server: expose the reasoning effort levels of the chat template (#31271)

* server: expose the reasoning effort levels of the chat template

The capability probe renders a user turn for each candidate level
(minimal, low, medium, high, xhigh, max) and for an unknown level. A
level is honored when it renders without raising and differently from
the unknown level, which shows the template fallback. Levels sharing a
render are aliases and the highest one is kept.

The caps serialize to JSON, and chat_template_caps in /props reports
the list as reasoning_effort_levels, from lowest to highest.

* jinja: keep the caps free of the json dependency

The caps keep reporting their flags as a map, and the effort levels
stay a plain member. common_chat_templates_get_caps() builds the JSON
the server reports from both, so jinja depends on json only for the
probe inputs.
This commit is contained in:
Pascal authored and GitHub committed 2026-10-27 22:39:37 +01:00
1 parent a919179942
commit 1b4554eff1
9 files changed
+90 -13

No files matched your search

+7 -6
View File
@@ -1940,12 +1940,13 @@ const common_chat_msg & common_chat_session::finish(const common_chat_input & ch
return result;
}
std::map<std::string, bool> common_chat_templates_get_caps(const common_chat_templates * chat_templates) {
common_json common_chat_templates_get_caps(const common_chat_templates * chat_templates) {
GGML_ASSERT(chat_templates != nullptr);
GGML_ASSERT(chat_templates->template_default != nullptr);
if (chat_templates->template_tool_use != nullptr) {
// take the more expressive template when available
return chat_templates->template_tool_use->caps.to_map();
}
return chat_templates->template_default->caps.to_map();
// take the more expressive template when available
const auto & caps = chat_templates->template_tool_use != nullptr ? chat_templates->template_tool_use->caps
: chat_templates->template_default->caps;
common_json result = caps.to_map();
result["reasoning_effort_levels"] = caps.reasoning_effort_levels;
return result;
}