diff --git a/apps/client/public/locales/en-US/translation.json b/apps/client/public/locales/en-US/translation.json index 971cbc11..ad884ddb 100644 --- a/apps/client/public/locales/en-US/translation.json +++ b/apps/client/public/locales/en-US/translation.json @@ -1169,8 +1169,9 @@ "Pick an agent role whose persona the public assistant adopts. The safety rules always still apply.": "Pick an agent role whose persona the public assistant adopts. The safety rules always still apply.", "Built-in assistant persona": "Built-in assistant persona", "Minimize": "Minimize", - "Current context size": "Current context size", - "Tokens generated this turn": "Tokens generated this turn", + "Context size / model limit": "Context size / model limit", + "Context window (tokens)": "Context window (tokens)", + "Shown as used / total in the chat header. Leave empty to hide the limit.": "Shown as used / total in the chat header. Leave empty to hide the limit.", "AI agent": "AI agent", "Take a look at the current document": "Take a look at the current document", "AI agent is typing…": "AI agent is typing…", diff --git a/apps/client/public/locales/ru-RU/translation.json b/apps/client/public/locales/ru-RU/translation.json index 349dc227..c6cb7c6a 100644 --- a/apps/client/public/locales/ru-RU/translation.json +++ b/apps/client/public/locales/ru-RU/translation.json @@ -704,8 +704,9 @@ "Ask the AI agent…": "Спросите AI-агента…", "Copy chat": "Копировать чат", "Created successfully": "Успешно создано", - "Current context size": "Текущий размер контекста", - "Tokens generated this turn": "Токенов сгенерировано за ход", + "Context size / model limit": "Размер контекста / лимит модели", + "Context window (tokens)": "Окно контекста (токены)", + "Shown as used / total in the chat header. Leave empty to hide the limit.": "Показывается в шапке чата как использовано / всего. Пусто — лимит скрыт.", "Delete this chat?": "Удалить этот чат?", "Deleted successfully": "Успешно удалено", "Edited by AI agent on behalf of {{name}}": "Отредактировано AI-агентом от имени {{name}}", diff --git a/apps/client/src/features/ai-chat/components/ai-chat-window.tsx b/apps/client/src/features/ai-chat/components/ai-chat-window.tsx index de0b9923..abd38952 100644 --- a/apps/client/src/features/ai-chat/components/ai-chat-window.tsx +++ b/apps/client/src/features/ai-chat/components/ai-chat-window.tsx @@ -161,12 +161,6 @@ export default function AiChatWindow() { const { data: messageRows, isLoading: messagesLoading } = useAiChatMessagesQuery(activeChatId ?? undefined); - // Live turn-token total (reasoning + output) for the in-flight turn, pushed up - // (THROTTLED to ~8 Hz inside ChatThread) so the header badge ticks mid-stream. - // `null` means no turn is in flight -> the badge falls back to the persisted - // context size below. - const [liveTurnTokens, setLiveTurnTokens] = useState(null); - // The page the user is currently viewing. AiChatWindow lives in a pathless // parent layout route, so useParams() can't see :pageSlug. Match the full // pathname against the authenticated page route instead so "the current page" @@ -306,6 +300,25 @@ export default function AiChatWindow() { return 0; }, [activeChatId, messageRows]); + // The model's max context window (badge denominator). Read the most recent row + // carrying `maxContextTokens` (set alongside contextTokens on a completed + // turn); 0 when no row has it (older rows, or no admin-configured limit) — the + // badge then shows just the current size with no denominator. + const maxContextTokens = useMemo(() => { + if (!activeChatId || !messageRows) return 0; + for (let i = messageRows.length - 1; i >= 0; i--) { + const meta = messageRows[i].metadata; + if (!meta) continue; + if ( + typeof meta.maxContextTokens === "number" && + meta.maxContextTokens > 0 + ) { + return meta.maxContextTokens; + } + } + return 0; + }, [activeChatId, messageRows]); + // On (re)open, settle the geometry before paint (useLayoutEffect → no // first-frame jump): compute an initial top-right placement the first time, // and re-clamp an existing geometry to the current viewport on later opens @@ -495,20 +508,17 @@ export default function AiChatWindow() { )}
