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
|`freshness`| Time filter: `day` (24h), `week`, `month`, or `year`|
59
66
|`date_after`| Only results published after this date (YYYY-MM-DD) |
@@ -88,6 +95,9 @@ await web_search({
88
95
- OpenClaw uses the Brave **Search** plan. If you have a legacy subscription (e.g. the original Free plan with 2,000 queries/month), it remains valid but does not include newer features like LLM Context or higher rate limits.
89
96
- Each Brave plan includes **\$5/month in free credit** (renewing). The Search plan costs \$5 per 1,000 requests, so the credit covers 1,000 queries/month. Set your usage limit in the Brave dashboard to avoid unexpected charges. See the [Brave API portal](https://brave.com/search/api/) for current plans.
90
97
- The Search plan includes the LLM Context endpoint and AI inference rights. Storing results to train or tune models requires a plan with explicit storage rights. See the Brave [Terms of Service](https://api-dashboard.search.brave.com/terms-of-service).
98
+
-`llm-context` mode returns grounded source entries instead of the normal web-search snippet shape.
99
+
-`llm-context` mode does not support `ui_lang`, `freshness`, `date_after`, or `date_before`.
100
+
-`ui_lang` must include a region subtag like `en-US`.
91
101
- Results are cached for 15 minutes by default (configurable via `cacheTtlMinutes`).
92
102
93
103
See [Web tools](/tools/web) for the full web_search configuration.
2. PRs: `checks` (Linux Node test split into 2 shards), `checks-windows`, `macos`, `android`
37
-
3. Pushes to `main`: `build-artifacts` + `release-check` + Bun compat + `compat-node22`
38
+
1.`preflight` decides which lanes exist at all. The `docs-scope` and `changed-scope` logic are steps inside this job, not standalone jobs.
39
+
2.`security-fast`, `check`, `check-additional`, `check-docs`, and `skills-python` fail quickly without waiting on the heavier artifact and platform matrix jobs.
40
+
3.`build-artifacts` overlaps with the fast Linux lanes so downstream consumers can start as soon as the shared build is ready.
41
+
4. Heavier platform and runtime lanes fan out after that: `checks-fast-core`, `checks-fast-extensions`, `extension-fast`, `checks`, `checks-windows`, `macos-node`, `macos-swift`, and `android`.
38
42
39
43
Scope logic lives in `scripts/ci-changed-scope.mjs` and is covered by unit tests in `src/scripts/ci-changed-scope.test.ts`.
40
-
The same shared scope module also drives the separate `install-smoke` workflow through a narrower `changed-smoke` gate, so Docker/install smoke only runs for install, packaging, and container-relevant changes.
44
+
The separate `install-smoke` workflow reuses the same scope script through its own `preflight` job. It computes `run_install_smoke` from the narrower changed-smoke signal, so Docker/install smoke only runs for install, packaging, and container-relevant changes.
45
+
46
+
On pushes, the `checks` matrix adds the push-only `compat-node22` lane. On pull requests, that lane is skipped and the matrix stays focused on the normal test/channel lanes.
- The state directory returned by OpenClaw's local state resolver, usually `~/.openclaw`
39
39
- The active config file path
40
-
- The OAuth / credentials directory
40
+
- The resolved `credentials/` directory when it exists outside the state directory
41
41
- Workspace directories discovered from the current config, unless you pass `--no-include-workspace`
42
42
43
-
If you use `--only-config`, OpenClaw skips state, credentials, and workspace discovery and archives only the active config file path.
43
+
Model auth profiles are already part of the state directory under
44
+
`agents/<agentId>/agent/auth-profiles.json`, so they are normally covered by the
45
+
state backup entry.
44
46
45
-
OpenClaw canonicalizes paths before building the archive. If config, credentials, or a workspace already live inside the state directory, they are not duplicated as separate top-level backup sources. Missing paths are skipped.
47
+
If you use `--only-config`, OpenClaw skips state, credentials-directory, and workspace discovery and archives only the active config file path.
48
+
49
+
OpenClaw canonicalizes paths before building the archive. If config, the
50
+
credentials directory, or a workspace already live inside the state directory,
51
+
they are not duplicated as separate top-level backup sources. Missing paths are
52
+
skipped.
46
53
47
54
The archive payload stores file contents from those source trees, and the embedded `manifest.json` records the resolved absolute source paths plus the archive layout used for each asset.
48
55
@@ -56,7 +63,8 @@ If you still want a partial backup in that situation, rerun:
56
63
openclaw backup create --no-include-workspace
57
64
```
58
65
59
-
That keeps state, config, and credentials in scope while skipping workspace discovery entirely.
66
+
That keeps state, config, and the external credentials directory in scope while
67
+
skipping workspace discovery entirely.
60
68
61
69
If you only need a copy of the config file itself, `--only-config` also works when the config is malformed because it does not rely on parsing the config for workspace discovery.
Copy file name to clipboardExpand all lines: docs/concepts/models.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -29,7 +29,7 @@ Related:
29
29
-`agents.defaults.pdfModel` is used by the `pdf` tool. If omitted, the tool
30
30
falls back to `agents.defaults.imageModel`, then the resolved session/default
31
31
model.
32
-
-`agents.defaults.imageGenerationModel` is used by the shared image-generation capability. If omitted, `image_generate` can still infer a provider default from compatible auth-backed image-generation plugins. If you set a specific provider/model, also configure that provider's auth/API key.
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
33
- Per-agent defaults can override `agents.defaults.model` via `agents.list[].model` plus bindings (see [/concepts/multi-agent](/concepts/multi-agent)).
Copy file name to clipboardExpand all lines: docs/gateway/configuration-reference.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -970,12 +970,12 @@ Time format in system prompt. Default: `auto` (OS preference).
970
970
- Also used as fallback routing when the selected/default model cannot accept image input.
971
971
-`imageGenerationModel`: accepts either a string (`"provider/model"`) or an object (`{ primary, fallbacks }`).
972
972
- Used by the shared image-generation capability and any future tool/plugin surface that generates images.
973
-
- Typical values: `google/gemini-3-pro-image-preview` for native Gemini image generation, `fal/fal-ai/flux/dev` for fal, or `openai/gpt-image-1` for OpenAI Images.
973
+
- Typical values: `google/gemini-3.1-flash-image-preview` for native Gemini image generation, `fal/fal-ai/flux/dev` for fal, or `openai/gpt-image-1` for OpenAI Images.
974
974
- 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/*`).
975
-
- If omitted, `image_generate` can still infer a best-effort provider default from compatible auth-backed image-generation providers.
975
+
- 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.
976
976
-`pdfModel`: accepts either a string (`"provider/model"`) or an object (`{ primary, fallbacks }`).
977
977
- Used by the `pdf` tool for model routing.
978
-
- If omitted, the PDF tool falls back to `imageModel`, then to best-effort provider defaults.
978
+
- If omitted, the PDF tool falls back to `imageModel`, then to the resolved session/default model.
979
979
-`pdfMaxBytesMb`: default PDF size limit for the `pdf` tool when `maxBytesMb` is not passed at call time.
980
980
-`pdfMaxPages`: default maximum pages considered by extraction fallback mode in the `pdf` tool.
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?v=4&size=40){kind=avatar}
0 commit comments