diff --git a/docs/resources/llama-stack-spec.html b/docs/resources/llama-stack-spec.html
index de52131b5..363d968f9 100644
--- a/docs/resources/llama-stack-spec.html
+++ b/docs/resources/llama-stack-spec.html
@@ -21,7 +21,7 @@
"info": {
"title": "[DRAFT] Llama Stack Specification",
"version": "0.0.1",
- "description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-10-31 10:35:38.305313"
+ "description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-10-31 14:28:52.128905"
},
"servers": [
{
@@ -320,11 +320,18 @@
"post": {
"responses": {
"200": {
- "description": "A single turn in an interaction with an Agentic System.",
+ "description": "A single turn in an interaction with an Agentic System. **OR** streamed agent turn completion response.",
"content": {
"text/event-stream": {
"schema": {
- "$ref": "#/components/schemas/Turn"
+ "oneOf": [
+ {
+ "$ref": "#/components/schemas/Turn"
+ },
+ {
+ "$ref": "#/components/schemas/AgentTurnResponseStreamChunk"
+ }
+ ]
}
}
}
@@ -3832,6 +3839,215 @@
"messages"
]
},
+ "AgentTurnResponseEvent": {
+ "type": "object",
+ "properties": {
+ "payload": {
+ "oneOf": [
+ {
+ "$ref": "#/components/schemas/AgentTurnResponseStepStartPayload"
+ },
+ {
+ "$ref": "#/components/schemas/AgentTurnResponseStepProgressPayload"
+ },
+ {
+ "$ref": "#/components/schemas/AgentTurnResponseStepCompletePayload"
+ },
+ {
+ "$ref": "#/components/schemas/AgentTurnResponseTurnStartPayload"
+ },
+ {
+ "$ref": "#/components/schemas/AgentTurnResponseTurnCompletePayload"
+ }
+ ]
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "payload"
+ ],
+ "title": "Streamed agent execution response."
+ },
+ "AgentTurnResponseStepCompletePayload": {
+ "type": "object",
+ "properties": {
+ "event_type": {
+ "type": "string",
+ "const": "step_complete",
+ "default": "step_complete"
+ },
+ "step_type": {
+ "type": "string",
+ "enum": [
+ "inference",
+ "tool_execution",
+ "shield_call",
+ "memory_retrieval"
+ ]
+ },
+ "step_details": {
+ "oneOf": [
+ {
+ "$ref": "#/components/schemas/InferenceStep"
+ },
+ {
+ "$ref": "#/components/schemas/ToolExecutionStep"
+ },
+ {
+ "$ref": "#/components/schemas/ShieldCallStep"
+ },
+ {
+ "$ref": "#/components/schemas/MemoryRetrievalStep"
+ }
+ ]
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "event_type",
+ "step_type",
+ "step_details"
+ ]
+ },
+ "AgentTurnResponseStepProgressPayload": {
+ "type": "object",
+ "properties": {
+ "event_type": {
+ "type": "string",
+ "const": "step_progress",
+ "default": "step_progress"
+ },
+ "step_type": {
+ "type": "string",
+ "enum": [
+ "inference",
+ "tool_execution",
+ "shield_call",
+ "memory_retrieval"
+ ]
+ },
+ "step_id": {
+ "type": "string"
+ },
+ "model_response_text_delta": {
+ "type": "string"
+ },
+ "tool_call_delta": {
+ "$ref": "#/components/schemas/ToolCallDelta"
+ },
+ "tool_response_text_delta": {
+ "type": "string"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "event_type",
+ "step_type",
+ "step_id"
+ ]
+ },
+ "AgentTurnResponseStepStartPayload": {
+ "type": "object",
+ "properties": {
+ "event_type": {
+ "type": "string",
+ "const": "step_start",
+ "default": "step_start"
+ },
+ "step_type": {
+ "type": "string",
+ "enum": [
+ "inference",
+ "tool_execution",
+ "shield_call",
+ "memory_retrieval"
+ ]
+ },
+ "step_id": {
+ "type": "string"
+ },
+ "metadata": {
+ "type": "object",
+ "additionalProperties": {
+ "oneOf": [
+ {
+ "type": "null"
+ },
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "number"
+ },
+ {
+ "type": "string"
+ },
+ {
+ "type": "array"
+ },
+ {
+ "type": "object"
+ }
+ ]
+ }
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "event_type",
+ "step_type",
+ "step_id"
+ ]
+ },
+ "AgentTurnResponseStreamChunk": {
+ "type": "object",
+ "properties": {
+ "event": {
+ "$ref": "#/components/schemas/AgentTurnResponseEvent"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "event"
+ ],
+ "title": "streamed agent turn completion response."
