answer: string;
+  if (validation.passed) {
+    const issues = validation.spec_warnings.length > 0
+      ? `\n\n**Warnings** (non-blocking):\n${validation.spec_warnings.map((w) => `- ${w}`).join("\n")}`
+      : "";
+    answer = `**Valid** (tier: ${validation.tier}, confidence: ${validation.adjusted_confidence.toFixed(2)})\n\nAll critical physical checks pass — form factor/speed compatibility, fiber type/wavelength consistency, and reach limits are all within bounds.${issues}`;
+  } else {
+    const errList = validation.spec_errors.map((e) => `- ❌ ${e}`).join("\n");
+    answer = `**Invalid** (tier: ${validation.tier})\n\nThe following physical plausibility checks failed:\n\n${errList}\n\nThis data should not be persisted to the transceiver database without manual review.`;
+  }
+
+  return {
+    id: makeId("spec-valid", JSON.stringify(spec) + url),
+    source: `validation:${extraction.vendor_slug}:${url}`,
+    kind: "sft-jsonl",
+    messages: [
+      { role: "system", content: SYSTEM_PROMPT },
+      { role: "user", content: question },
+      { role: "assistant", content: answer },
+    ],
+  };
+}
+
+function makeDiscoveryPair(vendorSlug: string, vendorName: string, catalogUrl: string, productCount: number): SftRecord {
+  return {
+    id: makeId("discovery", vendorSlug + catalogUrl),
+    source: `discovery:${vendorSlug}`,
+    kind: "sft-jsonl",
+    messages: [
+      { role: "system", content: SYSTEM_PROMPT },
+      {
+        role: "user",
+        content: `Where can I find ${vendorName}'s transceiver catalog to scrape product specifications?`,
+      },
+      {
+        role: "assistant",
+        content: `**${vendorName} Transceiver Catalog**\n\n- Catalog URL: ${catalogUrl}\n- Products discovered: ${productCount}\n- Crawl strategy: Navigate to the catalog URL, identify product listing pages, follow individual product links to extract SKU, form factor, speed, fiber type, wavelength, and reach specifications.\n\nWhen crawling ${vendorName}, look for product table structures, data sheets linked as PDFs, and compatibility matrices in the navigation sidebar.`,
+      },
+    ],
+  };
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// File path routing
+// ─────────────────────────────────────────────────────────────────────────────
+
+function getOutputFile(type: "spec_qa" | "crawl_reasoning" | "validation" | "discovery", tier: string): string {
+  const dir = join(REPO_DIR, "qa-pairs");
+  ensureDir(dir);
+  return join(dir, `${type}-${tier}.jsonl`);
+}
+
+function getRawExtractionFile(vendorSlug: string): string {
+  const dir = join(REPO_DIR, "crawl-extractions", vendorSlug);
+  ensureDir(dir);
+  const date = new Date().toISOString().split("T")[0];
+  return join(dir, `${date}.jsonl`);
+}
+
+function getValidatedSpecFile(tier: string): string {
+  const dir = join(REPO_DIR, "validated-specs");
+  ensureDir(dir);
+  return join(dir, `${tier}.jsonl`);
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Git operations
+// ─────────────────────────────────────────────────────────────────────────────
+
+let pendingChanges = 0;
+const BATCH_COMMIT_THRESHOLD = 50;  // commit every N records
+
+function gitAddAll(): void {
+  execSync("git add -A", { cwd: REPO_DIR, stdio: "pipe" });
+}
+
+function gitCommit(message: string): void {
+  try {
+    execSync(
+      `git -c user.email="tip-crawler@context-x.org" -c user.name="TIP Crawler" commit -m "${message}"`,
+      { cwd: REPO_DIR, stdio: "pipe" }
+    );
+  } catch {
+    // Empty commit (nothing new) — ignore
+  }
+}
+
+function gitPush(): void {
+  const remote = `http://rene:${GITEA_TOKEN}@${GITEA_BASE.replace("http://", "")}/rene/tip-training-data.git`;
+  execSync(`git push "${remote}" main`, { cwd: REPO_DIR, stdio: "pipe" });
+}
+
+export function flushToGitea(label = "batch"): void {
+  try {
+    gitAddAll();
+    gitCommit(`crawl: add ${label} training records [${new Date().toISOString()}]`);
+    gitPush();
+    pendingChanges = 0;
+    console.log(`[training-writer] Pushed to Gitea: ${label}`);
+  } catch (err) {
+    console.warn(`[training-writer] Git push failed (non-fatal): ${(err as Error).message.slice(0, 120)}`);
+  }
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Public API
+// ─────────────────────────────────────────────────────────────────────────────
+
+/**
+ * Write a single crawl extraction to all appropriate training files.
