refactor: simpler streaming preview and small AI SDK cleanups

- useChat throttles streamed message updates (experimental_throttle,
  150 ms), replacing the two hand-written 150 ms timers of the
  display_diagram and edit_diagram previews (94 lines less). The preview
  now only runs while the input streams; once it is complete the tool
  handler takes over, so a queued preview can no longer redraw an edit
  the handler rejected and rolled back. Measured on a streamed 60-cell
  diagram: 41 redraws at least 97 ms apart, before 37 with gaps down to
  48 ms
- The diagram check endpoint uses streamText with Output.object instead
  of the deprecated streamObject, and returns its fixed result as a plain
  text response; new route test
- Import createGateway/gateway from ai and drop the direct
  @ai-sdk/gateway dependency
- The per-request message structure logs only print with
  DEBUG_LLM_PAYLOAD=true
- Remove an empty onFinish callback

lib/ai-providers.ts

@@ -2,14 +2,18 @@ import { createAmazonBedrock } from "@ai-sdk/amazon-bedrock"
 import { createAnthropic } from "@ai-sdk/anthropic"
 import { azure, createAzure } from "@ai-sdk/azure"
 import { createDeepSeek, deepseek } from "@ai-sdk/deepseek"
-import { createGateway, gateway } from "@ai-sdk/gateway"
 import { createGoogleGenerativeAI, google } from "@ai-sdk/google"
 import { createVertex } from "@ai-sdk/google-vertex"
 import { createOpenAI, openai } from "@ai-sdk/openai"
 import { aihubmix, createAihubmix } from "@aihubmix/ai-sdk-provider"
 import { fromNodeProviderChain } from "@aws-sdk/credential-providers"
 import { createOpenRouter } from "@openrouter/ai-sdk-provider"
-import { defaultSettingsMiddleware, wrapLanguageModel } from "ai"
+import {
+    createGateway,
+    defaultSettingsMiddleware,
+    gateway,
+    wrapLanguageModel,
+} from "ai"
 import { createOllama, ollama } from "ollama-ai-provider-v2"
 import {
     adminProvidersToConfig,