story: DGR-043 Expose GGUF compatibility and measured cost inputs to existing routing

This commit is contained in:
Dobromir Popov
2026-08-01 01:58:13 +03:00
parent d53acb1145
commit e6ad9fdca9
6 changed files with 272 additions and 5 deletions

View File

@@ -193,6 +193,11 @@ class CapabilityState:
memory_capacity_bytes: int | None = None
kv_capacity_tokens: int | None = None
max_concurrent_sessions: int | None = None
measured_tokens_per_second: float | None = None
reported_queue_depth: int | None = None
seam_latency_ms: float | None = None
healthy: bool | None = None
reliability: float | None = None
@property
def proven(self) -> bool:
@@ -239,6 +244,11 @@ class CapabilityState:
"memory_capacity_bytes": self.memory_capacity_bytes,
"kv_capacity_tokens": self.kv_capacity_tokens,
"max_concurrent_sessions": self.max_concurrent_sessions,
"measured_tokens_per_second": self.measured_tokens_per_second,
"reported_queue_depth": self.reported_queue_depth,
"seam_latency_ms": self.seam_latency_ms,
"healthy": self.healthy,
"reliability": self.reliability,
}
@@ -500,6 +510,9 @@ def _parse_report(doc: Mapping[str, Any]) -> dict:
capacity = doc.get("capacity")
if capacity is not None:
capacity = _object(capacity, "capacity")
routing = doc.get("routing")
if routing is not None:
routing = _object(routing, "routing")
return {
"model_id": _text(model.get("model_id"), "model.model_id"),
@@ -530,6 +543,24 @@ def _parse_report(doc: Mapping[str, Any]) -> dict:
None if capacity is None else capacity.get("max_concurrent_sessions"),
"capacity.max_concurrent_sessions",
),
"measured_tokens_per_second": _optional_positive_float(
None if routing is None else routing.get("tokens_per_second"),
"routing.tokens_per_second",
),
"reported_queue_depth": _optional_nonnegative_int(
None if routing is None else routing.get("queue_depth"),
"routing.queue_depth",
),
"seam_latency_ms": _optional_nonnegative_float(
None if routing is None else routing.get("seam_latency_ms"),
"routing.seam_latency_ms",
),
"healthy": _optional_bool(
None if routing is None else routing.get("healthy"), "routing.healthy"
),
"reliability": _optional_unit_float(
None if routing is None else routing.get("reliability"), "routing.reliability"
),
"_status": _text(doc.get("status"), "status"),
}
@@ -566,6 +597,45 @@ def _optional_positive_int(value: Any, field_name: str) -> int | None:
return value
def _optional_nonnegative_int(value: Any, field_name: str) -> int | None:
if value is None:
return None
if isinstance(value, bool) or not isinstance(value, int) or value < 0:
raise _ReportError(f"{field_name!r} must be a non-negative integer")
return value
def _optional_positive_float(value: Any, field_name: str) -> float | None:
if value is None:
return None
if isinstance(value, bool) or not isinstance(value, (int, float)) or value <= 0:
raise _ReportError(f"{field_name!r} must be a positive number")
return float(value)
def _optional_nonnegative_float(value: Any, field_name: str) -> float | None:
if value is None:
return None
if isinstance(value, bool) or not isinstance(value, (int, float)) or value < 0:
raise _ReportError(f"{field_name!r} must be a non-negative number")
return float(value)
def _optional_bool(value: Any, field_name: str) -> bool | None:
if value is None:
return None
if not isinstance(value, bool):
raise _ReportError(f"{field_name!r} must be a boolean")
return value
def _optional_unit_float(value: Any, field_name: str) -> float | None:
parsed = _optional_nonnegative_float(value, field_name)
if parsed is not None and parsed > 1:
raise _ReportError(f"{field_name!r} must be a number from 0 to 1")
return parsed
def _maybe_int(value: Any) -> int | None:
if isinstance(value, bool) or not isinstance(value, int):
return None