mirror of
https://github.com/openclaw/openclaw.git
synced 2026-07-16 13:11:33 +00:00
fa77fe10d5
* chore(models): migrate active GPT-5.5 references * test(workboard): expect GPT-5.6 Sol default * chore: keep release notes in PR body * test(models): align picker fixtures with Sol default * test: update PDF default model expectation * test(qa): migrate thinking smoke to Luna * test(gateway): align mock catalog with Sol default * ci: retrigger exact-head PR checks * test(gateway): document default catalog invariant
838 lines
40 KiB
Markdown
838 lines
40 KiB
Markdown
---
|
||
summary: "Tools config (policy, experimental toggles, provider-backed tools) and custom provider/base-URL setup"
|
||
read_when:
|
||
- Configuring `tools.*` policy, allowlists, or experimental features
|
||
- Registering custom providers or overriding base URLs
|
||
- Setting up OpenAI-compatible self-hosted endpoints
|
||
title: "Configuration — tools and custom providers"
|
||
sidebarTitle: "Tools and custom providers"
|
||
---
|
||
|
||
`tools.*` config keys and custom provider / base-URL setup. For agents, channels, and other top-level config keys, see [Configuration reference](/gateway/configuration-reference).
|
||
|
||
## Tools
|
||
|
||
### Tool profiles
|
||
|
||
`tools.profile` sets a base allowlist before `tools.allow`/`tools.deny`:
|
||
|
||
<Note>
|
||
Local onboarding defaults new local configs to `tools.profile: "coding"` when unset (existing explicit profiles are preserved).
|
||
</Note>
|
||
|
||
| Profile | Includes |
|
||
| ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||
| `minimal` | `session_status` only |
|
||
| `coding` | `group:fs`, `group:runtime`, `group:web`, `group:sessions`, `group:memory`, `cron`, `get_goal`, `create_goal`, `update_goal`, `update_plan`, `skill_workshop`, `image`, `image_generate`, `music_generate`, `video_generate` |
|
||
| `messaging` | `group:messaging`, `sessions_list`, `sessions_history`, `sessions_send`, `session_status` |
|
||
| `full` | No restriction (same as unset) |
|
||
|
||
`coding` and `messaging` also implicitly allow `bundle-mcp` (configured MCP servers).
|
||
|
||
### Tool groups
|
||
|
||
| Group | Tools |
|
||
| ------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||
| `group:runtime` | `exec`, `process`, `code_execution` (`bash` is accepted as an alias for `exec`) |
|
||
| `group:fs` | `read`, `write`, `edit`, `apply_patch` |
|
||
| `group:sessions` | `sessions_list`, `sessions_history`, `sessions_send`, `sessions_spawn`, `sessions_yield`, `subagents`, `session_status`, `spawn_task`, `dismiss_task` |
|
||
| `group:memory` | `memory_search`, `memory_get` |
|
||
| `group:web` | `web_search`, `x_search`, `web_fetch` |
|
||
| `group:ui` | `browser`, `canvas` |
|
||
| `group:automation` | `heartbeat_respond`, `cron`, `gateway` |
|
||
| `group:messaging` | `message` |
|
||
| `group:nodes` | `nodes`, `computer` |
|
||
| `group:agents` | `agents_list`, `get_goal`, `create_goal`, `update_goal`, `update_plan`, `skill_workshop` |
|
||
| `group:media` | `image`, `image_generate`, `music_generate`, `video_generate`, `tts` |
|
||
| `group:openclaw` | All built-in tools above except `read`/`write`/`edit`/`apply_patch`/`exec`/`process`/`canvas` (excludes plugin tools) |
|
||
| `group:plugins` | Tools owned by loaded plugins, including configured MCP servers exposed through `bundle-mcp` |
|
||
|
||
`spawn_task` lets a coding agent propose confirmed follow-up work without starting it. The Control UI shows the title and summary as an actionable chip; a Gateway-backed TUI shows an equivalent interactive prompt. Accepting either creates a fresh managed-worktree session and sends the full prompt there while the current turn continues. `dismiss_task` withdraws a still-pending suggestion by the ephemeral `task_id` returned from `spawn_task`.
|
||
|
||
The tools are offered only when the initiating operator surface can receive and action Gateway task-suggestion events. Channel sessions and local/embedded TUI sessions do not receive them; channel transports need a portable typed task action before they can safely expose this flow. Suggestions are process-local and disappear when the Gateway restarts. Both tools remain in the `coding` profile and `group:sessions`, so normal `tools.allow` and `tools.deny` policy configures them automatically when the surface supports them.
|
||
|
||
### MCP and plugin tools inside sandbox tool policy
|
||
|
||
Configured MCP servers are exposed as plugin-owned tools under the `bundle-mcp` plugin id. Normal tool profiles can allow them, but `tools.sandbox.tools` is an additional gate for sandboxed sessions. If sandbox mode is `"all"` or `"non-main"`, include one of these entries in the sandbox tool allowlist when MCP/plugin tools should be visible:
|
||
|
||
- `bundle-mcp` for OpenClaw-managed MCP servers from `mcp.servers`
|
||
- the plugin id for a specific native plugin
|
||
- `group:plugins` for all loaded plugin-owned tools
|
||
- exact MCP server tool names or server globs such as `outlook__send_mail` or `outlook__*` when you only want one server
|
||
|
||
Server globs use the provider-safe MCP server prefix, not necessarily the raw `mcp.servers` key. Non-`[A-Za-z0-9_-]` characters become `-`, names that do not start with a letter get an `mcp-` prefix, and long or duplicate prefixes may be truncated or suffixed; for example, `mcp.servers["Outlook Graph"]` uses a glob like `outlook-graph__*`.
