From 291afbbb95816f25bada82b6263f8bb93ce3a455 Mon Sep 17 00:00:00 2001 From: Peter Steinberger Date: Sat, 4 Apr 2026 21:52:10 +0100 Subject: [PATCH] docs: refresh transcript sanitization mirrors --- docs/concepts/multi-agent.md | 3 ++- docs/concepts/session-tool.md | 7 +++++-- docs/platforms/android.md | 6 ++++-- docs/platforms/mac/webchat.md | 6 ++++-- docs/tools/index.md | 3 ++- docs/tools/multi-agent-sandbox-tools.md | 7 ++++--- docs/tools/subagents.md | 7 +++++-- docs/web/control-ui.md | 2 +- docs/web/webchat.md | 2 +- 9 files changed, 28 insertions(+), 15 deletions(-) diff --git a/docs/concepts/multi-agent.md b/docs/concepts/multi-agent.md index 96037a2ecc8..7d05d58b29f 100644 --- a/docs/concepts/multi-agent.md +++ b/docs/concepts/multi-agent.md @@ -26,7 +26,8 @@ Auth profiles are **per-agent**. Each agent reads from its own: `sessions_history` is the safer cross-session recall path here too: it returns a bounded, sanitized view, not a raw transcript dump. Assistant recall strips thinking tags, `` scaffolding, plain-text tool-call XML -payloads, downgraded tool-call scaffolding, leaked model control tokens, and +payloads (including `` and truncated tool-call blocks), downgraded +tool-call scaffolding, leaked ASCII/full-width model control tokens, and malformed MiniMax tool-call XML before redaction/truncation. Main agent credentials are **not** shared automatically. Never reuse `agentDir` diff --git a/docs/concepts/session-tool.md b/docs/concepts/session-tool.md index ccf96d7ed4e..32f67c9ef93 100644 --- a/docs/concepts/session-tool.md +++ b/docs/concepts/session-tool.md @@ -37,10 +37,13 @@ The returned view is intentionally bounded and safety-filtered: - assistant text is normalized before recall: - thinking tags are stripped - `` / `` scaffolding blocks are stripped - - plain-text tool-call XML payload blocks such as `...` / `...` are stripped + - plain-text tool-call XML payload blocks such as `...`, + `...`, and `...` + are stripped, including truncated payloads that never close cleanly - downgraded tool-call/result scaffolding such as `[Tool Call: ...]`, `[Tool Result ...]`, and `[Historical context ...]` is stripped - - leaked model control tokens such as `<|assistant|>` / `<｜...｜>` are stripped + - leaked model control tokens such as `<|assistant|>`, other ASCII + `<|...|>` tokens, and full-width `<｜...｜>` variants are stripped - malformed MiniMax tool-call XML such as `` / `` is stripped - credential/token-like text is redacted before it is returned diff --git a/docs/platforms/android.md b/docs/platforms/android.md index 519c39354ab..4b5cf996eb3 100644 --- a/docs/platforms/android.md +++ b/docs/platforms/android.md @@ -138,8 +138,10 @@ Pairing details: [Pairing](/channels/pairing). The Android Chat tab supports session selection (default `main`, plus other existing sessions): - History: `chat.history` (display-normalized; inline directive tags are - stripped from visible text, pure `NO_REPLY` assistant rows are omitted, and - oversized rows can be replaced with placeholders) + stripped from visible text, plain-text tool-call XML payloads and leaked + ASCII/full-width model control tokens are stripped, pure `NO_REPLY` + assistant rows are omitted, and oversized rows can be replaced with + placeholders) - Send: `chat.send` - Push updates (best-effort): `chat.subscribe` → `event:"chat"` diff --git a/docs/platforms/mac/webchat.md b/docs/platforms/mac/webchat.md index 468fd887ddb..03fb2c33232 100644 --- a/docs/platforms/mac/webchat.md +++ b/docs/platforms/mac/webchat.md @@ -31,8 +31,10 @@ agent (with a session switcher for other sessions). - Data plane: Gateway WS methods `chat.history`, `chat.send`, `chat.abort`, `chat.inject` and events `chat`, `agent`, `presence`, `tick`, `health`. - `chat.history` returns display-normalized transcript rows: inline directive - tags are stripped from visible text, pure `NO_REPLY` assistant rows are - omitted, and oversized rows can be replaced with placeholders. + tags are stripped from visible text, plain-text tool-call XML payloads and + leaked ASCII/full-width model control tokens are stripped, pure `NO_REPLY` + assistant rows are omitted, and oversized rows can be replaced with + placeholders. - Session: defaults to the primary session (`main`, or `global` when scope is global). The UI can switch between sessions. - Onboarding uses a dedicated session to keep first‑run setup separate. diff --git a/docs/tools/index.md b/docs/tools/index.md index 58c90281743..4b3f881c9df 100644 --- a/docs/tools/index.md +++ b/docs/tools/index.md @@ -149,7 +149,8 @@ Use `group:*` shorthands in allow/deny lists: `sessions_history` returns a bounded, safety-filtered recall view. It strips thinking tags, `` scaffolding, plain-text tool-call XML -payloads, downgraded tool-call scaffolding, leaked model control tokens, and +payloads (including `` and truncated tool-call blocks), downgraded +tool-call scaffolding, leaked ASCII/full-width model control tokens, and malformed MiniMax tool-call XML from assistant text, then applies redaction/truncation and possible oversized-row placeholders instead of acting as a raw transcript dump. diff --git a/docs/tools/multi-agent-sandbox-tools.md b/docs/tools/multi-agent-sandbox-tools.md index d8cc62cef12..378aff8d37d 100644 --- a/docs/tools/multi-agent-sandbox-tools.md +++ b/docs/tools/multi-agent-sandbox-tools.md @@ -297,9 +297,10 @@ Legacy `agent.