better supports_string_content cap detect

common/jinja/caps.cpp

@@ -23,7 +23,7 @@ void caps_apply_preserve_reasoning(jinja::context & ctx, bool enabled) {
     ctx.set_val("preserve_thinking",         mk_val<value_bool>(enabled));
     ctx.set_val("clear_thinking",            mk_val<value_bool>(!enabled));
     ctx.set_val("truncate_history_thinking", mk_val<value_bool>(!enabled));
-    ctx.set_val("drop_thinking",            mk_val<value_bool>(!enabled));
+    ctx.set_val("drop_thinking",             mk_val<value_bool>(!enabled));
 }
 
 void caps_apply_reasoning_effort(jinja::context & ctx, const std::string & effort) {
@@ -117,6 +117,8 @@ caps caps_get(jinja::program & prog) {
 
     JJ_DEBUG("%s\n", ">>> Running capability check: typed content");
 
+    static const std::string content_marker = "STRING_MARKER";
+
     // case: typed content support
     caps_try_execute(
         prog,
@@ -125,22 +127,26 @@ caps caps_get(jinja::program & prog) {
             return json::array({
                 {
                     {"role", "user"},
-                    {"content", "content"}
+                    {"content", content_marker}
                 }
             });
         },
         nullptr, // ctx_fn
         nullptr, // tools_fn
-        [&](context &, bool success, value & messages, value &, const std::string &) {
+        [&](context &, bool success, value & messages, value &, const std::string & rendered) {
             auto & content = messages->at(0)->at("content");
             caps_print_stats(content, "messages[0].content");
-            if (has_op(content, "selectattr") || has_op(content, "array_access")) {
+            bool used_as_array = has_op(content, "selectattr") || has_op(content, "array_access");
+            if (used_as_array) {
                 // accessed as an array
                 result.supports_typed_content = true;
             }
             if (!success) {
                 // failed to execute with content as string
                 result.supports_string_content = false;
+            } else if (used_as_array && rendered.find(content_marker) == std::string::npos) {
+                // edge case: string may be accessed for checking, but does not appear in the output
+                result.supports_string_content = false;
             }
         }
     );

tests/test-jinja.cpp

@@ -10,6 +10,7 @@
 #include "jinja/parser.h"
 #include "jinja/lexer.h"
 #include "jinja/utils.h"
+#include "jinja/caps.h"
 
 #include "testing.h"
 
@@ -33,6 +34,7 @@ static void test_array_methods(testing & t);
 static void test_object_methods(testing & t);
 static void test_hasher(testing & t);
 static void test_stats(testing & t);
+static void test_caps(testing & t);
 static void test_string_parts(testing & t);
 static void test_fuzzing(testing & t);
 
@@ -73,6 +75,7 @@ int main(int argc, char *argv[]) {
     if (!g_python_mode) {
         t.test("hasher", test_hasher);
         t.test("stats", test_stats);
+        t.test("caps", test_caps);
         t.test("string parts", test_string_parts);
         t.test("fuzzing", test_fuzzing);
     }
@@ -2059,6 +2062,52 @@ static void test_stats(testing & t) {
     });
 }
 
+static void test_caps(testing & t) {
+    static auto get_caps = [](const std::string & tmpl) -> jinja::caps {
+        jinja::lexer lexer;
+        auto lexer_res = lexer.tokenize(tmpl);
+
+        jinja::program prog = jinja::parse_from_tokens(lexer_res);
+
+        return jinja::caps_get(prog);
+    };
+
+    t.test("string content", [](testing & t) {
+        auto caps = get_caps(
+            "{% for message in messages %}"
+            "{{ message['role'] + ': ' + message['content'] }}"
+            "{% endfor %}"
+        );
+        t.assert_true("supports string content", caps.supports_string_content);
+        t.assert_true("does not support typed content", !caps.supports_typed_content);
+    });
+
+    t.test("typed content, raises on string", [](testing & t) {
+        // rendering with string content throws: 'selectattr' is not a String filter
+        auto caps = get_caps(
+            "{% for message in messages %}"
+            "{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}"
+            "{{ content['text'] }}"
+            "{% endfor %}"
+            "{% endfor %}"
+        );
+        t.assert_true("does not support string content", !caps.supports_string_content);
+        t.assert_true("supports typed content", caps.supports_typed_content);
+    });
+
+    t.test("typed content, silently drops string", [](testing & t) {
+        // rendering with string content does not throw, but content[0]['text'] yields
+        // undefined for a string, so the message is silently dropped (MiniMax-M1 shape)
+        auto caps = get_caps(
+            "{% for message in messages %}"
+            "{{ message['content'][0]['text'] }}"
+            "{% endfor %}"
+        );
+        t.assert_true("does not support string content", !caps.supports_string_content);
+        t.assert_true("supports typed content", caps.supports_typed_content);
+    });
+}
+
 static void test_string_parts(testing & t) {
     static auto render = [](const std::string & tmpl, const json & vars) -> jinja::string {
         jinja::lexer lexer;