- {/* While a turn streams, show the LIVE turn-token count (ticks ~8 Hz); - once it finishes, fall back to the persisted context size. Require - > 0 so the very first emit (an empty tail message, count 0) does not - flash a "0" badge before any token streams in (#151 review). */} - {liveTurnTokens !== null && liveTurnTokens > 0 ? ( - - - {formatTokens(liveTurnTokens)} - - - ) : contextTokens > 0 ? ( - + {/* Always show the persisted "current / max" context. The denominator + (the admin-configured model limit) is appended only when known; + not clamped when current > max (shown as-is, e.g. "210k / 200k"). + Hidden entirely until a turn has recorded a context figure. */} + {contextTokens > 0 ? ( + {formatTokens(contextTokens)} + {maxContextTokens > 0 + ? ` / ${formatTokens(maxContextTokens)}` + : ""} ) : null} @@ -634,7 +644,6 @@ export default function AiChatWindow() { assistantName={currentRole?.name} onTurnFinished={onTurnFinished} onServerChatId={onServerChatId} - onLiveTurnTokens={setLiveTurnTokens} /> )}
diff --git a/apps/client/src/features/ai-chat/components/chat-thread.tsx b/apps/client/src/features/ai-chat/components/chat-thread.tsx index c906a940..14f9a2ad 100644 --- a/apps/client/src/features/ai-chat/components/chat-thread.tsx +++ b/apps/client/src/features/ai-chat/components/chat-thread.tsx @@ -20,7 +20,6 @@ import { } from "@/features/ai-chat/utils/role-launch.ts"; import { describeChatError } from "@/features/ai-chat/utils/error-message.ts"; import { extractServerChatId } from "@/features/ai-chat/utils/adopt-chat-id.ts"; -import { liveTurnTokens } from "@/features/ai-chat/utils/count-stream-tokens.ts"; import { dequeue, enqueueMessage, @@ -67,12 +66,6 @@ interface ChatThreadProps { * Copy/export button available mid-stream). Distinct from onTurnFinished, * which fires only at the terminal outcome. */ onServerChatId?: (serverChatId?: string) => void; - /** Reports the live turn-token total (reasoning + output) for the in-flight - * turn so the parent can show a header badge that ticks mid-stream. THROTTLED - * here (~8 Hz) so the parent re-renders a handful of times a second, not on - * every streamed delta. Called with `null` when no turn is in flight (the - * parent then reverts the badge to the persisted context size). */ - onLiveTurnTokens?: (tokens: number | null) => void; } /** @@ -117,7 +110,6 @@ export default function ChatThread({ assistantName, onTurnFinished, onServerChatId, - onLiveTurnTokens, }: ChatThreadProps) { const { t } = useTranslation(); @@ -328,53 +320,6 @@ export default function ChatThread({ // the SAME on-screen banner text can be mirrored into the export (issue #160). const errorView = error ? describeChatError(error.message ?? "", t) : null; - // Report the live turn-token total to the parent header badge, THROTTLED to - // ~8 Hz so the parent re-renders a few times a second instead of on every - // streamed delta. The tail assistant message's reasoning+output (estimate while - // streaming, authoritative once a step reports usage) is the live figure. When - // the turn ends we emit a final exact value, then `null` so the parent reverts - // the badge to the persisted context size. - const lastEmitRef = useRef(0); - const emitTimerRef = useRef | null>(null); - useEffect(() => { - if (!onLiveTurnTokens) return; - if (!isStreaming) { - // Turn ended (or never started): clear any pending throttle and revert. - if (emitTimerRef.current) { - clearTimeout(emitTimerRef.current); - emitTimerRef.current = null; - } - lastEmitRef.current = 0; - onLiveTurnTokens(null); - return; - } - const tail = messages[messages.length - 1]; - const live = tail?.role === "assistant" ? liveTurnTokens(tail) : null; - const total = live ? live.reasoning + live.output : 0; - const now = Date.now(); - const MIN_INTERVAL = 