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

@@ -4684,6 +4684,11 @@ class _TrackerHandler(http.server.BaseHTTPRequestHandler):
friendly_name=friendly_name,
capability=capability,
)
# A report may seed the same load/throughput inputs that legacy nodes
# supply through registration and heartbeats. The optional block is
# backend-neutral; routing still applies its usual queue adjustment.
if capability.reported_queue_depth is not None:
entry.queue_depth = capability.reported_queue_depth
with server.lock:
self._purge_expired_nodes()
# Dedup: replace the same node id or the same endpoint+model assignment.