|
||
|
||
```json5
|
||
{
|
||
agents: { defaults: { sandbox: { mode: "all" } } },
|
||
mcp: {
|
||
servers: {
|
||
outlook: { command: "node", args: ["./outlook-mcp.js"] },
|
||
},
|
||
},
|
||
tools: {
|
||
sandbox: {
|
||
tools: {
|
||
alsoAllow: ["web_search", "web_fetch", "memory_search", "memory_get", "bundle-mcp"],
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
Without that sandbox-layer entry, the MCP server can still load successfully while its tools are filtered before the provider request. Use `openclaw doctor` to catch this shape for OpenClaw-managed servers in `mcp.servers`. MCP servers loaded from bundled plugin manifests or Claude `.mcp.json` use the same sandbox gate, but this diagnostic does not enumerate those sources yet; use the same allowlist entries if their tools disappear in sandboxed turns.
|
||
|
||
### `tools.codeMode`
|
||
|
||
`tools.codeMode` enables the generic OpenClaw code-mode surface. When enabled
|
||
for a run with tools, normal OpenClaw tools move behind the in-sandbox `tools.*`
|
||
catalog bridge, and MCP tools are available through the generated `MCP`
|
||
namespace. The model normally sees `exec` and `wait`; tools such as `computer`
|
||
whose structured results cannot cross the JSON-only bridge stay direct.
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
codeMode: {
|
||
enabled: true,
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
The shorthand is also accepted:
|
||
|
||
```json5
|
||
{
|
||
tools: { codeMode: true },
|
||
}
|
||
```
|
||
|
||
MCP declarations are exposed through the read-only virtual API file surface in
|
||
code mode. Guest code can call `API.list("mcp")` and
|
||
`API.read("mcp/<server>.d.ts")` to inspect TypeScript-style signatures before
|
||
calling `MCP.<server>.<tool>()`. See [Code mode](/reference/code-mode) for the
|
||
runtime contract, limits, and debugging steps.
|
||
|
||
### `tools.allow` / `tools.deny`
|
||
|
||
Global tool allow/deny policy (deny wins). Case-insensitive, supports `*` wildcards. Applied even when Docker sandbox is off.
|
||
|
||
```json5
|
||
{
|
||
tools: { deny: ["browser", "canvas"] },
|
||
}
|
||
```
|
||
|
||
`write` and `apply_patch` are separate tool ids. `allow: ["write"]` also enables `apply_patch` for compatible models, but `deny: ["write"]` does not deny `apply_patch`. To block all file mutation, deny `group:fs` or list each mutating tool explicitly:
|
||
|
||
```json5
|
||
{
|
||
tools: { deny: ["write", "edit", "apply_patch"] },
|
||
}
|
||
```
|
||
|
||
<Note>
|
||
`allow` and `alsoAllow` cannot both be set in the same scope (`tools`, `tools.byProvider.<id>`, `agents.list[].tools`) — config validation rejects it. Merge `alsoAllow` entries into `allow`, or drop `allow` and use `profile` + `alsoAllow` instead.
|
||
</Note>
|
||
|
||
### `tools.byProvider`
|
||
|
||
Further restrict tools for specific providers or models. Order: base profile → provider profile → allow/deny.
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
profile: "coding",
|
||
byProvider: {
|
||
"google-antigravity": { profile: "minimal" },
|
||
"openai/gpt-5.4": { allow: ["group:fs", "sessions_list"] },
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
### `tools.toolsBySender`
|
||
|
||
Restricts tools for a specific requester identity. This is defense-in-depth on top of channel access control; sender values must come from the channel adapter, not message text.
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
toolsBySender: {
|
||
"channel:discord:1234567890123": { alsoAllow: ["group:fs"] },
|
||
"id:guest-user-id": { deny: ["group:runtime", "group:fs"] },
|
||
"*": { deny: ["exec", "process", "write", "edit", "apply_patch"] },
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
Keys use explicit prefixes: `channel:<channelId>:<senderId>`, `id:<senderId>`, `e164:<phone>`, `username:<handle>`, `name:<displayName>`, or `"*"`. Channel ids are canonical OpenClaw ids; aliases such as `teams` normalize to `msteams`. Legacy unprefixed keys are accepted as `id:` only. Matching order is channel+id, id, e164, username, name, then wildcard.
|
||
|
||
Per-agent `agents.list[].tools.toolsBySender` overrides the global sender match when it matches, even with an empty `{}` policy.
|
||
|
||
### `tools.elevated`
|
||
|
||
Controls elevated exec access outside the sandbox:
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
elevated: {
|
||
enabled: true,
|
||
allowFrom: {
|
||
whatsapp: ["+15555550123"],
|
||
discord: ["1234567890123", "987654321098765432"],
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
- Per-agent override (`agents.list[].tools.elevated`) can only further restrict.
|
||
- `/elevated on|off|ask|full` stores state per session; inline directives apply to single message.
