Skip to main content
The gateway now ships in the praisonai-bot package. praisonai serve gateway still works exactly as documented here; for a standalone install see praisonai-bot Migration.
from praisonaiagents import Agent

agent = Agent(name="assistant", instructions="Be helpful.")
# Reliability presets configure retries and timeouts around agent.start
agent.start("Retry this if the network blips")
reliability is a single posture switch on BotOS, gateway YAML, or the CLI that maps a profile name onto drain window, concurrency ceiling, and admission queue — without touching individual settings. The user deploys with a reliability preset; retries, timeouts, and drain behaviour apply automatically.

​
Quick Start

1

Python — pass reliability= to BotOS

from praisonaiagents import Agent
from praisonai.bots import BotOS

agent = Agent(name="assistant", instructions="Help the user.")
bot = BotOS(agent=agent, platforms=["telegram", "discord"], reliability="production")
bot.start()
2

YAML — set reliability: at the top level

# gateway.yaml
reliability: production

agents:
  assistant:
    instructions: "Help the user."

channels:
  telegram:
    token: "${TELEGRAM_TOKEN}"
Run with:
praisonai gateway start --config gateway.yaml
3

CLI flag — override any YAML value

praisonai gateway start --config gateway.yaml --reliability production
The CLI flag takes the highest precedence and overrides whatever is in the YAML file.
4

Override individual settings after the preset

Explicit kwargs on BotOS always win over the preset:
from praisonaiagents import Agent
from praisonai.bots import BotOS

agent = Agent(name="assistant", instructions="Help the user.")

bot = BotOS(
    agent=agent,
    platforms=["telegram"],
    reliability="production",
    drain_timeout=30.0,   # overrides the preset's 15 s
)
bot.start()

​
Profiles

Three built-in profiles cover the most common deployment scenarios.
ProfileDrain windowAdmission ceilingOverflow behaviour
production15 sCPU-scaled max_concurrent_runsBounded fair-wait queue (overflow=queue)
default / None (unset)5 snonepass-through
off0 s (immediate teardown)nonetoday’s no-backpressure behaviour

​
How It Works

The resolver _reliability.py converts the profile string into concrete values for drain_timeout, max_concurrent_runs, and admission_policy. Those values are passed directly to the underlying WebSocketGateway build step. Precedence (highest → lowest):
  1. Explicit kwargs on BotOS.__init__ — e.g. drain_timeout=30
  2. reliability= preset — e.g. "production"
  3. SDK defaults

​
Configuration Surfaces

​
Python

from praisonai.bots import BotOS

# Minimal
bot = BotOS(agent=agent, platforms=["telegram"], reliability="production")

# From a YAML config file (reads top-level `reliability:` or `gateway.reliability`)
bot = BotOS.from_config("gateway.yaml")

​
YAML

Both placements are accepted: 
# Top-level
reliability: production

# Or nested under gateway:
gateway:
  reliability: production
  max_concurrent_runs: 8   # explicit override still respected

​
CLI

praisonai gateway start --config gateway.yaml --reliability production
praisonai gateway start --config gateway.yaml --reliability off
praisonai gateway start --config gateway.yaml --reliability default

​
Common Patterns

​
Production deployment

from praisonaiagents import Agent
from praisonai.bots import BotOS

agent = Agent(name="support", instructions="Answer customer questions.")
bot = BotOS(
    agent=agent,
    platforms=["telegram", "discord", "slack"],
    reliability="production",
)
bot.start()

​
Extend the drain window for slow agents

bot = BotOS(
    agent=agent,
    platforms=["telegram"],
    reliability="production",
    drain_timeout=45.0,   # 45s instead of preset 15s
)

​
Disable all backpressure for development

reliability: off

​
Best Practices

production composes drain + admission control together. Enabling them separately is error-prone — the preset guarantees a coherent configuration.
Explicit YAML keys like gateway.drain_timeout override the preset. That is correct behaviour when you need to tune a single value, but it can surprise you if you forget the preset was set.
An unrecognised profile (e.g. reliability: "fast") raises at startup, not at first request. This fail-fast behaviour is intentional — silent fallback to default would hide misconfiguration.
Deploying a new preset to a single pod via the CLI flag lets you validate behaviour before updating the shared gateway.yaml.

Gateway Overview

Bot gateway architecture and core concepts

Gateway Graceful Drain

In-flight turn drain on shutdown or reload

Gateway Admission Control

Cap concurrent runs and queue overflow requests

Gateway Flow Control

Back-pressure and send-policy options