+ },
+ "AgentTurnResponseTurnCompletePayload": {
+ "type": "object",
+ "properties": {
+ "event_type": {
+ "type": "string",
+ "const": "turn_complete",
+ "default": "turn_complete"
+ },
+ "turn": {
+ "$ref": "#/components/schemas/Turn"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "event_type",
+ "turn"
+ ]
+ },
+ "AgentTurnResponseTurnStartPayload": {
+ "type": "object",
+ "properties": {
+ "event_type": {
+ "type": "string",
+ "const": "turn_start",
+ "default": "turn_start"
+ },
+ "turn_id": {
+ "type": "string"
+ }
+ },
+ "additionalProperties": false,
+ "required": [
+ "event_type",
+ "turn_id"
+ ]
+ },
"InferenceStep": {
"type": "object",
"properties": {
@@ -6846,57 +7062,57 @@
}
],
"tags": [
- {
- "name": "Safety"
- },
- {
- "name": "Scoring"
- },
- {
- "name": "BatchInference"
- },
- {
- "name": "DatasetIO"
- },
- {
- "name": "Models"
- },
- {
- "name": "Eval"
- },
- {
- "name": "Telemetry"
- },
- {
- "name": "Shields"
- },
- {
- "name": "Datasets"
- },
{
"name": "Memory"
},
- {
- "name": "PostTraining"
- },
- {
- "name": "ScoringFunctions"
- },
- {
- "name": "SyntheticDataGeneration"
- },
- {
- "name": "Inspect"
- },
- {
- "name": "MemoryBanks"
- },
{
"name": "Inference"
},
+ {
+ "name": "Eval"
+ },
+ {
+ "name": "MemoryBanks"
+ },
+ {
+ "name": "Models"
+ },
+ {
+ "name": "BatchInference"
+ },
+ {
+ "name": "PostTraining"
+ },
{
"name": "Agents"
},
+ {
+ "name": "Shields"
+ },
+ {
+ "name": "Telemetry"
+ },
+ {
+ "name": "Inspect"
+ },
+ {
+ "name": "DatasetIO"
+ },
+ {
+ "name": "SyntheticDataGeneration"
+ },
+ {
+ "name": "Datasets"
+ },
+ {
+ "name": "Scoring"
+ },
+ {
+ "name": "ScoringFunctions"
+ },
+ {
+ "name": "Safety"
+ },
{
"name": "BuiltinTool",
"description": ""
@@ -7081,6 +7297,34 @@
"name": "CreateAgentTurnRequest",
"description": ""
},
+ {
+ "name": "AgentTurnResponseEvent",
+ "description": "Streamed agent execution response.\n\n"
+ },
+ {
+ "name": "AgentTurnResponseStepCompletePayload",
+ "description": ""
+ },
+ {
+ "name": "AgentTurnResponseStepProgressPayload",
+ "description": ""
+ },
+ {
+ "name": "AgentTurnResponseStepStartPayload",
+ "description": ""
+ },
+ {
+ "name": "AgentTurnResponseStreamChunk",
+ "description": "streamed agent turn completion response.\n\n"
+ },
+ {
+ "name": "AgentTurnResponseTurnCompletePayload",
+ "description": ""
+ },
+ {
+ "name": "AgentTurnResponseTurnStartPayload",
+ "description": ""
+ },
{
"name": "InferenceStep",
"description": ""
@@ -7429,6 +7673,13 @@
"AgentCreateResponse",
"AgentSessionCreateResponse",
"AgentStepResponse",
+ "AgentTurnResponseEvent",
+ "AgentTurnResponseStepCompletePayload",
+ "AgentTurnResponseStepProgressPayload",
+ "AgentTurnResponseStepStartPayload",
+ "AgentTurnResponseStreamChunk",
+ "AgentTurnResponseTurnCompletePayload",
+ "AgentTurnResponseTurnStartPayload",
"Attachment",
"BatchChatCompletionRequest",
"BatchChatCompletionResponse",
diff --git a/docs/resources/llama-stack-spec.yaml b/docs/resources/llama-stack-spec.yaml
index 0cf378168..7dd231965 100644
--- a/docs/resources/llama-stack-spec.yaml
+++ b/docs/resources/llama-stack-spec.yaml
@@ -86,6 +86,138 @@ components:
required:
- step
type: object
+ AgentTurnResponseEvent:
+ additionalProperties: false
+ properties:
+ payload:
+ oneOf:
+ - $ref: '#/components/schemas/AgentTurnResponseStepStartPayload'
+ - $ref: '#/components/schemas/AgentTurnResponseStepProgressPayload'
+ - $ref: '#/components/schemas/AgentTurnResponseStepCompletePayload'
+ - $ref: '#/components/schemas/AgentTurnResponseTurnStartPayload'
+ - $ref: '#/components/schemas/AgentTurnResponseTurnCompletePayload'
+ required:
+ - payload
+ title: Streamed agent execution response.
