Skip to content

ypollak2/llm-router

v4.0.2 Feature

This release adds 1 notable feature 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

Fixed CI hangs on Python 3.12/3.13 and unblocked PyPI publishes.

Full changelog

What's new

  • Fix: CI hang on Python 3.12/3.13 — test_agno_integration.py caused agno's async initialisation to hang on Python 3.12/3.13, timing out the 20-min job and blocking every PyPI publish since v4.0.1. Both workflows now exclude agno tests from the standard run.
  • Fix: PyPI publish unblocked — the publish gate job was using Python 3.12 + agno, so every publish attempt was cancelled. Now unblocked.
  • New: 59 cost-contract tests across two new test files:
    • tests/test_routing_value.py (32 tests): complexity→profile mapping, subscription-aware model ordering, pressure-based chain reordering, circuit-breaker isolation, model chain shape guards
    • tests/test_config_routing_value.py (27 tests): provider detection, Claude subscription double-billing prevention, Ollama liveness gating, routing defaults

Upgrade

pip install --upgrade claude-code-llm-router && llm-router install
View diff on GitHub

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

Share on X Share on Bluesky

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]