feat(opencode): send x-opencode-session header for all providers

[SeanThomasWilliams]

Why

LiteLLM and other proxy or relay setups use the x-opencode-session header for session affinity routing. Today this header is only sent for opencode providers, so non-opencode providers behind a proxy cannot route consistently.

What changed

• Send x-opencode-session unconditionally for all providers
• Keep existing opencode-only headers (x-opencode-project, x-opencode-request, x-opencode-client) behind the existing provider check
• Preserve existing User-Agent behavior for non-anthropic providers

Impact

This enables stable session affinity across proxy setups, including LiteLLM, Ollama relay, and similar gateways, without changing existing provider-specific header behavior.

[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 related PRs that address session handling and headers, though not exact duplicates of PR #15520:

Potentially Related PRs:

1. PR feat: send x-session-id and x-parent-session-id headers in LLM API requests #12932 - feat: send x-session-id and x-parent-session-id headers in LLM API requests

   • Addresses session headers for LLM API requests, which is conceptually similar to adding session affinity headers

2. PR feat: add mistral session affinity header #11474 - feat: add mistral session affinity header

   • Directly related to session affinity routing like your PR, but specific to Mistral provider

3. PR feat(opencode): add LiteLLM provider with auto model discovery #14468 - feat(opencode): add LiteLLM provider with auto model discovery

   • Related to LiteLLM provider support mentioned in your PR's impact section

4. PR feat(opencode): add auto loading models for litellm providers #13896 - feat(opencode): add auto loading models for litellm providers

   • Also related to LiteLLM provider functionality

The current PR #15520 appears to be addressing a more comprehensive solution (sending the header unconditionally for all providers), whereas the related PRs are either provider-specific or handle different session header approaches.

[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.