|
||
- Elevated `exec` bypasses sandboxing and uses the configured escape path (`gateway` by default, or `node` when the exec target is `node`).
|
||
|
||
### `tools.exec`
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
exec: {
|
||
backgroundMs: 10000,
|
||
timeoutSec: 1800,
|
||
cleanupMs: 1800000,
|
||
approvalRunningNoticeMs: 10000,
|
||
notifyOnExit: true,
|
||
notifyOnExitEmptySuccess: false,
|
||
commandHighlighting: false,
|
||
applyPatch: {
|
||
enabled: true,
|
||
allowModels: ["gpt-5.6-sol"],
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
Values shown are defaults except `applyPatch.allowModels` (empty/unset by default, meaning any compatible model may use `apply_patch`). `approvalRunningNoticeMs` emits a running notice when approval-backed exec runs long; `0` disables it.
|
||
|
||
### `tools.loopDetection`
|
||
|
||
Tool-loop safety checks are **disabled by default**. Set `enabled: true` to activate detection. Settings can be defined globally in `tools.loopDetection` and overridden per-agent at `agents.list[].tools.loopDetection`.
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
loopDetection: {
|
||
enabled: true,
|
||
historySize: 30,
|
||
warningThreshold: 10,
|
||
unknownToolThreshold: 10,
|
||
criticalThreshold: 20,
|
||
globalCircuitBreakerThreshold: 30,
|
||
detectors: {
|
||
genericRepeat: true,
|
||
knownPollNoProgress: true,
|
||
pingPong: true,
|
||
},
|
||
postCompactionGuard: {
|
||
windowSize: 3,
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
<ParamField path="historySize" type="number">
|
||
Max tool-call history retained for loop analysis.
|
||
</ParamField>
|
||
<ParamField path="warningThreshold" type="number">
|
||
Repeating no-progress pattern threshold for warnings.
|
||
</ParamField>
|
||
<ParamField path="unknownToolThreshold" type="number">
|
||
Blocks repeated calls to the same unavailable/unknown tool name after this many misses.
|
||
</ParamField>
|
||
<ParamField path="criticalThreshold" type="number">
|
||
Higher repeating threshold for blocking critical loops.
|
||
</ParamField>
|
||
<ParamField path="globalCircuitBreakerThreshold" type="number">
|
||
Hard stop threshold for any no-progress run.
|
||
</ParamField>
|
||
<ParamField path="detectors.genericRepeat" type="boolean">
|
||
Warn on repeated same-tool/same-args calls.
|
||
</ParamField>
|
||
<ParamField path="detectors.knownPollNoProgress" type="boolean">
|
||
Warn/block on known poll tools (`process.poll`, `command_status`, etc.).
|
||
</ParamField>
|
||
<ParamField path="detectors.pingPong" type="boolean">
|
||
Warn/block on alternating no-progress pair patterns.
|
||
</ParamField>
|
||
<ParamField path="postCompactionGuard.windowSize" type="number">
|
||
Number of attempts after auto-compaction the guard stays armed for; aborts if the agent repeats the same (tool, args, result) inside that window.
|
||
</ParamField>
|
||
|
||
<Warning>
|
||
If `warningThreshold >= criticalThreshold` or `criticalThreshold >= globalCircuitBreakerThreshold`, validation fails.
|
||
</Warning>
|
||
|
||
### `tools.web`
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
web: {
|
||
search: {
|
||
enabled: true,
|
||
apiKey: "brave_api_key", // or BRAVE_API_KEY env (Brave provider)
|
||
maxResults: 5,
|
||
timeoutSeconds: 30,
|
||
cacheTtlMinutes: 15,
|
||
},
|
||
fetch: {
|
||
enabled: true,
|
||
provider: "firecrawl", // optional; omit for auto-detect
|
||
maxChars: 20000,
|
||
maxCharsCap: 20000,
|
||
maxResponseBytes: 750000,
|
||
timeoutSeconds: 30,
|
||
cacheTtlMinutes: 15,
|
||
maxRedirects: 3,
|
||
readability: true,
|
||
userAgent: "custom-ua",
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
Values shown are defaults except `provider` and `userAgent`. `maxResponseBytes` clamps to 32000–10000000; `maxChars` clamps to `maxCharsCap` (raise `maxCharsCap` to allow larger responses).
|
||
|
||
### `tools.media`
|
||
|
||
Configures inbound media understanding (image/audio/video):
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
media: {
|
||
concurrency: 2,
|
||
asyncCompletion: {
|
||
directSend: false, // deprecated: completions stay agent-mediated
|
||
},
|
||
audio: {
|
||
enabled: true,
|
||
maxBytes: 20971520,
|
||
scope: {
|
||
default: "deny",
|
||
rules: [{ action: "allow", match: { chatType: "direct" } }],
|
||
},
|
||
models: [
|
||
{ provider: "openai", model: "gpt-4o-mini-transcribe" },
|
||
{ type: "cli", command: "whisper", args: ["--model", "base", "{{MediaPath}}"] },
|
||
],
|
||
},
|
||
image: {
|
||
enabled: true,
|
||
timeoutSeconds: 180,
|
||
models: [{ provider: "ollama", model: "gemma4:26b", timeoutSeconds: 300 }],
|
||
},
|
||
video: {
|
||
enabled: true,
|
||
maxBytes: 52428800,
|
||
models: [{ provider: "google", model: "gemini-3-flash-preview" }],
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
`concurrency` (default `2`), `audio.maxBytes` (default 20 MB), and `video.maxBytes` (default 50 MB) are shown at their defaults; `image.maxBytes` defaults to 10 MB. Per-capability request timeout defaults: image/audio `60`s, video `120`s.
