Preserve LLM generation failure metadata

docs/internal/llm.md

@@ -216,6 +216,13 @@ than output-validation failures. Apart from documented context, capacity, and
 invalid-output categories, provider error values and types do not cross the
 adapter error chain; callers receive only a credential-redacted diagnostic.
 
+`LLMGenerationError` preserves the provider-neutral failure kind (`transport`,
+`provider_status`, `malformed_response`, or generic `generation`) and any HTTP
+status. When PromptKit exhausts an eligible transient-status retry budget, it
+also records that exhaustion and the attempts in that generation. Those fields
+do not include repair generations, and zero attempts means unavailable rather
+than proof that no request was sent.
+
 When PromptKit rejects backend admission before generation, the adapter maps
 `promptkit.ErrCapacityExceeded` to
 `contracts.ErrLLMCapacityExceeded`, retaining prompt context and a redacted