Plugin runtime helpers

기준일: 2026-07-26
공식 기준: Plugin runtime helpers

Plugin runtime helpers 문서는 OpenClaw 공식 문서(plugins/sdk-runtime)를 한국어로 정리한 가이드입니다. api.runtime -- the injected runtime helpers available to plugins 명령·설정 키·코드 예시는 공식 문서를 그대로 보존하며, 해석과 절차 안내는 한국어로 제공합니다. 최종 동작은 설치된 CLI 버전과 공식 원문을 확인하세요.

핵심 요약

api.runtime -- the injected runtime helpers available to plugins

한국어 가이드 범위: plugins/sdk-runtime 경로의 설정·명령·제약·예시를 학습용으로 재구성합니다.

문서 구성

공식 문서의 주요 섹션은 다음과 같습니다.

• Config loading and writes
• Reusable runtime utilities
• Runtime namespaces
• Storing runtime references
• Other top-level api fields
• 관련 문서

상세 내용

본문

Reference for the api.runtime object injected into every plugin during registration. Use these helpers instead of importing host internals directly.

위 내용은 공식 문서의 해당 섹션 요지입니다. 세부 플래그·기본값은 원문과 --help를 확인하세요.

register(api) {
  const runtime = api.runtime;
}

Config loading and writes

Prefer config that was already passed into the active call path, for example api.config during registration or a cfg argument on channel/provider callbacks. This keeps one process snapshot flowing through the work instead of reparsing config on hot paths.

위 내용은 공식 문서의 해당 섹션 요지입니다. 세부 플래그·기본값은 원문과 --help를 확인하세요.

주요 항목:

• afterWrite: { mode: "auto" } lets the gateway reload planner decide.
• afterWrite: { mode: "restart", reason: "..." } forces a clean restart when the writer knows hot reload is unsafe.
• afterWrite: { mode: "none", reason: "..." } suppresses automatic reload/restart only when the caller owns the follow-up.

Reusable runtime utilities

Use inbound botLoopProtection facts for bot-authored inbound messages. Core applies the shared in-memory sliding-window guard before session record and dispatch, without tying the policy to one channel. The guard tracks (scopeId, conversationId, participant pair) keys, counts both directions of a pair together, applies a cooldown once the window budget is exceeded, and prunes inactive entries opportunistically.

위 내용은 공식 문서의 해당 섹션 요지입니다. 세부 플래그·기본값은 원문과 --help를 확인하세요.

type ChannelBotLoopProtectionConfig = {
  enabled?: boolean;
  maxEventsPerWindow?: number;
  windowSeconds?: number;
  cooldownSeconds?: number;
};

return {
  channel: "example",
  routeSessionKey,
  storePath,
  ctxPayload,
  recordInboundSession,
  runDispatch,
  botLoopProtection: {
    scopeId: "account-1",
    conversationId: "channel-1",
    senderId: "bot-a",
    receiverId: "bot-b",
    config: channelConfig.botLoopProtection,
    defaultsConfig: runtimeConfig.channels?.defaults?.botLoopProtection,
    defaultEnabled: allowBotsMode !== "off",
  },
};

Runtime namespaces

Agent identity, directories, and session management.

위 내용은 공식 문서의 해당 섹션 요지입니다. 세부 플래그·기본값은 원문과 --help를 확인하세요.

주요 항목:

• api.runtime.tasks.managedFlows is mutation-capable: create, advance, and cancel Task Flows.
• api.runtime.tasks.flows and api.runtime.tasks.runs are read-only DTO views for listing and status lookups; both expose bindSession(...) / fromToolContext(...) plus get, list, findLatest, and resolve.
• buildMentionRegexes
• matchesMentionPatterns
• matchesMentionWithExplicit
• implicitMentionKindWhen
• resolveInboundMentionDecision

// Resolve the agent's working directory (agentId is required)
    const agentDir = api.runtime.agent.resolveAgentDir(cfg, agentId);

    // Resolve agent workspace
    const workspaceDir = api.runtime.agent.resolveAgentWorkspaceDir(cfg, agentId);

