fix(openai): stop mapping params(top_k=) to top_logprobs

CHANGELOG.md

@@ -16,6 +16,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 * `ChatPosit()` now handles setting `chat.model` to a model from the other family (Claude vs. non-Claude): the underlying provider is swapped so requests go to the correct endpoint, instead of failing with a mismatched request. The `cache` setting is preserved across switches.
 * Anthropic-backed providers (`ChatAnthropic()`, `ChatPosit()`, `ChatBedrock()`, etc.) no longer fail with `Invalid signature in thinking block` when the conversation history contains reasoning from a non-Claude model (e.g., after switching `chat.model` across families); such thinking is now replayed as plain text so the model can still see it.
 * `content_image_file()` no longer fails with `ValueError: unknown file extension` when `resize` uses the `!` (ignore aspect ratio) flag on an image larger than the requested box, e.g. `resize="200x200!"`. (#433)
+* `params(top_k=)` is no longer sent as `top_logprobs` for OpenAI-based providers (the two are unrelated; OpenAI has no `top_k` sampling parameter). `top_k` is now dropped with the standard unsupported-parameter warning. (#412)
 
 
 ## [0.23.0] - 2026-09-04

chatlas/_provider_openai.py

@@ -600,16 +600,12 @@ def translate_model_params(self, params: StandardModelParams) -> "SubmitInputArg
             # determine whether to include `message.output_text.logprobs`
             res["log_probs"] = params["log_probs"]  # type: ignore
 
-        if "top_k" in params:
-            res["top_logprobs"] = params["top_k"]
-
         return res
 
     def supported_model_params(self) -> set[StandardModelParamNames]:
         return {
             "temperature",
             "top_p",
-            "top_k",
             "max_tokens",
             "log_probs",
         }