fix(core): preserve prompt cache affinity

[phall1]

Summary

Fixesanomalyco#42246

• propagate the stable V2 session cache key to OpenRouter requests
• send prompt_cache_key for native OpenAI Chat Completions
• avoid sending OpenAI-specific fields to generic compatible providers

This restores cache-affinity wiring described by anomalyco#39907 for current V2 routes.

Verification

• bun test test/provider/openai-chat.test.ts test/provider/openai-compatible-chat.test.ts test/provider/openrouter.test.ts in packages/llm (36 pass)
• bun typecheck in packages/llm
• bun test test/session-runner.test.ts in packages/core (85 pass)
• bun typecheck in packages/core
• full workspace typecheck (30 packages)
• Prettier check on all touched files

[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.

[phall1]

Superseded by upstream PR anomalyco#42248.