kunthawat/moreminimore-vibe
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
398 Commits 1 Branch 0 Tags
5d678c2ead765800a52ab0b1eedba4a22f3e6480
Commit Graph

56 Commits

Author SHA1 Message Date
Will Chen
5d678c2ead Smart auto (#476) 2025-06-23 23:08:29 -07:00
Will Chen
2f00dc5955 Add more logging around git commit failure (#467) 
Help with #464

Co-authored-by: William Chen <will@mac.lan>
 2025-06-23 13:11:28 -07:00
Will Chen
c879a4e01d always use engine if pro modes are enabled (#449) 2025-06-19 12:04:24 -07:00
Will Chen
9fbd7031d9 build ask mode (#444) 2025-06-19 10:42:51 -07:00
Will Chen
8464609ba8 Fix parsing dyad tags with nested tags: < > (#445) 
Fixes #441
 2025-06-19 10:08:26 -07:00
Will Chen
897d2e522c enable engine for all models (#434) 2025-06-18 17:17:29 -07:00
Will Chen
e326f14779 Revert "Revert "Update gemini 2.5 models to GA variants (#425)" (#429)" (#437) 
This reverts commit ff4e93d747.
 2025-06-18 17:11:17 -07:00
Will Chen
382fe9bab5 support setting for writing supabase migration files (#427) 2025-06-17 15:14:02 -07:00
Will Chen
d6d6918d1b Safe send (#421) 2025-06-16 21:58:20 -07:00
Will Chen
30b5c0d0ef Replace thinking with native Gemini thinking summaries (#400) 
This uses Gemini's native [thinking
summaries](https://cloud.google.com/vertex-ai/generative-ai/docs/thinking#thought-summaries)
which were recently added to the API.

Why? The grafted thinking would sometimes cause weird issues where the
model, especially Gemini 2.5 Flash, got confused and put dyad tags like
`<dyad-write>` inside the `<think>` tags.

This also improves the UX because you can see the native thoughts rather
than having the Gemini response load for a while without any feedback.

I tried adding Anthropic extended thinking, however it requires temp to
be set at 1, which isn't ideal for Dyad's use case where we need precise
syntax following.
 2025-06-16 17:29:32 -07:00
Will Chen
67dc9f4c42 Print engine/gateway URL more clearly (#396) 2025-06-13 10:05:12 -07:00
Will Chen
99e6592abc commit upgrade (#391) 2025-06-11 15:42:10 -07:00
Will Chen
fa80014e16 Remove budget saver mode (#378) 
This code was quite complex and hairy and resulted in very opaque errors
(for both free and pro users). There's not much benefit to budget saver
because Google removed 2.5 Pro free quota a while ago (after it
graduated the model from experimental to preview). Dyad Pro users can
still use 2.5 Flash free quota by disabling Dyad Pro by clicking on the
Dyad Pro button at the top.
 2025-06-10 13:54:27 -07:00
Will Chen
534cbad909 Allow manual context management (#376) 2025-06-10 13:52:20 -07:00
Will Chen
1a39238ecf Use max retries 3 when there's no backup clients (#339) 
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
 2025-06-09 13:43:54 -07:00
Will Chen
16bf0828f5 Fix stale app UI (supabase) & overall E2E test infra improvements (#337) 
Fixes #269
 2025-06-04 23:07:59 -07:00
Will Chen
3558663ab7 Support native Git (experimental) (#338) 2025-06-04 21:37:05 -07:00
Will Chen
7235eab227 Make CI run cross-platform (#295) 2025-06-03 13:04:16 -07:00
Will Chen
8a743ca4f5 LM studio e2e test (#297) 2025-05-31 23:04:28 -07:00
Will Chen
af7d6fa9f8 Create ollama e2e test (#296) 2025-05-31 22:01:48 -07:00
Will Chen
8cfd476ea9 Fix engine enabled (#255) 2025-05-27 00:10:49 -07:00
Will Chen
0f6f069e43 Update Flash to 05-20 (#226) 2025-05-22 10:37:26 -07:00
Will Chen
ae351c5ea0 Add staging engine (+ logs) (#225) 2025-05-22 10:33:09 -07:00
Will Chen
4d2b4783bc Fix scaffold copy and better error handling for create app (#202) 
I was over-eager in https://github.com/dyad-sh/dyad/pull/200 and removed
copyDirectoryRecursive which is actually needed to copy the scaffold
out.
 2025-05-19 17:58:49 -07:00
Will Chen
68cb6b3d7d Robust app folder rename (#200) 
Fixes #89
 2025-05-19 14:59:55 -07:00
Will Chen
5966dd7f4b Proxy server to inject shim (#178) 
things to test:

