i/Aether
1
0
Fork 0
mirror of https://github.com/fawney19/Aether.git synced 2026-10-08 02:17:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(routing): make routing profiles the sole scheduler policy source

Browse Source 
Bootstrap an enabled system-default routing group from the legacy
scheduler config keys on startup, resolve the default ordering config
from that group before falling back to the legacy keys, and stop merging
keep_priority_on_conversion with the legacy flag when a policy is
resolved. Thread the policy-derived ordering config into candidate
preselection so it no longer reads system config independently.

Add per-API-format key priority overrides so a key serving several
formats keeps independent ordering, matching the legacy
global_priority_by_format semantics. Expose keep_priority_on_conversion
in the routing profile editor and read the effective policy in the
model routing preview, monitoring metrics and provider page badge.
This commit is contained in:
elky
2026-09-02 17:04:04 +08:00
parent 166236c2ee
commit 415b2da81b
32 changed files with 1001 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/aether-gateway/src/dispatch/pool_scheduler.rs
+21 -12
View File
@@ -754,19 +754,28 @@ impl<'a> PoolKeyCursor<'a> {
return None;
}
};
let api_format = self.group.candidate.endpoint_api_format.as_str();
rows.sort_by(|left, right| {
let left_priority = self
.routing_overlay
.as_ref()
.map_or(left.key_internal_priority, |overlay| {
overlay.key_priority(&left.key_id, left.key_internal_priority)
});
let right_priority = self
.routing_overlay
.as_ref()
.map_or(right.key_internal_priority, |overlay| {
overlay.key_priority(&right.key_id, right.key_internal_priority)
});
let left_priority = self.routing_overlay.as_ref().map_or(
left.key_internal_priority,
|overlay| {
overlay.key_priority_for_format(
&left.key_id,
api_format,
left.key_internal_priority,
)
},
);
let right_priority = self.routing_overlay.as_ref().map_or(
right.key_internal_priority,
|overlay| {
overlay.key_priority_for_format(
&right.key_id,
api_format,
right.key_internal_priority,
)
},
);
left_priority
.cmp(&right_priority)
.then(left.key_id.cmp(&right.key_id))