Repository navigation
docs: log the no-CLI baseline - #158
Merged
Merged
Conversation
2 of 4 tasks
4 tasks done
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Logs the night's measurements in docs/agent-dx-log.md: the CLI against a dev server and curl (and the create-hono 0.19 template) on five tasks — counter, TODO, login, refactor, and three agents in parallel — graded by scripts or a separate agent, not by the agent's own report.
Every condition built correct apps. rc.4 cost more turns than curl; #159 to #163 bring it level. Where the CLI wins: on a refactor, Sonnet without the CLI checked behavior in 0/5 runs (it handed the check back) and with the CLI in 5/5, at the same cost; and runs without the CLI killed every dev server on the machine in 24 of 44 runs, against 0 of 84 with the CLI.
The author should do the following, if applicable
pnpm run format:fix && pnpm run lint:fixto format the code