You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
"You can specify custom instruction files in your opencode.json [...] This allows you and your team to reuse existing rules rather than having to duplicate them to AGENTS.md."
"All instruction files are combined with your AGENTS.md files."
Expected behavior
Files specified in instructions array are automatically combined with AGENTS.md and included in the LLM context. The model should follow these rules.
Actual behavior
Anthropic models (Claude Sonnet 4.5, Opus 4.5, Haiku 4.5) completely ignore content from instructions array. The same configuration works correctly with OpenAI and Groq models.
Activity
github-actions commentedon Jan 16, 2026
This issue might be a duplicate of or related to existing issues. Please check:
Feel free to ignore if these don't address your specific case.
pedropombeiro commentedon Feb 3, 2026
Still seeing this in v1.1.49, FWIW.
rekram1-node commentedon Feb 3, 2026
What provider? Anthropic?
pedropombeiro commentedon Feb 3, 2026
Yes, Anthropic and also GitLab with Anthropic-based models.
github-actions commentedon Apr 5, 2026
To stay organized issues are automatically closed after 90 days of no activity. If the issue is still relevant please open a new one.