flagon-io/g1t

Pick any line to see why it is the way it is: the commit, the pull request and issue it came from, and what the agent was thinking.

Mission control shows model usage, yours and the workspace's: tokens, cost, active days, cache share, each day, and the mix3d ago		1	/**
		2	* What the proxy tells billing about one answer: its tokens, under the
		3	* run's session and the person it is for, for usage views. Billing still
		4	* prices runs from AI Gateway, not from these.
		5	*/
		6	import type { ModelUpstream } from "@g1t/contracts";
		7
		8	import type { Tokens } from "./usage";
		9
		10	export type TokenReport = {
		11	workspace: string;
		12	session: string;
		13	person: string | null;
		14	model: string;
Merge branch 'model-routing'2d ago		15	tier: "small" | "large" | "frontier" | null;
Mission control shows model usage, yours and the workspace's: tokens, cost, active days, cache share, each day, and the mix3d ago		16	input: number;
		17	output: number;
		18	cacheRead: number;
		19	cacheWrite: number;
		20	};
		21
		22	/**
		23	* Whether a request's answer is a model's answer, and so used tokens.
		24	* Counting tokens is a question about a request, not an answer.
		25	*/
		26	export function isAnswer(path: string): boolean {
		27	return /^\/v1\/messages\/?(\?|$)/.test(path);
		28	}
		29
		30	/**
Merge platform pause and the hourly usage watcher: staff can pause compute, schedules, indexing or renders for everyone, the watcher emails on a breach and is never blind quietly, and the models proxy holds each run to its cap (billing 0051, integrations 0006)1d ago		31	* Whether a run's token may make a request: a model's answer, counting a
		32	* request's tokens, or listing models. Nothing else, so no other route
		33	* (a batch of messages, say) spends past the run's cap uncounted.
		34	*/
		35	export function runMayCall(path: string, method: string): boolean {
		36	const route = path.split("?")[0];
		37	if (isAnswer(route)) return true;
		38	if (/^\/v1\/messages\/count_tokens\/?$/.test(route)) return true;
		39	return (method === "GET" || method === "HEAD") && /^\/v1\/models(\/[^/]+)?\/?$/.test(route);
		40	}
		41
		42	/**
Mission control shows model usage, yours and the workspace's: tokens, cost, active days, cache share, each day, and the mix3d ago		43	* The report for one answer, or null when it used nothing or its session
		44	* has no id to count it under. The model is the run's when its route names
		45	* one, else the one that answered.
		46	*/
		47	export function tokenReport(upstream: ModelUpstream, answeredBy: string | null, tokens: Tokens): TokenReport | null {
		48	const used = tokens.input + tokens.output + tokens.cacheRead + tokens.cacheWrite;
		49	if (used === 0 || !upstream.session) return null;
		50	return {
		51	workspace: upstream.workspace,
		52	session: upstream.session,
		53	person: upstream.requestedBy ?? null,
		54	model: upstream.model ?? answeredBy ?? "unknown",
		55	tier: upstream.tier ?? null,
		56	input: tokens.input,
		57	output: tokens.output,
		58	cacheRead: tokens.cacheRead,
		59	cacheWrite: tokens.cacheWrite,
		60	};
		61	}

This file's history is long; its oldest lines are credited to the oldest commit read.