Repository navigation
fix(changelog): send PRs to Claude in batches - #835
Merged
Merged
Conversation
The 6.6.0 milestone has 349 new PRs, and sending them in one request came to 288k tokens against a 200k limit. Even under that limit, an 8192-token output budget can't cover that many entries. PRs now go out in batches of up to 25 (and 200k characters), and the script fails loudly if a batch's output gets cut off. PR descriptions are capped at 8k characters. The existing duplicate-H2 merge combines the sections from different batches. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This branch was successfully deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What was wrong
The "Regenerate Release Notes" workflow failed for 6.6.0 (run):
generate-changelog.tsput every new PR into one request. With 349 PRs the input went over the context limit. A smaller input would still have run into the second problem: an 8192-token output can't hold entries for that many PRs, and the script never checkedstop_reason, so a cut-off changelog would have been written without any warning.What changed
max_tokenswent from 8192 to 16000. If a batch still stops onmax_tokens, the script throws rather than writing a partial changelog.## Development,## Headless CMSand so on.mergeDuplicateH2Sectionsalready runs after every write and merges them. Sections appear in the order they were first seen, so a## Breaking Changessection that only shows up in a later batch won't be at the top. That's worth checking when reviewing the 6.6.0 output.Testing
tscpasses and--dry-runworks. I didn't make a real Claude call locally. The workflow run after merge is the end-to-end test.Workspace: docs.webiny.com · fix failing docs job
🤖 Generated with Claude Code