Client

class qveris.QverisClient(config: QverisConfig | None = None, debug_callback: Callable[[str], None] | None = None, *, credential_provider: CredentialProvider | None = None, http_client: AsyncClient | None = None, transport: AsyncBaseTransport | None = None, limits: Limits | None = None)

Async client for Qveris API.

property rate_limit_retries : int

How many times the client has backed off on a 429/503 so far.

Rate-limit backoff is retried pressure, not failure — surface this rather than counting the retried responses as errors.

Core workflow and failure behavior

Select a capability from Discover, build parameters from its current schema, and Probe before Call when an agent generated the values, the schema is complex, or cost matters. Authentication, exhausted rate-limit retries, and request validation failures throw SDK errors; also inspect Call's success and error fields for business failures. search_tools, get_tools_by_ids, and execute_tool are compatibility aliases; new code should use discover, inspect, probe, and call.

found = await client.discover("weather data for a city")
tool = found.results[0]
details = await client.inspect(tool.tool_id, search_id=found.search_id)
parameters = {"q": "London"}  # Build from details.results[0].params
quote = await client.probe(tool.tool_id, parameters, checks=["schema", "quote"])
result = await client.call(tool.tool_id, parameters, search_id=found.search_id)
if not result.success:
    raise RuntimeError(result.error_message or "Capability call failed")