120; // ms (~8 Hz) - const elapsed = now - lastEmitRef.current; - if (elapsed >= MIN_INTERVAL) { - lastEmitRef.current = now; - onLiveTurnTokens(total); - } else if (!emitTimerRef.current) { - // Schedule a trailing emit so the FINAL value of a burst is not dropped. - emitTimerRef.current = setTimeout(() => { - emitTimerRef.current = null; - lastEmitRef.current = Date.now(); - onLiveTurnTokens(total); - }, MIN_INTERVAL - elapsed); - } - }, [messages, isStreaming, onLiveTurnTokens]); - - // Clear any pending throttle timer on unmount (chat switch via `key`) so a - // trailing emit can't fire into a torn-down thread's parent. - useEffect(() => { - return () => { - if (emitTimerRef.current) clearTimeout(emitTimerRef.current); - }; - }, []); - // A role was picked with autoStart=false: the role is bound but NOTHING was // sent, so chatId stays null and the empty state would keep showing the cards. // This flag hides the cards and reveals the composer (with the role indicated) diff --git a/apps/client/src/features/ai-chat/types/ai-chat.types.ts b/apps/client/src/features/ai-chat/types/ai-chat.types.ts index af595917..22a51058 100644 --- a/apps/client/src/features/ai-chat/types/ai-chat.types.ts +++ b/apps/client/src/features/ai-chat/types/ai-chat.types.ts @@ -116,6 +116,9 @@ export interface IAiChatMessageRow { // turn. Distinct from `usage` (legacy cumulative totalUsage). Shown in the // floating window's header badge. contextTokens?: number; + // The model's max context window (denominator for the header badge); set + // alongside contextTokens on a completed turn; absent on older rows. + maxContextTokens?: number; // Set on an assistant row whose turn ended in a provider/stream error; the // raw provider error text (e.g. "402: ...") for inline display in the thread. error?: string; diff --git a/apps/client/src/features/ai-chat/utils/count-stream-tokens.test.ts b/apps/client/src/features/ai-chat/utils/count-stream-tokens.test.ts index 3e650f0d..6b00fbc4 100644 --- a/apps/client/src/features/ai-chat/utils/count-stream-tokens.test.ts +++ b/apps/client/src/features/ai-chat/utils/count-stream-tokens.test.ts @@ -1,17 +1,5 @@ import { describe, expect, it } from "vitest"; -import type { UIMessage } from "@ai-sdk/react"; -import { - estimateTokens, - liveTurnTokens, -} from "@/features/ai-chat/utils/count-stream-tokens.ts"; - -const msg = (parts: unknown[], metadata?: unknown): UIMessage => - ({ - id: Math.random().toString(), - role: "assistant", - parts, - metadata, - }) as UIMessage; +import { estimateTokens } from "@/features/ai-chat/utils/count-stream-tokens.ts"; describe("estimateTokens", () => { it("returns 0 for the empty string", () => { @@ -25,147 +13,3 @@ describe("estimateTokens", () => { expect(estimateTokens("12345678")).toBe(2); }); }); - -describe("liveTurnTokens — estimate path", () => { - it("is all zeros for an undefined message", () => { - expect(liveTurnTokens(undefined)).toEqual({ - reasoning: 0, - output: 0, - authoritative: false, - }); - }); - - it("is all zeros for a parts-less message", () => { - expect(liveTurnTokens({ id: "x", role: "assistant" } as UIMessage)).toEqual({ - reasoning: 0, - output: 0, - authoritative: false, - }); - }); - - it("estimates output from text parts", () => { - // 8 chars -> 2 tokens. - const r = liveTurnTokens(msg([{ type: "text", text: "12345678" }])); - expect(r).toEqual({ reasoning: 0, output: 2, authoritative: false }); - }); - - it("estimates reasoning from reasoning parts (kept separate from output)", () => { - const r = liveTurnTokens( - msg([ - { type: "reasoning", text: "12345678" }, - { type: "text", text: "abcd" }, - ]), - ); - expect(r).toEqual({ reasoning: 2, output: 1, authoritative: false }); - }); - - it("accumulates across multiple text + reasoning parts (multi-step)", () => { - const r = liveTurnTokens( - msg([ - { type: "reasoning", text: "abcd" }, // 1 - { type: "text", text: "abcd" }, // 1 - { type: "tool-getPage", state: "output-available" }, // ignored - { type: "reasoning", text: "abcd" }, // 1 - { type: "text", text: "abcdefgh" }, // 2 - ]), - ); - expect(r).toEqual({ reasoning: 2, output: 3, authoritative: false }); - }); - - it("ignores non text/reasoning parts (tools, step-start)", () => { - const r = liveTurnTokens( - msg([ - { type: "step-start" }, - { type: "tool-getPage", state: "input-available" }, - ]), - ); - expect(r).toEqual({ reasoning: 0, output: 0, authoritative: false }); - }); -}); - -describe("liveTurnTokens — authoritative path", () => { - it("returns authoritative usage verbatim, splitting reasoning out of output", () => { - // outputTokens INCLUDES reasoning in the AI SDK shape -> answer = 100 - 30. - const r = liveTurnTokens( - msg([{ type: "text", text: "estimate would be tiny" }], { - usage: { inputTokens: 500, outputTokens: 100, reasoningTokens: 30 }, - }), - ); - expect(r).toEqual({ reasoning: 30, output: 70, authoritative: true }); - }); - - it("treats missing reasoningTokens as 0 and keeps full output", () => { - const r = liveTurnTokens( - msg([{ type: "text", text: "x" }], { - usage: { inputTokens: 10, outputTokens: 42 }, - }), - ); - expect(r).toEqual({ reasoning: 0, output: 42, authoritative: true }); - }); - - it("never returns a negative output when reasoning exceeds reported output", () => { - const r = liveTurnTokens( - msg([], { usage: { outputTokens: 10, reasoningTokens: 40 } }), - ); - expect(r).toEqual({ reasoning: 40, output: 0, authoritative: true }); - }); - - it("falls back to the estimate when metadata has no usage object", () => { - const r = liveTurnTokens( - msg([{ type: "text", text: "abcd" }], { chatId: "c1" }), - ); - expect(r).toEqual({ reasoning: 0, output: 1, authoritative: false }); - }); -}); - -describe("liveTurnTokens — combined authoritative + estimate (#163)", () => { - it("ticks the in-flight step above the completed-steps authoritative base", () => { - // The authoritative usage is the sum over COMPLETED steps (step 1). The - // CURRENT step is streaming and its text is NOT in `usage` yet, but it IS in - // the parts -> the running estimate must push the live figure above the base - // so the badge keeps growing between step boundaries. - const longText = "x".repeat(800); // 800 chars -> 200 est output tokens - const r = liveTurnTokens( - msg([{ type: "text", text: longText }], { - usage: { inputTokens: 500, outputTokens: 40 }, // step-1 base: 40 output - }), - ); - // max(authOutput=40, estOutput=200) = 200 -> the counter ticks, not frozen. - expect(r.output).toBe(200); - expect(r.authoritative).toBe(true); - }); - - it("ticks reasoning of the in-flight step above the authoritative reasoning base", () => { - const longReasoning = "r".repeat(400); // 400 chars -> 100 est reasoning - const r = liveTurnTokens( - msg([{ type: "reasoning", text: longReasoning }], { - usage: { inputTokens: 100, outputTokens: 20, reasoningTokens: 20 }, - }), - ); - // reasoning: max(20, 100) = 100 ; output: max(max(0,20-20)=0, 0) = 0. - expect(r.reasoning).toBe(100); - expect(r.output).toBe(0); - expect(r.authoritative).toBe(true); - }); - - it("snaps to the authoritative figure once it exceeds the rough estimate", () => { - // Short on-screen text (estimate tiny) but a large authoritative output: - // the exact figure wins at the boundary (the counter never under-reports). - const r = liveTurnTokens( - msg([{ type: "text", text: "abcd" }], { - usage: { inputTokens: 10, outputTokens: 5000 }, - }), - ); - expect(r.output).toBe(5000); - }); - - it("is monotonic: max never drops below the authoritative base when the estimate is smaller", () => { - // Mirrors the legacy 'verbatim' tests: estimate < authoritative -> unchanged. - const r = liveTurnTokens( - msg([{ type: "text", text: "tiny" }], { - usage: { inputTokens: 500, outputTokens: 100, reasoningTokens: 30 }, - }), - ); - expect(r).toEqual({ reasoning: 30, output: 70, authoritative: true }); - }); -}); diff --git a/apps/client/src/features/ai-chat/utils/count-stream-tokens.ts