mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-06 04:40:43 +00:00
docs: typography hygiene + 2 in-body H1 removals across 6 pages
Replaced 60 typography characters (curly quotes, apostrophes, em/en dashes, non-breaking hyphens) with ASCII equivalents per docs/CLAUDE.md heading and content hygiene rules. - docs/start/openclaw.md: 10 chars; removed the duplicate '# Building a personal assistant with OpenClaw' H1 (Mintlify renders title from frontmatter). - docs/platforms/mac/remote.md: 10 chars; removed the duplicate '# Remote OpenClaw (macOS ⇄ remote host)' H1 (the U+21C4 codepoint and parens both produced brittle anchors). - docs/tools/thinking.md: 10 chars - docs/reference/templates/BOOTSTRAP.md: 10 chars (kept the in-body '# BOOTSTRAP.md - Hello, World' heading because the page is a template whose content is meant to be copied verbatim into a workspace BOOTSTRAP.md). - docs/plugins/sdk-provider-plugins.md: 10 chars - docs/platforms/macos.md: 10 chars
This commit is contained in:
Vincent Koc
@@ -5,9 +5,7 @@ read_when:
|
||||
title: "Remote control"
|
||||
---
|
||||
|
||||
# Remote OpenClaw (macOS ⇄ remote host)
|
||||
|
||||
This flow lets the macOS app act as a full remote control for an OpenClaw gateway running on another host (desktop/server). It’s the app’s **Remote over SSH** (remote run) feature. All features—health checks, Voice Wake forwarding, and Web Chat—reuse the same remote SSH configuration from _Settings → General_.
|
||||
This flow lets the macOS app act as a full remote control for an OpenClaw gateway running on another host (desktop/server). It's the app's **Remote over SSH** (remote run) feature. All features-health checks, Voice Wake forwarding, and Web Chat-reuse the same remote SSH configuration from _Settings → General_.
|
||||
|
||||
## Modes
|
||||
|
||||
@@ -19,7 +17,7 @@ This flow lets the macOS app act as a full remote control for an OpenClaw gatewa
|
||||
|
||||
Remote mode supports two transports:
|
||||
|
||||
- **SSH tunnel** (default): Uses `ssh -N -L ...` to forward the gateway port to localhost. The gateway will see the node’s IP as `127.0.0.1` because the tunnel is loopback.
|
||||
- **SSH tunnel** (default): Uses `ssh -N -L ...` to forward the gateway port to localhost. The gateway will see the node's IP as `127.0.0.1` because the tunnel is loopback.
|
||||
- **Direct (ws/wss)**: Connects straight to the gateway URL. The gateway sees the real client IP.
|
||||
|
||||
In SSH tunnel mode, discovered LAN/tailnet hostnames are saved as
|
||||
@@ -51,7 +49,7 @@ node.
|
||||
- **Identity file** (advanced): path to your key.
|
||||
- **Project root** (advanced): remote checkout path used for commands.
|
||||
- **CLI path** (advanced): optional path to a runnable `openclaw` entrypoint/binary (auto-filled when advertised).
|
||||
3. Hit **Test remote**. Success indicates the remote `openclaw status --json` runs correctly. Failures usually mean PATH/CLI issues; exit 127 means the CLI isn’t found remotely.
|
||||
3. Hit **Test remote**. Success indicates the remote `openclaw status --json` runs correctly. Failures usually mean PATH/CLI issues; exit 127 means the CLI isn't found remotely.
|
||||
4. Health checks and Web Chat will now run through this SSH tunnel automatically.
|
||||
|
||||
## Web Chat
|
||||
@@ -63,7 +61,7 @@ node.
|
||||
## Permissions
|
||||
|
||||
- The remote host needs the same TCC approvals as local (Automation, Accessibility, Screen Recording, Microphone, Speech Recognition, Notifications). Run onboarding on that machine to grant them once.
|
||||
- Nodes advertise their permission state via `node.list` / `node.describe` so agents know what’s available.
|
||||
- Nodes advertise their permission state via `node.list` / `node.describe` so agents know what's available.
|
||||
|
||||
## Security notes
|
||||
|
||||
@@ -79,7 +77,7 @@ node.
