Hermes Pipeline
74 lines
2.7 KiB
Markdown
74 lines
2.7 KiB
Markdown
---
|
|
name: conditional-input-routing
|
|
version: 1.0.0
|
|
description: Collect user input, classify or branch on its content, and route to appropriate
|
|
success or failure handling paths to produce a final result
|
|
inputs:
|
|
- name: request
|
|
type: string
|
|
description: User-provided input or request to be evaluated
|
|
steps:
|
|
- name: Start
|
|
action: input agent captures initial request into state
|
|
agent_type: input
|
|
output_field: request
|
|
- name: Classify
|
|
action: branching agent evaluates request and routes to next_node or on_failure
|
|
agent_type: branching
|
|
input_fields: request
|
|
output_field: decision
|
|
next_node: Approve
|
|
on_failure: Reject
|
|
- name: Approve
|
|
action: default agent processes approved request and sets result
|
|
agent_type: default
|
|
input_fields: request
|
|
output_field: result
|
|
prompt: 'Request approved: {request}'
|
|
- name: Reject
|
|
action: default agent processes rejected request and sets result
|
|
agent_type: default
|
|
input_fields: request
|
|
output_field: result
|
|
prompt: 'Request rejected: {request}'
|
|
outputs:
|
|
- name: result
|
|
type: string
|
|
description: Final output from either the approve or reject branch
|
|
tags: []
|
|
metadata:
|
|
source_repo: https://github.com/jwwelbor/AgentMap.git
|
|
extracted_at: ''
|
|
confidence: 0.9
|
|
---
|
|
|
|
# conditional-input-routing
|
|
|
|
Collect user input, classify or branch on its content, and route to appropriate success or failure handling paths to produce a final result
|
|
|
|
## Steps
|
|
|
|
1. {'name': 'Start', 'action': 'input agent captures initial request into state', 'agent_type': 'input', 'output_field': 'request'}
|
|
2. {'name': 'Classify', 'action': 'branching agent evaluates request and routes to next_node or on_failure', 'agent_type': 'branching', 'input_fields': 'request', 'output_field': 'decision', 'next_node': 'Approve', 'on_failure': 'Reject'}
|
|
3. {'name': 'Approve', 'action': 'default agent processes approved request and sets result', 'agent_type': 'default', 'input_fields': 'request', 'output_field': 'result', 'prompt': 'Request approved: {request}'}
|
|
4. {'name': 'Reject', 'action': 'default agent processes rejected request and sets result', 'agent_type': 'default', 'input_fields': 'request', 'output_field': 'result', 'prompt': 'Request rejected: {request}'}
|
|
|
|
## Inputs
|
|
|
|
- {'name': 'request', 'type': 'string', 'description': 'User-provided input or request to be evaluated'}
|
|
|
|
## Outputs
|
|
|
|
- {'name': 'result', 'type': 'string', 'description': 'Final output from either the approve or reject branch'}
|
|
|
|
## Failure Modes
|
|
|
|
- Input node fails to capture request (handled by on_failure if defined)
|
|
- Branching condition not met and no on_failure path defined
|
|
- Missing input_fields in state causing agent execution error
|
|
|
|
## Source
|
|
|
|
Extracted from: [https://github.com/jwwelbor/AgentMap.git](https://github.com/jwwelbor/AgentMap.git)
|
|
Confidence: 0.9
|