Relax prefill parser to allow space. (ggml-org#21240)

* Relax prefill parser to allow space.

* Move changes from prefix() to parser generation

* Only allow spaces if we're not having a pure content parser next

Author: pwilkin

common/chat-auto-parser-generator.cpp

@@ -100,19 +100,22 @@ common_peg_arena autoparser::build_parser(const generation_params & inputs) cons
 
         bool has_tools           = inputs.tools.is_array() && !inputs.tools.empty();
         bool has_response_format = inputs.json_schema.is_object() && !inputs.json_schema.empty();
+        bool pure_content        = reasoning.mode == reasoning_mode::NONE;
 
         if (has_response_format) {
             auto response_format = p.rule("response-format", p.content(p.schema(p.json(), "response-format-schema", inputs.json_schema)));
             parser = ctx.reasoning_parser + p.space() + p.choice({
                 p.literal("```json") + p.space() + response_format + p.space() + p.literal("```"),
                 response_format
             }) + p.end();
+            pure_content = false;
         } else if (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE && jinja_caps.supports_tool_calls) {
             parser = tools.build_parser(ctx);
+            pure_content = false;
         } else {
             parser = content.build_parser(ctx);
         }
-        return p.prefix(inputs.generation_prompt, reasoning.start) + parser;
+        return pure_content ? p.prefix(inputs.generation_prompt, reasoning.start) + parser : p.prefix(inputs.generation_prompt, reasoning.start) << parser;
     });
 }
 

common/chat.cpp

@@ -1709,7 +1709,7 @@ static common_chat_params common_chat_templates_apply_jinja(const struct common_
         data.format                    = COMMON_CHAT_FORMAT_PEG_NATIVE;
         data.generation_prompt         = params.generation_prompt;
         auto parser                    = build_chat_peg_parser([&params](common_chat_peg_builder &p) {
-            return p.prefix(params.generation_prompt) + p.content(p.rest());
+            return p.prefix(params.generation_prompt) << p.content(p.rest());
         });
         data.parser                    = parser.save();
         return data;