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
- **exit 127 / not found**: `openclaw` isn’t on PATH for non-login shells. Add it to `/etc/paths`, your shell rc, or symlink into `/usr/local/bin`/`/opt/homebrew/bin`.
|
||||
- **exit 127 / not found**: `openclaw` isn't on PATH for non-login shells. Add it to `/etc/paths`, your shell rc, or symlink into `/usr/local/bin`/`/opt/homebrew/bin`.
|
||||
- **Health probe failed**: check SSH reachability, PATH, and that Baileys is logged in (`openclaw status --json`).
|
||||
- **Web Chat stuck**: confirm the gateway is running on the remote host and the forwarded port matches the gateway WS port; the UI requires a healthy WS connection.
|
||||
- **Node IP shows 127.0.0.1**: expected with the SSH tunnel. Switch **Transport** to **Direct (ws/wss)** if you want the gateway to see the real client IP.
|
||||
@@ -94,7 +92,7 @@ Pick sounds per notification from scripts with `openclaw` and `node.invoke`, e.g
|
||||
openclaw nodes notify --node <id> --title "Ping" --body "Remote gateway ready" --sound Glass
|
||||
```
|
||||
|
||||
There is no global “default sound” toggle in the app anymore; callers choose a sound (or none) per request.
|
||||
There is no global "default sound" toggle in the app anymore; callers choose a sound (or none) per request.
|
||||
|
||||
## Related
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ read_when:
|
||||
title: "macOS app"
|
||||
---
|
||||
|
||||
The macOS app is the **menu‑bar companion** for OpenClaw. It owns permissions,
|
||||
The macOS app is the **menu-bar companion** for OpenClaw. It owns permissions,
|
||||
manages/attaches to the Gateway locally (launchd or manual), and exposes macOS
|
||||
capabilities to the agent as a node.
|
||||
|
||||
@@ -16,7 +16,7 @@ capabilities to the agent as a node.
|
||||
- Owns TCC prompts (Notifications, Accessibility, Screen Recording, Microphone,
|
||||
Speech Recognition, Automation/AppleScript).
|
||||
- Runs or connects to the Gateway (local or remote).
|
||||
- Exposes macOS‑only tools (Canvas, Camera, Screen Recording, `system.run`).
|
||||
- Exposes macOS-only tools (Canvas, Camera, Screen Recording, `system.run`).
|
||||
- Starts the local node host service in **remote** mode (launchd), and stops it in **local** mode.
|
||||
- Optionally hosts **PeekabooBridge** for UI automation.
|
||||
- Installs the global CLI (`openclaw`) on request via npm, pnpm, or bun (the app prefers npm, then pnpm, then bun; Node remains the recommended Gateway runtime).
|
||||
@@ -34,7 +34,7 @@ capabilities to the agent as a node.
|
||||
|
||||
## Launchd control
|
||||
|
||||
The app manages a per‑user LaunchAgent labeled `ai.openclaw.gateway`
|
||||
The app manages a per-user LaunchAgent labeled `ai.openclaw.gateway`
|
||||
(or `ai.openclaw.<profile>` when using `--profile`/`OPENCLAW_PROFILE`; legacy `com.openclaw.*` still unloads).
|
||||
|
||||
```bash
|
||||
@@ -44,7 +44,7 @@ launchctl bootout gui/$UID/ai.openclaw.gateway
|
||||
|
||||
Replace the label with `ai.openclaw.<profile>` when running a named profile.
|
||||
|
||||
If the LaunchAgent isn’t installed, enable it from the app or run
|
||||
If the LaunchAgent isn't installed, enable it from the app or run
|
||||
`openclaw gateway install`.
|
||||
|
||||
## Node capabilities (mac)
|
||||
@@ -56,7 +56,7 @@ The macOS app presents itself as a node. Common commands:
|
||||
- Screen: `screen.snapshot`, `screen.record`
|
||||
- System: `system.run`, `system.notify`
|
||||
|
||||
The node reports a `permissions` map so agents can decide what’s allowed.
|
||||
The node reports a `permissions` map so agents can decide what's allowed.
|
||||
|
||||
Node service + app IPC:
|
||||
|
||||
@@ -104,8 +104,8 @@ Notes:
|
||||
|
||||
- `allowlist` entries are glob patterns for resolved binary paths, or bare command names for PATH-invoked commands.
|
||||
- Raw shell command text that contains shell control or expansion syntax (`&&`, `||`, `;`, `|`, `` ` ``, `$`, `<`, `>`, `(`, `)`) is treated as an allowlist miss and requires explicit approval (or allowlisting the shell binary).
|
||||
- Choosing “Always Allow” in the prompt adds that command to the allowlist.
