Move template manager files under parser; update CODEOWNERS (#26052)

.github/CODEOWNERS

@@ -13,7 +13,7 @@
 /python/sglang/multimodal_gen/test/server/ascend  @ping1jing2 @ssshinigami @Makcum888e @e-martirosian
 /python/sglang/srt/batch_invariant_ops @Fridge003 @hebiao064
 /python/sglang/srt/compilation @hebiao064 @Oasis-Git
-/python/sglang/srt/constrained @hnyls2002 @DarkSharpness
+/python/sglang/srt/constrained @hnyls2002 @DarkSharpness @JustinTong0323
 /python/sglang/srt/disaggregation @ByronHsu @hnyls2002 @ShangmingCai @HaiShaw @sogalin
 /python/sglang/srt/disaggregation/ascend @ping1jing2 @iforgetmyname
 /python/sglang/srt/disaggregation/encode_receiver.py @ShangmingCai @liusy58 @ZhengWG @gty111
@@ -23,11 +23,13 @@
 /python/sglang/srt/distributed/device_communicators/mooncake_transfer_engine.py @ShangmingCai @stmatengss
 /python/sglang/srt/dllm @ClawSeven @btw616
 /python/sglang/srt/entrypoints @ispobock @CatherineSue @slin1237 @merrymercy @JustinTong0323
+/python/sglang/srt/entrypoints/anthropic @JustinTong0323
+/python/sglang/srt/entrypoints/openai @JustinTong0323
 /python/sglang/srt/entrypoints/engine_score_mixin.py @sundar24295s @chanh @fortunecookiee
 /python/sglang/srt/entrypoints/grpc_server.py @CatherineSue @slin1237
 /python/sglang/srt/entrypoints/openai/serving_score.py @sundar24295s @chanh @fortunecookiee
 /python/sglang/srt/eplb @fzyzcjy @ch-wan @xutizhou
-/python/sglang/srt/function_call @CatherineSue @JustinTong0323
+/python/sglang/srt/function_call @JustinTong0323
 /python/sglang/srt/grpc @CatherineSue @slin1237
 /python/sglang/srt/hardware_backend/mlx @yeahdongcn
 /python/sglang/srt/hardware_backend/musa @yeahdongcn
@@ -60,9 +62,11 @@
 /python/sglang/srt/models/transformers.py @adarshxs
 /python/sglang/srt/multimodal @mickqian @JustinTong0323 @yhyang201 @yuan-luo
 /python/sglang/srt/observability @merrymercy @fzyzcjy @sufeng-buaa
+/python/sglang/srt/parser @JustinTong0323
 /python/sglang/srt/platforms @merrymercy @whybeyoung @alexnails
 /python/sglang/srt/ray @Qiaolin-Yu @xyuzh
 /python/sglang/srt/speculative @Ying1123 @merrymercy @hnyls2002 @Qiaolin-Yu
+/python/sglang/srt/utils/hf_transformers @JustinTong0323
 /sgl-kernel @ispobock @BBuf @yizhang2077 @merrymercy @FlamingoPg @HaiShaw
 /sgl-kernel/csrc/musa @yeahdongcn
 /sgl-model-gateway @slin1237 @CatherineSue

python/sglang/srt/entrypoints/anthropic/serving.py

@@ -52,8 +52,8 @@ from sglang.srt.entrypoints.openai.protocol import (
     ToolChoice,
     ToolChoiceFuncName,
 )
-from sglang.srt.managers.template_detection import detect_inline_system_support
 from sglang.srt.observability.req_time_stats import monotonic_time
+from sglang.srt.parser.template_detection import detect_inline_system_support
 
 if TYPE_CHECKING:
     from sglang.srt.entrypoints.openai.serving_chat import OpenAIServingChat

python/sglang/srt/entrypoints/engine.py

@@ -88,10 +88,10 @@ from sglang.srt.managers.multi_tokenizer_mixin import (
     run_multi_detokenizer_router_process,
 )
 from sglang.srt.managers.scheduler import run_scheduler_process
-from sglang.srt.managers.template_detection import resolve_auto_parsers
-from sglang.srt.managers.template_manager import TemplateManager
 from sglang.srt.managers.tokenizer_manager import TokenizerManager
 from sglang.srt.observability.trace import process_tracing_init, trace_set_thread_info
+from sglang.srt.parser.template_detection import resolve_auto_parsers
+from sglang.srt.parser.template_manager import TemplateManager
 from sglang.srt.plugins import load_plugins
 from sglang.srt.server_args import PortArgs, ServerArgs
 from sglang.srt.utils import (

python/sglang/srt/entrypoints/http_server.py

@@ -149,7 +149,6 @@ from sglang.srt.managers.multi_tokenizer_mixin import (
     read_from_shared_memory,
     write_data_for_multi_tokenizer,
 )
-from sglang.srt.managers.template_manager import TemplateManager
 from sglang.srt.managers.tokenizer_manager import ServerStatus, TokenizerManager
 from sglang.srt.observability.func_timer import enable_func_timer
 from sglang.srt.observability.trace import (
@@ -158,6 +157,7 @@ from sglang.srt.observability.trace import (
     trace_set_thread_info,
 )
 from sglang.srt.parser.reasoning_parser import ReasoningParser
+from sglang.srt.parser.template_manager import TemplateManager
 from sglang.srt.server_args import PortArgs, ServerArgs
 from sglang.srt.utils import (
     add_prometheus_middleware,

