pedrohsdb c939d34603 set extract-actions thinking budget to 512, others to 1024 (#4249)

2025-12-09 12:57:10 -08:00

..

__init__.py

Implement LLM router (#95)

2024-03-16 23:13:18 -07:00

api_handler_factory.py

set extract-actions thinking budget to 512, others to 1024 (#4249)

2025-12-09 12:57:10 -08:00

api_handler.py

Move LLMAPIHandler to its own file (#4216)

2025-12-05 16:36:59 -07:00

commentjson.py

vendor and update commentjson since it is abandoned (#2689)

2025-06-12 10:50:16 -04:00

config_registry.py

add support for gpt 5.1 (#4197)

2025-12-04 17:08:16 -05:00

exceptions.py

raise exception when non dict response (#4057)

2025-11-21 15:19:06 +08:00

models.py

Move LLMAPIHandler to its own file (#4216)

2025-12-05 16:36:59 -07:00

schema_validator.py

Add schema validation and default value filling for extraction results (#4063)

2025-11-28 15:10:41 +08:00

ui_tars_llm_caller.py

ui tars integration fix (#2714)

2025-06-13 16:52:14 -04:00

ui_tars_response.py

support volcengine + migrate ui tars to volcengine (#2705)

2025-06-13 21:17:32 +08:00

utils_test.py

Add tests (mostly AI generaed/vibe coding) for parse_api_response + existing tests (#2688)

2025-06-11 14:47:58 -07:00

utils.py

Add invalid response to log to help us better debug it (#4142)

2025-11-29 00:58:10 -05:00

vertex_cache_manager.py

restore vertex cache credentials (#4050)

2025-11-20 14:54:53 -08:00