Claude Code Cowork process exited with code 127 on macOS Intel
Fix Claude Code Cowork tasks failing immediately with exit code 127 Includes evidence for Claude Code troubleshooting demand.
Claude Code process exited with code 127 Error listings
Fix Claude Code Cowork tasks failing immediately with exit code 127 Includes evidence for Claude Code troubleshooting demand.
Claude Code process exited with code 127 Fix Claude Code hooks not running due to shell variable expansion failure in hooks.json Includes evidence for Claude Code troubleshooting demand.
SessionStart:startup hook error Failed with non-blocking status code: /bin/sh: ${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.cmd: No such file or directory Fix Claude Code terminal input freezing after running /compact command Includes evidence for Claude Code troubleshooting demand.
Claude Code input invisible / cursor frozen for up to 20s after /compact Fix LiteLLM llm_as_a_judge guardrail failing with BadRequestError when using vLLM self-hosted model Includes evidence for LiteLLM troubleshooting demand.
litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. Fix Anthropic API 400 error when using service_tier through Portkey gateway Includes evidence for Anthropic API troubleshooting demand.
Claude API 400 Bad Request — service_tier rewritten to deprecated 'speed' field Fix Claude Code git push failing with HTTP 403 from internal git proxy Includes evidence for Claude Code troubleshooting demand.
HTTP 403 Forbidden from git proxy on git-receive-pack Fix Claude Code MCP tool calls being blocked by Cloudflare WAF returning 403 errors Includes evidence for Claude Code troubleshooting demand.
HTML 403 block from Cloudflare WAF on anthropic.com MCP relay path Fix Claude Code MCP POST requests being blocked by Cloudflare WAF SQL injection rules Includes evidence for Claude Code troubleshooting demand.
Cloudflare WAF blocks MCP tool calls with SQL-shaped patterns, returns opaque HTML error page Fix Claude Code 'Request was aborted' errors in cli.js Includes evidence for Claude Code troubleshooting demand.
Request was aborted. at makeRequest (entrypoints/cli.js:51:6192) Fix Claude Code UI watchdog killing sessions on long-running synchronous MCP tool calls Includes evidence for Claude Code troubleshooting demand.
The session stopped responding. Send your message again to resume with a fresh process. Fix missing x-ratelimit headers on LiteLLM proxy streaming responses Includes evidence for LiteLLM troubleshooting demand.
x-ratelimit-* headers dropped on streaming and plain-dict responses (v3 parallel_request_limiter) Fix Anthropic API streaming responses that end abruptly without message_stop event when using tool_use with large JSON payloads Includes evidence for Anthropic API troubleshooting demand.
Streaming responses interrupted mid-transmission — connection closes without message_stop event Fix Anthropic SDK stripping directory paths from filenames during multipart file uploads, causing 400 errors with skills.versions.create() Includes evidence for Anthropic API troubleshooting demand.
400 invalid_request_error — skills.versions.create() requires SKILL.md inside top-level directory Fix custom headers (e.g. Cloudflare AI Gateway auth) being dropped during Anthropic SDK tool-use loop Includes evidence for Anthropic API troubleshooting demand.
toolRunner drops defaultHeaders on follow-up requests (breaks proxy/gateway setups) Fix Firebase MCP server returning no tools available in Cursor and Windsurf AI code editors despite valid configuration and authentication Includes evidence for Cursor troubleshooting demand.
Firebase MCP server shows zero tools available in Cursor and Windsurf despite valid config and auth Fix LiteLLM returning 400 errors when using OpenAI Codex CLI with Chinese domestic models via protocol translation Includes evidence for LiteLLM troubleshooting demand.
400 Bad Request — LiteLLM passes unsupported parameters to Chinese models for Codex CLI Fix Ollama Cloud streaming requests timing out after ~2 minutes on long generation with large context windows Includes evidence for Ollama troubleshooting demand.
ReadTimeout after 144.6s — ollama-cloud stream drop on long responses with large context Fix Pydantic AI silently dropping thinking=False setting when routing through OpenRouter, xAI, or Bedrock reasoning models Includes evidence for OpenRouter troubleshooting demand.
model_settings thinking=False silently dropped — reasoning field missing from OpenRouter request body Fix 400 error when using LiteLLM with Codex CLI and Chinese/domestic LLM models Includes evidence for LiteLLM troubleshooting demand.
400 Bad Request — unsupported parameter passed to model API Fix LiteLLM ChatGPT image generation returning 403 Cloudflare challenge page Includes evidence for LiteLLM troubleshooting demand.
Enable JavaScript and cookies to continue