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. 👍