f024e67860
* fix: preserve thinking choices across models and runtimes Consolidate thinking defaults, runtime capability selection, and request intent. Keep native none distinct from logical off, honor declared effort restrictions, and share provider wire policy with standalone completions. Preserve mandatory OpenRouter reasoning without an effort selector, refresh incomplete cached capabilities, and retain default-on reasoning replay. Remove duplicate policy and wrappers while keeping existing configuration. * fix: preserve prepared thinking state and defaults Keep standalone wrappers alive across calls and resolve provider thinking before serialization. Preserve trusted runtime alias context, align transport fixtures with verified provider contracts, and consolidate duplicate test setup. * fix: preserve omitted reasoning and scoped model capabilities
5.2 KiB
| summary | read_when | title | ||
|---|---|---|---|---|
| Use the OpenCode Go catalog with the shared OpenCode setup |
|
OpenCode Go |
OpenCode Go is a separate paid subscription inside OpenCode.
It uses the same OPENCODE_API_KEY credential infrastructure as Zen, but a Zen
key does not automatically include Go entitlement. Go keeps its own runtime
provider id (opencode-go) so upstream per-model routing stays correct.
OpenCode Go is bundled in the OpenClaw package, so onboarding
and configuration are sufficient; no separate plugin install is required.
| Property | Value |
|---|---|
| Runtime provider | opencode-go |
| Plugin | Bundled (opencode-go) |
| Auth | OPENCODE_API_KEY (alias: OPENCODE_ZEN_API_KEY) |
| Parent setup | OpenCode |
Getting started
OpenCode Go is already included with OpenClaw. Continue with interactive onboarding or pass the shared OpenCode API key directly.
```bash openclaw onboard --auth-choice opencode-go ``` ```bash openclaw config set agents.defaults.model.primary "opencode-go/kimi-k3" ``` ```bash openclaw models list --provider opencode-go ``` ```bash openclaw onboard --opencode-go-api-key "$OPENCODE_API_KEY" ``` ```bash openclaw models list --provider opencode-go ```Config example
{
env: { vars: { OPENCODE_API_KEY: "YOUR_API_KEY_HERE" } }, // pragma: allowlist secret
agents: { defaults: { model: { primary: "opencode-go/kimi-k3" } } },
}
Catalog
Run openclaw models list --provider opencode-go for the current model list.
OpenClaw combines Go's advertised model IDs with authoritative metadata from
https://models.opencode.ai/api.json, so new upstream models appear without an
OpenClaw update when they use a supported transport on the trusted OpenCode
endpoint. The upstream catalog is downloaded and
cached only when OpenCode Zen or Go is configured or explicitly selected with
OpenCode credentials; it is never fetched at startup or while using unrelated
providers.
Example refs include opencode-go/deepseek-v4-flash, opencode-go/kimi-k3, and
opencode-go/qwen3.8-max. Use the CLI for the current lineup rather than treating
these examples as an inventory. OpenClaw excludes deprecated rows from active
discovery and applies refreshed lifecycle status to its offline fallback.
Bundled preview rows stay hidden until accepted upstream metadata supplies them.
Existing explicit refs in the bundled seed remain resolvable.
The Go model-list endpoint is a general inventory, not an account-entitlement check. A successful listing does not grant access: inference still requires an active Go subscription, including for promotional models.
DeepSeek V4 models apply the same thinking controls in agent turns and standalone
completions. Explicit off disables native thinking and removes reasoning from
replayed history; enabled thinking preserves the reasoning needed for follow-up turns.
Both paths also omit unsupported controls for MiniMax models with fixed reasoning
and remove Kimi K2 reasoning replay fields.
Privacy
Retention and training policies vary by model. Review the current OpenCode Go privacy table before using a model, because provider policy can change independently of OpenClaw.