+ * Skips if confidence is below the minimum threshold.
+ */
+export function writeExtractionRecord(extraction: CrawlExtraction): {
+  written: boolean;
+  pairs: number;
+  reason?: string;
+} {
+  const { validation, spec } = extraction;
+
+  // Reject very low confidence
+  if (validation.adjusted_confidence < MIN_CONFIDENCE_LOW) {
+    return { written: false, pairs: 0, reason: `confidence ${validation.adjusted_confidence} < threshold` };
+  }
+
+  const tier = validation.tier === "rejected" ? "low" : validation.tier;
+  let pairsWritten = 0;
+
+  // 1. Raw extraction log (always, for audit)
+  appendFileSync(
+    getRawExtractionFile(extraction.vendor_slug),
+    JSON.stringify({ ...extraction, raw_html_snippet: undefined }) + "\n",
+    "utf8"
+  );
+
+  // 2. Validated spec archive
+  if (validation.passed) {
+    appendFileSync(
+      getValidatedSpecFile(tier),
+      JSON.stringify({ spec, url: extraction.url, vendor: extraction.vendor_slug, confidence: validation.adjusted_confidence }) + "\n",
+      "utf8"
+    );
+  }
+
+  // 3. Spec QA pair
+  const qaPair = makeSpecQaPair(extraction);
+  if (qaPair) {
+    appendRecord(getOutputFile("spec_qa", tier), qaPair);
+    pairsWritten++;
+  }
+
+  // 4. Crawl reasoning pair (CoT) — high tier only to avoid polluting with noisy traces
+  if (tier === "high" || tier === "medium") {
+    const cotPair = makeCrawlReasoningPair(extraction);
+    if (cotPair) {
+      appendRecord(getOutputFile("crawl_reasoning", tier), cotPair);
+      pairsWritten++;
+    }
+  }
+
+  // 5. Validation pair — always valuable (includes both passed and failed examples)
+  if (spec.part_number || spec.form_factor) {
+    const valPair = makeValidationPair(extraction);
+    appendRecord(getOutputFile("validation", tier), valPair);
+    pairsWritten++;
+  }
+
+  pendingChanges += pairsWritten;
+
+  // Auto-flush when threshold reached
+  if (pendingChanges >= BATCH_COMMIT_THRESHOLD) {
+    flushToGitea(`auto-${extraction.vendor_slug}`);
+  }
+
+  return { written: true, pairs: pairsWritten };
+}
+
+/**
+ * Write a vendor discovery record when we successfully crawl a new catalog.
+ */
+export function writeDiscoveryRecord(
+  vendorSlug: string,
+  vendorName: string,
+  catalogUrl: string,
+  productCount: number
+): void {
+  const pair = makeDiscoveryPair(vendorSlug, vendorName, catalogUrl, productCount);
+  const file = getOutputFile("discovery", "high");
+  appendRecord(file, pair);
+  pendingChanges++;
+}
+
+/**
+ * Force push all pending changes to Gitea (call at end of crawler run).
+ */
+export function finalFlush(vendorSlug: string): void {
+  if (pendingChanges > 0) {
+    flushToGitea(`final-${vendorSlug}`);
+  }
+}
diff --git a/packages/scraper/src/crawler-llm/vendor-discovery-crawler.ts b/packages/scraper/src/crawler-llm/vendor-discovery-crawler.ts
new file mode 100644
index 0000000..71b9de5
--- /dev/null
+++ b/packages/scraper/src/crawler-llm/vendor-discovery-crawler.ts
@@ -0,0 +1,473 @@
+/**
+ * Vendor Discovery Crawler — Intelligent transceiver catalog spider.
+ *
+ * Architecture:
+ *   vendor catalog URL
+ *     → PlaywrightCrawler (Crawlee) — renders JS, handles bot-detection
+ *     → page type detection (product vs. listing)
+ *     → LLM extraction (core.ts scrapeWithLLM)
+ *     → spec physical validation (spec-validator.ts)
+ *     → DB persist (db.ts findOrCreateScrapedTransceiver)
+ *     → training data (training-data-writer.ts)
+ *
+ * Each vendor config defines catalog entry points and optional blocklist patterns.
