Files
File Viewer
Agentic Loop
Network
  Click a file in the tree to view its contents.

  Or try a preset prompt below to watch the agentic loop in action.
Network Log
0 requests
# Method URL Status Size Time
Where's My Context?
1x
Model Settings
Reasoning Effort what do these settings do?

Reasoning effort controls how many thinking tokens the model spends before producing its final answer. Higher effort improves accuracy on hard problems at the cost of latency and token spend. Thinking tokens are billed but do not appear in the context bar above — budget for them separately.

Level Anthropic effort OpenAI reasoning.effort
Off none — no thinking tokens
Low low — ~1k think tokens low
Medium medium medium (default for o-series)
High high high
Max max — up to 32k think tokens xhigh — Extreme Thinking mode

Anthropic deprecated the explicit budget_tokens parameter in Claude 4.x in favour of this effort enum. The underlying mechanism is the same: the model generates a scratchpad of chain-of-thought tokens that are not returned to the caller but influence the final answer.

Full context window (estimated) 0 / 200,000 tokens (0%)
Used tokens breakdown
System Prompt
AGENTS.md
Skills
Tool Definitions
Tool Results
Your Prompt
Model Response
Token counts are estimated (~4 chars per token). Actual counts vary by model tokenizer.

How AI Assistants Work

  1. Assemble context — system prompt + AGENTS.md, any invoked /tools, tool schemas
  2. Read your prompt — added to the context window
  3. Call the model — sends everything to the LLM
  4. Execute tools — model requests file reads, grep, edits
  5. Loop — tool results go back to the model for the next turn
  6. Respond — final answer with all context consumed
Ready — mock repo loaded
Simulation mode