Skip to content

ypollak2/llm-router

v4.0.3 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo LLM Frameworks
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-routing anthropic claude claude-code cost-optimization gemini
+7 more
litellm llm llm-router mcp-server model-router ollama openai

Summary

AI summary

Test isolation fix ensures CI determinism by preventing inheritance of LLM_ROUTER_ENFORCE.

Full changelog

What's new

  • Test isolation fix — enforcement hook tests no longer inherit shell's LLM_ROUTER_ENFORCE, making CI deterministic regardless of local dev env
  • CI now caches packagesuv package cache persists between runs; install drops from ~18 min to ~30s after first run
  • Lint via uvx ruff — no full venv install needed for linting; lint job finishes in ~10s
  • Simplified publish — single job: lint → version check → build → PyPI

Upgrade

```bash
pip install --upgrade claude-code-llm-router && llm-router install
```

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track ypollak2/llm-router

Get notified when new releases ship.

Sign up free

About ypollak2/llm-router

Subscription-aware LLM router for Claude Code. Routes tasks to 20+ providers (OpenAI, Gemini, Groq, Ollama, Codex) based on complexity classification, Claude subscription pressure, and cost. Free tasks stay on Claude subscription; expensive tasks fall back to the cheapest capable model. Includes 30 MCP tools, 6 auto-routing hooks, semantic dedup cache, prompt caching, daily spend cap, and a live web dashboard.

All releases →

Related context

Earlier breaking changes

  • v9.2.0 Changes auto‑route directive from advisory "DO NOT SKIP" to hard constraint with explicit blocked tools list.
  • v9.2.0 Breaks permanent downgrade of enforcement after first Edit/Write; v13 now requires per‑turn routing.

Beta — feedback welcome: [email protected]