fix: honest costs in streams, oracle-sized timeouts, history & log cleanup

Cost showed $0 for every streamed request: the X-Cortiq-Cost-USD header is
written before generation, when the cost cannot be known. The gateway now
ships the final number in a closing SSE event (`cortiq_cost_usd`, alongside
the token estimate when the provider sent no usage), and the console prefers
it over the header. Money renders with 4 decimals, the last two in a smaller
font — $0.0006 stays readable instead of collapsing to $0.

Timeouts, both ends: the router default was 800 ms, silently degrading every
prompt the hosted router escalates to its oracle (~10 s) — now 15 s. Provider
clients had NO timeout at all (a dead OpenRouter host hung requests forever) —
now a 10 s connect timeout, with no overall cap so long generations and
streams are never cut.

Benchmark history: per-run × and a Clear-all button. Logs view: a clear
button backed by DELETE /admin/api/logs.

This commit is contained in:

infosave2007

2026-08-07 19:15:27 +03:00

parent ec92bdddb7

commit 54b73f1365

20 changed files with 120 additions and 38 deletions

									
										web/js/i18n/de.js
									
Vendored

		+1
		
												View File
												
				@@ -601,4 +601,5 @@ export default {

				  "bm.liveRunning": "läuft…",

				  "bm.spent": "ausgegeben",

				  "bm.verdict": "🏁 Fertig: Antworten {p}, ausgegeben {s}",

				  "bm.clearHistory": "Alle löschen",

				};