- [x] allow real URL to open in new window
- [x] packaging in electron?
- [ ] does it work on windows?
- [x] make sure it works with older apps
- [x] what about cache / reuse? - maybe use a bigger range of ports??
 2025-05-16 23:28:26 -07:00
Will Chen
f9f33596bd Smart files context (#184) 2025-05-16 22:21:45 -07:00
Will Chen
92fb4f9b27 useful utility for debugging raw LLM response (#181) 
Co-authored-by: graphite-app[bot] <96075541+graphite-app[bot]@users.noreply.github.com>
 2025-05-16 11:06:27 -07:00
Will Chen
7bcb68e87d Fix model client gateway prefix check (openAI erroneously not using dyad gateway for dyad pro) (#174) 2025-05-15 16:31:52 -07:00
Will Chen
09fc028f94 Mark which models are eligible for turbo edits (#172) 2025-05-15 16:02:42 -07:00
Will Chen
bbf4bb765c Allow overriding gateway URL (#169) 2025-05-15 15:09:45 -07:00
Will Chen
35b459d82d Support turbo edits (pro) (#166) 2025-05-14 23:35:50 -07:00
Will Chen
d545babb63 Quick fix for Google models (#160) 2025-05-13 22:21:27 -07:00
Will Chen
069c221292 Implement saver mode (#154) 2025-05-13 15:34:41 -07:00
Will Chen
ee5865dcf8 Precise custom model selection & simplify language model/provider log… (#147) 
…ic (no merging)
 2025-05-12 23:24:39 -07:00
Will Chen
f628c81f4c Refactor constants/models and inline (#143) 2025-05-12 22:20:16 -07:00
Will Chen
877c8f7f4f Simplify provider logic and migrate getContextWindow (#142) 2025-05-12 22:18:49 -07:00
Will Chen
cd7eaa8ece Prep for custom models: support reading custom providers (#131) 2025-05-12 14:52:48 -07:00
Will Chen
2537fbb342 lint using oxlint (#106) 2025-05-08 17:21:35 -07:00
Will Chen
0d56651220 Run prettier on everything (#104) 2025-05-06 23:02:28 -07:00
Will Chen
744ea68ac8 fix auto model logic so that dyad pro key doesn't error 2025-05-06 22:12:59 -07:00
Piotr Wilkin (ilintar)
5fc49231ee Add LM Studio support (#22) 2025-05-02 14:51:32 -07:00
Will Chen
9fb5439ecf Summarize into new chat suggested action (#34) 2025-04-28 16:14:12 -07:00
Will Chen
e65b80bcfa Set explicit max output tokens to avoid truncated responses (#31) 2025-04-28 13:43:34 -07:00
Will Chen
04b9f81647 Do not use free variant for dyad pro gateway 2025-04-26 11:12:20 -07:00
Will Chen
4848b2f085 Add toggle for disabling Dyad Pro (#24) 
* Add toggle for disabling Dyad Pro
* Entering key for Dyad pro enables dyad pro
 2025-04-26 10:13:35 -07:00
Will Chen
2ad10ba039 Support LLM gateway with Dyad API key (#23) 
* Do not make API key input (password) - hurts usability
* Support LLM gateway (and add GPT 4.1 mini model)
* Show Dyad Pro button
* Fix to use auto (not dyad) for detecting dyad pro
* Fix description of gpt 4.1-mini
 2025-04-26 08:52:08 -07:00
Will Chen
b616598bab Add ollama support (#7) 2025-04-23 14:48:57 -07:00
Will Chen
922ee7d90a Handle token refresh for supabase 2025-04-23 12:59:09 -07:00
Will Chen
4294ce5767 Supabase support: client, auth & SQL 2025-04-23 12:59:09 -07:00