fix (core): Enable prompt caching for openai-compatible by default un…

[shantur]

Enable prompt caching for openai-compatible by default unless disabled.

---

If this causes issues for you, please disable by putting the following in your opencode.json:

{
 "provider": {
    "my-provider": {
      "options": {
        "setCacheKey": false
      }
    }
 }
}

[github-actions]

Thanks for your contribution!

This PR doesn't have a linked issue. All PRs must reference an existing issue.

Please:

1. Open an issue describing the bug/feature (if one doesn't exist)
2. Add Fixes #<number> or Closes #<number> to this PR description

See CONTRIBUTING.md for details.

[github-actions]

This PR doesn't fully meet our contributing guidelines and PR template.

What needs to be fixed:

• PR description is missing required template sections. Please use the PR template.

Please edit this PR description to address the above within 2 hours, or it will be automatically closed.

If you believe this was flagged incorrectly, please let a maintainer know.

[github-actions]

The following comment was made by an LLM, it may be inaccurate:

Based on my search, I found potential related PRs, but no direct duplicates:

Related PRs (not duplicates):

1. PR feat(provider): add provider-specific cache configuration system (significant token usage reduction) #5422 - "feat(provider): add provider-specific cache configuration system" - This is related as it introduces the cache configuration system that your PR likely builds upon.

2. PR fix(cache): improve Anthropic prompt cache hit rate with system split and tool stability #14743 - "fix(cache): improve Anthropic prompt cache hit rate with system split and tool stability" - Related to cache optimization but for Anthropic specifically.

3. PR fix(opencode): wire OpenAI previous_response_id session caching #20848 - "fix(opencode): wire OpenAI previous_response_id session caching" - Related to caching for OpenAI providers.

4. PR fix: reuse OpenAI Responses previous_response_id across turns #22149 - "fix: reuse OpenAI Responses previous_response_id across turns" - Another OpenAI caching-related PR.

These PRs address caching for various providers but don't appear to be duplicates of your current PR #22569, which specifically enables prompt caching for openai-compatible providers by default.

[rekram1-node]

vouch

[github-actions]

This pull request has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.

Feel free to open a new pull request that follows our guidelines.

[shantur]

@rekram1-node - Seems like I wasn't quick enough :)