fix: report AI usage before tools run and price self usage consistently

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

frontend/src/lib/components/UserSettings.svelte

@@ -10,8 +10,7 @@
 	import UserInfoSettings from './settings/UserInfoSettings.svelte'
 	import AIUserSettings from './settings/AIUserSettings.svelte'
 	import AiUsagePanel from './workspaceSettings/AiUsagePanel.svelte'
-	import { copilotInfo } from '$lib/aiStore'
-	import { workspaceStore } from '$lib/stores'
+	import { copilotInfo, copilotWorkspace } from '$lib/aiStore'
 	import {
 		getDarkModeVariant,
 		setDarkModeVariant,
@@ -108,9 +107,13 @@
 						<AIUserSettings />
 					</div>
 				</div>
-				{#if $workspaceStore}
+				<!-- Keyed on the workspace `copilotInfo` reflects, not on `$workspaceStore`:
+				     a session acting on another workspace loads that workspace's AI config
+				     while navigation stays put, and pricing usage from one workspace with
+				     another's rates would silently misstate it. -->
+				{#if $copilotWorkspace}
 					<AiUsagePanel
-						workspace={$workspaceStore}
+						workspace={$copilotWorkspace}
 						modelPricing={$copilotInfo.modelPricing ?? {}}
 						scope="self"
 					/>

frontend/src/lib/components/copilot/chat/anthropic.ts

@@ -193,7 +193,7 @@ export async function parseAnthropicCompletion(
 	tools: Tool<any>[],
 	helpers: any,
 	abortController?: AbortController,
-	options?: { workspace?: string }
+	options?: { workspace?: string; onTokenUsage?: (usage: ChatTokenUsage) => void }
 ): Promise<ParsedCompletionResult> {
 	let toolCallsToProcess: ChatCompletionMessageFunctionToolCall[] = []
 	let error = null
@@ -415,6 +415,7 @@ export async function parseAnthropicCompletion(
 
 	const finalMessage = await completion.finalMessage()
 	const tokenUsage = anthropicUsageToChatTokenUsage(finalMessage.usage)
+	options?.onTokenUsage?.(tokenUsage)
 
 	// Process tool calls if any
 	if (toolCallsToProcess.length > 0) {

frontend/src/lib/components/copilot/chat/chatLoop.ts

@@ -338,11 +338,18 @@ export async function runChatLoop(config: ChatLoopConfig): Promise<ChatLoopResul
 	// actually served it rather than to whatever is selected when the loop ends.
 	let iterationModel: ReasoningProviderModel | undefined
 
-	const trackUsage = (usage: ChatTokenUsage | null | undefined) => {
-		tokenUsage = addChatTokenUsage(tokenUsage, usage)
+	// Reported as the provider's usage arrives, not when the parser returns: a parser
+	// waits on tool execution, which can wait on a person, and a tab closed in that
+	// gap would drop a response that was already billed. Accounting for the turn's
+	// own totals stays on the return path, where every parser reports uniformly.
+	const reportUsage = (usage: ChatTokenUsage | null | undefined) => {
 		if (usage && iterationModel) {
 			config.onUsage?.(usage, iterationModel)
 		}
+	}
+
+	const trackUsage = (usage: ChatTokenUsage | null | undefined) => {
+		tokenUsage = addChatTokenUsage(tokenUsage, usage)
 		// Some providers/paths report no usage (prompt 0); keep the last real one.
 		if (usage && usage.prompt > 0) {
 			lastIterationUsage = usage
@@ -399,7 +406,14 @@ export async function runChatLoop(config: ChatLoopConfig): Promise<ChatLoopResul
 			...(pendingUserMessage ? [pendingUserMessage] : [])
 		]
 		const toolDefs = tools.map((t) => t.def)
-		const parseOptions = { workspace, provider: modelProvider.provider }
+		// Report each response as its usage arrives rather than after the parser
+		// returns: a parser waits on tool execution, which can wait on a person, and
+		// a tab closed in that gap would drop a response the provider already billed.
+		const parseOptions = {
+			workspace,
+			provider: modelProvider.provider,
+			onTokenUsage: reportUsage
+		}
 
 		if (isOpenAI) {
 			const reasoningSummaryCacheKey = getReasoningSummaryCacheKey(workspace, modelProvider)

frontend/src/lib/components/copilot/chat/openai-responses.ts

@@ -392,7 +392,7 @@ export async function parseOpenAIResponsesCompletion(
 	addedMessages: ChatCompletionMessageParam[],
 	tools: Tool<any>[],
 	helpers: any,
-	options?: { workspace?: string }
+	options?: { workspace?: string; onTokenUsage?: (usage: ChatTokenUsage) => void }
 ): Promise<ParsedCompletionResult> {
 	let toolCallsToProcess: ChatCompletionMessageFunctionToolCall[] = []
 	let error: OpenAIError | ResponseErrorEvent | null = null
@@ -566,6 +566,7 @@ export async function parseOpenAIResponsesCompletion(
 
 	const finalResponse = await runner.finalResponse()
 	const tokenUsage = openAIResponsesUsageToChatTokenUsage(finalResponse.usage)
+	options?.onTokenUsage?.(tokenUsage)
 
 	for (const item of finalResponse.output ?? []) {
 		if (item.type === 'web_search_call' && !surfacedWebSearchCalls.has(item.id)) {

frontend/src/lib/components/copilot/lib.ts

@@ -1162,7 +1162,11 @@ export async function parseOpenAICompletion(
 	tools: Tool<any>[],
 	helpers: any,
 	_abortController?: AbortController, // unused, for signature compatibility with parseAnthropicCompletion
-	options?: { workspace?: string; provider?: string }
+	options?: {
+		workspace?: string
+		provider?: string
+		onTokenUsage?: (usage: ChatTokenUsage) => void
+	}
 ): Promise<{ shouldContinue: boolean; tokenUsage: ChatTokenUsage }> {
 	const finalToolCalls: Record<number, ChatCompletionChunk.Choice.Delta.ToolCall> = {}
 	// The tool call currently receiving argument deltas; when the stream moves on
@@ -1312,6 +1316,7 @@ export async function parseOpenAICompletion(
 
 	callbacks.onMessageEnd()
 
+	options?.onTokenUsage?.(tokenUsage)
 	// Stream over: every parsed call is queued until its turn in processToolCall.
 	for (const toolCall of Object.values(finalToolCalls)) {
 		if (toolCall.id) {

frontend/src/lib/components/copilot/modelPricing.ts

@@ -96,8 +96,8 @@ const MODEL_PRICES: [name: string, price: PriceEntry | null][] = [
 	// one, so the write rate never applies. The -mini/-nano entries must precede
 	// the family entry, which would otherwise claim them.
 	// Revisions past gpt-5 are priced separately by OpenAI and are not tracked here.
-	// `strictVariants` does not cover these: a version bump is digits, not a name
-	// segment, so `gpt-5-6` would otherwise still match `gpt-5`.
+	// The matcher's revision guard already keeps them off the family rate; these
+	// entries stay so a revision the guard admits still resolves to no rate.
 	['gpt-5.6', null],
 	['gpt-5.5', null],
 	['gpt-5.4', null],