prefill cannot be used with thinking models

matteoserva · matteoserva · commit d585a1490fd9 · 2025-05-27T09:30:37.000+02:00
diff --git a/tools/server/utils.hpp b/tools/server/utils.hpp
@@ -766,7 +766,7 @@ static json oaicompat_chat_params_parse(
         /* TODO: test this properly */
         inputs.reasoning_format = COMMON_REASONING_FORMAT_NONE;
 
-        if (inputs.chat_template_kwargs.find("enable_thinking") != inputs.chat_template_kwargs.end()) {
+        if (inputs.enable_thinking || inputs.chat_template_kwargs.find("enable_thinking") != inputs.chat_template_kwargs.end()) {
             throw std::runtime_error("Assistant response prefill is incompatible with enable_thinking.");
         }
 

Original file line number	Diff line number	Diff line change
`@@ -766,7 +766,7 @@ static json oaicompat_chat_params_parse(`
`766`	`766`	`/* TODO: test this properly */`
`767`	`767`	`inputs.reasoning_format = COMMON_REASONING_FORMAT_NONE;`
`768`	`768`
`769`		`- if (inputs.chat_template_kwargs.find("enable_thinking") != inputs.chat_template_kwargs.end()) {`
	`769`	`+ if (inputs.enable_thinking \|\| inputs.chat_template_kwargs.find("enable_thinking") != inputs.chat_template_kwargs.end()) {`
`770`	`770`	`throw std::runtime_error("Assistant response prefill is incompatible with enable_thinking.");`
`771`	`771`	`}`
`772`	`772`