TaskFlow
DashboardFreewriteWhiteboardsProjectsCRMTasksNotificationsSettingsAgent TowerAPI Docs
OpenClaw Docs
?

User

Member

Caricamento in corso...

Home
Progetti
Task
Notifiche
CRM

    OpenClaw

    Documentation Mirror

    Documentation Overview

    Docs

    Auth credential semantics
    Scheduled tasks
    Hooks
    Automation & tasks
    Standing orders
    Task flow
    Background tasks
    BlueBubbles
    Broadcast groups
    Channel routing
    Discord
    Feishu
    Google Chat
    Group messages
    Groups
    iMessage
    Chat channels
    IRC
    LINE
    Channel location parsing
    Matrix
    Matrix migration
    Matrix push rules for quiet previews
    Mattermost
    Microsoft Teams
    Nextcloud Talk
    Nostr
    Pairing
    QA channel
    QQ bot
    Signal
    Slack
    Synology Chat
    Telegram
    Tlon
    Channel troubleshooting
    Twitch
    WeChat
    WhatsApp
    Yuanbao
    Zalo
    Zalo personal
    CI pipeline
    ACP
    Agent
    Agents
    Approvals
    Backup
    Browser
    Channels
    Clawbot
    `openclaw commitments`
    Completion
    Config
    Configure
    Cron
    Daemon
    Dashboard
    Devices
    Directory
    DNS
    Docs
    Doctor
    Flows (redirect)
    Gateway
    Health
    Hooks
    CLI reference
    Inference CLI
    Logs
    MCP
    Memory
    Message
    Migrate
    Models
    Node
    Nodes
    Onboard
    Pairing
    Plugins
    Proxy
    QR
    Reset
    Sandbox CLI
    Secrets
    Security
    Sessions
    Setup
    Skills
    Status
    System
    `openclaw tasks`
    TUI
    Uninstall
    Update
    Voicecall
    Webhooks
    Wiki
    Active memory
    Agent runtime
    Agent loop
    Agent runtimes
    Agent workspace
    Gateway architecture
    Channel docking
    Inferred commitments
    Compaction
    Context
    Context engine
    Delegate architecture
    Dreaming
    Experimental features
    Features
    Markdown formatting
    Memory overview
    Builtin memory engine
    Honcho memory
    QMD memory engine
    Memory search
    Messages
    Model failover
    Model providers
    Models CLI
    Multi-agent routing
    OAuth
    OpenClaw App SDK
    Presence
    QA overview
    Matrix QA
    Command queue
    Steering queue
    Retry policy
    Session management
    Session pruning
    Session tools
    SOUL.md personality guide
    Streaming and chunking
    System prompt
    Timezones
    TypeBox
    Typing indicators
    Usage tracking
    Date and time
    Node + tsx crash
    Diagnostics flags
    Authentication
    Background exec and process tool
    Bonjour discovery
    Bridge protocol
    CLI backends
    Configuration — agents
    Configuration — channels
    Configuration — tools and custom providers
    Configuration
    Configuration examples
    Configuration reference
    Diagnostics export
    Discovery and transports
    Doctor
    Gateway lock
    Health checks
    Heartbeat
    Gateway runbook
    Local models
    Gateway logging
    Multiple gateways
    Network model
    OpenAI chat completions
    OpenResponses API
    OpenShell
    OpenTelemetry export
    Gateway-owned pairing
    Prometheus metrics
    Gateway protocol
    Remote access
    Remote gateway setup
    Sandbox vs tool policy vs elevated
    Sandboxing
    Secrets management
    Secrets apply plan contract
    Security audit checks
    Security
    Tailscale
    Tools invoke API
    Troubleshooting
    Trusted proxy auth
    Debugging
    Environment variables
    FAQ
    FAQ: first-run setup
    FAQ: models and auth
    GPT-5.5 / Codex agentic parity
    GPT-5.5 / Codex parity maintainer notes
    Help
    Scripts
    Testing
    Testing: live suites
    General troubleshooting
    OpenClaw
    Ansible
    Azure
    Bun (experimental)
    ClawDock
    Release channels
    DigitalOcean
    Docker
    Docker VM runtime
    exe.dev
    Fly.io
    GCP
    Hetzner
    Hostinger
    Install
    Installer internals
    Kubernetes
    macOS VMs
    Migration guide
    Migrating from Claude
    Migrating from Hermes
    Nix
    Node.js
    Northflank
    Oracle Cloud
    Podman
    Railway
    Raspberry Pi
    Render
    Uninstall
    Updating
    Logging
    Network
    Audio and voice notes
    Camera capture
    Image and media support
    Nodes
    Location command
    Media understanding
    Talk mode
