From 5aeb35fa3880df62bd1c3cb849d6a5117a99d414 Mon Sep 17 00:00:00 2001 From: "openclaw-docs-sync[bot]" Date: Fri, 24 Apr 2026 01:42:43 +0000 Subject: [PATCH] chore(sync): mirror docs from openclaw/openclaw@86f69ba5a06ae256906c3a26308801e0b84e0091 --- .openclaw-sync/source.json | 4 ++-- docs/nodes/media-understanding.md | 3 +++ 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json index eb344389d..93cf75977 100644 --- a/.openclaw-sync/source.json +++ b/.openclaw-sync/source.json @@ -1,5 +1,5 @@ { "repository": "openclaw/openclaw", - "sha": "1a8a6f8fba042476701fa9ac91eb87f38d3be3f9", - "syncedAt": "2026-04-24T01:36:37.228Z" + "sha": "86f69ba5a06ae256906c3a26308801e0b84e0091", + "syncedAt": "2026-04-24T01:41:03.210Z" } diff --git a/docs/nodes/media-understanding.md b/docs/nodes/media-understanding.md index ca9151e9b..08e527c34 100644 --- a/docs/nodes/media-understanding.md +++ b/docs/nodes/media-understanding.md @@ -136,6 +136,9 @@ Rules: - If the active primary image model already supports vision natively, OpenClaw skips the `[Image]` summary block and passes the original image into the model instead. +- If a Gateway/WebChat primary model is text-only, image attachments are + preserved as offloaded `media://inbound/*` refs so the image tool or configured + image model can still inspect them instead of losing the attachment. - Explicit `openclaw infer image describe --model ` requests are different: they run that image-capable provider/model directly, including Ollama refs such as `ollama/qwen2.5vl:7b`.