Skip to content

ypollak2/llm-router

v9.1.3 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 8d 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

Affected surfaces

auth breaking_upgrade

Summary

AI summary

Fixed .env path resolution bug that hid critical environment variables.

Changes in this release

Feature Low

Changes default render mode from `block` to `echo`, configurable via LLM_ROUTER_RENDER_MODE env var.

Changes default render mode from `block` to `echo`, configurable via LLM_ROUTER_RENDER_MODE env var.

Source: llm_adapter@2026-05-26

Confidence: high

Bugfix Medium

Fixes .env path resolution to use Path.cwd() as primary lookup with 4 parent fallback.

Fixes .env path resolution to use Path.cwd() as primary lookup with 4 parent fallback.

Source: llm_adapter@2026-05-26

Confidence: high

Bugfix Low

Renders routed responses as normal black text in Claude Code CLI instead of warning-styled orange.

Renders routed responses as normal black text in Claude Code CLI instead of warning-styled orange.

Source: llm_adapter@2026-05-26

Confidence: high

Bugfix Low

Adds `os.getcwd()` as first .env search path in session-start.py for consistency.

Adds `os.getcwd()` as first .env search path in session-start.py for consistency.

Source: llm_adapter@2026-05-26

Confidence: high

Full changelog

Fixed

  • Critical: .env path resolution — auto-route hook used 3 parent directories (resolving to src/.env instead of project root). Now uses Path.cwd() as primary lookup + 4 parents as fallback. Without this fix, OLLAMA_BUDGET_MODELS, LLM_ROUTER_CLAUDE_SUBSCRIPTION, and API keys were invisible to the hook.
  • Echo rendering — routed responses now render as normal black text in Claude Code CLI instead of warning-styled orange text. Uses contextForAgent (same priority as MANDATORY ROUTE) instead of additionalContext (which Claude ignores when CLAUDE.md is loaded).
  • session-start.py — added os.getcwd() as first .env search path for consistency.

Changed

  • Default render mode changed from block to echo. Configurable via LLM_ROUTER_RENDER_MODE=block env var for zero-cost (warning-styled) display.

Upgrade

pip install --upgrade claude-code-llm-router
llm-router install --force

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]