clawdbot/docs/concepts/messages.md

summary, read_when

summary	read_when
Message flow, sessions, queueing, and reasoning visibility	Explaining how inbound messages become replies Clarifying sessions, queueing modes, or streaming behavior Documenting reasoning visibility and usage implications

Messages

This page ties together how Clawdbot handles inbound messages, sessions, queueing, streaming, and reasoning visibility.

Message flow (high level)

Inbound message
  -> routing/bindings -> session key
  -> queue (if a run is active)
  -> agent run (streaming + tools)
  -> outbound replies (provider limits + chunking)

Key knobs live in configuration:

• messages.* for prefixes, queueing, and group behavior.
• agents.defaults.* for block streaming and chunking defaults.
• Provider overrides (whatsapp.*, telegram.*, etc.) for caps and streaming toggles.

See Configuration for full schema.

Inbound dedupe

Providers can redeliver the same message after reconnects. Clawdbot keeps a short-lived cache keyed by provider/account/peer/session/message id so duplicate deliveries do not trigger another agent run.

Sessions and devices

Sessions are owned by the gateway, not by clients.

• Direct chats collapse into the agent main session key.
• Groups/channels get their own session keys.
• The session store and transcripts live on the gateway host.

Multiple devices/providers can map to the same session, but history is not fully synced back to every client. Recommendation: use one primary device for long conversations to avoid divergent context. The Control UI and TUI always show the gateway-backed session transcript, so they are the source of truth.

Details: Session management.

Inbound bodies and history context

Clawdbot separates the prompt body from the command body:

• Body: prompt text sent to the agent. This may include provider envelopes and optional history wrappers.
• CommandBody: raw user text for directive/command parsing.
• RawBody: legacy alias for CommandBody (kept for compatibility).

When a provider supplies history, it uses a shared wrapper:

• [Chat messages since your last reply - for context]
• [Current message - respond to this]

Directive stripping only applies to the current message section so history remains intact. Providers that wrap history should set CommandBody (or RawBody) to the original message text and keep Body as the combined prompt. History buffers are configurable via messages.groupChat.historyLimit (global default) and per-provider overrides like slack.historyLimit or telegram.accounts.<id>.historyLimit (set 0 to disable).

Queueing and followups

If a run is already active, inbound messages can be queued, steered into the current run, or collected for a followup turn.

• Configure via messages.queue (and messages.queue.byProvider).
• Modes: interrupt, steer, followup, collect, plus backlog variants.

Details: Queueing.

Streaming, chunking, and batching

Block streaming sends partial replies as the model produces text blocks. Chunking respects provider text limits and avoids splitting fenced code.

Key settings:

• agents.defaults.blockStreamingDefault (on|off, default off)
• agents.defaults.blockStreamingBreak (text_end|message_end)
• agents.defaults.blockStreamingChunk (minChars|maxChars|breakPreference)
• agents.defaults.blockStreamingCoalesce (idle-based batching)
• agents.defaults.humanDelay (human-like pause between block replies)
• Provider overrides: *.blockStreaming and *.blockStreamingCoalesce (non-Telegram providers require explicit *.blockStreaming: true)

Details: Streaming + chunking.

Reasoning visibility and tokens

Clawdbot can expose or hide model reasoning:

• /reasoning on|off|stream controls visibility.
• Reasoning content still counts toward token usage when produced by the model.
• Telegram supports reasoning stream into the draft bubble.

Details: Thinking + reasoning directives and Token use.

Prefixes, threading, and replies

Outbound message formatting is centralized in messages:

• messages.responsePrefix (outbound prefix) and whatsapp.messagePrefix (WhatsApp inbound prefix)
• Reply threading via replyToMode and per-provider defaults

Details: Configuration and provider docs.