- Agents/Anthropic: report 1M session context for Claude Opus/Sonnet 4 models even when local model config still advertises 200k, matching model discovery and preventing premature status/UI overflow. Fixes #66766.

- Models/OpenRouter: hide missing-auth direct provider rows in `/model status` when they are only duplicated by a nested OpenRouter model id such as `openrouter/google/...`, while preserving explicitly configured direct providers. Fixes #62317.

- Models: preserve an explicitly selected provider/model such as `opencode-go/deepseek-v4-pro` when another provider owns the same bare model alias. Fixes #79325.

- Models/config: explain missing `models.providers.<provider>.models[]` registration when a model exists only in `agents.defaults.models`, instead of returning a bare unknown-model error. Fixes #80089.

- Kimi Code: use Kimi's stable `kimi-for-coding` API model id in bundled catalog, onboarding, and docs while normalizing legacy `kimi-code` and `k2p5` refs. Fixes #79965.

- Volcengine/Kimi: strip provider-unsupported tool schema length and item constraint keywords for direct and coding-plan models so hosted Kimi runs do not reject message tools with `minLength`. Fixes #38817.

- DeepSeek: backfill V4 `reasoning_content` replay fields for unowned OpenAI-compatible proxy providers, preventing follow-up request failures outside the bundled DeepSeek and OpenRouter routes. Fixes #79608.

Gateway model capability checks also read explicit `models.providers.<id>.models[]` metadata. If a custom or proxy model accepts images, set `input: ["text", "image"]` on that model so WebChat and node-origin attachment paths pass images as native model inputs instead of text-only media refs.

`agents.defaults.models["provider/model"]` only controls model visibility, aliases, and per-model metadata for agents. It does not register a new runtime model by itself. For custom provider models, also add `models.providers.<provider>.models[]` with at least the matching `id`.

### Moonshot AI (Kimi)

Moonshot ships as a bundled provider plugin. Use the built-in provider by default, and add an explicit `models.providers.moonshot` entry only when you need to override the base URL or model metadata:

expect(result.model?.input).toEqual(["text"]);

});

it("explains when an agent model entry is missing provider model registration", async () => {

const cfg = {

agents: {

defaults: {

models: {

"microsoft-foundry/Kimi-K2.6-1": {

contextWindow: 262144,

maxOutputTokens: 16384,

},

},

},

},

} as unknown as OpenClawConfig;

const result = await resolveModelAsync("microsoft-foundry", "Kimi-K2.6-1", "/tmp/agent", cfg, {

runtimeHooks: createRuntimeHooks(),

skipPiDiscovery: true,

});

expect(result.error).toBe(

'Unknown model: microsoft-foundry/Kimi-K2.6-1. Found agents.defaults.models["microsoft-foundry/Kimi-K2.6-1"], but no matching models.providers["microsoft-foundry"].models[] entry. Add { "id": "Kimi-K2.6-1" } to models.providers["microsoft-foundry"].models[] to register this provider model.',

);

});

it("repairs stale text-only Foundry fallback rows for GPT-family models", () => {

const cfg = {

models: {

return suppressed;

}

const base = `Unknown model: ${params.provider}/${params.modelId}`;

const registrationHint = buildMissingProviderModelRegistrationHint({

provider: params.provider,

modelId: params.modelId,

cfg: params.cfg,

});

if (registrationHint) {

return `${base}. ${registrationHint}`;

}

const runtimeHooks = params.runtimeHooks ?? DEFAULT_PROVIDER_RUNTIME_HOOKS;

const hint = runtimeHooks.buildProviderUnknownModelHintWithPlugin({

provider: params.provider,

});

return hint ? `${base}. ${hint}` : base;

}

function buildMissingProviderModelRegistrationHint(params: {

provider: string;

modelId: string;

cfg?: OpenClawConfig;

}): string | undefined {

const configuredModels = params.cfg?.agents?.defaults?.models;

if (!configuredModels) {

return undefined;

}

const agentModelKey = modelKey(params.provider, params.modelId);

if (

!configuredModels[agentModelKey] &&

!configuredModels[`${params.provider}/${params.modelId}`]

) {

return undefined;

}

const providerConfig = findNormalizedProviderValue(

params.cfg?.models?.providers,

params.provider,

) as { models?: unknown } | undefined;

const providerModels = Array.isArray(providerConfig?.models) ? providerConfig.models : [];

const hasProviderModel = providerModels.some((entry) => {

if (!entry || typeof entry !== "object" || !("id" in entry)) {

return false;

}

const id = (entry as { id?: unknown }).id;

return typeof id === "string" && id === params.modelId;

});

if (hasProviderModel) {

return undefined;

}

return `Found agents.defaults.models["${agentModelKey}"], but no matching models.providers["${params.provider}"].models[] entry. Add { "id": "${params.modelId}" } to models.providers["${params.provider}"].models[] to register this provider model.`;

}

},

},

},

} as OpenClawConfig,

} as unknown as OpenClawConfig,

allowedModelCatalog: [

{ provider: "anthropic", id: "claude-opus-4-6", name: "Claude Opus 4.5" },

{ provider: "openai", id: "gpt-4.1-mini", name: "GPT-4.1 mini" },

},

},

},

} as OpenClawConfig,

} as unknown as OpenClawConfig,

allowedModelCatalog: [

{ provider: "google", id: "gemini-3-flash-preview", name: "Gemini 3 Flash" },

{

},

},

},

} as OpenClawConfig,

} as unknown as OpenClawConfig,

allowedModelCatalog: [

{ provider: "google", id: "gemini-3-flash-preview", name: "Gemini 3 Flash" },

{