LLMRun.generate()
 └─ llmClient.streamChatCompletions()
-   └─ iterator.next()
-      └─ wait indefinitely
+   └─ withProviderInactivityTimeout()
+      ├─ race iterator.next() against 30s timeout
+      ├─ event received → reset timer → yield downstream
+      └─ timeout
+         ├─ abort provider request
+         └─ throw ProviderInactivityTimeoutError
+            ↳ LLMRun.retryBackup()

I find this much faster to scan than the prose which these language models tend to produce by default. The red/green highlighting visually stands out from the rest of the session transcript, so you can quickly parse the behavioral changes on a high level. This is especially useful when working out the design in back-and-forth conversation or when resuming work after switching sessions.

This diff does not replace the supporting explanations or documentation, rather it’s like a pseudocode but better at showing the location of changes in the actual program, using real function and class names in an informal but maximally compressed representation.