    Node troubleshooting
    Voice wake
    Pi integration architecture
    Pi development workflow
    Android app
    Platforms
    iOS app
    Linux app
    Gateway on macOS
    Canvas
    Gateway lifecycle
    macOS dev setup
    Health checks (macOS)
    Menu bar icon
    macOS logging
    Menu bar
    Peekaboo bridge
    macOS permissions
    Remote control
    macOS signing
    Skills (macOS)
    Voice overlay
    Voice wake (macOS)
    WebChat (macOS)
    macOS IPC
    macOS app
    Windows
    Plugin internals
    Plugin architecture internals
    Building plugins
    Plugin bundles
    Codex Computer Use
    Codex harness
    Community plugins
    Plugin compatibility
    Google Meet plugin
    Plugin hooks
    Plugin manifest
    Memory LanceDB
    Memory wiki
    Message presentation
    Agent harness plugins
    Building channel plugins
    Channel turn kernel
    Plugin entry points
    Plugin SDK migration
    Plugin SDK overview
    Building provider plugins
    Plugin runtime helpers
    Plugin setup and config
    Plugin SDK subpaths
    Plugin testing
    Skill workshop plugin
    Voice call plugin
    Webhooks plugin
    Zalo personal plugin
    OpenProse
    Alibaba Model Studio
    Anthropic
    Arcee AI
    Azure Speech
    Amazon Bedrock
    Amazon Bedrock Mantle
    Chutes
    Claude Max API proxy
    Cloudflare AI gateway
    ComfyUI
    Deepgram
    Deepinfra
    DeepSeek
    ElevenLabs
    Fal
    Fireworks
    GitHub Copilot
    GLM (Zhipu)
    Google (Gemini)
    Gradium
    Groq
    Hugging Face (inference)
    Provider directory
    Inferrs
    Inworld
    Kilocode
    LiteLLM
    LM Studio
    MiniMax
    Mistral
    Model provider quickstart
    Moonshot AI
    NVIDIA
    Ollama
    OpenAI
    OpenCode
    OpenCode Go
    OpenRouter
    Perplexity
    Qianfan
    Qwen
    Runway
    SGLang
    StepFun
    Synthetic
    Tencent Cloud (TokenHub)
    Together AI
    Venice AI
    Vercel AI gateway
    vLLM
    Volcengine (Doubao)
    Vydra
    xAI
    Xiaomi MiMo
    Z.AI
    Default AGENTS.md
    Release policy
    API usage and costs
    Credits
    Device model database
    Full release validation
    Memory configuration reference
    OpenClaw App SDK API design
    Prompt caching
    Rich output protocol
    RPC adapters
    SecretRef credential surface
    Session management deep dive
    AGENTS.md template
    BOOT.md template
    BOOTSTRAP.md template
    HEARTBEAT.md template
    IDENTITY template
    SOUL.md template
    TOOLS.md template
    USER template
    Tests
    Token use and costs
    Transcript hygiene
    Onboarding reference
    Contributing to the threat model
    Threat model (MITRE ATLAS)
    Formal verification (security models)
    Network proxy
    Agent bootstrapping
    Docs directory
    Getting started
    Docs hubs
    OpenClaw lore
    Onboarding (macOS app)
    Onboarding overview
    Personal assistant setup
    Setup
    Showcase
    Onboarding (CLI)
    CLI automation
    CLI setup reference
    ACP agents
    ACP agents — setup
    Agent send
    apply_patch tool
    Brave search
    Browser (OpenClaw-managed)
    Browser control API
    Browser troubleshooting
    Browser login
    WSL2 + Windows + remote Chrome CDP troubleshooting
    BTW side questions
    ClawHub
    Code execution
    Creating skills
    Diffs
    DuckDuckGo search
    Elevated mode
    Exa search
    Exec tool
    Exec approvals
    Exec approvals — advanced
    Firecrawl
    Gemini search
    Grok search
    Image generation
    Tools and plugins
    Kimi search
    LLM task
    Lobster
    Tool-loop detection
    Media overview
    MiniMax search
    Multi-agent sandbox and tools
    Music generation
    Ollama web search
    PDF tool
    Perplexity search
    Plugins
    Reactions
    SearXNG search
    Skills
    Skills config
    Slash commands
    Sub-agents
    Tavily
    Thinking levels
    Tokenjuice
    Trajectory bundles
    Text-to-speech
    Video generation
    Web search
    Web fetch
    Linux server
    Control UI
    Dashboard
    Web
    TUI
    WebChat

    OpenAPI Specs

    openapi
    TaskFlow
    docs/openclaw
    Original Docs

    Real-time Synchronized Documentation

    Last sync: 01/05/2026 07:04:37

    Note: This content is mirrored from docs.openclaw.ai and is subject to their terms and conditions.

