From 46ebb28d3b7e317402c623bd8ee8fcbff6b05ec5 Mon Sep 17 00:00:00 2001 From: "openclaw-docs-sync[bot]" Date: Tue, 28 Apr 2026 05:36:58 +0000 Subject: [PATCH] chore(sync): mirror docs from openclaw/openclaw@59162379627bc0a2c26af78df4823926dfa4f9fc --- .openclaw-sync/source.json | 4 ++-- docs/cli/onboard.md | 4 +++- docs/gateway/config-tools.md | 3 +++ docs/gateway/local-models.md | 7 +++++++ docs/start/wizard-cli-automation.md | 3 +++ docs/start/wizard-cli-reference.md | 2 ++ 6 files changed, 20 insertions(+), 3 deletions(-) diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json index 3076a90dd..2940dfdcb 100644 --- a/.openclaw-sync/source.json +++ b/.openclaw-sync/source.json @@ -1,5 +1,5 @@ { "repository": "openclaw/openclaw", - "sha": "d48c3e12a5d896cbdad3e7fcf5bba2af644a9ca5", - "syncedAt": "2026-04-28T05:34:31.416Z" + "sha": "59162379627bc0a2c26af78df4823926dfa4f9fc", + "syncedAt": "2026-04-28T05:35:28.467Z" } diff --git a/docs/cli/onboard.md b/docs/cli/onboard.md index e0c715034..bb15823dd 100644 --- a/docs/cli/onboard.md +++ b/docs/cli/onboard.md @@ -61,10 +61,12 @@ openclaw onboard --non-interactive \ --custom-model-id "foo-large" \ --custom-api-key "$CUSTOM_API_KEY" \ --secret-input-mode plaintext \ - --custom-compatibility openai + --custom-compatibility openai \ + --custom-image-input ``` `--custom-api-key` is optional in non-interactive mode. If omitted, onboarding checks `CUSTOM_API_KEY`. +OpenClaw marks common vision model IDs as image-capable automatically. Pass `--custom-image-input` for unknown custom vision IDs, or `--custom-text-input` to force text-only metadata. LM Studio also supports a provider-specific key flag in non-interactive mode: diff --git a/docs/gateway/config-tools.md b/docs/gateway/config-tools.md index 979863b03..660656b01 100644 --- a/docs/gateway/config-tools.md +++ b/docs/gateway/config-tools.md @@ -456,6 +456,7 @@ OpenClaw uses the built-in model catalog. Add custom providers via `models.provi - `models.providers.*.models`: explicit provider model catalog entries. + - `models.providers.*.models.*.input`: model input modalities. Use `["text"]` for text-only models and `["text", "image"]` for native image/vision models. Image attachments are only injected into agent turns when the selected model is marked image-capable. - `models.providers.*.models.*.contextWindow`: native model context window metadata. This overrides provider-level `contextWindow` for that model. - `models.providers.*.models.*.contextTokens`: optional runtime context cap. This overrides provider-level `contextTokens`; use it when you want a smaller effective context budget than the model's native `contextWindow`; `openclaw models list` shows both values when they differ. - `models.providers.*.models.*.compat.supportsDeveloperRole`: optional compatibility hint. For `api: "openai-completions"` with a non-empty non-native `baseUrl` (host not `api.openai.com`), OpenClaw forces this to `false` at runtime. Empty/omitted `baseUrl` keeps default OpenAI behavior. @@ -472,6 +473,8 @@ OpenClaw uses the built-in model catalog. Add custom providers via `models.provi +Interactive custom-provider onboarding infers image input for common vision model IDs such as GPT-4o, Claude, Gemini, Qwen-VL, LLaVA, Pixtral, InternVL, Mllama, MiniCPM-V, and GLM-4V, and skips the extra question for known text-only families. Unknown model IDs still prompt for image support. Non-interactive onboarding uses the same inference; pass `--custom-image-input` to force image-capable metadata or `--custom-text-input` to force text-only metadata. + ### Provider examples diff --git a/docs/gateway/local-models.md b/docs/gateway/local-models.md index a5480dd12..9eaf26860 100644 --- a/docs/gateway/local-models.md +++ b/docs/gateway/local-models.md @@ -168,6 +168,13 @@ catalog id and model ref: - `models.providers.mlx.models[].id: "mlx-community/Qwen3-30B-A3B-6bit"` - `agents.defaults.model.primary: "mlx/mlx-community/Qwen3-30B-A3B-6bit"` +Set `input: ["text", "image"]` on local or proxied vision models so image +attachments are injected into agent turns. Interactive custom-provider +onboarding infers common vision model IDs and asks only for unknown names. +Non-interactive onboarding uses the same inference; use `--custom-image-input` +for unknown vision IDs or `--custom-text-input` when a known-looking model is +text-only behind your endpoint. + Keep `models.mode: "merge"` so hosted models stay available as fallbacks. Use `models.providers..timeoutSeconds` for slow local or remote model servers before raising `agents.defaults.timeoutSeconds`. The provider timeout diff --git a/docs/start/wizard-cli-automation.md b/docs/start/wizard-cli-automation.md index 055fb1ef0..61b342eeb 100644 --- a/docs/start/wizard-cli-automation.md +++ b/docs/start/wizard-cli-automation.md @@ -166,11 +166,13 @@ openclaw onboard --non-interactive \ --custom-api-key "$CUSTOM_API_KEY" \ --custom-provider-id "my-custom" \ --custom-compatibility anthropic \ + --custom-image-input \ --gateway-port 18789 \ --gateway-bind loopback ``` `--custom-api-key` is optional. If omitted, onboarding checks `CUSTOM_API_KEY`. + OpenClaw marks common vision model IDs as image-capable automatically. Add `--custom-image-input` for unknown custom vision IDs, or `--custom-text-input` to force text-only metadata. Ref-mode variant: @@ -184,6 +186,7 @@ openclaw onboard --non-interactive \ --secret-input-mode ref \ --custom-provider-id "my-custom" \ --custom-compatibility anthropic \ + --custom-image-input \ --gateway-port 18789 \ --gateway-bind loopback ``` diff --git a/docs/start/wizard-cli-reference.md b/docs/start/wizard-cli-reference.md index 7ff2efdb9..9ffca43ea 100644 --- a/docs/start/wizard-cli-reference.md +++ b/docs/start/wizard-cli-reference.md @@ -202,6 +202,7 @@ What you set: - `--custom-api-key` (optional; falls back to `CUSTOM_API_KEY`) - `--custom-provider-id` (optional) - `--custom-compatibility ` (optional; default `openai`) + - `--custom-image-input` / `--custom-text-input` (optional; override inferred model input capability) @@ -212,6 +213,7 @@ What you set: Model behavior: - Pick default model from detected options, or enter provider and model manually. +- Custom-provider onboarding infers image support for common model IDs and asks only when the model name is unknown. - When onboarding starts from a provider auth choice, the model picker prefers that provider automatically. For Volcengine and BytePlus, the same preference also matches their coding-plan variants (`volcengine-plan/*`,