|
||||
- `system.run` environment overrides are filtered (drops `PATH`, `DYLD_*`, `LD_*`, `NODE_OPTIONS`, `PYTHON*`, `PERL*`, `RUBYOPT`, `SHELLOPTS`, `PS4`) and then merged with the app’s environment.
|
||||
- Choosing "Always Allow" in the prompt adds that command to the allowlist.
|
||||
- `system.run` environment overrides are filtered (drops `PATH`, `DYLD_*`, `LD_*`, `NODE_OPTIONS`, `PYTHON*`, `PERL*`, `RUBYOPT`, `SHELLOPTS`, `PS4`) and then merged with the app's environment.
|
||||
- For shell wrappers (`bash|sh|zsh ... -c/-lc`), request-scoped environment overrides are reduced to a small explicit allowlist (`TERM`, `LANG`, `LC_*`, `COLORTERM`, `NO_COLOR`, `FORCE_COLOR`).
|
||||
- For allow-always decisions in allowlist mode, known dispatch wrappers (`env`, `nice`, `nohup`, `stdbuf`, `timeout`) persist inner executable paths instead of wrapper paths. If unwrapping is not safe, no allowlist entry is persisted automatically.
|
||||
|
||||
@@ -189,7 +189,7 @@ Connect options:
|
||||
|
||||
Discovery options:
|
||||
|
||||
- `--include-local`: include gateways that would be filtered as “local”
|
||||
- `--include-local`: include gateways that would be filtered as "local"
|
||||
- `--timeout <ms>`: overall discovery window (default: `2000`)
|
||||
- `--json`: structured output for diffing
|
||||
|
||||
|
||||
@@ -287,7 +287,7 @@ API key auth, and dynamic model resolution.
|
||||
```
|
||||
|
||||
If resolving requires a network call, use `prepareDynamicModel` for async
|
||||
warm-up — `resolveDynamicModel` runs again after it completes.
|
||||
warm-up - `resolveDynamicModel` runs again after it completes.
|
||||
|
||||
</Step>
|
||||
|
||||
@@ -341,9 +341,9 @@ API key auth, and dynamic model resolution.
|
||||
<Accordion title="SDK seams powering the family builders">
|
||||
Each family builder is composed from lower-level public helpers exported from the same package, which you can reach for when a provider needs to go off the common pattern:
|
||||
|
||||
- `openclaw/plugin-sdk/provider-model-shared` — `ProviderReplayFamily`, `buildProviderReplayFamilyHooks(...)`, and the raw replay builders (`buildOpenAICompatibleReplayPolicy`, `buildAnthropicReplayPolicyForModel`, `buildGoogleGeminiReplayPolicy`, `buildHybridAnthropicOrOpenAIReplayPolicy`). Also exports Gemini replay helpers (`sanitizeGoogleGeminiReplayHistory`, `resolveTaggedReasoningOutputMode`) and endpoint/model helpers (`resolveProviderEndpoint`, `normalizeProviderId`, `normalizeGooglePreviewModelId`, `normalizeNativeXaiModelId`).
|
||||
- `openclaw/plugin-sdk/provider-stream` — `ProviderStreamFamily`, `buildProviderStreamFamilyHooks(...)`, `composeProviderStreamWrappers(...)`, plus the shared OpenAI/Codex wrappers (`createOpenAIAttributionHeadersWrapper`, `createOpenAIFastModeWrapper`, `createOpenAIServiceTierWrapper`, `createOpenAIResponsesContextManagementWrapper`, `createCodexNativeWebSearchWrapper`), DeepSeek V4 OpenAI-compatible wrapper (`createDeepSeekV4OpenAICompatibleThinkingWrapper`), Anthropic Messages thinking prefill cleanup (`createAnthropicThinkingPrefillPayloadWrapper`), and shared proxy/provider wrappers (`createOpenRouterWrapper`, `createToolStreamWrapper`, `createMinimaxFastModeWrapper`).
|
||||
- `openclaw/plugin-sdk/provider-tools` — `ProviderToolCompatFamily`, `buildProviderToolCompatFamilyHooks("gemini")`, underlying Gemini schema helpers (`normalizeGeminiToolSchemas`, `inspectGeminiToolSchemas`), and xAI compat helpers (`resolveXaiModelCompatPatch()`, `applyXaiModelCompat(model)`). The bundled xAI plugin uses `normalizeResolvedModel` + `contributeResolvedModelCompat` with these to keep xAI rules owned by the provider.
