Workflow YAML Framework Field

How the framework: key in YAML chooses an execution backend

The framework: key in YAML picks which execution backend runs your agents — but the rules differ between agents.yaml and workflow YAML.

from praisonaiagents import Agent, PraisonAIAgents

agent = Agent(name="Writer", instructions="Write helpful posts")
PraisonAIAgents(agents=[agent]).start("Write about caching")

The user picks a YAML file; framework: selects the backend that runs the workflow.

Quick Start

1. agents.yaml — any registered framework

   framework: crewai
   topic: Write a blog post
   roles:
     writer:
       role: Writer
       goal: Write engaging posts
       backstory: Senior editor
       tasks:
         draft:
           description: Write a post about {topic}
           expected_output: A 500-word post

   praisonai agents.yaml

2. workflow YAML — needs SUPPORTS_WORKFLOW

   framework: praisonai
   type: job
   steps:
     - id: research
       agent: researcher
     - id: write
       agent: writer
       depends_on: [research]

   praisonai workflow.yaml

Which file uses which?

Workflow YAML dispatch requires an adapter whose SUPPORTS_WORKFLOW = True. The built-in praisonai adapter has it. Third-party adapters opt in by setting the flag on their subclass — see Capability Flags.

If framework: is omitted, both agents.yaml and workflow YAML resolve via FrameworkAdapterRegistry.resolve_or_default(None) — which delegates to pick_default(). The observability session tagged around a workflow-YAML run now reflects the config-resolved framework, not a hardcoded "praisonai" label.

Safety fields

Only framework: praisonai honours approval: and guardrails:. On crewai and autogen, an active gate raises ValueError at startup (previously it was dropped with a warning). See Framework Safety Enforcement.

What you’ll see if the framework isn’t workflow-capable

Selecting a framework whose adapter has SUPPORTS_WORKFLOW = False raises:

ValueError: framework='crewai' in workflow YAML is not supported for workflow execution.
The workflow engine requires an adapter whose SUPPORTS_WORKFLOW flag is set (the native 'praisonai' adapter does).
Use a non-workflow agents.yaml with a supported registered framework, or set framework: praisonai. Frameworks supporting workflow execution: praisonai.

The trailing list names every registered adapter whose SUPPORTS_WORKFLOW flag is True, so it grows as you install workflow-capable plugins.

Make a custom framework workflow-capable

Set SUPPORTS_WORKFLOW = True on your adapter subclass to accept workflow YAML dispatch:

from praisonaiagents import BaseFrameworkAdapter

class MyWorkflowFrameworkAdapter(BaseFrameworkAdapter):
    name = "myframework"
    SUPPORTS_WORKFLOW = True

    def is_available(self) -> bool:
        return True

    def run(self, config, llm_config, topic, *,
            tools_dict=None, agent_callback=None,
            task_callback=None, cli_config=None) -> str:
        return f"myframework ran: {topic}"

Once registered, myframework is accepted in workflow YAML and appears in the “Frameworks supporting workflow execution” list. See Capability Flags.

What to do

Programmatic check

from praisonai.framework_adapters.workflow_framework import (
    validate_workflow_framework,
    framework_from_config,
)

cfg = {"framework": "praisonai", "steps": []}
fw = framework_from_config(cfg)                 # "praisonai" (uses process-default registry)
validate_workflow_framework(fw)                 # no-op when valid; raises ValueError otherwise

framework_from_config({}) returns the process-default registry’s pick_default() ("praisonai" on a standard install), not a hardcoded literal. framework_from_config({"framework": "CrewAI"}) returns "crewai" (lowercased before validation). Pass registry= (new in PR #5039) to route the default through an injected registry:

from praisonai.framework_adapters.registry import FrameworkAdapterRegistry

reg = FrameworkAdapterRegistry()
framework_from_config({}, registry=reg)         # → reg.pick_default().lower()
framework_from_config({"framework": "CrewAI"}, registry=reg)  # → "crewai"

validate_workflow_framework() reads the adapter’s SUPPORTS_WORKFLOW flag from the default registry. Pass registry= to test against an isolated registry:

from praisonai.framework_adapters.registry import FrameworkAdapterRegistry

reg = FrameworkAdapterRegistry()
reg.register("myframework", MyWorkflowFrameworkAdapter)
validate_workflow_framework("myframework", registry=reg)   # passes when SUPPORTS_WORKFLOW = True

How It Works

Best Practices

from praisonai.framework_adapters.registry import list_framework_choices

choices = list_framework_choices()
print(choices)  # ['crewai', 'praisonai', 'autogen', 'my_plugin']

Related