Commit Graph

8 Commits

Author SHA1 Message Date
Cole Medin
69aceeaad4
Merge pull request #12 from fernsdavid25/patch-1
Fix for llama 3.1 models
2024-10-24 07:19:25 -05:00
fernsdavid25
f7615093dd
Update max_tokens in constants.ts
max_tokens for llama 3.1 models must be less than or equal to 8000 but it is set to 8192. just change it to 8000 and the error is fixed.
2024-10-21 19:32:57 +05:30
Kofi
5b3521355a
Update prompts.ts 2024-10-21 07:46:42 -05:00
Kofi
f9021d32c4 feat(prompt): add planning step + organize shell commands
Adds structured planning phase before responses and reorganizes
available shell commands by category. Planning helps catch edge
cases early and shell categorization makes capabilities clearer.

Main changes:
- New chain-of-thought system for pre-response thinking
- Grouped shell commands by function (files, sys, dev tools, misc)
- Added brief cmd descriptions

No breaking changes, just better organization + process. Should
help reduce back-and-forth on PRs.

Tested w/o cmd env :)

- kofi
2024-10-21 12:34:06 +00:00
jonathan DS
8701be2f6d added Google Generative AI (gemini) integration 2024-10-15 18:47:35 -03:00
Cole Medin
4f7a06f56a Added the OpenRouter provider and a few models from OpenRouter (easily extendable to include more!) 2024-10-14 19:40:21 -05:00
Cole Medin
90a206f2d4 Added the ability to use practically any LLM you can dream of within Bolt.new 2024-10-13 13:53:43 -05:00
Sam Denty
6fb59d2bc5
fix: remove monorepo 2024-09-25 19:54:09 +01:00