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

@@ -71,8 +71,8 @@ from sglang.srt.parser.jinja_template_utils import process_content_for_template_
 from sglang.srt.parser.reasoning_parser import ReasoningParser
 
 if TYPE_CHECKING:
-    from sglang.srt.managers.template_manager import TemplateManager
     from sglang.srt.managers.tokenizer_manager import TokenizerManager
+    from sglang.srt.parser.template_manager import TemplateManager
 
 logger = logging.getLogger(__name__)
 

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

@@ -19,8 +19,8 @@ from sglang.srt.entrypoints.openai.serving_base import OpenAIServingBase
 from sglang.srt.managers.io_struct import EmbeddingReqInput
 
 if TYPE_CHECKING:
-    from sglang.srt.managers.template_manager import TemplateManager
     from sglang.srt.managers.tokenizer_manager import TokenizerManager
+    from sglang.srt.parser.template_manager import TemplateManager
 
 logger = logging.getLogger(__name__)
 

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

@@ -34,8 +34,8 @@ from sglang.srt.parser.code_completion_parser import (
 from sglang.utils import convert_json_schema_to_str
 
 if TYPE_CHECKING:
-    from sglang.srt.managers.template_manager import TemplateManager
     from sglang.srt.managers.tokenizer_manager import TokenizerManager
+    from sglang.srt.parser.template_manager import TemplateManager
 
 logger = logging.getLogger(__name__)
 

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

@@ -21,8 +21,8 @@ from sglang.srt.parser.conversation import generate_embedding_convs
 from sglang.srt.parser.jinja_template_utils import process_content_for_template_format
 
 if TYPE_CHECKING:
-    from sglang.srt.managers.template_manager import TemplateManager
     from sglang.srt.managers.tokenizer_manager import TokenizerManager
+    from sglang.srt.parser.template_manager import TemplateManager
 
 
 class OpenAIServingEmbedding(OpenAIServingBase):

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

@@ -74,8 +74,8 @@ from sglang.srt.parser.reasoning_parser import ReasoningParser
 from sglang.srt.utils import random_uuid
 
 if TYPE_CHECKING:
-    from sglang.srt.managers.template_manager import TemplateManager
     from sglang.srt.managers.tokenizer_manager import TokenizerManager
+    from sglang.srt.parser.template_manager import TemplateManager
 
 logger = logging.getLogger(__name__)
 

python/sglang/srt/parser/template_manager.py

@@ -23,14 +23,6 @@ import logging
 import os
 from typing import Dict, Optional
 
-from sglang.srt.managers.template_detection import (
-    REASONING_PARSER_RULES,
-    TOOL_CALL_PARSER_RULES,
-    ReasoningToggleConfig,
-    build_detection_context,
-    detect_reasoning_pattern,
-    match_rules,
-)
 from sglang.srt.managers.tokenizer_manager import TokenizerManager
 from sglang.srt.parser.code_completion_parser import (
     CompletionTemplate,
@@ -47,6 +39,14 @@ from sglang.srt.parser.conversation import (
     register_conv_template,
 )
 from sglang.srt.parser.jinja_template_utils import detect_jinja_template_content_format
+from sglang.srt.parser.template_detection import (
+    REASONING_PARSER_RULES,
+    TOOL_CALL_PARSER_RULES,
+    ReasoningToggleConfig,
+    build_detection_context,
+    detect_reasoning_pattern,
+    match_rules,
+)
 
 logger = logging.getLogger(__name__)
 

test/registered/unit/entrypoints/anthropic/test_serving.py

@@ -18,7 +18,7 @@ from sglang.srt.entrypoints.openai.protocol import (  # noqa: E402
     ChatCompletionRequest,
     ChatCompletionResponse,
 )
-from sglang.srt.managers.template_detection import (  # noqa: E402
+from sglang.srt.parser.template_detection import (  # noqa: E402
     detect_inline_system_support,
 )
 from sglang.test.ci.ci_register import register_cpu_ci  # noqa: E402

test/registered/unit/entrypoints/openai/test_serving_chat.py

@@ -28,7 +28,7 @@ from sglang.srt.entrypoints.openai.serving_chat import (
     normalize_tool_content,
 )
 from sglang.srt.managers.io_struct import GenerateReqInput
-from sglang.srt.managers.template_detection import ReasoningToggleConfig
+from sglang.srt.parser.template_detection import ReasoningToggleConfig
 from sglang.srt.utils import get_or_create_event_loop
 from sglang.test.ci.ci_register import register_cpu_ci
 
@@ -1164,7 +1164,7 @@ class ServingChatTestCase(unittest.TestCase):
 
     def test_dpsk_v32_encoding_path(self):
         """Test DeepSeek V3.2 encoding path detection and application."""
-        from sglang.srt.managers.template_manager import TemplateManager
+        from sglang.srt.parser.template_manager import TemplateManager
 
         # Only mock the fields that _use_dpsk_v32_encoding() actually reads:
         # tokenizer.chat_template and hf_config.architectures

test/registered/unit/parser/test_template_manager.py

@@ -4,7 +4,7 @@ import unittest
 from types import ModuleType, SimpleNamespace
 from unittest.mock import Mock, patch
 
-from sglang.srt.managers.template_detection import (
+from sglang.srt.parser.template_detection import (
     REASONING_PARSER_RULES,
     TOOL_CALL_PARSER_RULES,
     ReasoningToggleConfig,