+ * The crawler respects rate limits and uses stealth patches to avoid blocking.
+ *
+ * Run standalone:
+ *   tsx packages/scraper/src/crawler-llm/vendor-discovery-crawler.ts
+ *
+ * Or import and call discoverVendorCatalog() from the scheduler.
+ */
+
+import { PlaywrightCrawler, RequestQueue, Configuration, type Log } from "crawlee";
+import { pool, ensureVendor, findOrCreateScrapedTransceiver } from "../utils/db";
+import { scrapeWithLLM } from "./core";
+import { validateTransceiverSpec, combineValidations, type ExtractedSpec } from "./spec-validator";
+import {
+  writeExtractionRecord,
+  writeDiscoveryRecord,
+  finalFlush,
+  type CrawlExtraction,
+} from "./training-data-writer";
+import { makeCrawleeConfig } from "../utils/crawlee-config";
+import { createHash } from "crypto";
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Vendor catalog registry
+// ─────────────────────────────────────────────────────────────────────────────
+
+export interface VendorCatalogConfig {
+  slug: string;
+  name: string;
+  website: string;
+  catalogUrls: string[];          // entry points for the spider
+  blockPatterns?: RegExp[];       // URL patterns to skip
+  allowPatterns?: RegExp[];       // only follow these URL patterns (if set)
+  maxPages?: number;              // safety cap (default 200)
+  maxDepth?: number;              // link-follow depth (default 3)
+  delayMs?: number;               // polite crawl delay (default 1500)
+  marketStatus?: "Mainstream" | "Growth" | "Emerging" | "Legacy" | "EOL";
+  category?: "DataCenter" | "Telecom" | "Industrial" | "Enterprise";
+  domSupport?: boolean;
+}
+
+/** Vendor catalog registry — add new vendors here */
+export const VENDOR_CATALOG_REGISTRY: VendorCatalogConfig[] = [
+  {
+    slug: "cisco-tmg",
+    name: "Cisco",
+    website: "https://www.cisco.com",
+    catalogUrls: [
+      "https://www.cisco.com/c/en/us/products/interfaces-modules/transceiver-modules/index.html",
+    ],
+    allowPatterns: [/\/transceiver-modules\//, /\/products\/interfaces-modules\//],
+    blockPatterns: [/\/support\//, /\/community\//, /signin/, /login/],
+    maxPages: 300,
+    maxDepth: 4,
+    delayMs: 2000,
+    marketStatus: "Mainstream",
+    category: "DataCenter",
+    domSupport: true,
+  },
+  {
+    slug: "juniper",
+    name: "Juniper Networks",
+    website: "https://www.juniper.net",
+    catalogUrls: [
+      "https://www.juniper.net/us/en/products/routers/routing-transports/optical-transceiver-modules.html",
+    ],
+    allowPatterns: [/\/transceiver/, /\/optical/, /\/sfp/, /\/qsfp/],
+    blockPatterns: [/\/support\//, /\/community\//, /login/],
+    maxPages: 200,
+    maxDepth: 3,
+    delayMs: 2000,
+    marketStatus: "Mainstream",
+    category: "DataCenter",
+    domSupport: true,
+  },
+  {
+    slug: "arista",
+    name: "Arista Networks",
+    website: "https://www.arista.com",
+    catalogUrls: [
+      "https://www.arista.com/en/products/transceivers-cables",
+    ],
+    blockPatterns: [/\/support\//, /login/],
+    maxPages: 150,
+    maxDepth: 3,
+    delayMs: 1500,
+    marketStatus: "Mainstream",
+    category: "DataCenter",
+    domSupport: true,
+  },
+  {
+    slug: "fs-com",
+    name: "FS.com",
+    website: "https://www.fs.com",
+    catalogUrls: [
+      "https://www.fs.com/c/fiber-optic-transceivers-3013",
+    ],
+    blockPatterns: [/\/account/, /\/cart/, /\/checkout/, /login/],
+    maxPages: 500,
+    maxDepth: 4,
+    delayMs: 1000,
+    marketStatus: "Mainstream",
+    category: "DataCenter",
+    domSupport: true,
+  },
+  {
+    slug: "flexoptix",
+    name: "Flexoptix",
+    website: "https://www.flexoptix.net",
+    catalogUrls: [
+      "https://www.flexoptix.net/en/optical-transceivers.html",
+    ],
+    blockPatterns: [/\/account/, /\/cart/, /\/checkout/, /login/],
+    maxPages: 400,
+    maxDepth: 3,
+    delayMs: 1200,
+    marketStatus: "Mainstream",