    OpenClaw Docs

    v2.4.0 Production

    Last synced: Today, 22:00

    Technical reference for the OpenClaw framework. Real-time synchronization with the official documentation engine.

    Use this file to discover all available pages before exploring further.

    Channel turn kernel

    The channel turn kernel is the shared inbound state machine that turns a normalized platform event into an agent turn. Channel plugins provide the platform facts and the delivery callback. Core owns the orchestration: ingest, classify, preflight, resolve, authorize, assemble, record, dispatch, and finalize.

    Use this when your plugin is on the inbound message hot path. For non-message events (slash commands, modals, button interactions, lifecycle events, reactions, voice state), keep them plugin-local. The kernel only owns events that may become an agent text turn.

    info

    The kernel is reached through the injected plugin runtime as `runtime.channel.turn.*`. The plugin runtime type is exported from `openclaw/plugin-sdk/core`, so third-party native plugins can use these entry points the same way bundled channel plugins do.

    Why a shared kernel

    Channel plugins repeat the same inbound flow: normalize, route, gate, build a context, record session metadata, dispatch the agent turn, finalize delivery state. Without a shared kernel, a change to mention gating, tool-only visible replies, session metadata, pending history, or dispatch finalization has to be applied per channel.

    The kernel keeps four concepts deliberately separate:

    • text
      ConversationFacts
      : where the message came from
    • text
      RouteFacts
      : which agent and session should process it
    • text
      ReplyPlanFacts
      : where visible replies should go
    • text
      MessageFacts
      : what body and supplemental context the agent should see

    Slack DMs, Telegram topics, Matrix threads, and Feishu topic sessions all distinguish these in practice. Treating them as one identifier causes drift over time.

    Stage lifecycle

    The kernel runs the same fixed pipeline regardless of channel:

    1. text
      ingest
      -- adapter converts a raw platform event into
      text
      NormalizedTurnInput
    2. text
      classify
      -- adapter declares whether this event can start an agent turn
    3. text
      preflight
      -- adapter does dedupe, self-echo, hydration, debounce, decryption, partial fact prefill
    4. text
      resolve
      -- adapter returns a fully assembled turn (route, reply plan, message, delivery)
    5. text
      authorize
      -- DM, group, mention, and command policy applied to the assembled facts
    6. text
      assemble
      --
      text
      FinalizedMsgContext
      built from the facts via
      text
      buildContext
    7. text
      record
      -- inbound session metadata and last route persisted
    8. text
      dispatch
      -- agent turn executed through the buffered block dispatcher
    9. text
      finalize
      -- adapter
      text
      onFinalize
      runs even on dispatch error

    Each stage emits a structured log event when a

    text
    log
    callback is supplied. See Observability.

    Admission kinds

    The kernel does not throw when a turn is gated. It returns a

    text
    ChannelTurnAdmission
    :

    KindWhen
    text
    dispatch
    Turn is admitted. Agent turn runs and the visible reply path is exercised.
    text
    observeOnly
    Turn runs end-to-end but the delivery adapter sends nothing visible. Used for broadcast observer agents and other passive multi-agent flows.
    text
    handled
    A platform event was consumed locally (lifecycle, reaction, button, modal). Kernel skips dispatch.
    text
    drop
    Skip path. Optionally
    text
    recordHistory: true
    keeps the message in pending group history so a future mention has context.

    Admission can come from

    text
    classify
    (event class said it cannot start a turn), from
    text
    preflight
    (dedupe, self-echo, missing mention with history record), or from
    text
    resolveTurn
    itself.

