Skip to content

feat(ai-backend): add per-user AI quotas and provider usage budgets #453

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

Open
Nicks-19 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

feat(ai-backend): add per-user AI quotas and provider usage budgets #453

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
60e6aa9
feat(ai-backend): add per-user AI quotas and provider usage budgets
Nicks-19 Jul 6, 2026
a53b9fa
chore: resolve merge conflicts in router.py
Nicks-19 Jul 14, 2026
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
280 changes: 280 additions & 0 deletions services/ai/openapi.golden.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,10 +73,154 @@
}
]
}
},
"/api/v1/ai/request": {
"post": {
"tags": [
"ai"
],
"summary": "Check Quota Only",
"description": "Check request budget and concurrency, increment requests count and active concurrency.",
"operationId": "check_quota_only_api_v1_ai_request_post",
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/StandardResponse"
}
}
}
},
"422": {
"description": "Validation Error",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
}
}
},
"security": [
{
"APIKeyHeader": []
}
]
}
},
"/api/v1/ai/job/start": {
"post": {
"tags": [
"ai"
],
"summary": "Start Job",
"description": "Start a long-running job by checking quota limits and reserving estimated tokens.",
"operationId": "start_job_api_v1_ai_job_start_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/JobStartInput"
}
}
},
"required": true
},
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/JobStartResponse"
}
}
}
},
"422": {
"description": "Validation Error",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
}
}
},
"security": [
{
"APIKeyHeader": []
}
]
}
},
"/api/v1/ai/job/reconcile": {
"post": {
"tags": [
"ai"
],
"summary": "Reconcile Job",
"description": "Reconcile a completed/failed job and adjust usage tracker tokens and active concurrency.",
"operationId": "reconcile_job_api_v1_ai_job_reconcile_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/JobReconcileInput"
}
}
},
"required": true
},
"responses": {
"200": {
"description": "Successful Response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/StandardResponse"
}
}
}
},
"422": {
"description": "Validation Error",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
}
}
},
"security": [
{
"APIKeyHeader": []
}
]
}
}
},
"components": {
"schemas": {
"HTTPValidationError": {
"properties": {
"detail": {
"items": {
"$ref": "#/components/schemas/ValidationError"
},
"type": "array",
"title": "Detail"
}
},
"type": "object",
"title": "HTTPValidationError"
},
"HealthResponse": {
"properties": {
"status": {
Expand Down Expand Up @@ -107,6 +251,71 @@
],
"title": "HealthResponse"
},
"JobReconcileInput": {
"properties": {
"reservation_id": {
"type": "string",
"format": "uuid",
"title": "Reservation Id"
},
"actual_tokens": {
"anyOf": [
{
"type": "integer",
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Actual Tokens"
},
"status": {
"type": "string",
"pattern": "^(COMPLETED|FAILED|CANCELLED)$",
"title": "Status",
"default": "COMPLETED"
}
},
"type": "object",
"required": [
"reservation_id"
],
"title": "JobReconcileInput"
},
"JobStartInput": {
"properties": {
"estimated_tokens": {
"type": "integer",
"minimum": 1.0,
"title": "Estimated Tokens"
}
},
"type": "object",
"required": [
"estimated_tokens"
],
"title": "JobStartInput"
},
"JobStartResponse": {
"properties": {
"status": {
"type": "string",
"title": "Status"
},
"reservation_id": {
"type": "string",
"format": "uuid",
"title": "Reservation Id"
}
},
"type": "object",
"required": [
"status",
"reservation_id"
],
"title": "JobStartResponse"
},
"ReadinessResponse": {
"properties": {
"status": {
Expand All @@ -120,13 +329,84 @@
},
"type": "object",
"title": "Checks"
},
"loaded_models": {
"items": {
"type": "string"
},
"type": "array",
"title": "Loaded Models"
},
"load_error": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Load Error"
}
},
"type": "object",
"required": [
"status"
],
"title": "ReadinessResponse"
},
"StandardResponse": {
"properties": {
"status": {
"type": "string",
"title": "Status"
}
},
"type": "object",
"required": [
"status"
],
"title": "StandardResponse"
},
"ValidationError": {
"properties": {
"loc": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"type": "array",
"title": "Location"
},
"msg": {
"type": "string",
"title": "Message"
},
"type": {
"type": "string",
"title": "Error Type"
},
"input": {
"title": "Input"
},
"ctx": {
"type": "object",
"title": "Context"
}
},
"type": "object",
"required": [
"loc",
"msg",
"type"
],
"title": "ValidationError"
}
},
"securitySchemes": {
Expand Down
6 changes: 5 additions & 1 deletion services/ai/src/vidyasetu_ai/api/router.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
from fastapi import APIRouter, Depends

from vidyasetu_ai.api.routes.ai import router as ai_router
from vidyasetu_ai.api.routes.notes import router as notes_router
from vidyasetu_ai.core.security import require_internal_api_key
from vidyasetu_ai.schemas.health import HealthResponse
Expand All @@ -16,4 +17,7 @@
dependencies=[Depends(require_internal_api_key)],
)
def internal_ping() -> HealthResponse:
return HealthResponse(status="ok", service="vidyasetu-ai")
return HealthResponse(status="ok", service="vidyasetu-ai")


api_router.include_router(ai_router)
Loading