Skip to content

LCORE-1356: Updated OpenAPI specification #1239

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tisnik merged 1 commit into from
Mar 1, 2026
Merged

LCORE-1356: Updated OpenAPI specification #1239

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 16 additions & 2 deletions docs/openapi.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4447,7 +4447,7 @@
],
"summary": "Handle A2A Jsonrpc",
"description": "Handle A2A JSON-RPC requests following the A2A protocol specification.\n\nThis endpoint uses the DefaultRequestHandler from the A2A SDK to handle\nall JSON-RPC requests including message/send, message/stream, etc.\n\nThe A2A SDK application is created per-request to include authentication\ncontext while still leveraging FastAPI's authorization middleware.\n\nAutomatically detects streaming requests (message/stream JSON-RPC method)\nand returns a StreamingResponse to enable real-time chunk delivery.\n\nArgs:\n request: FastAPI request object\n auth: Authentication tuple\n mcp_headers: MCP headers for context propagation\n\nReturns:\n JSON-RPC response or streaming response",
"operationId": "handle_a2a_jsonrpc_a2a_get",
"operationId": "handle_a2a_jsonrpc_a2a_post",
"responses": {
"200": {
"description": "Successful Response",
Expand All @@ -4465,7 +4465,7 @@
],
"summary": "Handle A2A Jsonrpc",
"description": "Handle A2A JSON-RPC requests following the A2A protocol specification.\n\nThis endpoint uses the DefaultRequestHandler from the A2A SDK to handle\nall JSON-RPC requests including message/send, message/stream, etc.\n\nThe A2A SDK application is created per-request to include authentication\ncontext while still leveraging FastAPI's authorization middleware.\n\nAutomatically detects streaming requests (message/stream JSON-RPC method)\nand returns a StreamingResponse to enable real-time chunk delivery.\n\nArgs:\n request: FastAPI request object\n auth: Authentication tuple\n mcp_headers: MCP headers for context propagation\n\nReturns:\n JSON-RPC response or streaming response",
"operationId": "handle_a2a_jsonrpc_a2a_get",
"operationId": "handle_a2a_jsonrpc_a2a_post",
"responses": {
"200": {
"description": "Successful Response",
Expand Down Expand Up @@ -7343,6 +7343,14 @@
"title": "Authorization headers",
"description": "Headers to send to the MCP server. The map contains the header name and the path to a file containing the header value (secret). There are 3 special cases: 1. Usage of the kubernetes token in the header. To specify this use a string 'kubernetes' instead of the file path. 2. Usage of the client-provided token in the header. To specify this use a string 'client' instead of the file path. 3. Usage of the oauth token in the header. To specify this use a string 'oauth' instead of the file path. "
},
"headers": {
"items": {
"type": "string"
},
"type": "array",
"title": "Propagated headers",
"description": "List of HTTP header names to automatically forward from the incoming request to this MCP server. Headers listed here are extracted from the original client request and included when calling the MCP server. This is useful when infrastructure components (e.g. API gateways) inject headers that MCP servers need, such as x-rh-identity in HCC. Header matching is case-insensitive. These headers are additive with authorization_headers and MCP-HEADERS."
},
"timeout": {
"anyOf": [
{
Expand Down Expand Up @@ -8862,6 +8870,7 @@
"properties": {
"nevra": {
"type": "string",
"pattern": "^[a-zA-Z0-9._:+~\\-]*$",
"title": "Nevra",
"description": "CLA NEVRA identifier",
"default": "",
Expand All @@ -8871,6 +8880,7 @@
},
"version": {
"type": "string",
"pattern": "^[a-zA-Z0-9._\\-]*$",
"title": "Version",
"description": "Command line assistant version",
"default": "",
Expand Down Expand Up @@ -9013,6 +9023,7 @@
"properties": {
"os": {
"type": "string",
"pattern": "^[a-zA-Z0-9._ \\-]*$",
"title": "Os",
"description": "Operating system name",
"default": "",
Expand All @@ -9022,6 +9033,7 @@
},
"version": {
"type": "string",
"pattern": "^[a-zA-Z0-9._ \\-]*$",
"title": "Version",
"description": "Operating system version",
"default": "",
Expand All @@ -9032,6 +9044,7 @@
},
"arch": {
"type": "string",
"pattern": "^[a-zA-Z0-9._ \\-]*$",
"title": "Arch",
"description": "System architecture",
"default": "",
Expand All @@ -9042,6 +9055,7 @@
},
"id": {
"type": "string",
"pattern": "^[a-zA-Z0-9._\\-]*$",
"title": "Id",
"description": "Client machine ID",
"default": "",
Expand Down
119 changes: 119 additions & 0 deletions docs/openapi.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -627,6 +627,7 @@ Examples
}
}
```

## GET `/v1/providers`

> **Providers Endpoint Handler**
Expand Down Expand Up @@ -1572,6 +1573,82 @@ Examples
}
```

## POST `/v1/streaming_query/interrupt`

> **Streaming Query Interrupt Endpoint Handler**

Interrupt an in-progress streaming query by request identifier.