|
||
|
||
<AccordionGroup>
|
||
<Accordion title="Media model entry fields">
|
||
**Provider entry** (`type: "provider"` or omitted):
|
||
|
||
- `provider`: API provider id (`openai`, `anthropic`, `google`/`gemini`, `groq`, etc.)
|
||
- `model`: model id override
|
||
- `profile` / `preferredProfile`: `auth-profiles.json` profile selection
|
||
|
||
**CLI entry** (`type: "cli"`):
|
||
|
||
- `command`: executable to run
|
||
- `args`: templated args (supports `{{MediaPath}}`, `{{Prompt}}`, `{{MaxChars}}`, etc.; `openclaw doctor --fix` migrates deprecated `{input}` placeholders to `{{MediaPath}}`)
|
||
|
||
**Common fields:**
|
||
|
||
- `capabilities`: optional list (`image`, `audio`, `video`). Each provider plugin declares its own default capability set; for example the bundled `openai` provider defaults to image+audio, `anthropic`/`minimax` to image, `google` to image+audio+video, and `groq` to audio.
|
||
- `prompt`, `maxChars`, `maxBytes`, `timeoutSeconds`, `language`: per-entry overrides.
|
||
- `tools.media.image.timeoutSeconds` and matching image model `timeoutSeconds` entries also apply when the agent calls the explicit `image` tool. For image understanding, this timeout applies to the request itself and is not reduced by earlier preparation work.
|
||
- Failures fall back to the next entry.
|
||
|
||
Provider auth follows standard order: `auth-profiles.json` → env vars → `models.providers.*.apiKey`.
|
||
|
||
**Async completion fields:**
|
||
|
||
- `asyncCompletion.directSend`: deprecated compatibility flag. Completed async media tasks stay requester-session mediated so the agent receives the result, decides how to tell the user, and uses the message tool when source delivery requires it.
|
||
|
||
</Accordion>
|
||
</AccordionGroup>
|
||
|
||
### `tools.agentToAgent`
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
agentToAgent: {
|
||
enabled: false,
|
||
allow: ["home", "work"],
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
### `tools.sessions`
|
||
|
||
Controls which sessions can be targeted by the session tools (`sessions_list`, `sessions_history`, `sessions_send`).
|
||
|
||
Default: `tree` (current session + sessions spawned by it, such as subagents).
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
sessions: {
|
||
// "self" | "tree" | "agent" | "all"
|
||
visibility: "tree",
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
<AccordionGroup>
|
||
<Accordion title="Visibility scopes">
|
||
- `self`: only the current session key.
|
||
- `tree`: current session + sessions spawned by the current session (subagents).
|
||
- `agent`: any session belonging to the current agent id (can include other users if you run per-sender sessions under the same agent id).
|
||
- `all`: any session. Cross-agent targeting still requires `tools.agentToAgent`.
|
||
- Sandbox clamp: when the current session is sandboxed and `agents.defaults.sandbox.sessionToolsVisibility="spawned"` (the default), visibility is forced to `tree` even if `tools.sessions.visibility="all"`.
|
||
- When not `all`, `sessions_list` includes a compact `visibility` field
|
||
describing the effective mode and a warning that some sessions may be
|
||
omitted outside the current scope.
|
||
|
||
</Accordion>
|
||
</AccordionGroup>
|
||
|
||
### `tools.sessions_spawn`
|
||
|
||
Controls inline attachment support for `sessions_spawn`.
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
sessions_spawn: {
|
||
attachments: {
|
||
enabled: false, // opt-in: set true to allow inline file attachments
|
||
maxTotalBytes: 5242880, // 5 MB total across all files
|
||
maxFiles: 50,
|
||
maxFileBytes: 1048576, // 1 MB per file
|
||
retainOnSessionKeep: false, // keep attachments when cleanup="keep"
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
<AccordionGroup>
|
||
<Accordion title="Attachment notes">
|
||
- Attachments require `enabled: true`.
|
||
- Subagent attachments are materialized into the child workspace at `.openclaw/attachments/<uuid>/` with a `.manifest.json`.
|
||
- ACP attachments are image-only and forwarded inline to the ACP runtime after the same file count, per-file byte, and total byte limits pass.
|
||
- Attachment content is automatically redacted from transcript persistence.
|
||
- Base64 inputs are validated with strict alphabet/padding checks and a pre-decode size guard.
|
||
- Subagent attachment file permissions are `0700` for directories and `0600` for files.
|
||
- Subagent cleanup follows the `cleanup` policy: `delete` always removes attachments; `keep` retains them only when `retainOnSessionKeep: true`.
|
||
|
||
</Accordion>
|
||
</AccordionGroup>
|
||
|
||
<a id="toolsexperimental"></a>
|
||
|
||
### `tools.experimental`
|
||
|
||
Experimental built-in tool flags. Default off unless a strict-agentic GPT-5 auto-enable rule applies.