+ type: object
+ AgentTurnResponseStepCompletePayload:
+ additionalProperties: false
+ properties:
+ event_type:
+ const: step_complete
+ default: step_complete
+ type: string
+ step_details:
+ oneOf:
+ - $ref: '#/components/schemas/InferenceStep'
+ - $ref: '#/components/schemas/ToolExecutionStep'
+ - $ref: '#/components/schemas/ShieldCallStep'
+ - $ref: '#/components/schemas/MemoryRetrievalStep'
+ step_type:
+ enum:
+ - inference
+ - tool_execution
+ - shield_call
+ - memory_retrieval
+ type: string
+ required:
+ - event_type
+ - step_type
+ - step_details
+ type: object
+ AgentTurnResponseStepProgressPayload:
+ additionalProperties: false
+ properties:
+ event_type:
+ const: step_progress
+ default: step_progress
+ type: string
+ model_response_text_delta:
+ type: string
+ step_id:
+ type: string
+ step_type:
+ enum:
+ - inference
+ - tool_execution
+ - shield_call
+ - memory_retrieval
+ type: string
+ tool_call_delta:
+ $ref: '#/components/schemas/ToolCallDelta'
+ tool_response_text_delta:
+ type: string
+ required:
+ - event_type
+ - step_type
+ - step_id
+ type: object
+ AgentTurnResponseStepStartPayload:
+ additionalProperties: false
+ properties:
+ event_type:
+ const: step_start
+ default: step_start
+ type: string
+ metadata:
+ additionalProperties:
+ oneOf:
+ - type: 'null'
+ - type: boolean
+ - type: number
+ - type: string
+ - type: array
+ - type: object
+ type: object
+ step_id:
+ type: string
+ step_type:
+ enum:
+ - inference
+ - tool_execution
+ - shield_call
+ - memory_retrieval
+ type: string
+ required:
+ - event_type
+ - step_type
+ - step_id
+ type: object
+ AgentTurnResponseStreamChunk:
+ additionalProperties: false
+ properties:
+ event:
+ $ref: '#/components/schemas/AgentTurnResponseEvent'
+ required:
+ - event
+ title: streamed agent turn completion response.
+ type: object
+ AgentTurnResponseTurnCompletePayload:
+ additionalProperties: false
+ properties:
+ event_type:
+ const: turn_complete
+ default: turn_complete
+ type: string
+ turn:
+ $ref: '#/components/schemas/Turn'
+ required:
+ - event_type
+ - turn
+ type: object
+ AgentTurnResponseTurnStartPayload:
+ additionalProperties: false
+ properties:
+ event_type:
+ const: turn_start
+ default: turn_start
+ type: string
+ turn_id:
+ type: string
+ required:
+ - event_type
+ - turn_id
+ type: object
Attachment:
additionalProperties: false
properties:
@@ -2866,7 +2998,7 @@ info:
description: "This is the specification of the llama stack that provides\n \
\ a set of endpoints and their corresponding interfaces that are tailored\
\ to\n best leverage Llama Models. The specification is still in\
- \ draft and subject to change.\n Generated at 2024-10-31 10:35:38.305313"
+ \ draft and subject to change.\n Generated at 2024-10-31 14:28:52.128905"
title: '[DRAFT] Llama Stack Specification'
version: 0.0.1
jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema
@@ -3059,8 +3191,11 @@ paths:
content:
text/event-stream:
schema:
- $ref: '#/components/schemas/Turn'
- description: A single turn in an interaction with an Agentic System.
+ oneOf:
+ - $ref: '#/components/schemas/Turn'
+ - $ref: '#/components/schemas/AgentTurnResponseStreamChunk'
+ description: A single turn in an interaction with an Agentic System. **OR**
+ streamed agent turn completion response.
tags:
- Agents
/agents/turn/get:
@@ -4145,23 +4280,23 @@ security:
servers:
- url: http://any-hosted-llama-stack.com
tags:
-- name: Safety
-- name: Scoring
-- name: BatchInference
-- name: DatasetIO
-- name: Models
-- name: Eval
-- name: Telemetry
-- name: Shields
-- name: Datasets
- name: Memory
-- name: PostTraining
-- name: ScoringFunctions
-- name: SyntheticDataGeneration
-- name: Inspect
-- name: MemoryBanks
- name: Inference
+- name: Eval
+- name: MemoryBanks
+- name: Models
+- name: BatchInference
+- name: PostTraining
- name: Agents
+- name: Shields
+- name: Telemetry
+- name: Inspect
+- name: DatasetIO
+- name: SyntheticDataGeneration
+- name: Datasets
+- name: Scoring
+- name: ScoringFunctions
+- name: Safety
- description:
name: BuiltinTool
- description:
name: CreateAgentTurnRequest
+- description: 'Streamed agent execution response.
+
+
+ '
+ name: AgentTurnResponseEvent
+- description:
+ name: AgentTurnResponseStepCompletePayload
+- description:
+ name: AgentTurnResponseStepProgressPayload
+- description:
+ name: AgentTurnResponseStepStartPayload
+- description: 'streamed agent turn completion response.
+
+
+ '
+ name: AgentTurnResponseStreamChunk
+- description:
+ name: AgentTurnResponseTurnCompletePayload
+- description:
+ name: AgentTurnResponseTurnStartPayload
- description:
name: InferenceStep
- description: