Encode generation payloads once on success

docs/internal/llm.md

@@ -34,9 +34,13 @@ resolved request target may supply the endpoint. Generation preparation then:
 1. validates shared execution-setting invariants and the final selected base
    endpoint;
 2. maps the internal request into the OpenAI-compatible chat payload;
-3. validates and merges extra parameters;
+3. checks extra-parameter keys against empty and reserved names, then merges
+   their values into the payload;
 4. composes `/chat/completions` through parsed URL path operations;
-5. resolves authentication and freezes the URL, body, and optional credential.
+5. encodes the complete body once on success. If encoding fails, extra values
+   are checked individually to retain invalid-request classification; otherwise
+   the complete-request failure remains a request failure;
+6. resolves authentication and freezes the URL, body, and optional credential.
 
 Each execution of that prepared request creates a fresh HTTP request, body
 reader, and attempt timeout context. It closes the response body and returns