|
||
|
||
```json5
|
||
{
|
||
tools: {
|
||
experimental: {
|
||
planTool: true, // enable experimental update_plan
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
- `planTool`: enables the structured `update_plan` tool for non-trivial multi-step work tracking.
|
||
- Default: `false` unless `agents.defaults.embeddedAgent.executionContract` (or a per-agent override) is set to `"strict-agentic"` for an `openai` provider run against a GPT-5-family model id (this covers OpenAI Codex CLI runs too, since Codex auth/model routing lives under the `openai` provider). Set `true` to force the tool on outside that scope, or `false` to keep it off even for strict-agentic GPT-5 runs.
|
||
- When enabled, the system prompt also adds usage guidance so the model only uses it for substantial work and keeps at most one step `in_progress`.
|
||
|
||
### `agents.defaults.subagents`
|
||
|
||
```json5
|
||
{
|
||
agents: {
|
||
defaults: {
|
||
subagents: {
|
||
allowAgents: ["research"],
|
||
model: "minimax/MiniMax-M2.7",
|
||
maxConcurrent: 8,
|
||
runTimeoutSeconds: 900,
|
||
announceTimeoutMs: 120000,
|
||
archiveAfterMinutes: 60,
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
- `model`: default model for spawned sub-agents. If omitted, sub-agents inherit the caller's model.
|
||
- `allowAgents`: default allowlist of configured target agent ids for `sessions_spawn` when the requester agent does not set its own `subagents.allowAgents` (`["*"]` = any configured target; default: same agent only). Stale entries whose agent config was deleted are rejected by `sessions_spawn` and omitted from `agents_list`; run `openclaw doctor --fix` to clean them up.
|
||
- `maxConcurrent`: max concurrent sub-agent runs. Default: `8`.
|
||
- `runTimeoutSeconds`: timeout (seconds) for `sessions_spawn` when the caller does not pass its own override. Default: `0` (no timeout); the `900` shown above is a common opt-in value, not the built-in default.
|
||
- `announceTimeoutMs`: per-call timeout (milliseconds) for gateway `agent` announce delivery attempts. Default: `120000`. Transient retries can make the total announce wait longer than one configured timeout.
|
||
- `archiveAfterMinutes`: minutes after a sub-agent session completes before it is auto-archived. Default: `60`; `0` disables auto-archive.
|
||
- Per-subagent tool policy: `tools.subagents.tools.allow` / `tools.subagents.tools.deny`.
|
||
|
||
---
|
||
|
||
## Custom providers and base URLs
|
||
|
||
Provider plugins publish their own model catalog rows. Add custom providers via `models.providers` in config or `~/.openclaw/agents/<agentId>/agent/models.json`.
|
||
|
||
Configuring a custom/local provider `baseUrl` is also the narrow network trust decision for model HTTP requests: OpenClaw allows that exact `scheme://host:port` origin through the guarded fetch path, without adding a separate config option or trusting other private origins.
|
||
|
||
```json5
|
||
{
|
||
models: {
|
||
mode: "merge", // merge (default) | replace
|
||
providers: {
|
||
"custom-proxy": {
|
||
baseUrl: "http://localhost:4000/v1",
|
||
apiKey: "LITELLM_KEY",
|
||
api: "openai-completions", // openai-completions | openai-responses | anthropic-messages | google-generative-ai | etc.
|
||
models: [
|
||
{
|
||
id: "llama-3.1-8b",
|
||
name: "Llama 3.1 8B",
|
||
reasoning: false,
|
||
input: ["text"],
|
||
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
||
contextWindow: 128000,
|
||
contextTokens: 96000,
|
||
maxTokens: 32000,
|
||
},
|
||
],
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
<AccordionGroup>
|
||
<Accordion title="Auth and merge precedence">
|
||
- Use `authHeader: true` + `headers` for custom auth needs.
|
||
- Override agent config root with `OPENCLAW_AGENT_DIR`.
|
||
- Merge precedence for matching provider IDs:
|
||
- Non-empty agent `models.json` `baseUrl` values win.
|
||
- Non-empty agent `apiKey` values win only when that provider is not SecretRef-managed in current config/auth-profile context.
|
||
- SecretRef-managed provider `apiKey` values are refreshed from source markers (`ENV_VAR_NAME` for env refs, `secretref-managed` for file/exec refs) instead of persisting resolved secrets.
|
||
- SecretRef-managed provider header values are refreshed from source markers (`secretref-env:ENV_VAR_NAME` for env refs, `secretref-managed` for file/exec refs).
|
||
- Empty or missing agent `apiKey`/`baseUrl` fall back to `models.providers` in config.
|
||
- Matching model `contextWindow`/`maxTokens`: the explicit config value wins when present and valid (a positive finite number); otherwise the implicit/generated catalog value is used.
|
||
- Matching model `contextTokens` follows the same explicit-wins-else-implicit rule; use it to limit effective context without changing native model metadata.
|
||
- Provider-plugin catalogs are stored as generated plugin-owned catalog shards under the agent's plugin state.
|
||
- Use `models.mode: "replace"` when you want config to fully rewrite `models.json` and skip merging in plugin-owned catalog shards.
|
||
- Marker persistence is source-authoritative: markers are written from the active source config snapshot (pre-resolution), not from resolved runtime secret values.
|
||
|
||
</Accordion>
|
||
</AccordionGroup>
|
||
|
||
### Provider field details
|
||
|
||
<AccordionGroup>
|
||
<Accordion title="Top-level catalog">
|
||
- `models.mode`: provider catalog behavior (`merge` or `replace`).
|
||
- `models.providers`: custom provider map keyed by provider id.
|
||
- Safe edits: use `openclaw config set models.providers.<id> '<json>' --strict-json --merge` or `openclaw config set models.providers.<id>.models '<json-array>' --strict-json --merge` for additive updates. `config set` refuses destructive replacements unless you pass `--replace`.
|
||
|
||
</Accordion>
|
||
<Accordion title="Provider connection and auth">
|
||
- `models.providers.*.api`: request adapter (`openai-completions`, `openai-responses`, `openai-chatgpt-responses`, `anthropic-messages`, `google-generative-ai`, `google-vertex`, `github-copilot`, `bedrock-converse-stream`, `ollama`, `azure-openai-responses`). For self-hosted `/v1/chat/completions` backends such as MLX, vLLM, SGLang, and most OpenAI-compatible local servers, use `openai-completions`. A custom provider with `baseUrl` but no `api` defaults to `openai-completions`; set `openai-responses` only when the backend supports `/v1/responses`.
|
||
- `models.providers.*.apiKey`: provider credential (prefer SecretRef/env substitution).
|
||
- `models.providers.*.auth`: auth strategy (`api-key`, `token`, `oauth`, `aws-sdk`).
|
||
- `models.providers.*.contextWindow`: default native context window for models under this provider when the model entry does not set `contextWindow`.
|
||
- `models.providers.*.contextTokens`: default effective runtime context cap for models under this provider when the model entry does not set `contextTokens`.
|
||
- `models.providers.*.maxTokens`: default output-token cap for models under this provider when the model entry does not set `maxTokens`.
|
||
- `models.providers.*.timeoutSeconds`: optional per-provider model HTTP request timeout in seconds, including connect, headers, body, and total request abort handling.
|
||
- `models.providers.*.injectNumCtxForOpenAICompat`: for Ollama + `openai-completions`, inject `options.num_ctx` into requests (default: `true`).
|
||
- `models.providers.*.authHeader`: force credential transport in the `Authorization` header when required.
|
||
- `models.providers.*.baseUrl`: upstream API base URL.
|
||
- `models.providers.*.headers`: extra static headers for proxy/tenant routing.
|
||
|
||
</Accordion>
|
||
<Accordion title="Request transport overrides">
|
||
`models.providers.*.request`: transport overrides for model-provider HTTP requests.
|
||
|
||
- `request.headers`: extra headers (merged with provider defaults). Values accept SecretRef.
|
||
- `request.auth`: auth strategy override. Modes: `"provider-default"` (use provider's built-in auth), `"authorization-bearer"` (with `token`), `"header"` (with `headerName`, `value`, optional `prefix`).
|
||
- `request.proxy`: HTTP proxy override. Modes: `"env-proxy"` (use `HTTP_PROXY`/`HTTPS_PROXY` env vars), `"explicit-proxy"` (with `url`). Both modes accept an optional `tls` sub-object.
|
||
- `request.tls`: TLS override for direct connections. Fields: `ca`, `cert`, `key`, `passphrase` (all accept SecretRef), `serverName`, `insecureSkipVerify`.
|
||
- `request.allowPrivateNetwork`: when `true`, allow model-provider HTTP requests to private, CGNAT, or similar ranges through the provider HTTP fetch guard. Custom/local provider base URLs already trust the exact configured origin, except metadata/link-local origins, which remain blocked without explicit opt-in. Set this to `false` to opt out of exact-origin trust. WebSocket uses the same `request` for headers/TLS but not that fetch SSRF gate. Default `false`.
|
||
|
||
</Accordion>
|
||
<Accordion title="Model catalog entries">
|
||
- `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.
|
||
- `models.providers.*.models.*.compat.requiresStringContent`: optional compatibility hint for string-only OpenAI-compatible chat endpoints. When `true`, OpenClaw flattens pure text `messages[].content` arrays into plain strings before sending the request.
|
||
- `models.providers.*.models.*.compat.strictMessageKeys`: optional compatibility hint for strict OpenAI-compatible chat endpoints. When `true`, OpenClaw strips outgoing Chat Completions message objects to `role` and `content` before sending the request.
|
||
- `models.providers.*.models.*.compat.thinkingFormat`: optional thinking payload hint. Use `"together"` for Together-style `reasoning.enabled`, `"qwen"` for top-level `enable_thinking`, or `"qwen-chat-template"` for `chat_template_kwargs.enable_thinking` on Qwen-family OpenAI-compatible servers that support request-level chat-template kwargs, such as vLLM. Configured vLLM Qwen models expose binary `/think` choices (`off`, `on`) for these formats.
|
||
- `models.providers.*.models.*.compat.requiresReasoningContentOnAssistantMessages`: optional compatibility hint for DeepSeek-style Chat Completions backends that require prior assistant messages to keep `reasoning_content` on replay. When `true`, OpenClaw preserves that field on outgoing assistant messages. Use this when wiring a custom DeepSeek-compatible proxy that rejects requests after stripped reasoning. Default `false`.