    Entry points

    The runtime exposes three preferred entry points so adapters can opt in at the level that matches the channel.

    typescript
    runtime.channel.turn.run(...) // adapter-driven full pipeline runtime.channel.turn.runPrepared(...) // channel owns dispatch; kernel runs record + finalize runtime.channel.turn.buildContext(...) // pure facts to FinalizedMsgContext mapping

    Two older runtime helpers remain available for Plugin SDK compatibility:

    typescript
    runtime.channel.turn.runResolved(...) // deprecated compatibility alias; prefer run runtime.channel.turn.dispatchAssembled(...) // deprecated compatibility alias; prefer run or runPrepared

    run

    Use when your channel can express its inbound flow as a

    text
    ChannelTurnAdapter<TRaw>
    . The adapter has callbacks for
    text
    ingest
    , optional
    text
    classify
    , optional
    text
    preflight
    , mandatory
    text
    resolveTurn
    , and optional
    text
    onFinalize
    .

    typescript
    await runtime.channel.turn.run({ channel: "tlon", accountId, raw: platformEvent, adapter: { ingest(raw) { return { id: raw.messageId, timestamp: raw.timestamp, rawText: raw.body, textForAgent: raw.body, }; }, classify(input) { return { kind: "message", canStartAgentTurn: input.rawText.length > 0 }; }, async preflight(input, eventClass) { if (await isDuplicate(input.id)) { return { admission: { kind: "drop", reason: "dedupe" } }; } return {}; }, resolveTurn(input) { return buildAssembledTurn(input); }, onFinalize(result) { clearPendingGroupHistory(result); }, }, });

    text
    run
    is the right shape when the channel has small adapter logic and benefits from owning the lifecycle through hooks.

    runPrepared

    Use when the channel has a complex local dispatcher with previews, retries, edits, or thread bootstrap that must stay channel-owned. The kernel still records the inbound session before dispatch and surfaces a uniform

    text
    DispatchedChannelTurnResult
    .

    typescript
    const { dispatchResult } = await runtime.channel.turn.runPrepared({ channel: "matrix", accountId, routeSessionKey, storePath, ctxPayload, recordInboundSession, record: { onRecordError, updateLastRoute, }, onPreDispatchFailure: async (err) => { await stopStatusReactions(); }, runDispatch: async () => { return await runMatrixOwnedDispatcher(); }, });

    Rich channels (Matrix, Mattermost, Microsoft Teams, Feishu, QQ Bot) use

    text
    runPrepared
    because their dispatcher orchestrates platform-specific behavior the kernel must not learn about.

    buildContext

    A pure function that maps fact bundles into

    text
    FinalizedMsgContext
    . Use it when your channel hand-rolls part of the pipeline but wants consistent context shape.

    typescript
    const ctxPayload = runtime.channel.turn.buildContext({ channel: "googlechat", accountId, messageId, timestamp, from, sender, conversation, route, reply, message, access, media, supplemental, });

    text
    buildContext
    is also useful inside
    text
    resolveTurn
    callbacks when assembling a turn for
    text
    run
    .

    note

    Deprecated SDK helpers such as `dispatchInboundReplyWithBase` still bridge through an assembled-turn helper. New plugin code should use `run` or `runPrepared`.

    Fact types

    The facts the kernel consumes from your adapter are platform-agnostic. Translate platform objects into these shapes before handing them to the kernel.

    NormalizedTurnInput

    FieldPurpose
    text
    id
    Stable message id used for dedupe and logs
    text
    timestamp
    Optional epoch ms
    text
    rawText
    Body as received from the platform
    text
    textForAgent
    Optional cleaned body for the agent (mention strip, typing trim)
    text
    textForCommands
    Optional body used for
    text
    /command
    parsing
    text
    raw
    Optional pass-through reference for adapter callbacks that need the original

    ChannelEventClass

    FieldPurpose
    text
    kind
    text
    message
    ,
    text
    command
    ,
    text
    interaction
    ,
    text
    reaction
    ,
    text
    lifecycle
    ,
    text
    unknown
    text
    canStartAgentTurn
    If false the kernel returns
    text
    { kind: "handled" }
    text
    requiresImmediateAck
    Hint for adapters that need to ACK before dispatch

    SenderFacts

    FieldPurpose
    text
    id
    Stable platform sender id
    text
    name
    Display name
    text
    username
    Handle if distinct from
    text
    name
    text
    tag
    Discord-style discriminator or platform tag
    text
    roles
    Role ids, used for member-role allowlist matching
    text
    isBot
    True when the sender is a known bot (kernel uses for dropping)
    text
    isSelf
    True when the sender is the configured agent itself
    text
    displayLabel
    Pre-rendered label for envelope text

