2.1.0

---

Agents

Compatibility Matrix

Agent Version	Schema Version
0.4.1	2.1.0

AgentManifest

The complete definition of an agent deployment — identity, version, environment, and agent-specific configuration.

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	Description
name	string	yes	-
value	string	yes	-

SecretRef

Reference to a secret made available to the agent as environment variables.

Field	Type	Required	Default	Description
secretName	string	yes	-

AgentConfig

Configuration specific to the Interactive Agent — defines the LLM, behavioral context, tools, and integrations.

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	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.

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	Description
id	string	yes	-

Preamble

Opening message configuration shown when a conversation starts.

Field	Type	Required	Default	Description
examples	list[string]	yes	-
greeting	string	yes	-
language_instruction	string	yes	-

Relationships

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	Description
prompt	PromptRef	yes	-
hostname	string	yes	-
port	integer	yes	-
path	string	yes	-

IntegrationWebhook

Webhook endpoint the agent sends events to for external integrations.

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	Description
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.

Field	Type	Required	Default	Description
id	string	no	-
terms	dict[string, GlossaryEntry]	yes	-

GlossaryEntry

A single glossary term.

Field	Type	Required	Default	Description
name	string	yes	-
description	string	yes	-
synonyms	list[string]	no	-

MacroSchema

A reusable text block that can be injected into routine steps.

Field	Type	Required	Default	Description
id	string	no	-
text	string	yes	-

VariableSchema

A set of named variables with optional defaults, used to parameterize agent behavior.

Field	Type	Required	Default	Description
id	string	no	-
variables	dict[string, VariableEntry]	yes	-

VariableEntry

A single variable definition.

Field	Type	Required	Default	Description
description	string	yes	-
default_value	any	no	-