|
||
|
||
</Accordion>
|
||
<Accordion title="Amazon Bedrock discovery">
|
||
- `plugins.entries.amazon-bedrock.config.discovery`: Bedrock auto-discovery settings root.
|
||
- `plugins.entries.amazon-bedrock.config.discovery.enabled`: turn implicit discovery on/off.
|
||
- `plugins.entries.amazon-bedrock.config.discovery.region`: AWS region for discovery.
|
||
- `plugins.entries.amazon-bedrock.config.discovery.providerFilter`: optional provider-id filter for targeted discovery.
|
||
- `plugins.entries.amazon-bedrock.config.discovery.refreshInterval`: polling interval for discovery refresh.
|
||
- `plugins.entries.amazon-bedrock.config.discovery.defaultContextWindow`: fallback context window for discovered models.
|
||
- `plugins.entries.amazon-bedrock.config.discovery.defaultMaxTokens`: fallback max output tokens for discovered models.
|
||
|
||
</Accordion>
|
||
</AccordionGroup>
|
||
|
||
Interactive custom-provider onboarding infers image input for known vision-model-id patterns, including GPT-4o/GPT-4.1/GPT-5+, the `o1`/`o3`/`o4` reasoning families, Claude, Gemini, any `-vl`-suffixed id (Qwen-VL and similar), and named families such as LLaVA, Pixtral, InternVL, Mllama, MiniCPM-V, and GLM-4V; it skips the extra question for known text-only families (Llama, DeepSeek, Mistral/Mixtral, Kimi/Moonshot, Codestral, Devstral, Phi, QwQ, CodeLlama, and bare Qwen ids without a vl/vision suffix). 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
|
||
|
||
<AccordionGroup>
|
||
<Accordion title="Cerebras (GLM 4.7 / GPT OSS)">
|
||
The official external `cerebras` provider plugin can configure this via `openclaw onboard --auth-choice cerebras-api-key`. Use explicit provider config only when overriding defaults.
|
||
|
||
```json5
|
||
{
|
||
env: { CEREBRAS_API_KEY: "sk-..." },
|
||
agents: {
|
||
defaults: {
|
||
model: {
|
||
primary: "cerebras/zai-glm-4.7",
|
||
fallbacks: ["cerebras/gpt-oss-120b"],
|
||
},
|
||
models: {
|
||
"cerebras/zai-glm-4.7": { alias: "GLM 4.7 (Cerebras)" },
|
||
"cerebras/gpt-oss-120b": { alias: "GPT OSS 120B (Cerebras)" },
|
||
},
|
||
},
|
||
},
|
||
models: {
|
||
mode: "merge",
|
||
providers: {
|
||
cerebras: {
|
||
baseUrl: "https://api.cerebras.ai/v1",
|
||
apiKey: "${CEREBRAS_API_KEY}",
|
||
api: "openai-completions",
|
||
models: [
|
||
{ id: "zai-glm-4.7", name: "GLM 4.7 (Cerebras)" },
|
||
{ id: "gpt-oss-120b", name: "GPT OSS 120B (Cerebras)" },
|
||
],
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
Use `cerebras/zai-glm-4.7` for Cerebras; `zai/glm-4.7` for Z.AI direct.
|
||
|
||
</Accordion>
|
||
<Accordion title="Kimi Coding">
|
||
```json5
|
||
{
|
||
env: { KIMI_API_KEY: "sk-..." },
|
||
agents: {
|
||
defaults: {
|
||
model: { primary: "kimi/kimi-for-coding" },
|
||
models: { "kimi/kimi-for-coding": { alias: "Kimi Code" } },
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
Anthropic-compatible, built-in provider. Shortcut: `openclaw onboard --auth-choice kimi-code-api-key`.
|
||
|
||
</Accordion>
|
||
<Accordion title="Local models (LM Studio)">
|
||
See [Local Models](/gateway/local-models). TL;DR: run a large local model via LM Studio Responses API on serious hardware; keep hosted models merged for fallback.
|
||
</Accordion>
|
||
<Accordion title="MiniMax M3 (direct)">
|
||
```json5
|
||
{
|
||
agents: {
|
||
defaults: {
|
||
model: { primary: "minimax/MiniMax-M3" },
|
||
models: {
|
||
"minimax/MiniMax-M3": { alias: "Minimax" },
|
||
},
|
||
},
|
||
},
|
||
models: {
|
||
mode: "merge",
|
||
providers: {
|
||
minimax: {
|
||
baseUrl: "https://api.minimax.io/anthropic",
|
||
apiKey: "${MINIMAX_API_KEY}",
|
||
api: "anthropic-messages",
|
||
models: [
|
||
{
|
||
id: "MiniMax-M3",
|
||
name: "MiniMax M3",
|
||
reasoning: true,
|
||
input: ["text", "image"],
|
||
cost: { input: 0.6, output: 2.4, cacheRead: 0.12, cacheWrite: 0 },
|
||
contextWindow: 1000000,
|
||
maxTokens: 131072,
|
||
},
|
||
],
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
Set `MINIMAX_API_KEY`. Shortcuts: `openclaw onboard --auth-choice minimax-global-api` or `openclaw onboard --auth-choice minimax-cn-api`. The model catalog defaults to M3 and also includes the M2.7 variants. On the Anthropic-compatible streaming path, OpenClaw disables MiniMax M2.x thinking by default unless you explicitly set `thinking` yourself; MiniMax-M3 (and M3.x) stays on the provider's omitted/adaptive thinking path by default. `/fast on` or `params.fastMode: true` rewrites `MiniMax-M2.7` to `MiniMax-M2.7-highspeed`.
|
||
|
||
</Accordion>
|
||
<Accordion title="Moonshot AI (Kimi)">
|
||
```json5
|
||
{
|
||
env: { MOONSHOT_API_KEY: "sk-..." },
|
||
agents: {
|
||
defaults: {
|
||
model: { primary: "moonshot/kimi-k2.6" },
|
||
models: { "moonshot/kimi-k2.6": { alias: "Kimi K2.6" } },
|
||
},
|
||
},
|
||
models: {
|
||
mode: "merge",
|
||
providers: {
|
||
moonshot: {
|
||
baseUrl: "https://api.moonshot.ai/v1",
|
||
apiKey: "${MOONSHOT_API_KEY}",
|
||
api: "openai-completions",
|
||
models: [
|
||
{
|
||
id: "kimi-k2.6",
|
||
name: "Kimi K2.6",
|
||
reasoning: false,
|
||
input: ["text", "image"],
|
||
cost: { input: 0.95, output: 4, cacheRead: 0.16, cacheWrite: 0 },
|
||
contextWindow: 262144,
|
||
maxTokens: 262144,
|
||
},
|
||
],
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
For the China endpoint: `baseUrl: "https://api.moonshot.cn/v1"` or `openclaw onboard --auth-choice moonshot-api-key-cn`.
|
||
|
||
Native Moonshot endpoints advertise streaming usage compatibility on the shared `openai-completions` transport, and OpenClaw keys that off endpoint capabilities rather than the built-in provider id alone.
|
||
|
||
</Accordion>
|
||
<Accordion title="OpenCode">
|
||
```json5
|
||
{
|
||
agents: {
|
||
defaults: {
|
||
model: { primary: "opencode/claude-opus-4-6" },
|
||
models: { "opencode/claude-opus-4-6": { alias: "Opus" } },
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
Set `OPENCODE_API_KEY` (or `OPENCODE_ZEN_API_KEY`). Use `opencode/...` refs for the Zen catalog or `opencode-go/...` refs for the Go catalog. Shortcut: `openclaw onboard --auth-choice opencode-zen` or `openclaw onboard --auth-choice opencode-go`.
|
||
|
||
</Accordion>
|
||
<Accordion title="Synthetic (Anthropic-compatible)">
|
||
```json5
|
||
{
|
||
env: { SYNTHETIC_API_KEY: "sk-..." },
|
||
agents: {
|
||
defaults: {
|
||
model: { primary: "synthetic/hf:MiniMaxAI/MiniMax-M2.5" },
|
||
models: { "synthetic/hf:MiniMaxAI/MiniMax-M2.5": { alias: "MiniMax M2.5" } },
|
||
},
|
||
},
|
||
models: {
|
||
mode: "merge",
|
||
providers: {
|
||
synthetic: {
|
||
baseUrl: "https://api.synthetic.new/anthropic",
|
||
apiKey: "${SYNTHETIC_API_KEY}",
|
||
api: "anthropic-messages",
|
||
models: [
|
||
{
|
||
id: "hf:MiniMaxAI/MiniMax-M2.5",
|
||
name: "MiniMax M2.5",
|
||
reasoning: true,
|
||
input: ["text"],
|
||
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
||
contextWindow: 192000,
|
||
maxTokens: 65536,
|
||
},
|
||
],
|
||
},
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
Base URL should omit `/v1` (Anthropic client appends it). Shortcut: `openclaw onboard --auth-choice synthetic-api-key`.
|
||
|
||
</Accordion>
|
||
<Accordion title="Z.AI (GLM-4.7)">
|
||
```json5
|
||
{
|
||
agents: {
|
||
defaults: {
|
||
model: { primary: "zai/glm-4.7" },
|
||
models: { "zai/glm-4.7": {} },
|
||
},
|
||
},
|
||
}
|
||
```
|
||
|
||
Set `ZAI_API_KEY`. Model refs use the canonical `zai/*` provider ID. Shortcut: `openclaw onboard --auth-choice zai-api-key`.
|
||
|
||
- General endpoint: `https://api.z.ai/api/paas/v4`
|
||
- Coding endpoint: `https://api.z.ai/api/coding/paas/v4`
|
||
- The default `zai-api-key` auth choice probes your key and auto-detects which endpoint it belongs to (falling back to a prompt, defaulting to Global, if detection is inconclusive). Dedicated CN and Coding-Plan auth choices are also available for explicit selection.
|
||
- For the general endpoint, define a custom provider with the base URL override.
|
||
|
||
</Accordion>
|
||
</AccordionGroup>
|
||
|
||
---
|
||
|
||
## Related
|
||
|
||
- [Configuration — agents](/gateway/config-agents)
|
||
- [Configuration — channels](/gateway/config-channels)
|
||
- [Configuration reference](/gateway/configuration-reference) — other top-level keys
|
||
- [Tools and plugins](/tools)
|