Skip to main content

Thinking Levels (/think directives)

What it does​

  • Inline directive in any inbound body: /t <level>, /think:<level>, or /thinking <level>.
  • Levels (aliases): off | minimal | low | medium | high | xhigh | adaptive
    • minimal → “think”
    • low → “think hard”
    • medium → “think harder”
    • high → “ultrathink” (max budget)
    • xhigh → “ultrathink+” (GPT-5.2 + Codex models only)
    • adaptive → provider-managed adaptive reasoning budget (supported for Anthropic Claude 4.6 model family)
    • x-high, x_high, extra-high, extra high, and extra_high map to xhigh.
    • highest, max map to high.
  • Provider notes:
    • Anthropic Claude 4.6 models default to adaptive when no explicit thinking level is set.
    • Z.AI (zai/*) only supports binary thinking (on/off). Any non-off level is treated as on (mapped to low).
    • Moonshot (moonshot/*) maps /think off to thinking: { type: "disabled" } and any non-off level to thinking: { type: "enabled" }. When thinking is enabled, Moonshot only accepts tool_choice auto|none; OpenClaw normalizes incompatible values to auto.

Resolution order​

  1. Inline directive on the message (applies only to that message).
  2. Session override (set by sending a directive-only message).
  3. Global default (agents.defaults.thinkingDefault in config).
  4. Fallback: adaptive for Anthropic Claude 4.6 models, low for other reasoning-capable models, off otherwise.

Setting a session default​

  • Send a message that is only the directive (whitespace allowed), e.g. /think:medium or /t high.
  • That sticks for the current session (per-sender by default); cleared by /think:off or session idle reset.
  • Confirmation reply is sent (Thinking level set to high. / Thinking disabled.). If the level is invalid (e.g. /thinking big), the command is rejected with a hint and the session state is left unchanged.
  • Send /think (or /think:) with no argument to see the current thinking level.

Application by agent​

  • Embedded Pi: the resolved level is passed to the in-process Pi agent runtime.

Fast mode (/fast)​

  • Levels: on|off.
  • Directive-only message toggles a session fast-mode override and replies Fast mode enabled. / Fast mode disabled..
  • Send /fast (or /fast status) with no mode to see the current effective fast-mode state.
  • OpenClaw resolves fast mode in this order:
    1. Inline/directive-only /fast on|off
    2. Session override
    3. Per-model config: agents.defaults.models["<provider>/<model>"].params.fastMode
    4. Fallback: off
  • For openai/*, fast mode applies the OpenAI fast profile: service_tier=priority when supported, plus low reasoning effort and low text verbosity.
  • For openai-codex/*, fast mode applies the same low-latency profile on Codex Responses. OpenClaw keeps one shared /fast toggle across both auth paths.
  • For direct anthropic/* API-key requests, fast mode maps to Anthropic service tiers: /fast on sets service_tier=auto, /fast off sets service_tier=standard_only.
  • Anthropic fast mode is API-key only. OpenClaw skips Anthropic service-tier injection for Claude setup-token / OAuth auth and for non-Anthropic proxy base URLs.

Verbose directives (/verbose or /v)​

  • Levels: on (minimal) | full | off (default).
  • Directive-only message toggles session verbose and replies Verbose logging enabled. / Verbose logging disabled.; invalid levels return a hint without changing state.
  • /verbose off stores an explicit session override; clear it via the Sessions UI by choosing inherit.
  • Inline directive affects only that message; session/global defaults apply otherwise.
  • Send /verbose (or /verbose:) with no argument to see the current verbose level.
  • When verbose is on, agents that emit structured tool results (Pi, other JSON agents) send each tool call back as its own metadata-only message, prefixed with <emoji> ``<tool-name>``: <arg> when available (path/command). These tool summaries are sent as soon as each tool starts (separate bubbles), not as streaming deltas.
  • Tool failure summaries remain visible in normal mode, but raw error detail suffixes are hidden unless verbose is on or full.
  • When verbose is full, tool outputs are also forwarded after completion (separate bubble, truncated to a safe length). If you toggle /verbose on|full|off while a run is in-flight, subsequent tool bubbles honor the new setting.

Reasoning visibility (/reasoning)​

  • Levels: on|off|stream.
  • Directive-only message toggles whether thinking blocks are shown in replies.
  • When enabled, reasoning is sent as a separate message prefixed with Reasoning:.
  • stream (Telegram only): streams reasoning into the Telegram draft bubble while the reply is generating, then sends the final answer without reasoning.
  • Alias: /reason.
  • Send /reasoning (or /reasoning:) with no argument to see the current reasoning level.

Heartbeats​

  • Heartbeat probe body is the configured heartbeat prompt (default: Read HEARTBEAT.md if it exists (workspace context). Follow it strictly. Do not infer or repeat old tasks from prior chats. If nothing needs attention, reply HEARTBEAT_OK.). Inline directives in a heartbeat message apply as usual (but avoid changing session defaults from heartbeats).
  • Heartbeat delivery defaults to the final payload only. To also send the separate Reasoning: message (when available), set agents.defaults.heartbeat.includeReasoning: true or per-agent agents.list[].heartbeat.includeReasoning: true.

Web chat UI​

  • The web chat thinking selector mirrors the session's stored level from the inbound session store/config when the page loads.
  • Picking another level applies only to the next message (thinkingOnce); after sending, the selector snaps back to the stored session level.
  • To change the session default, send a /think:<level> directive (as before); the selector will reflect it after the next reload.