CEL Think
cel_thinkPerforms cognitive reasoning to analyze observations and plan subsequent actions, forming the thinking component of browser and native app automation.
Instructions
CEL's cognitive layer: delegated autonomy, planning, knowledge, run tracking, and LLM passthrough.
Efficiency rule: if the MCP host already reasons well step-by-step, prefer cel_see + cel_act and keep planning in the host. Use run_goal only when you intentionally want CEL to take over the control loop.
Delegated Autonomous Execution: run_goal — give a natural language goal, CEL runs a full internal see→plan→act loop autonomously. This can be convenient, but it adds an internal planner loop and may be slower or more expensive than host-driven execution. Only goal, max_steps (default 80), and timeout_ms (default 900_000) are tunable — vision, self-healing, decomposition, and notebook are implicit in the canonical loop and no longer per-invocation knobs (see docs/canonical-agent-plan.md).
Planning: plan (LLM-powered step planning with optional history for multi-step context), plan_with_vision (plan with screenshot — use for visual/spatial tasks).
Knowledge Store (persisted to ~/.cellar/cel-store.db): store_knowledge (save facts with source and optional tags), search_knowledge (FTS5 full-text search, default 10 results, scope by workflow).
Working Memory: memory_get, memory_set (per-workflow scratchpad, not persisted across sessions).
Observations: observe (record insight with priority high/medium/low), get_observations (retrieve, default 50).
Run Tracking: run_start, run_finish, run_log_step (per-step with confidence score), run_history, run_steps.
LLM Passthrough: llm_complete (text, 4096 tokens default), llm_complete_with_image (vision, 4096 tokens default).
Maintenance: eviction (TTL cleanup — default 90 days runs, 365 days knowledge).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||