|
||||
- `openclaw/plugin-sdk/provider-model-shared` - `ProviderReplayFamily`, `buildProviderReplayFamilyHooks(...)`, and the raw replay builders (`buildOpenAICompatibleReplayPolicy`, `buildAnthropicReplayPolicyForModel`, `buildGoogleGeminiReplayPolicy`, `buildHybridAnthropicOrOpenAIReplayPolicy`). Also exports Gemini replay helpers (`sanitizeGoogleGeminiReplayHistory`, `resolveTaggedReasoningOutputMode`) and endpoint/model helpers (`resolveProviderEndpoint`, `normalizeProviderId`, `normalizeGooglePreviewModelId`, `normalizeNativeXaiModelId`).
|
||||
- `openclaw/plugin-sdk/provider-stream` - `ProviderStreamFamily`, `buildProviderStreamFamilyHooks(...)`, `composeProviderStreamWrappers(...)`, plus the shared OpenAI/Codex wrappers (`createOpenAIAttributionHeadersWrapper`, `createOpenAIFastModeWrapper`, `createOpenAIServiceTierWrapper`, `createOpenAIResponsesContextManagementWrapper`, `createCodexNativeWebSearchWrapper`), DeepSeek V4 OpenAI-compatible wrapper (`createDeepSeekV4OpenAICompatibleThinkingWrapper`), Anthropic Messages thinking prefill cleanup (`createAnthropicThinkingPrefillPayloadWrapper`), and shared proxy/provider wrappers (`createOpenRouterWrapper`, `createToolStreamWrapper`, `createMinimaxFastModeWrapper`).
|
||||
- `openclaw/plugin-sdk/provider-tools` - `ProviderToolCompatFamily`, `buildProviderToolCompatFamilyHooks("gemini")`, underlying Gemini schema helpers (`normalizeGeminiToolSchemas`, `inspectGeminiToolSchemas`), and xAI compat helpers (`resolveXaiModelCompatPatch()`, `applyXaiModelCompat(model)`). The bundled xAI plugin uses `normalizeResolvedModel` + `contributeResolvedModelCompat` with these to keep xAI rules owned by the provider.
|
||||
|
||||
Some stream helpers stay provider-local on purpose. `@openclaw/anthropic-provider` keeps `wrapAnthropicProviderStream`, `resolveAnthropicBetas`, `resolveAnthropicFastMode`, `resolveAnthropicServiceTier`, and the lower-level Anthropic wrapper builders in its own public `api.ts` / `contract-api.ts` seam because they encode Claude OAuth beta handling and `context1m` gating. The xAI plugin similarly keeps native xAI Responses shaping in its own `wrapStreamFn` (`/fast` aliases, default `tool_stream`, unsupported strict-tool cleanup, xAI-specific reasoning-payload removal).
|
||||
|
||||
@@ -488,7 +488,7 @@ API key auth, and dynamic model resolution.
|
||||
A provider plugin can register speech, realtime transcription, realtime
|
||||
voice, media understanding, image generation, video generation, web fetch,
|
||||
and web search alongside text inference. OpenClaw classifies this as a
|
||||
**hybrid-capability** plugin — the recommended pattern for company plugins
|
||||
**hybrid-capability** plugin - the recommended pattern for company plugins
|
||||
(one plugin per vendor). See
|
||||
[Internals: Capability Ownership](/plugins/architecture#capability-ownership-model).
|
||||
|
||||
@@ -536,7 +536,7 @@ API key auth, and dynamic model resolution.
|
||||
request-id suffixes.
|
||||
</Tab>
|
||||
<Tab title="Realtime transcription">
|
||||
Prefer `createRealtimeTranscriptionWebSocketSession(...)` — the shared
|
||||
Prefer `createRealtimeTranscriptionWebSocketSession(...)` - the shared
|
||||
helper handles proxy capture, reconnect backoff, close flushing, ready
|
||||
handshakes, audio queueing, and close-event diagnostics. Your plugin
|
||||
only maps upstream events.
