[BUG] applyCaching overrides previous provider options #7349

Closed
opened 2026-02-16 18:06:55 -05:00 by yindo · 2 comments
Owner

Originally created by @dpuyosa on GitHub (Jan 23, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

transform.applyCaching overrides previous providerOptions like the one set in transform.normalizeMessages for openaiCompatible.

Plugins

OpenCode version

1.1.34

Steps to reproduce

For example have a OpenaiCompatible provider with a Claude model and interleaving.

The interleaving is supposed to add a providerOption with the reasoning part in transform.normalizeMessages, but it doesnt appear in the final prompt.

Screenshot and/or share link

No response

Operating System

No response

Terminal

No response

Originally created by @dpuyosa on GitHub (Jan 23, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description `transform.applyCaching` overrides previous `providerOptions` like the one set in `transform.normalizeMessages` for `openaiCompatible`. ### Plugins - ### OpenCode version 1.1.34 ### Steps to reproduce For example have a OpenaiCompatible provider with a Claude model and interleaving. The interleaving is supposed to add a `providerOption` with the reasoning part in `transform.normalizeMessages`, but it doesnt appear in the final prompt. ### Screenshot and/or share link _No response_ ### Operating System _No response_ ### Terminal _No response_
yindo added the bug label 2026-02-16 18:06:55 -05:00
yindo closed this issue 2026-02-16 18:06:55 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Jan 23, 2026):

This issue might be a duplicate of existing issues. Please check:

  • #6473: applyCaching called too freely, causes LiteLLM to fail

Feel free to ignore if this doesn't address your specific case.

@github-actions[bot] commented on GitHub (Jan 23, 2026): This issue might be a duplicate of existing issues. Please check: - #6473: applyCaching called too freely, causes LiteLLM to fail Feel free to ignore if this doesn't address your specific case.
Author
Owner

@adolago commented on GitHub (Jan 23, 2026):

Fixed: applyCaching now deep-merges providerOptions so earlier normalizeMessages options (e.g., openaiCompatible reasoning) are preserved. Commit: 45515ab9cd.

@adolago commented on GitHub (Jan 23, 2026): Fixed: applyCaching now deep-merges providerOptions so earlier normalizeMessages options (e.g., openaiCompatible reasoning) are preserved. Commit: 45515ab9cd.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#7349