Escalation Pipeline

The escalation pipeline adjusts execution complexity from simple answers to full autonomous loops — all via Agent(autonomy=True).

from praisonaiagents import Agent

agent = Agent(
    instructions="You are a helpful coding assistant.",
    llm="gpt-4o-mini",
    autonomy=True,
)

stage = agent.get_recommended_stage("Refactor the auth module")
print(stage)  # "autonomous"

response = agent.start("What is Python?")
print(response)

The user sends a prompt; the agent escalates from direct answers to heuristic, planned, or autonomous execution based on task signals.

How It Works

Escalation Stages

Quick Start

Enable autonomy

from praisonaiagents import Agent

agent = Agent(
    instructions="You are a helpful coding assistant.",
    llm="gpt-4o-mini",
    autonomy=True,
)

# Fast heuristics — no LLM call
stage = agent.get_recommended_stage("What is Python?")
signals = agent.analyze_prompt("Refactor the auth module")

print(stage)    # direct
print(signals)  # {'refactor_intent', 'complex_keywords'}

response = agent.start("What is Python?")
print(response)

Custom configuration

from praisonaiagents import Agent, AutonomyConfig

agent = Agent(
    instructions="You are a coding assistant.",
    autonomy=AutonomyConfig(
        max_iterations=30,
        doom_loop_threshold=5,
        auto_escalate=True,
    ),
)

print(agent.autonomy_enabled)
print(agent.autonomy_config)

Stages and Signals

Stage	Name	Typical trigger
0	DIRECT	Simple questions (`simple_question`)
1	HEURISTIC	File paths, code blocks
2	PLANNED	Edit, test, or build intent
3	AUTONOMOUS	Multi-step refactor, complex keywords

from praisonaiagents import Agent

agent = Agent(instructions="Assistant", autonomy=True)

agent.get_recommended_stage("What is Python?")           # direct
agent.get_recommended_stage("Read src/main.py")          # heuristic
agent.get_recommended_stage("Fix the bug in auth.py")    # planned
agent.get_recommended_stage("Refactor auth and add tests") # autonomous

Signal	Trigger examples
`simple_question`	”what is”, “define”, “explain”
`file_references`	Paths like `src/main.py`
`edit_intent`	”edit”, “modify”, “fix”
`refactor_intent`	”refactor”, “restructure”
`complex_keywords`	”analyse”, “optimise”, “refactor”

CLI

# Simple question — DIRECT stage
praisonai "What is Python?"

# Complex task — escalates to AUTONOMOUS
praisonai "Refactor the auth module and add tests"

praisonai chat --autonomy

Pipeline Components

Under praisonaiagents/escalation/:

Doom loop detector — identical calls and no-progress patterns
Loop guard — idempotency-aware tool-call guardrails on every Agent. See Loop Guard.
Pipeline orchestration — escalation triggers and recovery
Observability hooks — metrics for escalation events

Best Practices

Enable with autonomy=True

Pass autonomy=True or an AutonomyConfig — the agent selects the stage automatically during execution.

Inspect signals before heavy runs

Call analyze_prompt() to preview complexity without an LLM call when building UIs or routing logic.

Override a false-positive doom-loop stop

A detected doom loop is now a recoverable approval decision, not a hardcoded block. The default still stops (backward-compatible), but a legitimate repeat — e.g. polling a build-status endpoint — can continue with doom_loop=allow:

permissions:
  doom_loop: allow

from praisonaiagents import Agent
from praisonaiagents.permissions import PermissionManager

agent = Agent(
    instructions="Poll the build until it finishes.",
    permission_manager=PermissionManager(rules={"doom_loop": "allow"}),
)

The gate is fail-closed: deny, timeout, no backend, or any error falls back to the historical hard-stop. See Approval.

Stay agent-centric

No standalone pipeline objects — escalation, loop guard, and doom-loop detection live on Agent.

Doom Loop Detection

Pattern-based detection of stuck agent loops

Subagent Delegation

Delegate subtasks when autonomy escalates

Getting Started

Install

Core Concepts

Guides

Features

Models

Databases

Observability

Memory

Telemetry & Analytics

Knowledge

RAG

Persistence

Tools

Other Features

Developers

Configuration

Best Practices

Getting Started (No Code)

Escalation Pipeline

How It Works

Escalation Stages

Quick Start

Stages and Signals

CLI

Pipeline Components

Best Practices

Doom Loop Detection

Subagent Delegation

​How It Works

​Escalation Stages

​Quick Start

​Stages and Signals

​CLI

​Pipeline Components

​Best Practices

​Related

Doom Loop Detection

Subagent Delegation

How It Works

Escalation Stages

Quick Start

Stages and Signals

CLI

Pipeline Components

Best Practices

Related