anthropics/claude-code v2.1.294
Fixed prompt and agent hooks written as instructions (such as "Block commands that...") allowing what they should block
ProofCode ↗
Key points
- Improved how prompt hooks on Stop and SubagentStop written as instructions (such as "Carry on if the build is broken") are judged, so Claude is less likely to stop early
Sources (1)
- [1]anthropics/claude-code v2.1.294GitHub: anthropics/claude-code · Oct 8, 05:03 AM
- Fixed `prompt` and `agent` hooks written as instructions (such as "Block commands that...") allowing what they should block
- Improved how `prompt` hooks on Stop and SubagentStop written as instructions (such as "Carry on if the build is broken") are judged, so Claude is less likely to stop early
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026Building on our commitment to American scientific discovery
- Oct 7, 2026[AINews] Claude Haiku 5.5 — better than GPT-6 Luna at the same pricing
- Oct 7, 2026anthropics/claude-code v2.1.293
- Oct 6, 2026anthropics/claude-code v2.1.292
- Oct 6, 2026unslothai/unsloth v0.1.903-beta: New Browser + Voice Cloning
- Oct 6, 2026Thoughts from San Francisco
