feat(routing): linked complexity-boundary sliders — your own low/medium/high

The tier boundaries lived on the router and were global for every customer
of a hosted router; per-gateway tuning meant hand-editing score ranges. The
Routing page now has one track with two draggable handles (the low|medium
and medium|high boundaries) over three colored zones: handles push each
other (low can't cross medium — it shoves it along, and vice versa), the
numbers ride on the handles and the legend updates live, so nobody types
ranges by hand. Unchecked = the router's own bands, untouched behavior.

Under the hood the gateway re-maps the router's CONTINUOUS complexity score
with the user's boundaries ([routing.bands] low/medium in gateway.toml,
validated 0 < low < medium < 1) before tier chains, escalation and stats —
verified live: with bands at 0.70/0.72 a score-0.27 request that used to be
medium routed low, and back after restoring the defaults.

2 new strings in all 7 languages.
This commit is contained in:
infosave2007
2026-08-08 09:48:36 +03:00
parent 179c414a0e
commit 788c87c565
12 changed files with 172 additions and 1 deletions
+4
View File
@@ -931,6 +931,7 @@ async fn get_routing(State(state): State<SharedState>) -> ApiResult {
.collect();
ok(json!({
"tiers": tiers_to_map(&live.cfg.routing),
"bands": live.cfg.routing.bands,
"tasks": tasks,
"default": live.cfg.routing.default,
"policy": live.cfg.routing.policy,
@@ -978,6 +979,8 @@ struct RoutingBody {
tiers: HashMap<String, Vec<String>>,
#[serde(default)]
tasks: HashMap<String, TierTargets>,
#[serde(default)]
bands: Option<crate::config::TierBands>,
default: String,
#[serde(default)]
policy: RoutingPolicy,
@@ -997,6 +1000,7 @@ async fn put_routing(State(state): State<SharedState>, Json(body): Json<RoutingB
// empty rule (no models AND no forced tier) = "по сложности"
.filter(|(_, v)| !v.models().is_empty())
.collect(),
bands: body.bands,
default: body.default,
policy: body.policy,
};
+35
View File
@@ -404,6 +404,31 @@ pub struct RoutingCfg {
/// called "tasks" — serde extracts it before the flattened tier map.
#[serde(default, skip_serializing_if = "HashMap::is_empty")]
pub tasks: HashMap<String, TierTargets>,
/// Local complexity bands: re-map the router's continuous score into
/// low/medium/high with YOUR OWN boundaries. The hosted router's bands
/// are global for all customers; these are per-gateway. `None` = keep
/// the router's tier verdict as delivered.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub bands: Option<TierBands>,
}
/// Score boundaries: `score ≤ low` → low, `≤ medium` → medium, else high.
#[derive(Clone, Copy, Debug, Serialize, Deserialize)]
pub struct TierBands {
pub low: f32,
pub medium: f32,
}
impl TierBands {
pub fn tier_of(&self, score: f32) -> &'static str {
if score <= self.low {
"low"
} else if score <= self.medium {
"medium"
} else {
"high"
}
}
}
/// A routing tier is either a list of model_ids or the string `default`.
@@ -861,6 +886,7 @@ impl Default for Config {
default: String::new(),
policy: RoutingPolicy::default(),
tasks: HashMap::new(),
bands: None,
},
breaker: BreakerCfg::default(),
protocols: ProtocolsCfg {
@@ -988,6 +1014,15 @@ impl Config {
}
}
}
if let Some(b) = &self.routing.bands {
if !(b.low > 0.0 && b.low < b.medium && b.medium < 1.0) {
anyhow::bail!(
"config: routing.bands must satisfy 0 < low < medium < 1 (got {} / {})",
b.low,
b.medium
);
}
}
for (task, targets) in &self.routing.tasks {
for id in &targets.models() {
if !ids.contains(id.as_str()) {
+13
View File
@@ -231,6 +231,19 @@ impl Pipeline {
let prof = profile.as_deref().unwrap_or(&live.cfg.route.profile);
match live.router.route(&text, prof).await {
Ok(Some(dec)) => {
let mut dec = dec;
// per-gateway complexity bands: re-map the
// router's continuous score with the user's
// own boundaries (sliders on the Routing page)
if let Some(b) = &live.cfg.routing.bands {
if matches!(
dec.complexity_tier.as_str(),
"low" | "medium" | "high"
) {
dec.complexity_tier =
b.tier_of(dec.complexity_score).to_string();
}
}
let src = dec.source.clone();
let (cands, task_rule) = live
.routing