Prompt caching is weak with using custom model provider (configured to use Op...
Open
Bugs
- Dominant language
- No language data
- Stars
- 2.1k
- Forks
- 153
- PR merge metrics
- No merged PRs in 30d
Description
Prompt caching is weak with using custom model provider (configured to use Opencode GO). Below screenshot is the best % I got so far
---
| Field | Value |
| --- | --- |
| App version | 1.0.22 |
| OS | macOS 26.5.0 |
| Theme | GitHub |
| Path | /chat |
| Tenure | Week 4 |
Contributor guide
Research direction
No files, tests, or entry points are identified. Start by reproducing the prompt-caching behavior in the /chat path with the custom model provider configured to use Opencode GO, then compare it with the reported screenshot and app version 1.0.22. Done should include a reproducible case and verified caching behavior, but the expected cache rate is not specified.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100