    ConversationFacts

    FieldPurpose
    text
    kind
    text
    direct
    ,
    text
    group
    , or
    text
    channel
    text
    id
    Conversation id used for routing
    text
    label
    Human label for the envelope
    text
    spaceId
    Optional outer space identifier (Slack workspace, Matrix homeserver)
    text
    parentId
    Outer conversation id when this is a thread
    text
    threadId
    Thread id when this message is inside a thread
    text
    nativeChannelId
    Platform-native channel id when different from the routing id
    text
    routePeer
    Peer used for
    text
    resolveAgentRoute
    lookup

    RouteFacts

    FieldPurpose
    text
    agentId
    Agent that should handle this turn
    text
    accountId
    Optional override (multi-account channels)
    text
    routeSessionKey
    Session key used for routing
    text
    dispatchSessionKey
    Session key used at dispatch when different from route key
    text
    persistedSessionKey
    Session key written to persisted session metadata
    text
    parentSessionKey
    Parent for branched/threaded sessions
    text
    modelParentSessionKey
    Model-side parent for branched sessions
    text
    mainSessionKey
    Main DM owner pin for direct conversations
    text
    createIfMissing
    Allow record step to create a missing session row

    ReplyPlanFacts

    FieldPurpose
    text
    to
    Logical reply target written into context
    text
    To
    text
    originatingTo
    Originating context target (
    text
    OriginatingTo
    )
    text
    nativeChannelId
    Platform-native channel id for delivery
    text
    replyTarget
    Final visible-reply destination if it differs from
    text
    to
    text
    deliveryTarget
    Lower-level delivery override
    text
    replyToId
    Quoted/anchored message id
    text
    replyToIdFull
    Full-form quoted id when the platform has both
    text
    messageThreadId
    Thread id at delivery time
    text
    threadParentId
    Parent message id of the thread
    text
    sourceReplyDeliveryMode
    text
    thread
    ,
    text
    reply
    ,
    text
    channel
    ,
    text
    direct
    , or
    text
    none

    AccessFacts

    text
    AccessFacts
    carries the booleans the authorize stage needs. Identity matching stays in the channel: the kernel only consumes the result.

    FieldPurpose
    text
    dm
    DM allow/pairing/deny decision and
    text
    allowFrom
    list
    text
    group
    Group policy, route allow, sender allow, allowlist, mention requirement
    text
    commands
    Command authorization across configured authorizers
    text
    mentions
    Whether mention detection is possible and whether the agent was mentioned

    MessageFacts

    FieldPurpose
    text
    body
    Final envelope body (formatted)
    text
    rawBody
    Raw inbound body
    text
    bodyForAgent
    Body the agent sees
    text
    commandBody
    Body used for command parsing
    text
    envelopeFrom
    Pre-rendered sender label for the envelope
    text
    senderLabel
    Optional override for the rendered sender
    text
    preview
    Short redacted preview for logs
    text
    inboundHistory
    Recent inbound history entries when the channel keeps a buffer

    SupplementalContextFacts

    Supplemental context covers quote, forwarded, and thread-bootstrap context. The kernel applies the configured

    text
    contextVisibility
    policy. The channel adapter only provides facts and
    text
    senderAllowed
    flags so cross-channel policy stays consistent.

    InboundMediaFacts

    Media is fact-shaped. Platform download, auth, SSRF policy, CDN rules, and decryption stay channel-local. The kernel maps facts into

    text
    MediaPath
    ,
    text
    MediaUrl
    ,
    text
    MediaType
    ,
    text
    MediaPaths
    ,
    text
    MediaUrls
    ,
    text
    MediaTypes
    , and
    text
    MediaTranscribedIndexes
    .

    Adapter contract

    For full

    text
    run
    , the adapter shape is:

    typescript
    type ChannelTurnAdapter<TRaw> = { ingest(raw: TRaw): Promise<NormalizedTurnInput | null> | NormalizedTurnInput | null; classify?(input: NormalizedTurnInput): Promise<ChannelEventClass> | ChannelEventClass; preflight?( input: NormalizedTurnInput, eventClass: ChannelEventClass, ): Promise<PreflightFacts | ChannelTurnAdmission | null | undefined>; resolveTurn( input: NormalizedTurnInput, eventClass: ChannelEventClass, preflight: PreflightFacts, ): Promise<ChannelTurnResolved> | ChannelTurnResolved; onFinalize?(result: ChannelTurnResult): Promise<void> | void; };

    text
    resolveTurn
    returns a
    text
    ChannelTurnResolved
    , which is an
    text
    AssembledChannelTurn
    with an optional admission kind. Returning
    text
    { admission: { kind: "observeOnly" } }
    runs the turn without producing visible output. The adapter still owns the delivery callback; it just becomes a no-op for that turn.

    text
    onFinalize
    runs on every result, including dispatch errors. Use it to clear pending group history, remove ack reactions, stop status indicators, and flush local state.

