From: Gabe Goodhart Date: Fri, 5 Sep 2025 20:31:24 +0000 (-0600) Subject: Thinking model disabled assistant prefill (#15404) X-Git-Tag: upstream/0.0.6527~133 X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=5fac79cbc77b6d12c9feb5f34fc63586b35fd561;p=pkg%2Fggml%2Fsources%2Fllama.cpp Thinking model disabled assistant prefill (#15404) * feat: Set enable_thinking IFF not disabled and supported Branch: gabe-l-hart/thinking-model-disabled-agent-prefill Signed-off-by: Gabe Goodhart * fix: Fix inverted logic condition for prefill error Branch: gabe-l-hart/thinking-model-disabled-agent-prefill Signed-off-by: Gabe Goodhart * fix: Always parse the enable_thinking kwarg to overwrite the default value From what I can tell, this started as a Qwen3-specific keyword, but from the use in `chat.cpp` translates this inputs.enable_thinking to the right thinking kwarg for the given model, this is now more of a standardized kwarg, so it should always override the default value when sent as part of the chat_template_kwargs field in the API. Branch: gabe-l-hart/thinking-model-disabled-agent-prefill Signed-off-by: Gabe Goodhart * fix: Don't limit tempalte expansion check to jinja With the use_jinja check, non-jinja models would enable thinking and always fail assistant prefill Branch: gabe-l-hart/thinking-model-disabled-agent-prefill Signed-off-by: Gabe Goodhart * feat: Add the error text to json type errors in json_value Branch: gabe-l-hart/thinking-model-disabled-agent-prefill Signed-off-by: Gabe Goodhart * feat: Explicitly reject string values for "enable_thinking" There are too many possible "truthy" / "falsy" strings and too many ambiguous strings that don't have a clear truthy/falsy value, so the simplest thing to do here is to reject the request. Ideally, this would be a 422 (Unprocessable Entity), but right now it's coming back as a 500. Branch: gabe-l-hart/thinking-model-disabled-agent-prefill Signed-off-by: Gabe Goodhart * refactor: Move logic for detecting template enable_thinking support to common Branch: gabe-l-hart/thinking-model-disabled-agent-prefill Signed-off-by: Gabe Goodhart * fix: Use raw pointer for common chat template function Branch: gabe-l-hart/thinking-model-disabled-agent-prefill Signed-off-by: Gabe Goodhart --------- Signed-off-by: Gabe Goodhart --- diff --git a/common/chat.cpp b/common/chat.cpp index e962adfd..a8a4c3e3 100644 --- a/common/chat.cpp +++ b/common/chat.cpp @@ -163,6 +163,19 @@ common_chat_tool_choice common_chat_tool_choice_parse_oaicompat(const std::strin throw std::runtime_error("Invalid tool_choice: " + tool_choice); } +bool common_chat_templates_support_enable_thinking(const common_chat_templates * chat_templates) { + common_chat_templates_inputs dummy_inputs; + common_chat_msg msg; + msg.role = "user"; + msg.content = "test"; + dummy_inputs.messages = {msg}; + dummy_inputs.enable_thinking = false; + const auto rendered_no_thinking = common_chat_templates_apply(chat_templates, dummy_inputs); + dummy_inputs.enable_thinking = true; + const auto rendered_with_thinking = common_chat_templates_apply(chat_templates, dummy_inputs); + return rendered_no_thinking.prompt != rendered_with_thinking.prompt; +} + template <> std::vector common_chat_msgs_parse_oaicompat(const json & messages) { std::vector msgs; diff --git a/common/chat.h b/common/chat.h index ccd26f27..41851022 100644 --- a/common/chat.h +++ b/common/chat.h @@ -199,6 +199,8 @@ common_chat_msg common_chat_parse(const std::string & input, bool is_p common_chat_tool_choice common_chat_tool_choice_parse_oaicompat(const std::string & tool_choice); +bool common_chat_templates_support_enable_thinking(const common_chat_templates * chat_templates); + // Parses a JSON array of messages in OpenAI's chat completion API format. // T can be std::string containing JSON or nlohmann::ordered_json template std::vector common_chat_msgs_parse_oaicompat(const T & messages); diff --git a/tools/server/server.cpp b/tools/server/server.cpp index 44487eca..de7c9931 100644 --- a/tools/server/server.cpp +++ b/tools/server/server.cpp @@ -2267,6 +2267,12 @@ struct server_context { metrics.init(); + // thinking is enabled if: + // 1. It's not explicitly disabled (reasoning_budget == 0) + // 2. The chat template supports it + const bool enable_thinking = params_base.reasoning_budget != 0 && common_chat_templates_support_enable_thinking(chat_templates.get()); + SRV_INF("Enable thinking? %d\n", enable_thinking); + oai_parser_opt = { /* use_jinja */ params_base.use_jinja, /* prefill_assistant */ params_base.prefill_assistant, @@ -2275,7 +2281,7 @@ struct server_context { /* common_chat_templates */ chat_templates.get(), /* allow_image */ mctx ? mtmd_support_vision(mctx) : false, /* allow_audio */ mctx ? mtmd_support_audio (mctx) : false, - /* enable_thinking */ params_base.reasoning_budget != 0, + /* enable_thinking */ enable_thinking, }; } diff --git a/tools/server/utils.hpp b/tools/server/utils.hpp index 036060bb..8636cf51 100644 --- a/tools/server/utils.hpp +++ b/tools/server/utils.hpp @@ -54,8 +54,8 @@ static T json_value(const json & body, const std::string & key, const T & defaul if (body.contains(key) && !body.at(key).is_null()) { try { return body.at(key); - } catch (NLOHMANN_JSON_NAMESPACE::detail::type_error const &) { - LOG_WRN("Wrong type supplied for parameter '%s'. Expected '%s', using default value\n", key.c_str(), json(default_value).type_name()); + } catch (NLOHMANN_JSON_NAMESPACE::detail::type_error const & err) { + LOG_WRN("Wrong type supplied for parameter '%s'. Expected '%s', using default value: %s\n", key.c_str(), json(default_value).type_name(), err.what()); return default_value; } } else { @@ -708,6 +708,16 @@ static json oaicompat_chat_params_parse( inputs.chat_template_kwargs[item.key()] = item.value().dump(); } + // parse the "enable_thinking" kwarg to override the default value + auto enable_thinking_kwarg = json_value(inputs.chat_template_kwargs, "enable_thinking", std::string("")); + if (enable_thinking_kwarg == "true") { + inputs.enable_thinking = true; + } else if (enable_thinking_kwarg == "false") { + inputs.enable_thinking = false; + } else if (!enable_thinking_kwarg.empty() && enable_thinking_kwarg[0] == '"') { + throw std::runtime_error("invalid type for \"enable_thinking\" (expected boolean, got string)"); + } + // if the assistant message appears at the end of list, we do not add end-of-turn token // for ex. this can be useful to modify the reasoning process in reasoning models bool prefill_assistant_message = !inputs.messages.empty() && inputs.messages.back().role == "assistant" && opt.prefill_assistant; @@ -724,7 +734,7 @@ static json oaicompat_chat_params_parse( /* TODO: test this properly */ inputs.reasoning_format = COMMON_REASONING_FORMAT_NONE; - if ( (!inputs.enable_thinking) || inputs.chat_template_kwargs.find("enable_thinking") != inputs.chat_template_kwargs.end()) { + if ( inputs.enable_thinking ) { throw std::runtime_error("Assistant response prefill is incompatible with enable_thinking."); }