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
{{ message }}
Repository navigation
Should the Read tool respect opencode config values for max_bytes and max_lines? #29604
The Read tool currently uses hardcoded constants for truncation: 50KB for bytes and 2000 for line count, instead of honoring configuration from tool_output.max_bytes or tool_output.max_lines in opencode config.
Other tools (such as Shell) do respect these config values via the Truncate service. Is this hardcoded behavior in the Read tool by design, or is it ok to adjust Read's behavior to use the Truncate service/configured limits like the other tools?
Activity
github-actions commentedon May 27, 2026
This issue might be a duplicate of existing issues. Please check:
MAX_LINES/MAX_BYTESbeing hardcoded and not configurable in the truncation implementationMAX_LINE_LENGTHconfigurable (also hardcoded)rekram1-node commentedon May 27, 2026
hm good point ig its not rlly customizable rn
wellescastro commentedon May 29, 2026
Yeah, I started a draft with the potential fix #29896
rekram1-node commentedon Jun 23, 2026
Automated: closing question issues.
GitHub Issues are for bug reports and feature requests only — questions / support are no longer tracked here.
If this is a bug or feature request, please open a new issue with the appropriate template.