fix: fallback custom model output limit to OUTPUT_TOKEN_MAX instead of 0

[comzip]

Issue for this PR

Fixes #22253

Type of change

• Bug fix

What does this PR do?

Custom provider models without an explicit limit.output get output: 0 as a sentinel value. This 0 propagates to the API call, causing maxOutputTokens must be >= 1 errors. Changed the fallback from 0 to ProviderTransform.OUTPUT_TOKEN_MAX (32000), consistent with built-in model behavior.

How did you verify your code works?

Added a test: custom model without limit.output now gets OUTPUT_TOKEN_MAX instead of 0. Also updated an existing test that was asserting the old (broken) behavior.

Screenshots / recordings

N/A

Checklist

• I have tested my changes locally
• I have not included unrelated changes in this PR

[github-actions]

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

Based on the search results, I found two potentially related PRs that might be addressing similar issues:

1. PR fix: guard Anthropic thinking budgetTokens for unknown output limits #22581: fix: guard Anthropic thinking budgetTokens for unknown output limits

   • Related because it also deals with handling unknown/unset output limits

2. PR fix: handle invalid maxOutputTokens value (0 or undefined) #22016: fix: handle invalid maxOutputTokens value (0 or undefined)

   • Related because it addresses the exact issue of handling 0 values for maxOutputTokens that should be treated differently

These PRs appear to be addressing similar token limit validation issues, though they may target different providers or specific cases. You may want to check if they overlap in scope or if they're complementary fixes.

[comzip]

The unit (windows) CI failure is in packages/opencode/test/cli/tui/plugin-loader.test.ts and is unrelated to this PR. My changes only touch packages/opencode/src/provider/provider.ts. This appears to be a pre-existing issue on the base branch.

[rekram1-node]

Automated PR Cleanup

Thank you for contributing to opencode.

Due to the high volume of PRs from users and AI agents, we periodically close older PRs using automated criteria so maintainers can focus review time on the most active and community-supported contributions.

This PR was closed because it matched the following cleanup criteria:

• The PR was created more than 1 month ago
• The PR had fewer than 2 positive reactions
• Positive reactions are counted as thumbs-up, heart, celebration, or rocket reactions on the PR

PRs created within the last month are not affected by this cleanup.

If you believe this PR was closed incorrectly, or if you are still actively working on it, please leave a comment explaining why it should be reopened. A maintainer can review and reopen it if appropriate.

Thanks again for taking the time to contribute.