feat: per-key spend accounting and per-task complexity pinning

API keys page: the table now answers "which department spends what" — per-key
requests, tokens in/out and cost for a selectable window (24h/7d/30d) plus a
cumulative all-time cost column, joined from stats by the key's account.

The stats log stays bounded while the accounting survives: once stats.jsonl
exceeds max_file_mb (default 16, 0 disables), records older than the
retention window fold into cumulative per-account totals in a small sidecar
file (tmp+rename on both) and leave the log. alltime = folded + in-file, a
record is never counted twice, verified end-to-end on synthetic data
(1.2 MB → 301 KB, totals identical before/after compaction and restarts).

Routing: a task rule can now PIN the complexity tier —
`[routing.tasks.legal] models=[...] tier="high"` (old plain-array rules parse
unchanged). The pinned tier replaces the router's verdict before the
escalation check and reports itself as route_source "router+task-rule@high".
The Routing page grows a per-task «Complexity» selector (Auto/low/medium/
high); verified live: a code prompt with a pinned high went
router+task-rule@high → the expensive model.

13 new strings in all 7 languages; docs/ROUTING(.ru) updated.
This commit is contained in:
infosave2007
2026-08-08 08:42:11 +03:00
parent ef28a6633d
commit 95e560dc72
18 changed files with 441 additions and 50 deletions
+13 -6
View File
@@ -232,15 +232,22 @@ impl Pipeline {
match live.router.route(&text, prof).await {
Ok(Some(dec)) => {
let src = dec.source.clone();
let (cands, task_rule) = live
let mut dec = dec;
let (cands, task_rule, forced) = live
.routing
.candidates_for(&dec.task_label, &dec.complexity_tier);
// surface which rule chose the head of the chain
let src = if task_rule {
format!("{src}+task-rule")
} else {
src
// surface which rule chose the head of the chain,
// and when the rule pinned the complexity —
// "…+task-rule@high" — reflect it in the
// decision so headers/stats tell the truth
let src = match (task_rule, &forced) {
(true, Some(tier)) => format!("{src}+task-rule@{tier}"),
(true, None) => format!("{src}+task-rule"),
_ => src,
};
if let Some(tier) = forced {
dec.complexity_tier = tier;
}
(dec, src, cands)
}
Ok(None) | Err(_) => {