Repository navigation
Conversation
Brings in the April 20 system prompt verbosity revert from the postmortem (https://www.anthropic.com/engineering/april-23-postmortem), which shipped in claude-agent-sdk 0.2.116 (parity with Claude Code v2.1.116). The other two issues called out in the postmortem (the cache-clearing thinking-blocks bug and the default reasoning effort regression) were already addressed in versions prior to the 0.2.114 this repo is currently on. Also picks up subsequent SDK improvements through 0.2.119: - Parity with Claude Code v2.1.117 (0.2.117) - managedSettings option for embedders to pass policy-tier settings to the spawned CLI in-memory (0.2.118) - excludeDynamicSections keeps static auto-memory instructions in the cacheable system-prompt block; reconnect claude.ai-proxied MCP servers after transport-stream abort; SessionStore.append() retries before dropping a batch (0.2.119)
benbrandt
enabled auto-merge (squash)
April 24, 2026 13:44
benbrandt
pushed a commit
that referenced
this pull request
Apr 24, 2026
🤖 I have created a release *beep* *boop* --- ## [0.31.0](v0.30.0...v0.31.0) (2026-04-24) ### Features * allow configuring models through env vars ([#586](#586)) ([1e15f3d](1e15f3d)) * Support effort levels ([#464](#464)) ([9e1185b](9e1185b)) * Update to acp sdk v0.20 ([#589](#589)) ([92adcbd](92adcbd)) * Update to claude-agent-sdk 0.2.119 ([#587](#587)) ([ef1dbd1](ef1dbd1)) ### Bug Fixes * Forward full systemPrompt preset options from _meta ([#591](#591)) ([b3ddfc3](b3ddfc3)) * Session Replay and Permission rendering ([#593](#593)) ([5faefab](5faefab)), closes [#579](#579) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). Co-authored-by: acp-release-bot[bot] <246668977+acp-release-bot[bot]@users.noreply.github.com>
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.
Bumps
@anthropic-ai/claude-agent-sdkfrom0.2.114to0.2.119(latest).Why
Primarily to pick up the April 20 system prompt verbosity revert called out in the April 23 postmortem, which shipped in
claude-agent-sdk0.2.116(parity with Claude Code v2.1.116). Per the postmortem, an instruction added on April 16 — "Length limits: keep text between tool calls to ≤25 words. Keep final responses to ≤100 words unless the task requires more detail." — caused a measurable drop in coding quality for Sonnet 4.6, Opus 4.6, and Opus 4.7, and was reverted in the v2.1.116 release.The other two regressions described in the postmortem (the cache-clearing thinking-blocks bug fixed on April 10, and the default reasoning effort revert on April 7) were already addressed before the
0.2.114this repo currently pins, so this upgrade is specifically about the verbosity-prompt fix and the SDK improvements that have landed since.What's also included between 0.2.114 and 0.2.119
From the SDK release notes:
Options.managedSettingsfor embedders to pass policy-tier settings to the spawned CLI in-memory, honored below IT-controlled managed sourcesexcludeDynamicSectionsnow keeps static auto-memory instructions in the cacheable system-prompt block; only the per-user memory directory path and per-machine environment values are relocated to the first user messageSessionStore.append()failures are now retried up to 3 times with short backoff before the batch is dropped andmirror_erroris emittedNo source changes were required in this repo — the public API surface this project uses is unchanged.
Verification
npm run build✅npm run check(lint + prettier) ✅npm run test:run✅ (197 passed, 11 skipped)