+    category: "DataCenter",
+    domSupport: true,
+  },
+  {
+    slug: "nokia",
+    name: "Nokia",
+    website: "https://www.nokia.com",
+    catalogUrls: [
+      "https://www.nokia.com/networks/products/optical-interfaces/transceiver-modules/",
+    ],
+    blockPatterns: [/\/support\//, /login/, /\/community\//],
+    maxPages: 200,
+    maxDepth: 3,
+    delayMs: 2000,
+    marketStatus: "Mainstream",
+    category: "Telecom",
+    domSupport: true,
+  },
+  {
+    slug: "huawei",
+    name: "Huawei",
+    website: "https://e.huawei.com",
+    catalogUrls: [
+      "https://e.huawei.com/en/products/optical-transmission/transceiver-modules",
+    ],
+    blockPatterns: [/\/support\//, /login/],
+    maxPages: 200,
+    maxDepth: 3,
+    delayMs: 2500,
+    marketStatus: "Mainstream",
+    category: "Telecom",
+    domSupport: true,
+  },
+  {
+    slug: "ii-vi",
+    name: "II-VI / Coherent",
+    website: "https://www.coherent.com",
+    catalogUrls: [
+      "https://www.coherent.com/networking/transceivers",
+    ],
+    blockPatterns: [/login/, /\/account/],
+    maxPages: 150,
+    maxDepth: 3,
+    delayMs: 1500,
+    marketStatus: "Mainstream",
+    category: "DataCenter",
+    domSupport: true,
+  },
+];
+
+// ─────────────────────────────────────────────────────────────────────────────
+// State tracking
+// ─────────────────────────────────────────────────────────────────────────────
+
+interface CrawlStats {
+  pagesVisited: number;
+  productPagesFound: number;
+  extractionsSucceeded: number;
+  extractionsFailed: number;
+  validationPassed: number;
+  validationFailed: number;
+  dbInserted: number;
+  trainingPairsWritten: number;
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// HTML cleaning
+// ─────────────────────────────────────────────────────────────────────────────
+
+function cleanHtml(html: string): string {
+  return html
+    .replace(/<script[^>]*>[\s\S]*?<\/script>/gi, "")
+    .replace(/<style[^>]*>[\s\S]*?<\/style>/gi, "")
+    .replace(/<!--[\s\S]*?-->/g, "")
+    .replace(/<[^>]+>/g, " ")
+    .replace(/\s+/g, " ")
+    .trim();
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// URL filtering
+// ─────────────────────────────────────────────────────────────────────────────
+
+function shouldFollowUrl(url: string, config: VendorCatalogConfig): boolean {
+  // Must be same domain
+  try {
+    const parsed = new URL(url);
+    const domain = new URL(config.website).hostname.replace("www.", "");
+    if (!parsed.hostname.includes(domain)) return false;
+  } catch {
+    return false;
+  }
+
+  // Block patterns
+  if (config.blockPatterns?.some((re) => re.test(url))) return false;
+
+  // Allow patterns (if defined, URL must match at least one)
+  if (config.allowPatterns && config.allowPatterns.length > 0) {
+    return config.allowPatterns.some((re) => re.test(url));
+  }
+
+  return true;
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Main crawl function
+// ─────────────────────────────────────────────────────────────────────────────
+
+export async function discoverVendorCatalog(
+  config: VendorCatalogConfig,
+  options: { dryRun?: boolean; verbose?: boolean } = {}
+): Promise<CrawlStats> {
+  const stats: CrawlStats = {
+    pagesVisited: 0,
+    productPagesFound: 0,
+    extractionsSucceeded: 0,
+    extractionsFailed: 0,
+    validationPassed: 0,
+    validationFailed: 0,
+    dbInserted: 0,
+    trainingPairsWritten: 0,
+  };
+
+  const maxPages = config.maxPages ?? 200;
+  const delayMs = config.delayMs ?? 1500;
+  const log = (...args: unknown[]) => { if (options.verbose) console.log(`[${config.slug}]`, ...args); };
+
+  // Ensure vendor exists in DB
+  const vendorId = await ensureVendor(config.name, "distributor", config.website, undefined);
+  log(`Vendor ID: ${vendorId}`);
+
+  const requestQueue = await RequestQueue.open(`vendor-${config.slug}-${Date.now()}`);
