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

env.example

@@ -123,9 +123,14 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
 
 # Temperature (Optional)
 # Controls randomness in AI responses. Lower = more deterministic.
-# Leave unset for models that don't support temperature (e.g., GPT-5.1 reasoning models)
+# Leave unset for models that don't support temperature (e.g., GPT-5.1 reasoning models).
+# Claude 4.7 and later reject it; the request is then retried without it.
 # TEMPERATURE=0
 
+# Debug Logging (Optional)
+# Log the structure of the messages each chat request sends to the model
+# DEBUG_LLM_PAYLOAD=true
+
 # Access Control (Optional)
 # ACCESS_CODE_LIST=your-secret-code,another-code