28 Commits

Author	SHA1	Message	Date
sharath	13c31d42f6	feat(kimi-k2): add support for Kimi-K2 model with updated token limits and parameters	2025-07-15 13:12:30 +00:00
sharath	df871a6eb9	chore(backend): add grok fallbacks ... - Moved fallback model assignment to a dedicated function in `prepare_params`. - Removed redundant fallback handling from `make_llm_api_call`. - Updated model constants to include aliases for `xai/grok-4`.	2025-07-11 15:11:02 +00:00
sharath	d3480100f6	Merge branch 'PRODUCTION'	2025-07-11 13:13:34 +00:00
Sharath	8cbaf3d44a	fix(backend): anthropic overloaded fallback failure (#929)	2025-07-11 18:36:15 +05:30
marko-kraemer	957a2c9cbf	model fallback, add xai grok 4	2025-07-10 12:58:10 +02:00
Saumya	26a9de5a5d	chore: code cleanup and credential profiles	2025-07-09 15:00:30 +05:30
sharath	3fe6a6de61	refactor(llm): streamline cache control application for message content	2025-06-27 15:24:02 +00:00
sharath	e98ab052f9	chore(api, billing, llm): update worker count, refine billing tier names, and adjust logging in LLM API calls	2025-06-27 15:12:58 +00:00
sharath	fe637b0c51	feat(llm): add fallback parameters for Claude model in LLM service	2025-06-22 19:01:00 +00:00
sharath	1cbc2a63c9	refactor(llm): limit processing of user and assistant messages to a maximum of 4	2025-06-07 10:14:54 +00:00
marko-kraemer	c6d13b5187	run, thread_run, response processor, raise errs properly	2025-05-10 03:58:57 +02:00
Marco Vinciguerra	e1974c8125	feat: removed unused imports	2025-05-07 15:24:00 +02:00
Korzhavin Ivan	68fafdd385	Refactor agent and tool configurations to support new model names and parameters ... - Adjusted max_tokens logic based on model type, including new conditions for "gpt-4". - Enhanced MessageTool to include detailed documentation and examples for user interactions. - Improved ThreadManager to handle new tool choices and reasoning efforts. - Updated LLM service to incorporate enable_thinking and reasoning_effort parameters. - Modified chat input component to dynamically manage model selection and thinking options.	2025-05-03 14:17:46 +02:00
marko-kraemer	7a57ee210a	add conf, with local/dev/prod mode	2025-04-24 01:45:58 +01:00
LE Quoc Dat	c1514d56a1	improve cache-control	2025-04-23 17:06:40 +01:00
LE Quoc Dat	c84ee59dc6	thinking & reasoning	2025-04-18 05:49:41 +01:00
LE Quoc Dat	70882f9292	claude prompt-caching	2025-04-18 04:49:27 +01:00
marko-kraemer	647e10a74b	wip	2025-04-17 23:17:48 +01:00
Adam Cohen Hillel	f0c3c52cf4	exra	2025-04-15 19:11:09 +01:00
marko-kraemer	57d08c76af	wip	2025-04-10 17:02:21 +01:00
marko-kraemer	6eb516e61d	native tool call wip	2025-04-07 18:35:40 +01:00
marko-kraemer	3c0634f6bc	fix duplicate agent run	2025-04-06 17:45:02 +01:00
Marko Kraemer	7ee68b4282	Refactor to messages table ... * wip * bedrock support * wip * frontend messages table imp * messages imp	2025-04-06 11:10:18 +02:00
Marko Kraemer	9edad0073b	v1 full refactor LLM Response Processor (#24)	2025-04-04 17:06:49 +02:00
marko-kraemer	57153f19c8	fix imps	2025-04-01 11:49:35 -07:00
marko-kraemer	486f11ba77	logger	2025-03-31 19:36:26 -07:00
marko-kraemer	cbf7ca141e	logger v1	2025-03-31 18:26:52 -07:00
marko-kraemer	397c9a7dc6	fe reference wip	2025-03-29 23:48:57 -07:00