let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(auto-reply): tighten block streaming defaults

Browse Source
This commit is contained in:
Peter Steinberger
2026-01-09 22:40:58 +01:00
parent f8bf041396
commit 79af03ba5e
13 changed files with 71 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/concepts/agent.md
View File

@@ -83,13 +83,14 @@ When queue mode is `followup` or `collect`, inbound messages are held until the
current turn ends, then a new agent turn starts with the queued payloads. See
[`docs/queue.md`](/concepts/queue) for mode + debounce/cap behavior.
Block streaming sends completed assistant blocks as soon as they finish; disable
via `agents.defaults.blockStreamingDefault: "off"` if you only want the final response.
Block streaming sends completed assistant blocks as soon as they finish; it is
**off by default** (`agents.defaults.blockStreamingDefault: "off"`).
Tune the boundary via `agents.defaults.blockStreamingBreak` (`text_end` vs `message_end`; defaults to text_end).
Control soft block chunking with `agents.defaults.blockStreamingChunk` (defaults to
800–1200 chars; prefers paragraph breaks, then newlines; sentences last).
Coalesce streamed chunks with `agents.defaults.blockStreamingCoalesce` to reduce
single-line spam (idle-based merging before send).
single-line spam (idle-based merging before send). Non-Telegram providers require
explicit `*.blockStreaming: true` to enable block replies.
Verbose tool summaries are emitted at tool start (no debounce); Control UI
streams tool output via agent events when available.
More details: [Streaming + chunking](/concepts/streaming).

4
docs/concepts/messages.md
View File

@@ -57,11 +57,11 @@ 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.blockStreamingDefault` (`on|off`, default 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`
- Provider overrides: `*.blockStreaming` and `*.blockStreamingCoalesce` (non-Telegram providers require explicit `*.blockStreaming: true`)
Details: [Streaming + chunking](/concepts/streaming).

10
docs/concepts/streaming.md
View File

@@ -32,7 +32,7 @@ Legend:
- `provider send`: actual outbound messages (block replies).
**Controls:**
- `agents.defaults.blockStreamingDefault`: `"on"`/`"off"` (default on).
- `agents.defaults.blockStreamingDefault`: `"on"`/`"off"` (default off).
- Provider overrides: `*.blockStreaming` (and per-account variants) to force `"on"`/`"off"` per provider.
- `agents.defaults.blockStreamingBreak`: `"text_end"` or `"message_end"`.
- `agents.defaults.blockStreamingChunk`: `{ minChars, maxChars, breakPreference? }`.
@@ -69,14 +69,19 @@ progressive output.
- Joiner is derived from `blockStreamingChunk.breakPreference`
(`paragraph` → `\n\n`, `newline` → `\n`, `sentence` → space).
- Provider overrides are available via `*.blockStreamingCoalesce` (including per-account configs).
- Default coalesce `minChars` is bumped to 1500 for Signal/Slack/Discord unless overridden.
## “Stream chunks or everything”
This maps to:
- **Stream chunks:** `blockStreamingDefault: "on"` + `blockStreamingBreak: "text_end"` (emit as you go).
- **Stream chunks:** `blockStreamingDefault: "on"` + `blockStreamingBreak: "text_end"` (emit as you go). Non-Telegram providers also need `*.blockStreaming: true`.
- **Stream everything at end:** `blockStreamingBreak: "message_end"` (flush once, possibly multiple chunks if very long).
- **No block streaming:** `blockStreamingDefault: "off"` (only final reply).
**Provider note:** For non-Telegram providers, block streaming is **off unless**
`*.blockStreaming` is explicitly set to `true`. Telegram can stream drafts
(`telegram.streamMode`) without block replies.
## Telegram draft streaming (token-ish)
Telegram is the only provider with draft streaming:
@@ -85,6 +90,7 @@ Telegram is the only provider with draft streaming:
- `partial`: draft updates with the latest stream text.
- `block`: draft updates in chunked blocks (same chunker rules).
- `off`: no draft streaming.
- Draft streaming is separate from block streaming; block replies are off by default and only enabled by `*.blockStreaming: true` on non-Telegram providers.
- Final reply is still a normal message.
- `/reasoning stream` writes reasoning into the draft bubble (Telegram only).