    // Get agent identity
    const identity = api.runtime.agent.resolveAgentIdentity(cfg);

    // Get default thinking level
    const thinking = api.runtime.agent.resolveThinkingDefault({
      cfg,
      provider,
      model,
    });

    // Validate a user-provided thinking level against the active provider profile
    const policy = api.runtime.agent.resolveThinkingPolicy({ provider, model });
    const level = api.runtime.agent.normalizeThinkingLevel("extra high");
    if (level && policy.levels.some((entry) => entry.id === level)) {
      // pass level to an embedded run
    }

    // Get agent timeout
    const timeoutMs = api.runtime.agent.resolveAgentTimeoutMs(cfg);

    // Ensure workspace exists
    await api.runtime.agent.ensureAgentWorkspace(cfg);

    // Run an embedded agent turn
    const result = await api.runtime.agent.runEmbeddedAgent({
      sessionId: "my-plugin:task-1",
      runId: crypto.randomUUID(),
      workspaceDir: api.runtime.agent.resolveAgentWorkspaceDir(cfg, agentId),
      prompt: "Summarize the latest changes",
      timeoutMs: api.runtime.agent.resolveAgentTimeoutMs(cfg),
    });

const entry = api.runtime.agent.session.getSessionEntry({ agentId, sessionKey });
    for (const { sessionKey, entry } of api.runtime.agent.session.listSessionEntries({ agentId })) {
      // Iterate session rows without depending on the legacy sessions.json shape.
    }
    await api.runtime.agent.session.patchSessionEntry({
      agentId,
      sessionKey,
      update: (entry) => ({ thinkingLevel: "high" }),
    });

    const created = await api.runtime.agent.session.createSessionEntry({
      cfg,
      key: "agent:main:my-plugin:task-1",
      initialEntry: {
        agentHarnessId: "my-harness",
        modelSelectionLocked: true,
        pluginExtensions: { "my-plugin": { phase: "initializing" } },
      },
      afterCreate: async () => ({
        pluginExtensions: { "my-plugin": { phase: "ready" } },
      }),
    });

    const storePath = api.runtime.agent.session.resolveStorePath(cfg.session?.store, { agentId });
    await api.runtime.agent.session.runWithWorkAdmission(
      { storePath, sessionKey },
      async (signal) => {
        // Create or update the session, then pass signal to the admitted agent run.
      },
    );

const model = api.runtime.agent.defaults.model; // e.g. "gpt-5.6-sol"
    const provider = api.runtime.agent.defaults.provider; // e.g. "openai"

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",
    });

Storing runtime references

Use createPluginRuntimeStore to store the runtime reference for use outside the register callback:

위 내용은 공식 문서의 해당 섹션 요지입니다. 세부 플래그·기본값은 원문과 --help를 확인하세요.

import { createPluginRuntimeStore } from "openclaw/plugin-sdk/runtime-store";
    import type { PluginRuntime } from "openclaw/plugin-sdk/runtime-store";

    const store = createPluginRuntimeStore<PluginRuntime>({
      pluginId: "my-plugin",
      errorMessage: "my-plugin runtime not initialized",
    });

export default defineChannelPluginEntry({
      id: "my-plugin",
      name: "My Plugin",
      description: "Example",
      plugin: myPlugin,
      setRuntime: store.setRuntime,
    });

export function getRuntime() {
      return store.getRuntime(); // throws if not initialized
    }

    export function tryGetRuntime() {
      return store.tryGetRuntime(); // returns null if not initialized
    }

Other top-level api fields

Beyond api.runtime, the API object also provides:

위 내용은 공식 문서의 해당 섹션 요지입니다. 세부 플래그·기본값은 원문과 --help를 확인하세요.

관련 문서

주요 항목:

• Plugin internals — capability model and registry
• SDK entry points — definePluginEntry options
• SDK overview — subpath reference

실습 체크리스트

1. 공식 문서와 로컬 버전을 대조합니다: https://docs.openclaw.ai/plugins/sdk-runtime
2. 관련 CLI는 openclaw --help 및 하위 명령 --help로 옵션을 확인합니다.
3. 설정 변경 시 openclaw config / openclaw doctor로 유효성을 검사합니다.
4. Gateway·채널·플러그인 변경 후에는 필요 시 Gateway를 재시작합니다.

