Files
llama.cpp/common/jinja/caps.h
T
Pascal a946eb541a server: answer reasoning_effort levels the template rejects with 400 (#32332)
The reasoning effort probe already renders every candidate level, but
it dropped the ones the template raises on, so a request with such a
level (e.g. max on Qwen3.8) reached the template and came back as a
500 on /v1/chat/completions, /v1/responses and /v1/messages.

Keep the raising levels in reasoning_effort_rejected and reject them
in oaicompat_chat_params_parse with an invalid_argument, which the
server answers with a 400 listing the supported levels. Aliases and
levels a template ignores are not rejected, so high on Qwen3.8
still renders as xhigh.

Also trim the output_config.effort test to a single level.
2026-11-16 06:55:56 +01:00

48 lines
1.3 KiB
C++

#pragma once
#include "runtime.h"
#include <string>
#include <map>
#include <vector>
namespace jinja {
struct caps {
bool supports_tools = true;
bool supports_tool_calls = true;
bool supports_system_role = true;
bool supports_parallel_tool_calls = true;
// supports preserve reasoning trace in the full history, not just the last assistant message
bool supports_preserve_reasoning = false;
// supports reasoning effort levels
bool supports_reasoning_effort = false;
// reasoning effort levels the template renders distinctly, from lowest to highest
std::vector<std::string> reasoning_effort_levels;
// reasoning effort levels the template raises on
std::vector<std::string> reasoning_effort_rejected;
// one of the 2 content capabilities must be true
bool supports_string_content = true;
bool supports_typed_content = false;
bool supports_object_arguments = false;
// for reporting on server
std::map<std::string, bool> to_map() const;
// for debugging
std::string to_string() const;
};
caps caps_get(jinja::program & prog);
void caps_apply_preserve_reasoning(jinja::context & ctx, bool enabled);
void caps_apply_reasoning_effort(jinja::context & ctx, const std::string & effort);
} // namespace jinja