{% extends "base.html" %} {% from 'partials/toggle.html' import toggle %} {% block content %}

⚙️ System Settings

Agent Timeout Retries
Number of automatic retries when the LLM times out mid-reasoning during chat. Set to 0 to disable auto-retry.
LLM Max Retries
Maximum retry attempts on transient LLM errors (timeout, 5xx). Uses exponential backoff (2s, 4s, 8s…). Set to 0 to disable.
Max Concurrent Turns per Agent
Maximum parallel queries per agent (from different sessions). 0 = unlimited.
Max Concurrent Turns per Model
Global default for all models (when a model's own limit is 0). 0 = unlimited.
Max Concurrent LLM (Global)
Hard cap on simultaneous LLM calls across all agents and models. 1 = serialised (default, safest for shared API keys). Increase only if your provider allows concurrent calls.
Agent Queue Workers
Number of worker threads processing agent messages. Increase takes effect immediately; decrease requires restart.
Public History
Allow unauthenticated users to view the history and detail pages (read-only).
{{ toggle(id='public-history-toggle', onchange='togglePublicHistory(this.checked)', extra_class='flex-shrink-0 ml-4') }}
Max Tool Iterations
Maximum number of tool-call iterations allowed per agent turn and per evaluation. Prevents infinite loops in multi-step reasoning. Range: 1–1000.
Task Classifier
Automatically classify tasks as trivial or complex. Trivial tasks skip planning and execute directly.
{{ toggle(id='task-classifier-toggle', onchange='saveTaskClassifier()', extra_class='flex-shrink-0 ml-4') }}
Default LLM Model
Select the global default model for all agents and evaluations.
Theme
Choose between light, dark, or system-preferred appearance.

LLM Models

Manage LLM models and per-agent model assignments

Loading models...

{% include 'partials/logs_tab.html' %}
{% include 'partials/hmads.html' %}