[Feature] add tool parser (#3518)

* [Feature] Pass through the `chat_template_kwargs` to the data processing module (#3421)

* fix chat_template_args

* fix args

* add offline

* add offline

* fix

* fix

* fix default enable_thinking value

* fix default enable_thinking value

* modify condition

* Revert "modify condition"

This reverts commit 26430bdeb1.

* fix unit test

* add Tool Parser (#3272)

* add tool-parser

* add tool-parser

* add tool parser

* add tool parser

* fix

* add offline

* add offline

* fix

* parsers:tool&reasoning

* 修改tool parser名称·

* update

* fix reasoning-parser

* add requirements

* fix finish reason

* fix

* fix reasoning-parser

* fix

* fix

* fix

* fix

* fix

---------

Co-authored-by: zhuzixuan <zhuzixuan@baidu.com>

* [Feature] add tool parser (#3483)

* add tool parser

* add x1 enable_thinking

* restart ci

* fix vl reasoning parser

* modify call style

* modify call style

* add offline enablethinking

* fix completion

* fix

* fix unit test

* fix unit test

* fix unit test

* fix vl reasoning parser

* fix vl reasoning parser

* fix unit test

---------

Co-authored-by: zhuzixuan <zhuzixuan@baidu.com>

fastdeploy/entrypoints/openai/api_server.py

@@ -41,6 +41,7 @@ from fastdeploy.entrypoints.openai.protocol import (
 )
 from fastdeploy.entrypoints.openai.serving_chat import OpenAIServingChat
 from fastdeploy.entrypoints.openai.serving_completion import OpenAIServingCompletion
+from fastdeploy.entrypoints.openai.tool_parsers import ToolParserManager
 from fastdeploy.metrics.metrics import (
     EXCLUDE_LABELS,
     cleanup_prometheus_files,
@@ -73,7 +74,8 @@ parser.add_argument("--max-concurrency", default=512, type=int, help="max concur
 parser = EngineArgs.add_cli_args(parser)
 args = parser.parse_args()
 args.model = retrive_model_from_server(args.model, args.revision)
-
+if args.tool_parser_plugin:
+    ToolParserManager.import_tool_parser(args.tool_parser_plugin)
 llm_engine = None
 
 
@@ -126,6 +128,7 @@ async def lifespan(app: FastAPI):
         args.data_parallel_size,
         args.enable_logprob,
         args.workers,
+        args.tool_call_parser,
     )
     app.state.dynamic_load_weight = args.dynamic_load_weight
     chat_handler = OpenAIServingChat(engine_client, pid, args.ips, args.max_waiting_time)