+  for (const url of config.catalogUrls) {
+    await requestQueue.addRequest({ url, userData: { depth: 0 } });
+  }
+
+  const crawleeConfig = makeCrawleeConfig(`vendor-discovery-${config.slug}`);
+  const seenUrls = new Set<string>();
+
+  const crawler = new PlaywrightCrawler(
+    {
+      requestQueue,
+      maxRequestsPerCrawl: maxPages,
+      maxConcurrency: 1,        // polite single-thread crawl
+      navigationTimeoutSecs: 30,
+      requestHandlerTimeoutSecs: 60,
+
+      async requestHandler({ request, page, enqueueLinks }) {
+        if (stats.pagesVisited >= maxPages) return;
+        stats.pagesVisited++;
+        seenUrls.add(request.url);
+
+        log(`[${stats.pagesVisited}/${maxPages}] ${request.url}`);
+
+        // Polite delay
+        await new Promise((r) => setTimeout(r, delayMs));
+
+        // Get rendered HTML
+        const html = await page.content();
+        const cleanedText = cleanHtml(html).slice(0, 2000);
+
+        // Run LLM extraction (with page type detection)
+        let llmResult: Awaited<ReturnType<typeof scrapeWithLLM>> | null = null;
+        try {
+          llmResult = await scrapeWithLLM(html, request.url, {
+            vendorSlug: config.slug,
+            skipPageDetection: false,
+          });
+        } catch (err) {
+          stats.extractionsFailed++;
+          log(`LLM error: ${(err as Error).message.slice(0, 80)}`);
+        }
+
+        // Process product pages
+        if (llmResult?.extraction.is_product_page) {
+          stats.productPagesFound++;
+
+          const ext = llmResult.extraction;
+          if (llmResult.validation_passed) {
+            stats.extractionsSucceeded++;
+
+            // Build spec for physical validation
+            const spec: ExtractedSpec = {
+              part_number: ext.part_number ?? undefined,
+              form_factor: ext.form_factor ?? undefined,
+              speed_gbps: ext.speed_gbps ?? undefined,
+              fiber_type: undefined,    // not in stock extraction — derive later
+            };
+
+            // Spec plausibility check
+            const specResult = validateTransceiverSpec(spec);
+            const combined = combineValidations(specResult, ext.confidence);
+
+            if (combined.passed) {
+              stats.validationPassed++;
+            } else {
+              stats.validationFailed++;
+            }
+
+            // Persist to DB (even if spec validation has warnings — just low tier)
+            if (!options.dryRun && ext.part_number && combined.adjusted_confidence >= 0.5) {
+              try {
+                await findOrCreateScrapedTransceiver({
+                  partNumber: ext.part_number,
+                  vendorId,
+                  productUrl: request.url,
+                  formFactor: ext.form_factor ?? undefined,
+                  speedGbps: ext.speed_gbps ?? undefined,
+                  speed: ext.speed_gbps ? `${ext.speed_gbps}G` : undefined,
+                });
+                stats.dbInserted++;
+              } catch (dbErr) {
+                log(`DB error: ${(dbErr as Error).message.slice(0, 80)}`);
+              }
+            }
+
+            // Write training data
+            const crawlExt: CrawlExtraction = {
+              url: request.url,
+              vendor_slug: config.slug,
+              vendor_name: config.name,
+              spec,
+              validation: combined,
+              raw_html_snippet: cleanedText,
+              crawled_at: new Date().toISOString(),
+            };
+
+            const writeResult = writeExtractionRecord(crawlExt);
+            if (writeResult.written) {
+              stats.trainingPairsWritten += writeResult.pairs;
+            }
+
+          } else {
+            stats.extractionsFailed++;
+            log(`Extraction failed validation: ${llmResult.validation_errors.join("; ")}`);
+          }
+        }
+
+        // Discover more URLs at current depth
