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/config/schema.ts

@@ -19,7 +19,7 @@ const serverSchema = z.object({
 });
 
 const modelConfigBaseSchema = z.object({
-  provider: z.enum(['anthropic', 'openai', 'gemini', 'ollama', 'llamacpp', 'openrouter', 'bedrock', 'github', 'zhipuai']),
+  provider: z.enum(['anthropic', 'openai', 'gemini', 'ollama', 'llamacpp', 'openrouter', 'bedrock', 'github', 'zhipuai', 'xai']),
   model: z.string(),
   endpoint: z.string().optional(),
   api_key: z.string().optional(),
@@ -173,7 +173,7 @@ const agentsSchema = z.object({
   max_delegation_depth: z.number().min(1).max(10).default(3),
 }).default({});
 
-const embeddingProviderSchema = z.enum(['openai', 'gemini', 'ollama', 'llamacpp']);
+const embeddingProviderSchema = z.enum(['openai', 'gemini', 'ollama', 'llamacpp', 'voyage']);
 
 const embeddingSchema = z.object({
   enabled: z.boolean().default(false),