b/apps/client/src/features/ai-chat/utils/count-stream-tokens.ts index 9a900996..aaf99599 100644 --- a/apps/client/src/features/ai-chat/utils/count-stream-tokens.ts +++ b/apps/client/src/features/ai-chat/utils/count-stream-tokens.ts @@ -1,18 +1,11 @@ -import type { UIMessage } from "@ai-sdk/react"; - /** - * Live token counting for a streaming AI-chat turn — split into REASONING - * (thinking) and OUTPUT (answer) tokens, mirroring how Claude Code shows - * `Thinking… · 60 tokens` next to its thinking indicator. + * Rough client-side token estimation for AI-chat UI affordances. * - * No provider streams exact per-token usage mid-stream, so the live number is a - * CLIENT ESTIMATE (chars/≈4 heuristic) that is reconciled to AUTHORITATIVE usage - * once the server attaches it on a step/turn boundary (see the server's - * `chatStreamMetadata` + the client's read of `message.metadata.usage`). When - * authoritative usage is present we return it verbatim (the number "jumps to - * exact"); otherwise we return the running estimate. Pure + unit-testable: it - * never runs a real BPE tokenizer (that would be O(n²) on the hot path, bloat the - * bundle, and be wrong for Gemini/Ollama anyway). + * No provider streams exact per-token usage mid-stream, so any in-flight figure + * is a CLIENT ESTIMATE (chars/≈4 heuristic). Pure + unit-testable: it never runs + * a real BPE tokenizer (that would be O(n²) on the hot path, bloat the bundle, + * and be wrong for Gemini/Ollama anyway). Used by the in-body reasoning counter + * ("Thinking · N tokens"). */ /** @@ -24,90 +17,3 @@ export function estimateTokens(text: string): number { if (!text) return 0; return Math.ceil(text.length / 4); } - -/** Authoritative per-step/turn usage the server attaches to message metadata. */ -export interface AuthoritativeUsage { - inputTokens?: number; - outputTokens?: number; - totalTokens?: number; - reasoningTokens?: number; -} - -/** Live token split for a turn's tail (streaming) assistant message. */ -export interface LiveTurnTokens { - /** Thinking/reasoning tokens (estimate, or authoritative when available). */ - reasoning: number; - /** Answer/output tokens (estimate, or authoritative when available). */ - output: number; - /** True when the numbers come from authoritative server usage, not estimate. */ - authoritative: boolean; -} - -/** Read the authoritative usage off a UIMessage's metadata, if the server set it. */ -function metadataUsage(message: UIMessage): AuthoritativeUsage | undefined { - const meta = message?.metadata as - | { usage?: AuthoritativeUsage } - | undefined; - const usage = meta?.usage; - if (!usage || typeof usage !== "object") return undefined; - return usage; -} - -/** - * Token split for the given (streaming) assistant message. - * - * COMBINES the authoritative server usage with the running text estimate so the - * counter ticks in real time AND lands exact. The server only attaches - * `metadata.usage` at a step/turn boundary (`finish-step`/`finish`) and it is - * CUMULATIVE over COMPLETED steps — it does NOT yet include the in-flight step. - * So a multi-step turn that returned the authoritative figure verbatim would - * FREEZE between boundaries and jump in steps (issue #163). - * - * Instead we always compute the running ESTIMATE (chars/≈4 over the message's - * `reasoning`/`text` parts, which grows on every streamed delta) and take the - * per-component MAX of the authoritative base and the estimate: - * - between boundaries the estimate of the in-flight step ticks the number up; - * - at a boundary the authoritative figure snaps it to exact; - * - because the server's usage is cumulative and we only ever take the max, the - * number is MONOTONIC — it never drops. - * - * Providers that don't stream reasoning text still surface a reasoning count once - * the authoritative usage arrives (`max(reasoningTokens, 0)`); on the pure - * estimate path (no usage yet) such a turn shows `reasoning: 0` until then. - */ -export function liveTurnTokens(message: UIMessage | undefined): LiveTurnTokens { - if (!message) return { reasoning: 0, output: 0, authoritative: false }; - - // Running ESTIMATE over every reasoning/text part — grows on each delta. This - // includes the IN-FLIGHT step, which the authoritative usage does not cover yet. - let estReasoning = 0; - let estOutput = 0; - for (const part of message.parts ?? []) { - if (part.type === "reasoning") { - estReasoning += estimateTokens((part as { text?: string }).text ?? ""); - } else if (part.type === "text") { - estOutput += estimateTokens((part as { text?: string }).text ?? ""); - } - } - - const usage = metadataUsage(message); - if (!usage) { - // No authoritative usage streamed yet: the estimate IS the live figure. - return { reasoning: estReasoning, output: estOutput, authoritative: false }; - } - - // Authoritative sum over COMPLETED steps. `outputTokens` already INCLUDES - // reasoning in the AI SDK usage shape, so subtract it out for the "answer" - // figure (never go negative if a provider reports them inconsistently). - const authReasoning = usage.reasoningTokens ?? 0; - const authOutput = Math.max(0, (usage.outputTokens ?? 0) - authReasoning); - - // Per-component max: the in-flight step's estimate ticks above the completed- - // steps base between boundaries, and the authoritative figure wins once it - // exceeds the (rough) estimate at the next boundary. Monotonic by construction. - return { - reasoning: Math.max(authReasoning, estReasoning), - output: Math.max(authOutput, estOutput), - authoritative: true, - }; -} diff --git a/apps/client/src/features/workspace/components/settings/components/ai-provider-settings.tsx b/apps/client/src/features/workspace/components/settings/components/ai-provider-settings.tsx index 08348756..811c2610 100644 --- a/apps/client/src/features/workspace/components/settings/components/ai-provider-settings.tsx +++ b/apps/client/src/features/workspace/components/settings/components/ai-provider-settings.tsx @@ -7,6 +7,7 @@ import { Button, Group, Modal, + NumberInput, Paper, PasswordInput, Select, @@ -83,6 +84,9 @@ const STT_LANGUAGE_OPTIONS: { value: string; label: string }[] = [ // (empty means "leave unchanged" unless explicitly cleared). const formSchema = z.object({ chatModel: z.string(), + // Max context window in tokens shown in the chat header badge. A number, or "" + // when the NumberInput is empty (no limit). + chatContextWindow: z.union([z.number(), z.literal("")]), // Chat provider implementation (reasoning surfacing). Default openai-compatible. chatApiStyle: z.enum(["openai-compatible", "openai"]), // Cheap model id for the anonymous public-share assistant; empty = use chatModel. @@ -311,6 +315,7 @@ export default function AiProviderSettings() { validate: zod4Resolver(formSchema), initialValues: { chatModel: "", + chatContextWindow: "", chatApiStyle: "openai-compatible" as ChatApiStyle, publicShareChatModel: "", publicShareAssistantRoleId: "", @@ -334,6 +339,7 @@ export default function AiProviderSettings() { if (!settings) return; form.setValues({ chatModel: settings.chatModel ?? "", + chatContextWindow: settings.chatContextWindow ?? "", chatApiStyle: settings.chatApiStyle ?? "openai-compatible", publicShareChatModel: settings.publicShareChatModel ?? "", publicShareAssistantRoleId: settings.publicShareAssistantRoleId ?? "", @@ -364,6 +370,12 @@ export default function AiProviderSettings() { // Everything is OpenAI-compatible. driver: "openai", chatModel: values.chatModel, + // Max context window for the chat header badge; empty NumberInput ("") → + // 0, which clears the limit server-side (no denominator shown). + chatContextWindow: + typeof values.chatContextWindow === "number" + ? values.chatContextWindow + : 0, chatApiStyle: values.chatApiStyle, // Cheap model id for the anonymous public-share assistant; empty falls // back to chatModel server-side. @@ -767,6 +779,18 @@ export default function AiProviderSettings() { {t("Resolves to {{url}}", { url: chatResolved })} + +