+        const currentDepth = (request.userData?.depth as number) ?? 0;
+        const maxDepth = config.maxDepth ?? 3;
+
+        if (currentDepth < maxDepth) {
+          const links = await page.evaluate(() =>
+            Array.from(document.querySelectorAll("a[href]"))
+              .map((a) => (a as HTMLAnchorElement).href)
+              .filter(Boolean)
+          );
+
+          for (const link of links) {
+            if (seenUrls.has(link)) continue;
+            if (!shouldFollowUrl(link, config)) continue;
+            if (stats.pagesVisited >= maxPages) break;
+
+            seenUrls.add(link);
+            await requestQueue.addRequest({
+              url: link,
+              userData: { depth: currentDepth + 1 },
+            });
+          }
+        }
+      },
+
+      failedRequestHandler({ request, log: crawleeLog }: { request: Parameters<typeof crawleeLog.error>[1]; log: Log }) {
+        stats.extractionsFailed++;
+        (crawleeLog as Log).error(`Failed: ${(request as { url: string }).url}`);
+      },
+    },
+    crawleeConfig
+  );
+
+  await crawler.run();
+
+  // Write discovery record + final flush
+  writeDiscoveryRecord(config.slug, config.name, config.catalogUrls[0], stats.productPagesFound);
+  finalFlush(config.slug);
+
+  console.log(`\n=== ${config.name} Discovery Complete ===`);
+  console.log(`  Pages visited:      ${stats.pagesVisited}`);
+  console.log(`  Product pages:      ${stats.productPagesFound}`);
+  console.log(`  Extractions OK:     ${stats.extractionsSucceeded}`);
+  console.log(`  Spec valid:         ${stats.validationPassed}`);
+  console.log(`  DB inserts:         ${stats.dbInserted}`);
+  console.log(`  Training pairs:     ${stats.trainingPairsWritten}\n`);
+
+  return stats;
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Batch runner — crawl multiple vendors in sequence
+// ─────────────────────────────────────────────────────────────────────────────
+
+export async function runVendorDiscoveryBatch(
+  vendorSlugs?: string[],
+  options: { dryRun?: boolean; verbose?: boolean } = {}
+): Promise<void> {
+  const targets = vendorSlugs
+    ? VENDOR_CATALOG_REGISTRY.filter((v) => vendorSlugs.includes(v.slug))
+    : VENDOR_CATALOG_REGISTRY;
+
+  console.log(`Starting vendor discovery for ${targets.length} vendor(s)...`);
+
+  for (const config of targets) {
+    try {
+      await discoverVendorCatalog(config, options);
+    } catch (err) {
+      console.error(`[${config.slug}] Fatal crawl error:`, (err as Error).message);
+    }
+  }
+
+  console.log("Vendor discovery batch complete.");
+}
+
+// ─────────────────────────────────────────────────────────────────────────────
+// Standalone execution
+// ─────────────────────────────────────────────────────────────────────────────
+
+if (require.main === module) {
+  const target = process.argv[2];  // optional: specific vendor slug
+  const dryRun = process.argv.includes("--dry-run");
+  const verbose = process.argv.includes("--verbose");
+
+  const run = async () => {
+    if (target) {
+      const config = VENDOR_CATALOG_REGISTRY.find((v) => v.slug === target);
+      if (!config) {
+        console.error(`Unknown vendor slug: ${target}`);
+        console.log("Available:", VENDOR_CATALOG_REGISTRY.map((v) => v.slug).join(", "));
+        process.exit(1);
+      }
+      await discoverVendorCatalog(config, { dryRun, verbose });
+    } else {
+      await runVendorDiscoveryBatch(undefined, { dryRun, verbose });
+    }
+  };
+
+  run()
+    .then(() => pool.end())
+    .catch((err) => {
+      console.error("Fatal:", err);
+      pool.end();
+      process.exit(1);
+    });
+}
diff --git a/packages/scraper/src/scheduler.ts b/packages/scraper/src/scheduler.ts
index 292b84a..c75a3e9 100644
--- a/packages/scraper/src/scheduler.ts
+++ b/packages/scraper/src/scheduler.ts
@@ -155,6 +155,15 @@ export async function registerSchedules(boss: PgBoss): Promise<void> {
