2.1.0
Agents
Compatibility Matrix
0.4.1
2.1.0
AgentManifest
The complete definition of an agent deployment — identity, version, environment, and agent-specific configuration.
name
string
yes
-
Display name for this agent.
id
string
yes
-
Agent identifier.
version
string
yes
-
Agent version to deploy.
endpoint
boolean
no
False
Whether to expose the agent via a public URL.
env
list[EnvVar]
no
-
Environment variables available to the agent.
name
string
yes
-
value
string
yes
-
secrets
list[SecretRef]
no
-
Secrets made available to the agent as environment variables.
secretName
string
yes
-
agent_config
AgentConfig
yes
-
EnvVar
Environment variable passed to the agent at runtime.
name
string
yes
-
value
string
yes
-
SecretRef
Reference to a secret made available to the agent as environment variables.
secretName
string
yes
-
AgentConfig
Configuration specific to the Interactive Agent — defines the LLM, behavioral context, tools, and integrations.
llm_model
string
no
-
Model identifier in provider/model form (e.g. 'openai/gpt-4o-mini'). Determines which LLM the agent uses.
context
AgentContext
yes
-
session_stores
list[McpConfig]
no
-
id
string
yes
-
Unique identifier for this MCP connection.
hostname
string
yes
-
MCP server hostname including URL scheme (e.g. 'https://my-server'). Must not include path, query, fragment, or port.
port
integer
yes
-
transport
string
yes
-
Enum: ['sse', 'streamable-http']
mcps
list[McpConfig]
no
-
id
string
yes
-
Unique identifier for this MCP connection.
hostname
string
yes
-
MCP server hostname including URL scheme (e.g. 'https://my-server'). Must not include path, query, fragment, or port.
port
integer
yes
-
transport
string
yes
-
Enum: ['sse', 'streamable-http']
knowledge_base
KnowledgeBase
no
-
integration_webhook
IntegrationWebhook
no
-
AgentContext
The behavioral configuration that defines how the agent operates — its language, routines, policies, and glossaries.
description
DescriptionRef
yes
-
language
string
yes
-
Language the agent communicates in. Use match_user to automatically mirror the user's language, or specify a language name (e.g. 'English', 'Spanish').
routines
list[PromptRef]
no
-
id
string
yes
-
Prompt identifier or slug.
version
integer | string
no
-
Version to bind to (integer or string).
reevaluate_routines_after
list[ReevaluationTarget]
no
-
id
string
yes
-
policies
list[PromptRef]
no
-
id
string
yes
-
Prompt identifier or slug.
version
integer | string
no
-
Version to bind to (integer or string).
glossaries
list[PromptRef]
no
-
id
string
yes
-
Prompt identifier or slug.
version
integer | string
no
-
Version to bind to (integer or string).
preamble
Preamble
no
-
relationships
Relationships
no
-
DescriptionRef
Reference to the prompt that serves as the agent's description.
prompt_id
string
yes
-
Prompt identifier or slug.
version
integer | string
no
-
Version to bind to (integer or string).
PromptRef
A reference to a prompt at a specific version.
id
string
yes
-
Prompt identifier or slug.
version
integer | string
no
-
Version to bind to (integer or string).
ReevaluationTarget
A routine that triggers reevaluation of active routines after it completes.
id
string
yes
-
Preamble
Opening message configuration shown when a conversation starts.
examples
list[string]
yes
-
greeting
string
yes
-
language_instruction
string
yes
-
Relationships
priorities
list[Priority]
no
-
higher
string
yes
-
Routine or policy that takes priority.
over
list[string]
no
-
Routines or policies this entry takes priority over.
over_all_routines
boolean
no
-
When set, this entry takes priority over every routine. Only true is accepted — omit the key to opt out (use over instead).
Priority
A rule that determines which routine or policy takes precedence.
higher
string
yes
-
Routine or policy that takes priority.
over
list[string]
no
-
Routines or policies this entry takes priority over.
over_all_routines
boolean
no
-
When set, this entry takes priority over every routine. Only true is accepted — omit the key to opt out (use over instead).
McpConfig
Connection details for an MCP (Model Context Protocol) server.
id
string
yes
-
Unique identifier for this MCP connection.
hostname
string
yes
-
MCP server hostname including URL scheme (e.g. 'https://my-server'). Must not include path, query, fragment, or port.
port
integer
yes
-
transport
string
yes
-
Enum: ['sse', 'streamable-http']
KnowledgeBase
Configuration for connecting the agent to a knowledge base.
prompt
PromptRef
yes
-
hostname
string
yes
-
port
integer
yes
-
path
string
yes
-
IntegrationWebhook
Webhook endpoint the agent sends events to for external integrations.
hostname
string
yes
-
port
integer
yes
-
path
string
yes
-
URL path for the webhook (e.g. '/hooks/delivery').
Context
RoutineSchema
A multi-step conversational workflow that guides the agent through a sequence of actions.
id
string
no
-
title
string
yes
-
conditions
string | list[string]
no
-
description
string
no
-
extends
string
no
-
autonomous
AutonomousConfig
no
-
steps
list[RoutineStep]
yes
-
id
string
no
-
description
string
no
-
condition
string
no
-
source
string
no
-
fork
boolean
no
-
redirect
string
no
-
tools
list[string]
no
-
tool_instruction
string
no
-
chat_state
string
no
-
macro
string
no
-
think
string
no
-
output_schema
dict
no
-
AutonomousConfig
Configuration for autonomous routines that can be triggered via an API endpoint.
input_schema
dict
yes
-
output_schema
dict
yes
-
timeout_seconds
integer
no
120
callback_url_allowlist
list[string]
no
-
RoutineStep
A single step within a routine workflow.
id
string
no
-
description
string
no
-
condition
string
no
-
source
string
no
-
fork
boolean
no
-
redirect
string
no
-
tools
list[string]
no
-
tool_instruction
string
no
-
chat_state
string
no
-
macro
string
no
-
think
string
no
-
output_schema
dict
no
-
PolicySchema
A single-step behavioral rule — a condition-action pair that governs how the agent responds in specific situations.
id
string
no
-
name
string
yes
-
condition
string
yes
-
action
string
no
-
criticality
string
no
MEDIUM
Enum: ['HIGH', 'MEDIUM', 'LOW']
description
string
no
-
tools
list[string]
no
-
always_match
boolean
no
-
kind
string
no
-
GlossarySchema
A collection of domain-specific terms and definitions the agent uses to understand context.
id
string
no
-
terms
dict[string, GlossaryEntry]
yes
-
GlossaryEntry
A single glossary term.
name
string
yes
-
description
string
yes
-
synonyms
list[string]
no
-
MacroSchema
A reusable text block that can be injected into routine steps.
id
string
no
-
text
string
yes
-
VariableSchema
A set of named variables with optional defaults, used to parameterize agent behavior.
id
string
no
-
variables
dict[string, VariableEntry]
yes
-
VariableEntry
A single variable definition.
description
string
yes
-
default_value
any
no
-
Last updated
Was this helpful?