Parameters:
interrupt_request: Request payload containing the stream request ID.
auth: Auth context tuple resolved from the authentication dependency.
registry: Stream interrupt registry dependency used to cancel streams.

Returns:
StreamingInterruptResponse: Confirmation payload when interruption succeeds.

Raises:
HTTPException: If no active stream for the given request ID can be interrupted.





### 📦 Request Body

[StreamingInterruptRequest](#streaminginterruptrequest)

### ✅ Responses

| Status Code | Description | Component |
|-------------|---------------------|-----------------------------------------------------------|
| 200 | Successful response | [StreamingInterruptResponse](#streaminginterruptresponse) |
| 401 | Unauthorized | [UnauthorizedResponse](#unauthorizedresponse) |
| 403 | Permission denied | [ForbiddenResponse](#forbiddenresponse) |
| 404 | Resource not found | [NotFoundResponse](#notfoundresponse) |
| 422 | Validation Error | [HTTPValidationError](#httpvalidationerror) |


```json
{
"detail": {
"cause": "No Authorization header found",
"response": "Missing or invalid credentials provided by client"
}
}
```


```json
{
"detail": {
"cause": "No token found in Authorization header",
"response": "Missing or invalid credentials provided by client"
}
}
```



```json
{
"detail": {
"cause": "User 6789 is not authorized to access this endpoint.",
"response": "User does not have permission to access this endpoint"
}
}
```



```json
{
"detail": {
"cause": "Streaming Request with ID 123e4567-e89b-12d3-a456-426614174000 does not exist",
"response": "Streaming Request not found"
}
}
```
## GET `/v1/config`

> **Config Endpoint Handler**
Expand Down Expand Up @@ -4745,6 +4822,7 @@ Useful resources:
| provider_id | string | MCP provider identification |
| url | string | URL of the MCP server |
| authorization_headers | object | Headers to send to the MCP server. The map contains the header name and the path to a file containing the header value (secret). There are 3 special cases: 1. Usage of the kubernetes token in the header. To specify this use a string 'kubernetes' instead of the file path. 2. Usage of the client-provided token in the header. To specify this use a string 'client' instead of the file path. 3. Usage of the oauth token in the header. To specify this use a string 'oauth' instead of the file path. |
| headers | array | List of HTTP header names to automatically forward from the incoming request to this MCP server. Headers listed here are extracted from the original client request and included when calling the MCP server. This is useful when infrastructure components (e.g. API gateways) inject headers that MCP servers need, such as x-rh-identity in HCC. Header matching is case-insensitive. These headers are additive with authorization_headers and MCP-HEADERS. |
| timeout | | Timeout in seconds for requests to the MCP server. If not specified, the default timeout from Llama Stack will be used. Note: This field is reserved for future use when Llama Stack adds timeout support. |


Expand Down Expand Up @@ -5454,6 +5532,47 @@ Example:
| status | object | The status of the service |


## StreamingInterruptRequest


Model representing a request to interrupt an active streaming query.

Attributes:
request_id: Unique ID of the active streaming request to interrupt.


| Field | Type | Description |
|-------|------|-------------|
| request_id | string | The active streaming request ID to interrupt |


## StreamingInterruptResponse


Model representing a response to a streaming interrupt request.

Attributes:
request_id: The streaming request ID targeted by the interrupt call.
interrupted: Whether an in-progress stream was interrupted.
message: Human-readable interruption status message.

Example:
```python
response = StreamingInterruptResponse(
request_id="123e4567-e89b-12d3-a456-426614174000",
interrupted=True,
message="Streaming request interrupted",
)
```


| Field | Type | Description |
|-------|------|-------------|
| request_id | string | The streaming request ID targeted by the interrupt call |
| interrupted | boolean | Whether an in-progress stream was interrupted |
| message | string | Human-readable interruption status message |


## TLSConfiguration


Expand Down
Loading