fix(opencode): support encrypted_content and previous_response_id for OpenAI flows

[Maaannnn]

Issue for this PR

Closes #20847

Type of change

• Bug fix
• New feature
• Refactor / code improvement
• Documentation

What does this PR do?

This PR fixes two OpenAI replay gaps in packages/opencode.

• On the OpenAI Responses path, it persists openai.responseId on step-finish parts and reuses it as previous_response_id on later matching turns.
• On the OpenAI-compatible completions path, it captures streamed encrypted_content from raw chunks, stores it on reasoning metadata, and folds it back into replayed assistant messages.

It also adds regression tests for the two riskiest mock-only cases: automatic previous_response_id reuse in the prompt loop, and repeated raw chunks keeping the latest encrypted_content value.

How did you verify your code works?

• bun test --timeout 30000 test/provider/transform.test.ts test/session/message-v2.test.ts test/session/processor-effect.test.ts test/session/llm.test.ts
• bun test --timeout 30000 test/session/prompt-effect.test.ts -t "loop automatically reuses previous_response_id for matching OpenAI responses turns"
• bun typecheck

Key coverage added in this PR:

• test/session/processor-effect.test.ts
  Verifies multiple raw chunks keep the latest encrypted_content on reasoning metadata.
• test/session/prompt-effect.test.ts
  Verifies the next matching OpenAI Responses turn automatically sends previous_response_id.

Screenshots / recordings

Not applicable.

Checklist

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

[github-actions]

Hey! Your PR title Support encrypted_content and previous_response_id for OpenAI flows doesn't follow conventional commit format.

Please update it to start with one of:

• feat: or feat(scope): new feature
• fix: or fix(scope): bug fix
• docs: or docs(scope): documentation changes
• chore: or chore(scope): maintenance tasks
• refactor: or refactor(scope): code refactoring
• test: or test(scope): adding or updating tests

Where scope is the package name (e.g., app, desktop, opencode).

See CONTRIBUTING.md for details.

[github-actions]

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

I found some related PRs that address similar OpenAI functionality:

1. PR fix(opencode): wire OpenAI previous_response_id session caching #20848: "fix(opencode): wire OpenAI previous_response_id session caching"

   • fix(opencode): wire OpenAI previous_response_id session caching #20848
   • Directly related: addresses previous_response_id session caching for OpenAI

2. PR fix: reuse OpenAI Responses previous_response_id across turns #22149: "fix: reuse OpenAI Responses previous_response_id across turns"

   • fix: reuse OpenAI Responses previous_response_id across turns #22149
   • Directly related: handles reusing previous_response_id across conversation turns

These PRs appear to cover overlapping functionality with the current PR #23496 regarding previous_response_id handling. You may want to verify if PR #23496 is a continuation/enhancement of these earlier efforts or if there are unresolved gaps they didn't address (like the encrypted_content aspect).

[github-actions]

Thanks for updating your PR! It now meets our contributing guidelines. 👍

[github-actions]

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.