docs: add messages concept overview

This commit is contained in:
Peter Steinberger
2026-01-09 19:03:17 +00:00
parent ade06cb9fb
commit 840ccbccf6
3 changed files with 93 additions and 0 deletions

83
docs/concepts/messages.md Normal file
View File

@@ -0,0 +1,83 @@
---
summary: "Message flow, sessions, queueing, and reasoning visibility"
read_when:
- 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](/gateway/configuration) for full schema.
## 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](/concepts/session).
## 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](/concepts/queue).
## 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`)
- `agents.defaults.blockStreamingBreak` (`text_end|message_end`)
- `agents.defaults.blockStreamingChunk` (`minChars|maxChars|breakPreference`)
- `agents.defaults.blockStreamingCoalesce` (idle-based batching)
- Provider overrides: `*.blockStreaming` and `*.blockStreamingCoalesce`
Details: [Streaming + chunking](/concepts/streaming).
## 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](/tools/thinking) and [Token use](/token-use).
## Prefixes, threading, and replies
Outbound message formatting is centralized in `messages`:
- `messages.responsePrefix` and `messages.messagePrefix`
- Reply threading via `replyToMode` and per-provider defaults
Details: [Configuration](/gateway/configuration#messages) and provider docs.

View File

@@ -37,6 +37,14 @@
"source": "/model/",
"destination": "/models"
},
{
"source": "/messages",
"destination": "/concepts/messages"
},
{
"source": "/messages/",
"destination": "/concepts/messages"
},
{
"source": "/AGENTS.default",
"destination": "/reference/AGENTS.default"
@@ -575,6 +583,7 @@
"concepts/session-tool",
"concepts/presence",
"concepts/provider-routing",
"concepts/messages",
"concepts/groups",
"concepts/group-messages",
"concepts/typing-indicators",

View File

@@ -921,6 +921,7 @@ message envelopes). If unset, Clawdbot uses the host timezone at runtime.
### `messages`
Controls inbound/outbound prefixes and optional ack reactions.
See [Messages](/concepts/messages) for queueing, sessions, and streaming context.
```json5
{