diff --git a/common/arg.cpp b/common/arg.cpp
index 79405b59e..2669cacd6 100644
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -960,6 +960,11 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
         ));
     }
 
+    // if the preserve_reasoning kwarg was not specified explicitly, enable it by default
+    if (!params.default_template_kwargs.count("preserve_reasoning")) {
+        params.default_template_kwargs["preserve_reasoning"] = "true";
+    }
+
     return true;
 }
 
@@ -3553,6 +3558,10 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
                     LOG_WRN("Setting 'enable_thinking' via --chat-template-kwargs is deprecated. "
                             "Use --reasoning on / --reasoning off instead.\n");
                 }
+                if (item.key() == "preserve_reasoning") {
+                    LOG_WRN("Setting 'preserve_reasoning' via --chat-template-kwargs is deprecated. "
+                            "Use --reasoning-preserve / --no-reasoning-preserve instead.\n");
+                }
                 params.default_template_kwargs[item.key()] = item.value().dump();
             }
         }
@@ -3743,7 +3752,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
     add_opt(common_arg(
         {"--reasoning-preserve"},
         {"--no-reasoning-preserve"},
-        "preserve reasoning trace in the full history, not just the last assistant message (default: template default)\n"
+        "preserve reasoning trace in the full history, not just the last assistant message (default: enabled)\n"
         "compatible with certain templates having 'supports_preserve_reasoning' capability\n"
         "example: https://docs.z.ai/guides/capabilities/thinking-mode#preserved-thinking",
         [](common_params & params, bool value) {
@@ -3752,6 +3761,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
             } else {
                 params.default_template_kwargs["preserve_reasoning"] = "false";
             }
+            params.preserve_reasoning_specified = true;
         }
     ).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_REASONING_PRESERVE"));
     add_opt(common_arg(
diff --git a/common/common.h b/common/common.h
index 4e9448bb1..63d0badd0 100644
--- a/common/common.h
+++ b/common/common.h
@@ -270,7 +270,7 @@ struct common_params_sampling {
         COMMON_SAMPLER_TYPE_TEMPERATURE,
     };
 
-    common_grammar              grammar;      // optional grammar constraint (user / output-format / tool-calls)
+    common_grammar                      grammar;          // optional grammar constraint (user / output-format / tool-calls)
     bool                                grammar_lazy = false;
     std::vector<common_grammar_trigger> grammar_triggers; // optional triggers (for lazy grammars)
     std::set<llama_token>               preserved_tokens;
@@ -657,6 +657,7 @@ struct common_params {
     std::string ssl_file_cert = "";                                                                         // NOLINT
 
     std::map<std::string, std::string> default_template_kwargs;
+    bool preserve_reasoning_specified = false;
 
     // CLI params
     std::string server_base; // if set, connect to this server instead of starting a new one
diff --git a/tools/server/server-context.cpp b/tools/server/server-context.cpp
index f5477356d..f78cfb36d 100644
--- a/tools/server/server-context.cpp
+++ b/tools/server/server-context.cpp
@@ -1493,11 +1493,22 @@ private:
                 auto caps = common_chat_templates_get_caps(chat_params.tmpls.get());
                 auto it = params_base.default_template_kwargs.find("preserve_reasoning");
                 bool supported = caps.at("supports_preserve_reasoning");
-                bool enabled = it != params_base.default_template_kwargs.end();
+                bool specified = params_base.preserve_reasoning_specified;
+                // note: the kwarg is enabled by default if not specified explicitly, so check the value
+                bool enabled = it != params_base.default_template_kwargs.end() && it->second == "true";
+                if (supported) {
+                    SRV_TRC("preserve_reasoning kwarg: %s\n",
+                            it == params_base.default_template_kwargs.end() ? "unset (template default)" : it->second.c_str());
+                } else {
+                    SRV_TRC("%s", "preserve_reasoning kwarg: not supported by template\n");
+                }
+                if (supported && !specified) {
+                    SRV_WRN("%s", "chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve)\n");
+                }
                 if (supported && !enabled) {
                     SRV_INF("%s", "chat template supports preserving reasoning, consider enabling it via --reasoning-preserve\n");
                 }
-                if (!supported && enabled) {
+                if (!supported && specified && enabled) {
                     SRV_WRN("%s", "chat template does NOT support preserving reasoning, --reasoning-preserve has no effect\n");
                 }
             }