*` configs are migrated by `openclaw doctor`; prefer `agents.defau `sessions_history` in this profile still returns a bounded, sanitized recall view rather than a raw transcript dump. Assistant recall strips thinking tags, -`` scaffolding, plain-text tool-call XML payloads, -downgraded tool-call scaffolding, leaked model control tokens, and malformed -MiniMax tool-call XML before redaction/truncation. +`` scaffolding, plain-text tool-call XML payloads +(including `` and truncated tool-call blocks), downgraded +tool-call scaffolding, leaked ASCII/full-width model control tokens, and +malformed MiniMax tool-call XML before redaction/truncation. --- diff --git a/docs/tools/subagents.md b/docs/tools/subagents.md index b4e17713eac..a5ebe3c95d2 100644 --- a/docs/tools/subagents.md +++ b/docs/tools/subagents.md @@ -266,9 +266,12 @@ Announce payloads include a stats line at the end (even when wrapped): - assistant recall is normalized first: - thinking tags are stripped - `` / `` scaffolding blocks are stripped - - plain-text tool-call XML payload blocks such as `...` / `...` are stripped + - plain-text tool-call XML payload blocks such as `...`, + `...`, and `...` + are stripped, including truncated payloads that never close cleanly - downgraded tool-call/result scaffolding and historical-context markers are stripped - - leaked model control tokens such as `<|assistant|>` are stripped + - leaked model control tokens such as `<|assistant|>`, other ASCII + `<|...|>` tokens, and full-width `<｜...｜>` variants are stripped - malformed MiniMax tool-call XML is stripped - credential/token-like text is redacted - long blocks can be truncated diff --git a/docs/web/control-ui.md b/docs/web/control-ui.md index 7f7be98951c..e0c820f3553 100644 --- a/docs/web/control-ui.md +++ b/docs/web/control-ui.md @@ -123,7 +123,7 @@ Cron jobs panel notes: - `chat.send` is **non-blocking**: it acks immediately with `{ runId, status: "started" }` and the response streams via `chat` events. - Re-sending with the same `idempotencyKey` returns `{ status: "in_flight" }` while running, and `{ status: "ok" }` after completion. - `chat.history` responses are size-bounded for UI safety. When transcript entries are too large, Gateway may truncate long text fields, omit heavy metadata blocks, and replace oversized messages with a placeholder (`[chat.history omitted: message too large]`). -- `chat.history` also strips display-only inline directive tags from visible assistant text (for example `[[reply_to_*]]` and `[[audio_as_voice]]`) and omits assistant entries whose whole visible text is only `NO_REPLY`. +- `chat.history` also strips display-only inline directive tags from visible assistant text (for example `[[reply_to_*]]` and `[[audio_as_voice]]`), plain-text tool-call XML payloads (including `` and truncated tool-call blocks), and leaked ASCII/full-width model control tokens, and omits assistant entries whose whole visible text is only `NO_REPLY`. - `chat.inject` appends an assistant note to the session transcript and broadcasts a `chat` event for UI-only updates (no agent run, no channel delivery). - The chat header model and thinking pickers patch the active session immediately through `sessions.patch`; they are persistent session overrides, not one-turn-only send options. - Stop: diff --git a/docs/web/webchat.md b/docs/web/webchat.md index af0be1347a7..899dab5368a 100644 --- a/docs/web/webchat.md +++ b/docs/web/webchat.md @@ -26,7 +26,7 @@ Status: the macOS/iOS SwiftUI chat UI talks directly to the Gateway WebSocket. - The UI connects to the Gateway WebSocket and uses `chat.history`, `chat.send`, and `chat.inject`. - `chat.history` is bounded for stability: Gateway may truncate long text fields, omit heavy metadata, and replace oversized entries with `[chat.history omitted: message too large]`. -- `chat.history` is also display-normalized: inline delivery directive tags such as `[[reply_to_*]]` and `[[audio_as_voice]]` are stripped from visible text, and assistant entries whose whole visible text is only `NO_REPLY` are omitted. +- `chat.history` is also display-normalized: inline delivery directive tags such as `[[reply_to_*]]` and `[[audio_as_voice]]`, plain-text tool-call XML payloads (including `` and truncated tool-call blocks), and leaked ASCII/full-width model control tokens are stripped from visible text, and assistant entries whose whole visible text is only `NO_REPLY` are omitted. - `chat.inject` appends an assistant note directly to the transcript and broadcasts it to the UI (no agent run). - Aborted runs can keep partial assistant output visible in the UI. - Gateway persists aborted partial assistant text into transcript history when buffered output exists, and marks those entries with abort metadata.