Plugin runtime model helpers

Run a host-owned text completion without importing provider internals or duplicating OpenClaw model/auth/base URL preparation.

const result = await api.runtime.llm.complete({  messages: [{ role: "user", content: "Summarize this transcript." }],  purpose: "my-plugin.summary",  maxTokens: 512,  temperature: 0.2,  reasoning: "high",});

maxTokens and temperature are advisory sampling hints. The selected provider, CLI, or harness applies them when its transport exposes an equivalent control and otherwise may ignore them. They do not weaken the execution mode's isolation guarantees.

To require the configured agent runtime and a literal zero-tool model surface, select isolated execution explicitly:

const result = await api.runtime.llm.complete({  messages: [{ role: "user", content: "Return one JSON value." }],  systemPrompt: "You are a JSON-only function.",  model: "openai/gpt-5.6-sol",  execution: {    mode: "isolated-agent-runtime",    authProfileId: "openai:work",    timeoutMs: 30_000,  },});

This mode accepts exactly one user message. Core derives the configured CLI or harness owner, starts a fresh context, exposes no model-callable tools, and never falls back to direct provider transport. Unsupported runtimes fail before inference. result.execution.owner reports the selected owner; token usage remains absent when a CLI cannot report it.

Completion failures expose a stable code on the thrown error. Isolated callers can distinguish authorization, invalid isolated input, unsupported or unavailable runtimes, aborts, timeouts, rejected output, and other completion failures without matching message text.

Provider orchestration can also acquire the configured local-service lifecycle before issuing an HTTP request:

const lease = await api.runtime.llm.acquireLocalService(  {    providerId,    baseUrl,    headers,  },  signal,);try {  // Send and fully consume the provider request.} finally {  await lease?.release();}

acquireLocalService(...) is a stable, generic provider-service SDK contract. The host resolves process configuration from models.providers.<providerId>.localService; callers cannot supply a command, arguments, environment, or lifecycle policy. Process spawning, readiness, diagnostics, and idle-stop policy remain internal to the host.

Pass the exact configured provider id and resolved request base URL. Do not replace aliases with an adapter id: separate aliases can point at separate local GPU hosts. The host rejects endpoints that do not match the configured provider base URL, apart from the /v1 normalization used by Ollama and LM Studio adapters. The host owns startup serialization, readiness probes, request leases, abort handling, and idle shutdown.

The helper uses the same simple-completion preparation path as OpenClaw's built-in runtime and the host-owned runtime config snapshot. Context engines receive a session-bound llm.complete capability, so model calls use the active session's agent and do not silently fall back to the default agent. The result includes provider/model/agent attribution plus normalized token, cache, and estimated cost usage when available.

Direct completions can set responseFormat for provider-native constrained output. When the provider exposes them, the result also includes the concrete responseModel and terminal stopReason. Security-sensitive callers can set requiredAuthMode: "oauth"; the host then rejects a selected non-OAuth credential before dispatch. Isolated agent-runtime completions reject these direct-provider controls before dispatch.

Set reasoning to request a reasoning effort for the selected model. The host normalizes the canonical thinking levels (off, minimal, low, medium, high, xhigh, adaptive, max, and ultra) for the selected provider and model before dispatching the completion. adaptive becomes medium; max and ultra become max when supported, otherwise xhigh.

Synchronous model-selection policy, without preparing a model or starting a session.

resolveDefaultModelForAgent({ cfg, agentId }) resolves the agent's configured default. resolveAllowedModelRef({ cfg, catalog, raw, defaultProvider, defaultModel, agentId }) resolves a model name or alias against the supplied catalog and agent allowlist, returning { ref, key } or { error }. It does not select or validate an agent runtime; callers that require a particular harness must apply that separate policy.

resolveModelRuntimePolicy({ config, provider, modelId, agentId?, sessionKey? }) reads the configured runtime policy. It honors exact agent/default model entries, provider-model entries, provider-wildcard entries, and provider policy in that order. The result includes policy and its source ("model" or "provider") when configured, or an empty object when no policy matches. This lookup does not select an implicit runtime default or check harness availability.

Use these host operations instead of importing model-selection implementation modules into a plugin's registration entry.

Model and provider auth resolution.

Synchronous profile operations are also available: resolveProviderIdForAuth, ensureAuthProfileStore, resolveAuthProfileOrder, listProfilesForProvider, and isProviderApiKeyConfigured. They use the canonical host auth policy. Supply the owning agent directory when reading agent profiles, and use readOnly: true and allowKeychainPrompt: false for non-interactive profile inspection. Profile stores and resolved credentials must not be logged.

Capability factories should construct descriptors only. Keep credential inspection and resolution in the callbacks that need them, rather than performing them while registering a provider.

const auth = await api.runtime.modelAuth.getApiKeyForModel({ model, cfg }); // Request-ready auth, including provider runtime exchanges (e.g. OAuth refresh)const runtimeAuth = await api.runtime.modelAuth.getRuntimeAuthForModel({ model, cfg }); const providerAuth = await api.runtime.modelAuth.resolveApiKeyForProvider({  provider: "openai",  cfg,});