Headroom wrap [agent] times out repeatedly. My headroom wrap claude and headroom wrap codex command times out repeatedly in WSL.

[prateekrai1]

I tried several times headroom wrap claude and headroom wrap codex.

It failed repeatedly. Seems there's only issue when I wrap the coding agent. Other headroom commands seem to be working well.

Anyone overcame this issue?

After installing it worked, but after a couple of days, I started my wsl and it just times out.

I have tried wsl shutdown too

Headroom wrap claude timeout with different timeout settings

prate@ACER:/mnt/d/Payroll-Processor$ headroom wrap claude --port 8788

  ╔═══════════════════════════════════════════════╗
  ║            HEADROOM WRAP: CLAUDE              ║
  ╚═══════════════════════════════════════════════╝

  Starting Headroom proxy on port 8788...
  Error: Proxy failed to start on port 8788 within 180 seconds. Set HEADROOM_WRAP_PROXY_TIMEOUT to a larger number of seconds for slow startup.

Headroom proxy server

prate@ACER:/mnt/d/Payroll-Processor$ headroom proxy --port 8787

╔═══════════════════════════════════════════════════════════════════════╗
║                         HEADROOM PROXY                                 ║
║           The Context Optimization Layer for LLM Applications          ║
╚═══════════════════════════════════════════════════════════════════════╝

Starting proxy server...

  URL:          http://127.0.0.1:8787
  Mode:         token
  Optimization: ENABLED
  Caching:      ENABLED
  Rate Limit:   ENABLED
  Memory:       DISABLED
  License:      OSS (no license key)
  Code-Aware:   DISABLED (--code-aware or HEADROOM_CODE_AWARE_ENABLED=1 to enable)
  Context Tool: rtk
  Extensions:   (none discovered)
  Telemetry:    DISABLED (opt in: HEADROOM_TELEMETRY=on or headroom proxy --telemetry)

Performance Tuning:  (all defaults — set HEADROOM_COMPRESSION_STABLE_AFTER_TURN / HEADROOM_STALE_READ_COMPRESS_AFTER_TURNS to tune)

Routing:
  /v1/messages                    → https://api.anthropic.com
  /v1/chat/completions            → https://api.openai.com
  /v1/responses                   → https://api.openai.com  (HTTP + WebSocket)
  /v1internal:streamGenerateContent → https://cloudcode-pa.googleapis.com
  /v1/projects/.../publishers/... → https://us-central1-aiplatform.googleapis.com

Usage:
  Claude Code:   ANTHROPIC_BASE_URL=http://127.0.0.1:8787 claude
  Codex / OpenAI: OPENAI_BASE_URL=http://127.0.0.1:8787/v1 your-app

Endpoints:
  GET  /livez      Process liveness
  GET  /readyz     Traffic readiness
  GET  /health     Aggregate health
  GET  /stats      Detailed statistics
  GET  /stats-history Durable compression history + display session
  GET  /metrics    Prometheus metrics

Press Ctrl+C to stop.

CODEX OUTPUT

(.venv) prate@ACER:/mnt/d/Payroll-Processor$ npm install -g @openai/codex

added 2 packages in 21s
(.venv) prate@ACER:/mnt/d/Payroll-Processor$ headroom wrap codex
  Setting up rtk for Codex...
  Downloading rtk (Rust Token Killer)...
  rtk installed at /home/prate/.headroom/bin/rtk
  rtk instructions injected into /home/prate/.codex/AGENTS.md
  MCP retrieve tool: registered (restart OpenAI Codex CLI if it was already running)
  Serena MCP: uvx not found — install uv/uvx to enable Serena; skipping
  Codex config: injected Headroom provider (WS + HTTP) into /home/prate/.codex/config.toml

  ╔═══════════════════════════════════════════════╗
  ║              HEADROOM WRAP: CODEX             ║
  ╚═══════════════════════════════════════════════╝

  Starting Headroom proxy on port 8787...
  Error: Proxy failed to start on port 8787 within 90 seconds. Set HEADROOM_WRAP_PROXY_TIMEOUT to a larger number of seconds for slow startup.

[prateekrai1]

I exited the virtual environment and installed headroom on the host. It worked. Thank you.