mirror of
https://github.com/agentclientprotocol/claude-agent-acp.git
synced 2026-10-27 04:30:59 +00:00
ef1dbd1cb4
Bumps `@anthropic-ai/claude-agent-sdk` from `0.2.114` to `0.2.119` (latest). ## Why Primarily to pick up the April 20 system prompt verbosity revert called out in the [April 23 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). 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 `0.2.114` this 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](https://github.com/anthropics/claude-agent-sdk-typescript/releases): - **0.2.116** — parity with Claude Code v2.1.116 (postmortem fix) - **0.2.117** — parity with Claude Code v2.1.117 - **0.2.118** — adds `Options.managedSettings` for embedders to pass policy-tier settings to the spawned CLI in-memory, honored below IT-controlled managed sources - **0.2.119** - `excludeDynamicSections` now 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 message - Long-running SDK sessions now reconnect claude.ai-proxied MCP servers after a transport-stream abort - `SessionStore.append()` failures are now retried up to 3 times with short backoff before the batch is dropped and `mirror_error` is emitted No 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) --------- Co-authored-by: Ben Brandt <benjamin.j.brandt@gmail.com>