Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: yourcasualdev/opencode-cliproxyapi
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: main
Choose a base ref
...
head repository: yoni13/opencode-cliproxyapi
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: main
Choose a head ref
Checking mergeability… Don’t worry, you can still create the pull request.
  • 1 commit
  • 12 files changed
  • 1 contributor

Commits on Oct 5, 2026

  1. feat: reasoning variants, context limits, OpenCode v2, fast mode

    - Expose reasoning-effort levels (none/low/medium/high/xhigh/max, plus
      minimal/ultra where supported) as OpenCode variants from live models.dev
      reasoning_options; suffixed IDs keep their level by default
    - Enrich every model with context/output limits, attachment/tool-call/
      temperature flags, and modalities from canonical upstream metadata
    - Dual v1+v2 support from one package: server() for v1, setup() with
      ctx.provider.transform for v2
    - Fast mode: synthesize <id>-fast siblings for GPT-family models with
      experimental.modes.fast, sending the base model ID on the wire with
      service_tier priority (router-for-me/CLIProxyAPI#2235); server-listed
      -fast IDs are enriched, never duplicated
    - Canonical-provider-wins metadata merging; codex-max name guard
    yoni13 committed Oct 5, 2026
    Configuration menu
    Copy the full SHA
    61ee1ee View commit details
    Browse the repository at this point in the history
Loading