Fix: Claude Code Drops MCP Tools After Auto-Compaction
If MCP tools disappear around Claude Code compaction, distinguish a failed connection from deferred tools, authentication, permissions and discovery before reconnecting.
claude-code
118 posts · Page 8 of 12
Claude Code 2.1.191 Lets /rewind Reach Back Past a /clear
Claude Code v2.1.191 (June 24, 2026) extends /rewind so you can restore conversation and code state from before you ran /clear, recovering context that used to be gone for good.
Fix: MCP error -32000: Connection closed in Claude Code
MCP error -32000: Connection closed reports a closed transport in the TypeScript SDK. Diagnose startup failures, later disconnects, paths, stdout and HTTP separately.
Claude Code 2.1.187 Stops the Sandbox From Reading Your AWS Keys
The new sandbox.credentials setting in Claude Code v2.1.187 denies reads of credential files and unsets secret env vars before sandboxed Bash commands run. Here is why the default read policy was a hole, and how to close it.
Claude Code 2.1.183 Stops Auto Mode From Running Destructive Git and IaC Commands
Claude Code v2.1.183 (June 19, 2026) blocks git reset --hard, git clean -fd, and terraform/pulumi/cdk destroy in auto mode unless you asked for them, closing the agentic loophole where one bad turn nukes uncommitted work.
Claude Code 2.1.175 Closes the availableModels Loophole with enforceAvailableModels
For months availableModels restricted the model picker but left the Default option wide open. Claude Code 2.1.175 adds enforceAvailableModels so admins can finally pin a strict model allowlist.
Claude Subagents vs OpenAI Assistants for Parallel Work in 2026
Claude subagents give you orchestration-level parallelism out of the box: one agent spawns isolated sub-contexts that run concurrently. OpenAI Assistants never had that, and it shuts down August 26, 2026, so new parallel work belongs on the Responses API plus your own fan-out. Here is how the two models actually differ and which to reach for.
Claude Code 2.1.169 Adds --safe-mode and a /cd That Keeps the Prompt Cache Warm
Claude Code v2.1.169 (June 8, 2026) ships a --safe-mode flag that disables every customization for clean troubleshooting, and a /cd command that moves your session to a new directory without breaking the prompt cache mid-run.
Claude Code's Security-Guidance Plugin Reviews Its Own Diffs Before You Commit
Anthropic shipped a free security-guidance plugin for Claude Code that scans the agent's own edits for vulnerabilities in three layers, from a no-cost pattern match to an agentic review on commit.
Claude Agent SDK and claude -p Get Their Own Credit Pool on June 15
Anthropic is splitting programmatic Claude usage off your subscription on 2026-06-15. Here is what counts as programmatic, the per-plan credit, and how to keep your CI agents from silently stalling.