|
||||
@@ -769,10 +769,10 @@ providers:
|
||||
|
||||
## Next steps
|
||||
|
||||
- [Channel Plugins](/plugins/sdk-channel-plugins) — if your plugin also provides a channel
|
||||
- [SDK Runtime](/plugins/sdk-runtime) — `api.runtime` helpers (TTS, search, subagent)
|
||||
- [SDK Overview](/plugins/sdk-overview) — full subpath import reference
|
||||
- [Plugin Internals](/plugins/architecture-internals#provider-runtime-hooks) — hook details and bundled examples
|
||||
- [Channel Plugins](/plugins/sdk-channel-plugins) - if your plugin also provides a channel
|
||||
- [SDK Runtime](/plugins/sdk-runtime) - `api.runtime` helpers (TTS, search, subagent)
|
||||
- [SDK Overview](/plugins/sdk-overview) - full subpath import reference
|
||||
- [Plugin Internals](/plugins/architecture-internals#provider-runtime-hooks) - hook details and bundled examples
|
||||
|
||||
## Related
|
||||
|
||||
|
||||
@@ -21,10 +21,10 @@ Start with something like:
|
||||
|
||||
Then figure out together:
|
||||
|
||||
1. **Your name** — What should they call you?
|
||||
2. **Your nature** — What kind of creature are you? (AI assistant is fine, but maybe you're something weirder)
|
||||
3. **Your vibe** — Formal? Casual? Snarky? Warm? What feels right?
|
||||
4. **Your emoji** — Everyone needs a signature.
|
||||
1. **Your name** - What should they call you?
|
||||
2. **Your nature** - What kind of creature are you? (AI assistant is fine, but maybe you're something weirder)
|
||||
3. **Your vibe** - Formal? Casual? Snarky? Warm? What feels right?
|
||||
4. **Your emoji** - Everyone needs a signature.
|
||||
|
||||
Offer suggestions if they're stuck. Have fun with it.
|
||||
|
||||
@@ -32,8 +32,8 @@ Offer suggestions if they're stuck. Have fun with it.
|
||||
|
||||
Update these files with what you learned:
|
||||
|
||||
- `IDENTITY.md` — your name, creature, vibe, emoji
|
||||
- `USER.md` — their name, how to address them, timezone, notes
|
||||
- `IDENTITY.md` - your name, creature, vibe, emoji
|
||||
- `USER.md` - their name, how to address them, timezone, notes
|
||||
|
||||
Then open `SOUL.md` together and talk about:
|
||||
|
||||
@@ -47,15 +47,15 @@ Write it down. Make it real.
|
||||
|
||||
Ask how they want to reach you:
|
||||
|
||||
- **Just here** — web chat only
|
||||
- **WhatsApp** — link their personal account (you'll show a QR code)
|
||||
- **Telegram** — set up a bot via BotFather
|
||||
- **Just here** - web chat only
|
||||
- **WhatsApp** - link their personal account (you'll show a QR code)
|
||||
- **Telegram** - set up a bot via BotFather
|
||||
|
||||
Guide them through whichever they pick.
|
||||
|
||||
## When you are done
|
||||
|
||||
Delete this file. You don't need a bootstrap script anymore — you're you now.
|
||||
Delete this file. You don't need a bootstrap script anymore - you're you now.
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -6,13 +6,11 @@ read_when:
|
||||
title: "Personal assistant setup"
|
||||
---
|
||||
|
||||
# Building a personal assistant with OpenClaw
|
||||
|
||||
OpenClaw is a self-hosted gateway that connects Discord, Google Chat, iMessage, Matrix, Microsoft Teams, Signal, Slack, Telegram, WhatsApp, Zalo, and more to AI agents. This guide covers the "personal assistant" setup: a dedicated WhatsApp number that behaves like your always-on AI assistant.
|
||||
|
||||
## ⚠️ Safety first
|
||||
|
||||
You’re putting an agent in a position to:
|
||||
You're putting an agent in a position to:
|
||||
|
||||
- run commands on your machine (depending on your tool policy)
|
||||
- read/write files in your workspace
|
||||
@@ -26,7 +24,7 @@ Start conservative:
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- OpenClaw installed and onboarded — see [Getting Started](/start/getting-started) if you haven't done this yet
|
||||
- OpenClaw installed and onboarded - see [Getting Started](/start/getting-started) if you haven't done this yet
|
||||
- A second phone number (SIM/eSIM/prepaid) for the assistant
|
||||
|
||||
## The two-phone setup (recommended)
|
||||
@@ -39,7 +37,7 @@ flowchart TB
|
||||
B -- linked via QR --> C["<b>Your Mac (openclaw)<br></b><br>AI agent"]
|
||||
```
|
||||
|
||||
If you link your personal WhatsApp to OpenClaw, every message to you becomes “agent input”. That’s rarely what you want.
