feat: implement Tier 3 features — lane queue, credential redaction, token dashboard, xAI, Voyage AI

- Lane Queue: per-session FIFO queue in gateway replacing reject-when-busy (9 tests)
- Credential Redaction: redactConfig() expanded to cover 18+ secret fields (16 tests)
- Web UI Token Dashboard: system.tokenUsage endpoint + Usage page with summary cards
- xAI (Grok) Provider: OpenAI-compatible client with model pricing
- Voyage AI Embeddings: new embedding provider with configurable dimensions (5 tests)
- Update gap analysis: 90→95 match (70%→74%), Tier 3 section marked DONE
- Update state.json: test count 1001→1034, add tier3_completion entry

Total: 1034 tests passing across 85 files, typecheck clean

src/models/costs.ts

@@ -21,6 +21,12 @@ export const MODEL_COSTS_PER_MILLION: Record<string, { input: number; output: nu
   'claude-haiku-4': { input: 0, output: 0 },
   // Local / unknown models
   'default': { input: 0, output: 0 },
+  // xAI (Grok)
+  'grok-3': { input: 3, output: 15 },
+  'grok-3-mini': { input: 0.30, output: 0.50 },
+  'grok-2': { input: 2, output: 10 },
+  'grok-2-mini': { input: 0.10, output: 0.25 },
+  'grok-3-fast': { input: 5, output: 25 },
   // Bedrock (Meta Llama)
   'meta.llama3-1-70b-instruct-v1:0': { input: 0.72, output: 0.72 },
   'meta.llama3-1-8b-instruct-v1:0': { input: 0.22, output: 0.22 },