vendor: sync minja (#15161)

* vendor: sync minja

* Update minja.hpp

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <redacted>
---------

Co-authored-by: Sigbjørn Skjæret <redacted>

diff --git a/vendor/minja/chat-template.hpp b/vendor/minja/chat-template.hpp
index cf113bf2221d20554acb4516452fd848fb7b896c..d5295b335b4f750c0e01bcca8a698d621658f18c 100644 (file)
--- a/vendor/minja/chat-template.hpp
+++ b/vendor/minja/chat-template.hpp
@@ -162,8 +162,15 @@ class chat_template {
         }), false);
         caps_.supports_tools = contains(out, "some_tool");
 
-        auto out_empty = try_raw_render(json::array({dummy_user_msg, {{"role", "assistant"}, {"content", ""}}}), {}, false);
-        auto out_null = try_raw_render(json::array({dummy_user_msg, {{"role", "assistant"}, {"content", nullptr}}}), {}, false);
+        const auto render_with_content = [&](const json & content) {
+            const json assistant_msg {{"role", "assistant"}, {"content", content}};
+            // Render two assistant messages as some templates like QwQ-32B are handling
+            // the content differently depending on whether it's the last message or not
+            // (to remove the <think> tag in all but the last message).
+            return try_raw_render(json::array({dummy_user_msg, assistant_msg, dummy_user_msg, assistant_msg}), {}, false);
+        };
+        auto out_empty = render_with_content("");
+        auto out_null = render_with_content(json());
         caps_.requires_non_null_content = contains(out_empty, user_needle) && !contains(out_null, user_needle);
 
         json j_null;
@@ -191,12 +198,12 @@ class chat_template {
             dummy_user_msg,
             make_tool_calls_msg(json::array({make_tool_call("ipython", dummy_args_obj.dump())})),
         }), {}, false);
-        auto tool_call_renders_str_arguments = contains(out, "\"argument_needle\":") || contains(out, "'argument_needle':");
+        auto tool_call_renders_str_arguments = contains(out, "<parameter=argument_needle>") || contains(out, "\"argument_needle\":") || contains(out, "'argument_needle':");
         out = try_raw_render(json::array({
             dummy_user_msg,
             make_tool_calls_msg(json::array({make_tool_call("ipython", dummy_args_obj)})),
         }), {}, false);
-        auto tool_call_renders_obj_arguments = contains(out, "\"argument_needle\":") || contains(out, "'argument_needle':");
+        auto tool_call_renders_obj_arguments = contains(out, "<parameter=argument_needle>") || contains(out, "\"argument_needle\":") || contains(out, "'argument_needle':");
 
         caps_.supports_tool_calls = tool_call_renders_str_arguments || tool_call_renders_obj_arguments;
         caps_.requires_object_arguments = !tool_call_renders_str_arguments && tool_call_renders_obj_arguments;

diff --git a/vendor/minja/minja.hpp b/vendor/minja/minja.hpp
index dd107dccdaf117e7148f7b72dc3629c82421fe11..dad75efbba5f0c78b94e0181bb7b8a5a6f69e995 100644 (file)
--- a/vendor/minja/minja.hpp
+++ b/vendor/minja/minja.hpp
@@ -1291,6 +1291,12 @@ public:
     }
 };
 
+static bool in(const Value & value, const Value & container) {
+  return (((container.is_array() || container.is_object()) && container.contains(value)) ||
+      (value.is_string() && container.is_string() &&
+        container.to_str().find(value.to_str()) != std::string::npos));
+}
+
 class BinaryOpExpr : public Expression {
 public:
     enum class Op { StrConcat, Add, Sub, Mul, MulMul, Div, DivDiv, Mod, Eq, Ne, Lt, Gt, Le, Ge, And, Or, In, NotIn, Is, IsNot };
@@ -1355,13 +1361,8 @@ public:
               case Op::Gt:        return l > r;
               case Op::Le:        return l <= r;
               case Op::Ge:        return l >= r;
-              case Op::In:        return (((r.is_array() || r.is_object()) && r.contains(l)) ||
-                                          (l.is_string() && r.is_string() &&
-                                            r.to_str().find(l.to_str()) != std::string::npos));
-              case Op::NotIn:
-                                  return !(((r.is_array() || r.is_object()) && r.contains(l)) ||
-                                            (l.is_string() && r.is_string() &&
-                                              r.to_str().find(l.to_str()) != std::string::npos));
+              case Op::In:        return in(l, r);
+              case Op::NotIn:     return !in(l, r);
               default:            break;
           }
           throw std::runtime_error("Unknown binary operator");
@@ -1500,6 +1501,13 @@ public:
           } else if (method->get_name() == "pop") {
             vargs.expectArgs("pop method", {1, 1}, {0, 0});
             return obj.pop(vargs.args[0]);
+          } else if (method->get_name() == "keys") {
+            vargs.expectArgs("keys method", {0, 0}, {0, 0});
+            auto result = Value::array();
+            for (const auto& key : obj.keys()) {
+              result.push_back(Value(key));
+            }
+            return result;
           } else if (method->get_name() == "get") {
             vargs.expectArgs("get method", {1, 2}, {0, 0});
             auto key = vargs.args[0];
@@ -1541,6 +1549,16 @@ public:
           } else if (method->get_name() == "capitalize") {
             vargs.expectArgs("capitalize method", {0, 0}, {0, 0});
             return Value(capitalize(str));
+          } else if (method->get_name() == "upper") {
+            vargs.expectArgs("upper method", {0, 0}, {0, 0});
+            auto result = str;
+            std::transform(result.begin(), result.end(), result.begin(), ::toupper);
+            return Value(result);
+          } else if (method->get_name() == "lower") {
+            vargs.expectArgs("lower method", {0, 0}, {0, 0});
+            auto result = str;
+            std::transform(result.begin(), result.end(), result.begin(), ::tolower);
+            return Value(result);
           } else if (method->get_name() == "endswith") {
             vargs.expectArgs("endswith method", {1, 1}, {0, 0});
             auto suffix = vargs.args[0].get<std::string>();
@@ -2646,15 +2664,11 @@ inline std::shared_ptr<Context> Context::builtins() {
     auto items = Value::array();
     if (args.contains("object")) {
       auto & obj = args.at("object");
-      if (obj.is_string()) {
-        auto json_obj = json::parse(obj.get<std::string>());
-        for (const auto & kv : json_obj.items()) {
-          items.push_back(Value::array({kv.key(), kv.value()}));
-        }
-      } else if (!obj.is_null()) {
-        for (auto & key : obj.keys()) {
-          items.push_back(Value::array({key, obj.at(key)}));
-        }
+      if (!obj.is_object()) {
+        throw std::runtime_error("Can only get item pairs from a mapping");
+      }
+      for (auto & key : obj.keys()) {
+        items.push_back(Value::array({key, obj.at(key)}));
       }
     }
     return items;
@@ -2782,6 +2796,9 @@ inline std::shared_ptr<Context> Context::builtins() {
       if (!items.is_array()) throw std::runtime_error("object is not iterable");
       return items;
   }));
+  globals.set("in", simple_function("in", { "item", "items" }, [](const std::shared_ptr<Context> &, Value & args) -> Value {
+      return in(args.at("item"), args.at("items"));
+  }));
   globals.set("unique", simple_function("unique", { "items" }, [](const std::shared_ptr<Context> &, Value & args) -> Value {
       auto & items = args.at("items");
       if (!items.is_array()) throw std::runtime_error("object is not iterable");