|
||||
If you link your personal WhatsApp to OpenClaw, every message to you becomes "agent input". That's rarely what you want.
|
||||
|
||||
## 5-minute quick start
|
||||
|
||||
@@ -70,7 +68,7 @@ When onboarding finishes, OpenClaw auto-opens the dashboard and prints a clean (
|
||||
|
||||
## Give the agent a workspace (AGENTS)
|
||||
|
||||
OpenClaw reads operating instructions and “memory” from its workspace directory.
|
||||
OpenClaw reads operating instructions and "memory" from its workspace directory.
|
||||
|
||||
By default, OpenClaw uses `~/.openclaw/workspace` as the agent workspace, and will create it (plus starter `AGENTS.md`, `SOUL.md`, `TOOLS.md`, `IDENTITY.md`, `USER.md`, `HEARTBEAT.md`) automatically on setup/first agent run. `BOOTSTRAP.md` is only created when the workspace is brand new (it should not come back after you delete it). `MEMORY.md` is optional (not auto-created); when present, it is loaded for normal sessions. Subagent sessions only inject `AGENTS.md` and `TOOLS.md`.
|
||||
|
||||
@@ -111,7 +109,7 @@ If you already ship your own workspace files from a repo, you can disable bootst
|
||||
|
||||
## The config that turns it into "an assistant"
|
||||
|
||||
OpenClaw defaults to a good assistant setup, but you’ll usually want to tune:
|
||||
OpenClaw defaults to a good assistant setup, but you'll usually want to tune:
|
||||
|
||||
- persona/instructions in [`SOUL.md`](/concepts/soul)
|
||||
- thinking defaults (if desired)
|
||||
@@ -172,7 +170,7 @@ Set `agents.defaults.heartbeat.every: "0m"` to disable.
|
||||
- If the file is missing, the heartbeat still runs and the model decides what to do.
|
||||
- If the agent replies with `HEARTBEAT_OK` (optionally with short padding; see `agents.defaults.heartbeat.ackMaxChars`), OpenClaw suppresses outbound delivery for that heartbeat.
|
||||
- By default, heartbeat delivery to DM-style `user:<id>` targets is allowed. Set `agents.defaults.heartbeat.directPolicy: "block"` to suppress direct-target delivery while keeping heartbeat runs active.
|
||||
- Heartbeats run full agent turns — shorter intervals burn more tokens.
|
||||
- Heartbeats run full agent turns - shorter intervals burn more tokens.
|
||||
|
||||
```json5
|
||||
{
|
||||
@@ -193,7 +191,7 @@ Inbound attachments (images/audio/docs) can be surfaced to your command via temp
|
||||
Outbound attachments from the agent: include `MEDIA:<path-or-url>` on its own line (no spaces). Example:
|
||||
|
||||
```
|
||||
Here’s the screenshot.
|
||||
Here's the screenshot.
|
||||
MEDIA:https://example.com/screenshot.png
|
||||
```
|
||||
|
||||
|
||||
@@ -9,11 +9,11 @@ title: "Thinking levels"
|
||||
|
||||
- Inline directive in any inbound body: `/t <level>`, `/think:<level>`, or `/thinking <level>`.
|
||||
- Levels (aliases): `off | minimal | low | medium | high | xhigh | adaptive | max`
|
||||
- minimal → “think”
|
||||
- low → “think hard”
|
||||
- medium → “think harder”
|
||||
- high → “ultrathink” (max budget)
|
||||
- xhigh → “ultrathink+” (GPT-5.2+ and Codex models, plus Anthropic Claude Opus 4.7 effort)
|
||||
- minimal → "think"
|
||||
- low → "think hard"
|
||||
- medium → "think harder"
|
||||
- high → "ultrathink" (max budget)
|
||||
- xhigh → "ultrathink+" (GPT-5.2+ and Codex models, plus Anthropic Claude Opus 4.7 effort)
|
||||
- adaptive → provider-managed adaptive thinking (supported for Claude 4.6 on Anthropic/Bedrock, Anthropic Claude Opus 4.7, and Google Gemini dynamic thinking)
|
||||
- max → provider max reasoning (Anthropic Claude Opus 4.7; Ollama maps this to its highest native `think` effort)
|
||||
- `x-high`, `x_high`, `extra-high`, `extra high`, and `extra_high` map to `xhigh`.
|
||||
|
||||
Reference in New Issue
Block a user