자주 쓰는 명령·설정 예시

register(api) {
  const runtime = api.runtime;
}

type ChannelBotLoopProtectionConfig = {
  enabled?: boolean;
  maxEventsPerWindow?: number;
  windowSeconds?: number;
  cooldownSeconds?: number;
};

return {
  channel: "example",
  routeSessionKey,
  storePath,
  ctxPayload,
  recordInboundSession,
  runDispatch,
  botLoopProtection: {
    scopeId: "account-1",
    conversationId: "channel-1",
    senderId: "bot-a",
    receiverId: "bot-b",
    config: channelConfig.botLoopProtection,
    defaultsConfig: runtimeConfig.channels?.defaults?.botLoopProtection,
    defaultEnabled: allowBotsMode !== "off",
  },
};

// Resolve the agent's working directory (agentId is required)
    const agentDir = api.runtime.agent.resolveAgentDir(cfg, agentId);

    // Resolve agent workspace
    const workspaceDir = api.runtime.agent.resolveAgentWorkspaceDir(cfg, agentId);

    // Get agent identity
    const identity = api.runtime.agent.resolveAgentIdentity(cfg);

    // Get default thinking level
    const thinking = api.runtime.agent.resolveThinkingDefault({
      cfg,
      provider,
      model,
    });

    // Validate a user-provided thinking level against the active provider profile
    const policy = api.runtime.agent.resolveThinkingPolicy({ provider, model });
    const level = api.runtime.agent.normalizeThinkingLevel("extra high");
    if (level && policy.levels.some((entry) => entry.id === level)) {
      // pass level to an embedded run
    }

    // Get agent timeout
    const timeoutMs = api.runtime.agent.resolveAgentTimeoutMs(cfg);

    // Ensure workspace exists
    await api.runtime.agent.ensureAgentWorkspace(cfg);

    // Run an embedded agent turn
    const result = await api.runtime.agent.runEmbeddedAgent({
      sessionId: "my-plugin:task-1",
      runId: crypto.randomUUID(),
      workspaceDir: api.runtime.agent.resolveAgentWorkspaceDir(cfg, agentId),
      prompt: "Summarize the latest changes",
      timeoutMs: api.runtime.agent.resolveAgentTimeoutMs(cfg),
    });

const entry = api.runtime.agent.session.getSessionEntry({ agentId, sessionKey });
    for (const { sessionKey, entry } of api.runtime.agent.session.listSessionEntries({ agentId })) {
      // Iterate session rows without depending on the legacy sessions.json shape.
    }
    await api.runtime.agent.session.patchSessionEntry({
      agentId,
      sessionKey,
      update: (entry) => ({ thinkingLevel: "high" }),
    });

    const created = await api.runtime.agent.session.createSessionEntry({
      cfg,
      key: "agent:main:my-plugin:task-1",
      initialEntry: {
        agentHarnessId: "my-harness",
        modelSelectionLocked: true,
        pluginExtensions: { "my-plugin": { phase: "initializing" } },
      },
      afterCreate: async () => ({
        pluginExtensions: { "my-plugin": { phase: "ready" } },
      }),
    });

    const storePath = api.runtime.agent.session.resolveStorePath(cfg.session?.store, { agentId });
    await api.runtime.agent.session.runWithWorkAdmission(
      { storePath, sessionKey },
      async (signal) => {
        // Create or update the session, then pass signal to the admitted agent run.
      },
    );

const model = api.runtime.agent.defaults.model; // e.g. "gpt-5.6-sol"
    const provider = api.runtime.agent.defaults.provider; // e.g. "openai"

관련 링크

• 공식 원문: plugins/sdk-runtime
• OpenClaw 문서 홈

이 가이드는 공식 문서를 한국어 학습용으로 재구성한 것입니다. 옵션 기본값·플래그 이름은 설치 버전에 따라 달라질 수 있습니다.