config: template-detected parsers go to the engine's control-plane overlay

`init_tokenizer_manager` wrote the chat-template-detected `reasoning_parser` /
`tool_call_parser` onto the published `ServerArgs`, after
`TokenizerManager.__init__` had already projected the config bags — so the
namespace readers and the resolved-config readback disagreed with the instance,
and a second `Engine` in the same process would inherit the first one's
detection through the shared bags.

Detection is per-engine control-plane state, which the manager already models:
`record_config_updates` records it, the readback endpoints overlay it, and
`config_value` reports what is in effect. `OpenAIServingChat` — the only reader
of these two fields in the tokenizer process — follows the overlay. The
architecture pass (`resolve_auto_parsers`, before the schedulers fork) is
unchanged: the scheduler resolves its own bags from the instance it receives.

python/sglang/srt/entrypoints/engine.py

@@ -175,10 +175,12 @@ def init_tokenizer_manager(
             "tool-call parser",
         ),
     ):
-        if getattr(server_args, attr) != "auto":
+        if tokenizer_manager.config_value(attr) != "auto":
             continue
         if suggested is not None:
-            server_args.override(source="template-detection", **{attr: suggested})
+            tokenizer_manager.record_config_updates(
+                "template-detection", **{attr: suggested}
+            )
             logger.info(
                 f"Auto-detected --{attr.replace('_', '-')} as '{suggested}' from chat template"
             )
@@ -187,7 +189,9 @@ def init_tokenizer_manager(
                 f"--{attr.replace('_', '-')}=auto specified but could not detect "
                 f"{label} from chat template. Disabling {label}."
             )
-            server_args.override(source="template-detection", **{attr: None})
+            tokenizer_manager.record_config_updates(
+                "template-detection", **{attr: None}
+            )
 
     return tokenizer_manager, template_manager
 

python/sglang/srt/entrypoints/openai/serving_chat.py

@@ -203,8 +203,8 @@ class OpenAIServingChat(OpenAIServingBase):
     ):
         super().__init__(tokenizer_manager)
         self.template_manager = template_manager
-        self.tool_call_parser = self.tokenizer_manager.server_args.tool_call_parser
-        self.reasoning_parser = self.tokenizer_manager.server_args.reasoning_parser
+        self.tool_call_parser = self.tokenizer_manager.config_value("tool_call_parser")
+        self.reasoning_parser = self.tokenizer_manager.config_value("reasoning_parser")
         self.default_chat_template_kwargs = (
             self.tokenizer_manager.server_args.default_chat_template_kwargs or {}
         )
@@ -1049,9 +1049,7 @@ class OpenAIServingChat(OpenAIServingBase):
         # SGLang's ReasonerGrammarBackend owns the reasoning prefix
         # when --reasoning-parser is configured, so builtin xgrammar
         # tags must describe only the post-reasoning tool-call suffix.
-        xgrammar_reasoning = thinking_mode and (
-            self.tokenizer_manager.server_args.reasoning_parser is None
-        )
+        xgrammar_reasoning = thinking_mode and (self.reasoning_parser is None)
         tool_call_constraint = None
 
         # Apply chat template and its stop strings

python/sglang/srt/entrypoints/openai/serving_responses.py

@@ -97,8 +97,8 @@ class OpenAIServingResponses(OpenAIServingChat):
     ) -> None:
         super().__init__(tokenizer_manager, template_manager)
 
-        # template_manager is already set by parent class
-        self.reasoning_parser = self.tokenizer_manager.server_args.reasoning_parser
+        # template_manager is already set by parent class; reasoning_parser comes
+        # from the parent, which reads the manager's control-plane overlay.
         self.enable_prompt_tokens_details = enable_prompt_tokens_details
 
         # Parent OpenAIServingChat.__init__ already populated default_sampling_params.