Add some intelligence to the API results #39
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
gustav0d
suggested changes
Jun 24, 2025
gustav0d
left a comment
gustav0d
left a comment
There was a problem hiding this comment.
I guess it would be great if you just keep the singleQuote format
the rest of the code lgtm
celo-rod
force-pushed
the
feat-basic-llm-integration
branch
from
cbc5964 to
f96f340
Compare
celo-rod
force-pushed
the
feat-basic-llm-integration
branch
from
f96f340 to
789468b
Compare
gustav0d
suggested changes
Jun 24, 2025
README.md
Outdated
| "author": "hotheadhacker", | ||
| "license": "MIT", | ||
| "dependencies": { | ||
| "axios": "^1.10.0", |
There was a problem hiding this comment.
one more thing actually, I guess it would be better if you just use fetch instead of adding axios
Author
There was a problem hiding this comment.
Alright, I removed the axios usage & dependency @gustav0d
gustav0d
suggested changes
Jun 24, 2025
index.js
Outdated
Comment on lines
61
to
68
| if (response.ok) { | ||
| const reason = data.choices?.[0]?.message?.content?.trim(); | ||
| if (reason) { | ||
| return res.json({ reason, theme, source: 'llm' }); | ||
| } | ||
| console.warn('LLM response was empty, falling back to local reasons.'); | ||
| } else { | ||
| console.error('Fetch failed, falling back to local reasons:', data.error.message); |
There was a problem hiding this comment.
This could be a lot better using early return https://dev.to/arikaturika/one-concept-a-day-early-return-pattern-in-javascript-3pol
gustav0d
approved these changes
Jun 24, 2025
|
I would make the LLM an optional thing. Not everyone needs the power of 4 suns for saying no. I |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR introduces optional support for LLM (Large Language Model)-generated excuses using OpenRouter.ai, while preserving the existing offline behavior as fallback.
Changes
Related issues
Closes: #27