convert_payload_openai_to_ollama deep-copied the entire request payload on every completion routed to an Ollama model, and again on every tool-call iteration. The cost of that copy scales with the number of messages and nested content parts in the history, so long chats pay the most, purely as CPU work before the request even leaves the server.
The function only ever mutates two things: it deletes keys on the top-level dict and on the nested options dict. convert_messages_openai_to_ollama already builds fresh message dicts. Shallow-copying exactly those two levels therefore preserves behavior while removing the whole-tree copy.
Benchmark (per conversion call):
| payload | before | after | speedup |
| --- | --- | --- | --- |
| 200-message text chat (~180 KB) | 0.22 ms | 0.057 ms | 4x |
| 20-message chat + 1 MB base64 image | 0.41 ms | 0.38 ms | 1.1x |
The image row barely moves because deepcopy shares immutable strings; the win comes from container-heavy histories, which are exactly the payloads that grow over a conversation's lifetime.
The output is byte-identical to the previous implementation (verified against it, including dict key order, root parameter hoisting, max_tokens remapping, stop handling and response_format precedence), and the caller's payload is left unmodified exactly as before.
This is to bring consistency with apply_model_params_to_body_openai. Both now use a mapping dictionary then call and return apply_model_params_to_body directly.
We copy the params from from the original key to the new key, then delete it. This is to ensure Ollama only gets valid options.
(Add a comment as well)
1) Ollama natively supports frequency_penalty, so this is not necessary.
2) Repeat_penalty is being added to Open WebUI in PR #10016, allowing Ollama users to pick which penalty methods they want.