    Delivery adapter

    The kernel does not call the platform directly. The channel hands the kernel a

    text
    ChannelTurnDeliveryAdapter
    :

    typescript
    type ChannelTurnDeliveryAdapter = { deliver(payload: ReplyPayload, info: ChannelDeliveryInfo): Promise<ChannelDeliveryResult | void>; onError?(err: unknown, info: { kind: string }): void; }; type ChannelDeliveryResult = { messageIds?: string[]; threadId?: string; replyToId?: string; visibleReplySent?: boolean; };

    text
    deliver
    is called once per buffered reply chunk. Return platform message ids when the channel has them so the dispatcher can preserve thread anchors and edit later chunks. For observe-only turns, return
    text
    { visibleReplySent: false }
    or use
    text
    createNoopChannelTurnDeliveryAdapter()
    .

    Record options

    The record stage wraps

    text
    recordInboundSession
    . Most channels can use the defaults. Override via
    text
    record
    :

    typescript
    record: { groupResolution, createIfMissing: true, updateLastRoute, onRecordError: (err) => log.warn("record failed", err), trackSessionMetaTask: (task) => pendingTasks.push(task), }

    The dispatcher waits for the record stage. If record throws, the kernel runs

    text
    onPreDispatchFailure
    (when provided to
    text
    runPrepared
    ) and rethrows.

    Observability

    Each stage emits a structured event when a

    text
    log
    callback is supplied:

    typescript
    await runtime.channel.turn.run({ channel: "twitch", accountId, raw, adapter, log: (event) => { runtime.log?.debug?.(`turn.${event.stage}:${event.event}`, { channel: event.channel, accountId: event.accountId, messageId: event.messageId, sessionKey: event.sessionKey, admission: event.admission, reason: event.reason, }); }, });

    Logged stages:

    text
    ingest
    ,
    text
    classify
    ,
    text
    preflight
    ,
    text
    resolve
    ,
    text
    authorize
    ,
    text
    assemble
    ,
    text
    record
    ,
    text
    dispatch
    ,
    text
    finalize
    . Avoid logging raw bodies; use
    text
    MessageFacts.preview
    for short redacted previews.

    What stays channel-local

    The kernel owns orchestration. The channel still owns:

    • Platform transports (gateway, REST, websocket, polling, webhooks)
    • Identity resolution and display-name matching
    • Native commands, slash commands, autocomplete, modals, buttons, voice state
    • Card, modal, and adaptive-card rendering
    • Media auth, CDN rules, encrypted media, transcription
    • Edit, reaction, redaction, and presence APIs
    • Backfill and platform-side history fetch
    • Pairing flows that require platform-specific verification

    If two channels start needing the same helper for one of these, extract a shared SDK helper instead of pushing it into the kernel.

    Stability

    text
    runtime.channel.turn.*
    is part of the public plugin runtime surface. The fact types (
    text
    SenderFacts
    ,
    text
    ConversationFacts
    ,
    text
    RouteFacts
    ,
    text
    ReplyPlanFacts
    ,
    text
    AccessFacts
    ,
    text
    MessageFacts
    ,
    text
    SupplementalContextFacts
    ,
    text
    InboundMediaFacts
    ) and admission shapes (
    text
    ChannelTurnAdmission
    ,
    text
    ChannelEventClass
    ) are reachable through
    text
    PluginRuntime
    from
    text
    openclaw/plugin-sdk/core
    .

    Backward compatibility rules apply: new fact fields are additive, admission kinds are not renamed, and the entry point names stay stable. New channel needs that require a non-additive change must go through the plugin SDK migration process.

    Related

    • Building channel plugins for the broader channel plugin contract
    • Plugin runtime helpers for other
      text
      runtime.*
      surfaces
    • Plugin internals for load pipeline and registry mechanics

    © 2024 TaskFlow Mirror

    Powered by TaskFlow Sync Engine