This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Topics
+7 more
Summary
AI summaryFixed UserPromptSubmit hook in Claude Code to show the reason field instead of a generic "Blocked by hook" error.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Bugfix | Medium |
Fixes hook block message in Claude Code to display reason field instead of generic error. Fixes hook block message in Claude Code to display reason field instead of generic error. Source: llm_adapter@2026-05-25 Confidence: high |
— |
| Bugfix | Medium |
Ensures subscription overrides use correct response field for user visibility. Ensures subscription overrides use correct response field for user visibility. Source: llm_adapter@2026-05-25 Confidence: high |
— |
Full changelog
v9.0.4 — Critical Fix: Claude Code Hook Blocking (2026-05-24)
Fixed
- Hook Block Message — fixed
UserPromptSubmithook returning a generic "Blocked by hook" error in Claude Code. It now correctly uses thereasonfield to display direct execution responses. - Subscription Overrides — ensured critical pressure overrides also use the correct response field for user visibility.
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
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.
Related context
Related tools
Beta — feedback welcome: [email protected]