v0.8.11

Graphify-Labs/graphifyv0.8.11May 18, 2026by safishamsi

AI Summary

Improves LLM error handling for filtered responses and fixes issues with the OpenCode and Codex skills. Includes a significant performance improvement for surprise scoring.

Key Highlights

LLM empty choices/None message guard added for Gemini and other providers
OpenCode skill invalid agent reference and halt issues fixed
Codex skill now handles dirty artifacts in worktrees correctly
Surprise scoring performance boosted by ~11x per lookup

Full Release Notes

- Fix: LLM empty choices / None message guard — Gemini and other providers return `choices=[]` on content-filtered HTTP 200 responses; now raises a clean error instead of crashing with IndexError (#924)
- Fix: OpenCode skill removed invalid `general-purpose` agent reference and headless-incompatible interactive halt (#911, closes #825)
- Fix: Codex skill now uses graphify query/explain/path even when graph artifacts are dirty in worktree (#913, closes #860)
- Perf: precompute degrees once in surprise scoring — ~11x speedup per lookup on large graphs (#914)