     "maintenance:find-equivalences",
     // ── Re-Research approved equivalences ─────────────────────────────
     "maintenance:re-research-equivalences",
+    // ── Vendor Discovery Crawlers (TIPLLM training data + DB seeding) ─────
+    "discover:vendor:cisco-tmg",
+    "discover:vendor:juniper",
+    "discover:vendor:arista",
+    "discover:vendor:fs-com",
+    "discover:vendor:flexoptix",
+    "discover:vendor:nokia",
+    "discover:vendor:huawei",
+    "discover:vendor:ii-vi",
   ];
 
   for (const q of queues) {
@@ -432,6 +441,21 @@ export async function registerSchedules(boss: PgBoss): Promise<void> {
   await boss.schedule("scrape:catalog:3com-legacy-oem",       "0 6 * * *",   {}, { retryLimit: 2, expireInSeconds: 3600 });
   await boss.schedule("scrape:catalog:avaya-legacy-oem",      "15 6 * * *",  {}, { retryLimit: 2, expireInSeconds: 3600 });
 
+  // ══════════════════════════════════════════════════════════════════════
+  // VENDOR DISCOVERY CRAWLERS — weekly (deep crawl, Playwright, TIPLLM training)
+  // Each run: crawls catalog → LLM extract → spec validate → DB + Gitea SFT
+  // Staggered across Sun/Mon nights (low-traffic window, 2h expiry each)
+  // ══════════════════════════════════════════════════════════════════════
+
+  await boss.schedule("discover:vendor:cisco-tmg",  "0 20 * * 0",  {}, { retryLimit: 1, expireInSeconds: 7200 });
+  await boss.schedule("discover:vendor:juniper",    "0 22 * * 0",  {}, { retryLimit: 1, expireInSeconds: 7200 });
+  await boss.schedule("discover:vendor:arista",     "0 0  * * 1",  {}, { retryLimit: 1, expireInSeconds: 7200 });
+  await boss.schedule("discover:vendor:fs-com",     "0 2  * * 1",  {}, { retryLimit: 1, expireInSeconds: 7200 });
+  await boss.schedule("discover:vendor:flexoptix",  "0 4  * * 1",  {}, { retryLimit: 1, expireInSeconds: 7200 });
+  await boss.schedule("discover:vendor:nokia",      "0 6  * * 1",  {}, { retryLimit: 1, expireInSeconds: 7200 });
+  await boss.schedule("discover:vendor:huawei",     "0 8  * * 1",  {}, { retryLimit: 1, expireInSeconds: 7200 });
+  await boss.schedule("discover:vendor:ii-vi",      "0 10 * * 1",  {}, { retryLimit: 1, expireInSeconds: 7200 });
+
   // ══════════════════════════════════════════════════════════════════════
   // VENDOR LISTS — every 12h
   // ══════════════════════════════════════════════════════════════════════
@@ -2706,5 +2730,31 @@ export async function registerWorkers(boss: PgBoss): Promise<void> {
     console.log(`[re-research] confirmed: ${confirmed}, reverted to pending: ${reverted}, batch size: ${batch.rows.length}`);
   });
 
-  console.log("All workers registered (94 jobs, 24/7 continuous)");
+  // ══════════════════════════════════════════════════════════════════════
+  // VENDOR DISCOVERY CRAWLER WORKERS
+  // Each worker calls discoverVendorCatalog() for the matching slug.
+  // Results go to: TIP DB (findOrCreateScrapedTransceiver) +
+  //                Gitea tip-training-data repo (SFT JSONL pairs)
+  // ══════════════════════════════════════════════════════════════════════
+
+  const { discoverVendorCatalog, VENDOR_CATALOG_REGISTRY } = await import("./crawler-llm/vendor-discovery-crawler");
+
+  for (const vendorConfig of VENDOR_CATALOG_REGISTRY) {
+    const jobName = `discover:vendor:${vendorConfig.slug}`;
+    boss.work(jobName, async () => {
+      if (!isLoadAcceptable(3.0)) {
+        console.warn(`[${jobName}] Load too high — skipping deep crawl`);
+        return;
+      }
+      console.log(`[${jobName}] Starting vendor discovery crawl…`);
+      try {
+        await discoverVendorCatalog(vendorConfig, { verbose: false });
+      } catch (err) {
+        console.error(`[${jobName}] Fatal:`, (err as Error).message);
+        throw err;   // let pg-boss retry
+      }
+    });
+  }
+
+  console.log("All workers registered (102 jobs, 24/7 continuous + 8 weekly discovery crawlers)");
 }