102 Commits

Author	SHA1	Message	Date
sharath	c00497865f	fix(thread_manager): adjust max_tokens calculation for deepseek model	2025-06-06 18:48:55 +00:00
Soumyadas15	ed97fc1682	update content length fix - prod	2025-06-06 17:01:07 +05:30
Soumyadas15	3f771c2a70	Merge branch 'main' into content-length-fix	2025-06-06 16:40:51 +05:30
Soumyadas15	4d7bff34c5	fix content length issue	2025-06-06 15:49:47 +05:30
sharath	b5ae395fed	refactor(thread-manager): standardize max_tokens parameter in message compression methods	2025-06-06 09:18:34 +00:00
sharath	93660e4a61	feat(thread-manager): add message compression methods to handle long messages efficiently	2025-06-06 08:56:14 +00:00
Bobbie	1b269a96b6	Merge pull request #658 from escapade-mckv/prod-2a ... Prod 2a	2025-06-06 13:21:29 +05:30
Sharath	aee5945907	hotfix(context-limit): truncate more content to allow more messages	2025-06-06 12:36:11 +05:30
Sharath	25fcdfc058	hotfix(response_processor): remove debug log	2025-06-05 18:03:52 +05:30
sharath	524e1beb67	Merge branch 'PRODUCTION'	2025-06-05 12:17:59 +00:00
sharath	6fb2c544d3	fix(agent): increase timeout for pending Redis operations and improve error logging for cost calculation	2025-06-05 11:21:34 +00:00
sharath	11e8b4f7bd	Merge branch 'PRODUCTION' into sync/production	2025-06-05 06:48:53 +00:00
sharath	eda0c69bea	fix(context-limit-retry): don't retry when context limit reached	2025-06-05 06:46:27 +00:00
Soumyadas15	e99254544d	fix(bug): fix double json dumps in response processor	2025-06-03 12:51:38 +05:30
Soumyadas15	8a7c33c86b	chore(dev): thread compression for new format	2025-06-03 12:02:50 +05:30
Vukasin	a479c7385e	chore: remove logs	2025-06-02 22:02:50 +02:00
Vukasin	0c3b520fe6	Merge remote-tracking branch 'upstream/main' into feat/port-fix-and-panel-ajustments	2025-06-02 21:11:07 +02:00
Vukasin	4cd6753e42	fix: remove cost add litellm response usage	2025-06-02 21:06:39 +02:00
Soumyadas15	f65cc3eba9	Merge branch 'main' into mcp-5a-custom-1	2025-06-02 16:34:49 +05:30
Soumyadas15	c8d39d1fdd	feat: add http mcp support	2025-06-02 16:34:14 +05:30
Vukasin	7a8a45cfe8	Merge remote-tracking branch 'upstream/main' into feat/port-fix-and-panel-ajustments	2025-06-01 17:52:11 +02:00
Vukasin	82df42badf	fix: response procesor & billing modal and other fixes	2025-06-01 17:50:09 +02:00
Soumyadas15	d53f2f7a18	chore(dev): cleanup frontend	2025-06-01 02:23:53 +05:30
Soumyadas15	b42e78b598	chore(dev): agent builder	2025-05-31 21:01:20 +05:30
Soumyadas15	e6de1e0f7f	Merge branch 'main' into mcp-5a	2025-05-30 19:02:53 +05:30
Soumyadas15	dedd6432bb	chore(dev): auto generate xml schema or mcp	2025-05-30 13:01:11 +05:30
Soumyadas15	546d5078ea	chore(dev): properly process MCP results	2025-05-30 01:04:41 +05:30
sharath	c14a2e4cb4	fix(thread_manager): reduce maximum message content length from 300k to 200k characters to prevent context overload	2025-05-29 15:50:29 +00:00
sharath	0bfd7ecb3f	fix(thread_manager): adjust token count condition to handle default max token value	2025-05-29 15:28:53 +00:00
sharath	16ba4f7c36	fix(thread_manager): update message selection query to include only message_id and content	2025-05-29 14:20:57 +00:00
sharath	960dd671f2	feat(context-compression): add ExpandMessageTool for message expansion and integrate into agent run process	2025-05-29 13:47:31 +00:00
Soumyadas15	80d4784f4c	chore(dev): refactor xml tool calls	2025-05-29 01:20:30 +05:30
Soumyadas15	57407277ed	chore(dev): refactor xml tools	2025-05-28 17:37:54 +05:30
sharath	11da6ad829	fix(tools): invalid xml issues and unnecessary validation	2025-05-26 20:32:49 +00:00
LiYuanBr	9568b582b8	fix: Modify log level from INFO to DEFAULT as Langfuse doesnt support INFO	2025-05-26 01:24:40 -03:00
Soumyadas15	fb6c130136	chore(dev): fix double escape isue	2025-05-25 02:34:07 +05:30
sharath	7db395dd88	refactor(api): enhance trace handling in response processing	2025-05-24 12:50:36 +00:00
sharath	8255c507a5	fix(backend): enhance trace logging levels for error handling and execution status	2025-05-22 08:36:58 +00:00
sharath	ff1670be90	feat(backend): langfuse traces	2025-05-21 00:39:28 +00:00
marko-kraemer	70755d3074	save all browser states	2025-05-19 01:06:44 +02:00
sharath	35de7f1b40	fix(stream): redis latency issue mitigated	2025-05-15 23:28:28 +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
marko-kraemer	7ff15d8dc7	make non-anthropic model work with response example, fe padding bottom increase cuz of new chat input	2025-05-07 01:56:52 +02:00
marko-kraemer	12704f2786	fix	2025-05-05 02:53:24 +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	973861b2d2	wip	2025-05-03 02:26:25 +02:00
mameshini	2d32e91aac	Fix: proper param_name for tool parameter mapping	2025-04-30 08:53:32 -07:00
marko-kraemer	0fc3c4a573	print	2025-04-24 17:05:05 +01:00
LE Quoc Dat	034ea37745	add models, better logs	2025-04-24 12:46:22 +01:00