848 commits

Author	SHA1	Message	Date
Owen	ef051c2f8c	Dont count usage when the response was not successful	2026-08-19 15:59:01 -04:00
Owen	437ec50019	Update the usage records to use logs db	2026-08-19 12:03:30 -04:00
miloschwartz	bdd7f40688	batch identity key emails	2026-08-18 16:00:07 -04:00
Owen	7a61b182e0	Deduplicate inference resources by fullDomain to prevent duplicate routers	2026-08-17 17:13:22 -04:00
Owen	91b697b80b	Track public inference domains to avoid duplicate routers for siteResource aliases	2026-08-17 17:06:37 -04:00
miloschwartz	313f777e44	rename routes from inference to ai-gateway	2026-08-17 15:38:43 -04:00
miloschwartz	697bea814e	bump version	2026-08-17 15:00:18 -04:00
Owen	87a3e5ceea	Generate the cert properly	2026-08-17 13:45:51 -04:00
Owen	555b36e13e	Fix target pulling still being private	2026-08-17 13:40:09 -04:00
Owen	af515f1072	Pass 2 bring over browser resources and http resource cert gen	2026-08-17 12:00:12 -04:00
Owen	c90c67eab3	Pass 1 of pulling traefik config into functions	2026-08-17 12:00:12 -04:00
Owen	11daf4f927	Move certificates	2026-08-17 12:00:12 -04:00
Owen	58195b5959	Move the acme cert sync	2026-08-17 12:00:12 -04:00
Owen	b51aecf45a	Remove advanced resources paywall	2026-08-17 12:00:12 -04:00
miloschwartz	53b1d8a9f3	option to send identity keys in email	2026-08-14 17:37:17 -04:00
miloschwartz	a3dfb30a42	send email upon generate virtual api key	2026-08-14 16:51:27 -04:00
Owen	3a18a3994f	Fix private resource ssl when applying through blueprints	2026-08-14 14:21:00 -04:00
Owen	193f6da8d1	Handle the list of models without allow/block	2026-08-14 12:23:20 -04:00
Owen	954dc8d1d9	Handle overlapping fullDomain properly	2026-08-14 12:23:20 -04:00
Owen	234819f8f2	Dont load private resource inference without a exit node loaded	2026-08-14 12:23:20 -04:00
Owen	c8f170d197	Allow budgets to be set on the resources	2026-08-14 11:43:01 -04:00
Owen	4989d1e31a	Allow overlapping domains on public inference resources	2026-08-14 11:43:01 -04:00
Owen	574ae8f5f9	Include inference support in blueprints	2026-08-14 10:51:59 -04:00
Owen	03118f1ede	Support labels on blueprints ... Ref https://github.com/orgs/fosrl/discussions/2849	2026-08-14 09:16:50 -04:00
miloschwartz	9b10292e02	add model picker to create provider wizard	2026-08-13 15:08:10 -04:00
miloschwartz	e21c9eec31	Merge branch 'aig' of https://github.com/fosrl/pangolin into aig	2026-08-13 09:29:02 -04:00
miloschwartz	a9f32102b5	format custom error codes according to capability	2026-08-13 09:26:58 -04:00
Owen	7291628f86	optionally stamp ip header for downstream use	2026-08-13 09:14:37 -04:00
Owen	5fbb205044	search the right resource	2026-08-12 17:52:39 -04:00
Owen	3cfbd66a80	Merge branch 'dev' into aig	2026-08-12 16:34:52 -04:00
Owen	860fa47b7c	Split out the token header into a common middleware for efficiency	2026-08-12 16:30:42 -04:00
Owen	cc58e28e54	Allow merging a catalog file with the api response	2026-08-12 16:06:12 -04:00
Owen	653dd920ad	Allow remote header overrides and fix display issues with log	2026-08-12 15:54:22 -04:00
miloschwartz	dd78c2cc08	dont show servers idps in create user when idp mode is org on enterprise	2026-08-12 15:20:41 -04:00
Owen	47ae017f94	add virtual api keys to budgets	2026-08-12 13:21:56 -04:00
miloschwartz	c33fa8782b	Merge branch 'aig' of https://github.com/fosrl/pangolin into aig	2026-08-12 12:35:30 -04:00
miloschwartz	93cba1d098	support sending capability specific error codes	2026-08-12 12:34:25 -04:00
Owen	bed5817da3	send, process, store, display virtual api key ai information in usage and sessions	2026-08-12 11:20:25 -04:00
miloschwartz	49020fa6ea	add virtual api key validation in verifySession	2026-08-12 10:38:26 -04:00
Owen	ac3402a8b3	Adjust structure delete models	2026-08-12 09:41:42 -04:00
Owen	9369e60695	Merge branch 'dev' into aig	2026-08-12 09:19:12 -04:00
Owen	295e38d2af	Remove arbitrary max 50 limit from email whitelist ... Fix #3568	2026-08-12 09:11:10 -04:00
Owen	f7aca85417	link the usage with the session to display together	2026-08-11 16:15:01 -04:00
miloschwartz	c42df737b0	improve model provider selection algorithm	2026-08-11 16:10:46 -04:00
Owen	bc2f291352	normalize the requests to also store in the log for viewing later	2026-08-11 14:45:25 -04:00
miloschwartz	98f5e39a7f	show ai gateway resource details in launcher	2026-08-11 14:42:07 -04:00
Owen	c781be4e70	quiet up some more logs	2026-08-11 14:05:58 -04:00
Owen	48c4b44f72	log chat sessions to database	2026-08-11 12:19:28 -04:00
Owen	68a84181d9	remove excess logging	2026-08-11 12:19:27 -04:00
Owen	b60390d805	batch up usage records for insert	2026-08-11 12:19:27 -04:00