Start Debugging

Tag: claude-code

61 posts · Page 2 of 7

2026-07-04 claude-code ai-agents cli

Claude Code 2.1.200 Renames the default Permission Mode to Manual

Claude Code v2.1.200 (July 3, 2026) renames the 'default' permission mode to 'Manual' across the CLI, VS Code, and JetBrains, and stops AskUserQuestion dialogs from auto-continuing. The config value stays 'default', with 'manual' accepted as an alias.

2026-07-02 comparison mcp ai-agents

MCP stdio vs HTTP vs SSE Transport: Which Should You Choose in 2026?

Use stdio for a local server one client launches, use Streamable HTTP for anything remote or multi-client, and do not build new HTTP+SSE servers -- that transport was deprecated in the 2025-03-26 MCP spec. Here is the decision, the wire-level differences, and the code for each.

2026-07-01 errors claude-code ai-agents

Fix: Claude Code High Memory Usage and Context Window Overflow

High memory usage and context overflow are two different problems in Claude Code. Raise the Node heap for RAM, use /context and /compact for the window, /heapdump to diagnose.

2026-06-30 errors mcp claude-code

Fix: Claude Code Drops MCP Tools After Auto-Compaction

After auto-compaction, Claude Code can leave your MCP server connected but with no tools. Run /mcp to reconnect; if tools stay gone, /clear or restart. Here is why and how to prevent it.

2026-06-26 claude-code ai-agents cli

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.

2026-06-26 errors mcp claude-code

Fix: MCP error -32000: Connection closed in Claude Code

MCP error -32000 means your MCP server process exited before the handshake finished. Fix the missing binary, the Windows cmd /c wrap, the event-loop exit, and the startup race.

2026-06-25 claude-code ai-agents security

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.

2026-06-19 claude-code ai-agents cli

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.

2026-06-15 claude-code ai-agents governance

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.

2026-06-10 comparison ai-agents claude-code

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.