You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- Update/npm: prefer the npm binary that owns the installed global OpenClaw prefix so mixed Homebrew-plus-nvm setups update the right install. (#60153) Thanks @jayeshp19.
192
192
- Windows/restart: clean up stale gateway listeners before Windows self-restart and treat listener and argv probe failures as inconclusive, so scheduled-task relaunch no longer falls into an `EADDRINUSE` retry loop. (#60480) Thanks @arifahmedjoy.
193
193
- Plugins: suppress trust-warning noise during non-activating snapshot and CLI metadata loads. (#61427) Thanks @gumadeiras.
194
+
- Agents/video generation: accept `agents.defaults.videoGenerationModel` in strict config validation and `openclaw config set/get`, so gateways using `video_generate` no longer fail to boot after enabling a video model.
Copy file name to clipboardExpand all lines: docs/concepts/models.md
+2-1Lines changed: 2 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -30,7 +30,7 @@ Related:
30
30
falls back to `agents.defaults.imageModel`, then the resolved session/default
31
31
model.
32
32
-`agents.defaults.imageGenerationModel` is used by the shared image-generation capability. If omitted, `image_generate` can still infer an auth-backed provider default. It tries the current default provider first, then the remaining registered image-generation providers in provider-id order. If you set a specific provider/model, also configure that provider's auth/API key.
33
-
-`agents.defaults.videoGenerationModel` is used by the shared video-generation capability. Unlike image generation, this does not infer a provider default today. Set an explicit `provider/model` such as `qwen/wan2.6-t2v`, and configure that provider's auth/API key too.
33
+
-`agents.defaults.videoGenerationModel` is used by the shared video-generation capability. If omitted, `video_generate` can still infer an auth-backed provider default. It tries the current default provider first, then the remaining registered video-generation providers in provider-id order. If you set a specific provider/model, also configure that provider's auth/API key.
34
34
- Per-agent defaults can override `agents.defaults.model` via `agents.list[].model` plus bindings (see [/concepts/multi-agent](/concepts/multi-agent)).
35
35
36
36
## Quick model policy
@@ -252,4 +252,5 @@ This applies whenever OpenClaw regenerates `models.json`, including command-driv
252
252
-[Model Providers](/concepts/model-providers) — provider routing and auth
Copy file name to clipboardExpand all lines: docs/gateway/configuration-reference.md
+9-9Lines changed: 9 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1026,9 +1026,9 @@ Time format in system prompt. Default: `auto` (OS preference).
1026
1026
- If you select a provider/model directly, configure the matching provider auth/API key too (for example `GEMINI_API_KEY` or `GOOGLE_API_KEY` for `google/*`, `OPENAI_API_KEY` for `openai/*`, `FAL_KEY` for `fal/*`).
1027
1027
- If omitted, `image_generate` can still infer an auth-backed provider default. It tries the current default provider first, then the remaining registered image-generation providers in provider-id order.
1028
1028
-`videoGenerationModel`: accepts either a string (`"provider/model"`) or an object (`{ primary, fallbacks }`).
1029
-
- Used by the shared video-generation capability.
1029
+
- Used by the shared video-generation capability and the built-in `video_generate` tool.
1030
1030
- Typical values: `qwen/wan2.6-t2v`, `qwen/wan2.6-i2v`, `qwen/wan2.6-r2v`, `qwen/wan2.6-r2v-flash`, or `qwen/wan2.7-r2v`.
1031
-
-Set this explicitly before using shared video generation. Unlike `imageGenerationModel`, the video-generation runtime does not infer a provider default yet.
1031
+
-If omitted, `video_generate` can still infer an auth-backed provider default. It tries the current default provider first, then the remaining registered video-generation providers in provider-id order.
1032
1032
- If you select a provider/model directly, configure the matching provider auth/API key too.
1033
1033
- The bundled Qwen video-generation provider currently supports up to 1 output video, 1 input image, 4 input videos, 10 seconds duration, and provider-level `size`, `aspectRatio`, `resolution`, `audio`, and `watermark` options.
1034
1034
-`pdfModel`: accepts either a string (`"provider/model"`) or an object (`{ primary, fallbacks }`).
@@ -1936,12 +1936,12 @@ Defaults for Talk mode (macOS/iOS/Android).
1936
1936
1937
1937
Local onboarding defaults new local configs to `tools.profile: "coding"` when unset (existing explicit profiles are preserved).
|`session_status`| Lightweight `/status`-style readback and session model override |[Session Tools](/concepts/session-tool)|
72
73
73
74
For image work, use `image` for analysis and `image_generate` for generation or editing. If you target `openai/*`, `google/*`, `fal/*`, or another non-default image provider, configure that provider's auth/API key first.
74
75
76
+
For video work, use `video_generate`. If you target `qwen/*` or another non-default video provider, configure that provider's auth/API key first.
77
+
75
78
`session_status` is the lightweight status/readback tool in the sessions group.
76
79
It answers `/status`-style questions about the current session and can
77
80
optionally set a per-session model override; `model=default` clears that
@@ -121,12 +124,12 @@ config. Deny always wins over allow.
121
124
`tools.profile` sets a base allowlist before `allow`/`deny` is applied.
0 commit comments