server : reject prefilled assistant messages with tool calls (#27626)

* server: fix tool calls getting silently stripped with --prefill-assistant

Last assistant carries tool_calls + --prefill-assistant is on → request
flips into continuation mode, add_generation_prompt forced off, tail
rebuilt from reasoning_content + content only. Tool calls just vanish.

- Auto-continuation now skips trailing assistant msgs that have tool calls
- continue_final_message on those throws a clear error instead of
  silently corrupting the prompt
- Regression tests included, red before / green after

Fixes #27588

Developed with AI assistance, disclosed per the contribution policy.

* server : address review: fail on prefill-assistant + trailing tool_calls

Move validation into oaicompat_chat_params_parse (next to the existing
two-or-more-assistant check) and remove it from common_chat_templates_apply,
which has no precedent for validation. Drop the regression tests.

Per review: --prefill-assistant with a trailing assistant message
containing tool calls is not supported and should fail loudly.

tools/server/server-common.cpp

@@ -1280,6 +1280,12 @@ json oaicompat_chat_params_parse(
     if (inputs.continue_final_message != COMMON_CHAT_CONTINUATION_NONE && inputs.add_generation_prompt) {
         throw std::invalid_argument("Cannot set both add_generation_prompt and continue_final_message to true.");
     }
+    if (inputs.continue_final_message != COMMON_CHAT_CONTINUATION_NONE
+        && !inputs.messages.empty()
+        && inputs.messages.back().role == "assistant"
+        && !inputs.messages.back().tool_calls.empty()) {
+        throw std::invalid_argument("Cannot continue an assistant message that contains tool calls.");
+    }
     inputs.reasoning_format = opt.reasoning_format;
     if (body.contains("reasoning_format")) {
         inputs.reasoning_format = common_reasoning_format_from_name(body.at("reasoning_format").get<std::string>());