fix: llms/openai temperature+reasoning_effort for GPT-5 models

[feizhe1996]

Fix a bug where temperature=0 was silently dropped for reasoning models even when reasoning_effort="none" (which disables reasoning and makes temperature configurable again). The MarshalJSON guard now only omits temperature when reasoning is actually active (ReasoningEffort != "none").

Add reasoning_effort support for gpt-5.4 and later (gpt-5.[4-9]): valid values are none, low, medium, high, xhigh. Other GPT-5 variants and all o-series models continue to send no reasoning_effort parameter.

#1497

PR Checklist

• Read the Contributing documentation.
• Read the Code of conduct documentation.
• Name your Pull Request title clearly, concisely, and prefixed with the name of the primarily affected package you changed according to Good commit messages (such as memory: add interfaces for X, Y or util: add whizzbang helpers).
• Check that there isn't already a PR that solves the problem the same way to avoid creating a duplicate.
• Provide a description in this PR that addresses what the PR is solving, or reference the issue that it solves (e.g. Fixes #123).
• Describes the source of new concepts.
• References existing implementations as appropriate.
• Contains test coverage for new functions.
• Passes all golangci-lint checks.