agentify: Construct architecture and goldenfiles#104
Merged
Conversation
According to: go test ./ -race -cover -timeout=10s -covermode=atomic -coverpkg=./... these tests now cover ~20% of the codebase. Not ideal, but considering it was one night of llm documentation -> llm testwriting it's not too bad
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Time to make clai a bit easier to work with for agent, and more token efficient.
I spent $60 yesterday on LLMs crawling the codebase and structuring documentation for each command and important concepts.
In this, I found that Opus 4.6 is very expensive and not very efficient, $40 gave 3 doumentation files, while
gpt-5.2gave the rest + allgoldenfiles for ~$5.
So maybe anthropic models requires higher control where it swaps between different levels of models, or something.
Anyways, docs are now there + goldenfile tests which cover ~20% of the codebase