0.7.2

Stricter request validation

The OpenAI-compatible server now refuses request fields it does not understand instead of silently ignoring them, and --prefill-chunk-tokens auto works on the server as well as the CLI.

Notable

• Return 400 unknown_parameter naming any undeclared top-level request field, so a misspelled option such as max_token no longer generates under other settings.
• Return 400 unsupported_value for OpenAI parameters the server cannot honour, including logit_bias, reasoning_effort, verbosity, and the legacy functions and function_call; accept and ignore user, store, metadata, service_tier, prompt_cache_key, and safety_identifier.
• Refuse response_format other than {"type": "text"} explicitly rather than generating free text under a structured-output request.
• Bound every echoed field name in bytes, so a key built from combining marks cannot be quoted back whole.
• Accept --prefill-chunk-tokens auto on the server, where it runs at the 256 cap; help and rejections list the accepted values from one place.
• Add nine M5 Pro 24 GB community benchmark rows from issue 170.
• Withdraw the --experts-per-token experiment from issue 167 after measurement; the decode path is unchanged.

This is a source-only release.