Repository navigation
Bump claude-agent-sdk to 0.3.312 so newer Claude models work - #16
Merged
Merged
Conversation
The pinned 0.2.119 bundles Claude Code 2.1.119. The API now rejects newer models such as claude-opus-5-5 from that version with claude_code_version_too_old (2.1.280 or newer required), so every Anthropic scan batch failed. No 0.2.x release is new enough.
gracia-gu
added a commit
that referenced
this pull request
Nov 3, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
With the Anthropic provider and a newer model such as
claude-opus-5-5, every scan batch fails:@anthropic-ai/claude-agent-sdkis pinned to0.2.119, which bundles Claude Code 2.1.119. No 0.2.x release reaches 2.1.280, so this moves the exact pin to0.3.312(Claude Code 2.1.312). Thepackage.jsonchange is one line; the rest is the lockfile.Testing
pnpm -r typecheckpassespnpm test: 1662/1662 pass. One earlier run had 4 timing-related failures on a slow machine; a clean rerun passed.agentgg scanwithclaude-opus-5-5on a one-fileeval(req.query.q)repro. It fails on 0.2.119 and finds the RCE on 0.3.312.