3256 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
KernelDeimos	fa4b38cd02	fix: oops, no export (putility.libs.event)	2025-02-11 11:23:55 -05:00
KernelDeimos	e49af481ba	dev: make it easier to use putility emitter	2025-02-11 11:10:02 -05:00
KernelDeimos	a803d55cfb	fix: broken test in putility	2025-02-11 10:54:03 -05:00
KernelDeimos	70fde95255	fix: parse body before auth for /down	2025-02-10 17:54:23 -05:00
KernelDeimos	e5c3769bd8	fix: fix previous fix	2025-02-10 17:42:12 -05:00
KernelDeimos	390230c5a0	fix: potential fix for /down auth ... This is a temporary workaround for a bug de-syncing http session cookies.	2025-02-10 17:35:19 -05:00
KernelDeimos	2000b8909f	fix: allow command provider to not implement complete method	2025-02-10 17:22:10 -05:00
KernelDeimos	ad2ed295b1	dev: fix app close messages from ExecService	2025-02-10 13:59:47 -05:00
jelveh	a3513c22a2	do not repeat session picking in popup for file pickers	2025-02-07 18:07:02 -08:00
jelveh	4d380ffa8a	remove unnecessary confirmation dialog for file/directory pickers in popups	2025-02-07 17:47:58 -08:00
KernelDeimos	6dcb3777ca	dev: fix index_url issue	2025-02-07 15:57:29 -05:00
KernelDeimos	ca17f38929	dev: normalize Mistral, get tool calls working ... Mistral has a lot of unnecessary quirks because the SDK coerces to snake_case. We should see if the OpenAI client works with Mistral, and it it does we'll use that instead so we don't have to maintain all these exceptional cases.	2025-02-07 15:27:28 -05:00
KernelDeimos	735f275e7c	dev: normalize Groq (tool use works)	2025-02-07 14:01:34 -05:00
KernelDeimos	29cd14a01d	dev: XAI streaming function calls	2025-02-07 12:55:34 -05:00
jelveh	84b2400650	it fixes it surely!	2025-02-06 19:52:54 -08:00
jelveh	d4b4df06fd	Use the fetch API in Puter.js's Convert module	2025-02-06 19:45:10 -08:00
jelveh	1e5deabcdb	Update package-lock.json	2025-02-06 18:20:12 -08:00
jelveh	949d3ab17c	add Convert modules to Puter.js	2025-02-06 18:19:12 -08:00
KernelDeimos	62cf10072a	dev: include cost information in usage reports ... This adds an incremental migration from models reporting input and output tokens, to models reporting full token information. This means AIChatService doesn't need to lookup the model details or know about the different types of tokens supported by every model.	2025-02-06 17:34:57 -05:00
KernelDeimos	f7147ab312	dev: generalize how OpenAIUtil handles usage ... The current implementation would break for XAIService because it gets cumulative usage reports as the stream goes on (whereas OpenAI and DeepSeek only provide this at the end of the stream).	2025-02-06 17:34:57 -05:00
KernelDeimos	16e2729b1d	dev: migrate XAIService to normalized messages	2025-02-06 17:34:57 -05:00
KernelDeimos	ce0ab02f39	dev: add file output mode for convert	2025-02-06 17:34:57 -05:00
KernelDeimos	5e30958a14	tweak: enable convert module on selfhosted run	2025-02-06 17:34:57 -05:00
KernelDeimos	2b0e173975	dev: add convert module (and ConvertAPI)	2025-02-06 17:34:57 -05:00
ProgrammerIn-wonderlandandEric Dubé	12806a2395	only close TLS socket once	2025-02-06 17:13:04 -05:00
ProgrammerIn-wonderlandandEric Dubé	26666fe666	new API puter.net.generateWispV1URL()	2025-02-05 16:56:57 -05:00
KernelDeimos	c8bed6eaee	dev: add deepseek tool calls	2025-02-05 15:32:35 -05:00
KernelDeimos	d4eff82d3c	dev: add email attachments	2025-02-05 14:12:05 -05:00
KernelDeimos	da4a1a182b	dev: de-couple OpenAI SDK utilities from service ... This change will be helpful for making behavior across OpenAI-compatible APIs consistent.	2025-02-05 11:36:07 -05:00
KernelDeimos	50383aab59	dev: try this for now	2025-02-04 16:45:42 -05:00
KernelDeimos	e6fc773706	fix: unfixed fix from earlier	2025-02-04 16:36:06 -05:00
KernelDeimos	9dbba292c4	dev: coerce semantics of tool calls/use in messages ... If these APIs were standardized this would have been so much less painful, but alas, tool calls are implemented completely differently between Claude and OpenAI. Good job guys.	2025-02-04 16:15:47 -05:00
KernelDeimos	484bb5c201	fix: parser error for empty json buffer	2025-02-04 15:42:03 -05:00
KernelDeimos	d2358d234b	fix: fix name and id for openai tool calls	2025-02-04 14:36:30 -05:00
KernelDeimos	29c0241119	fix: let messages with tool_calls have content=null	2025-02-04 14:21:14 -05:00
KernelDeimos	8f27742038	fix: repair stream end	2025-02-04 14:09:28 -05:00
KernelDeimos	e2797c38d0	fix: add type=text	2025-02-04 14:02:01 -05:00
KernelDeimos	747614c28b	dev: integrate stream normalization for OpenAI	2025-02-04 13:57:10 -05:00
KernelDeimos	437467e0ce	dev: integrate stream normalization for Claude	2025-02-04 13:10:14 -05:00
Nariman JelvehandGitHub	0ce8fdc9f6	Merge pull request #1037 from HeyPuter/Add-TRADEMARK.md ... Create TRADEMARK.md	2025-02-03 14:23:24 -08:00
jelveh	4e17908664	Update TRADEMARK.md	2025-02-03 14:22:01 -08:00
KernelDeimos	f54b7b7b3d	dev: PoC for stream normalization	2025-02-03 16:57:13 -05:00
KernelDeimos	f0434435c4	dev: option to normalize AI response (non-streaming)	2025-02-03 14:03:27 -05:00
KernelDeimos	57231d31e4	dev: add email module to run-selfhosted	2025-02-03 13:14:52 -05:00
KernelDeimos	cfa3fde436	dev: error handling and text encoding	2025-02-03 13:11:29 -05:00
KernelDeimos	55d052cfc2	fix: various issues with Mail module	2025-02-03 12:25:22 -05:00
KernelDeimos	e281dc92e3	dev: add mail module	2025-02-03 10:08:39 -05:00
KernelDeimos	dc90999fee	dev: enable gpt-o3-mini	2025-01-31 14:48:49 -05:00
KernelDeimos	d88dedb66c	dev: normalize Claude input ... - add merging of same-role messages for all normalized inputs - generalize Claude-specific system message extraction - remove redundant behavior from Claude	2025-01-31 11:22:06 -05:00
KernelDeimos	40aa52225f	dev: make ai fallback configurable	2025-01-31 10:32:36 -05:00