@eddyskywalker/dsh-chatgpt-subscription 0.37.0 → 0.38.1

package/lib/client.js

@@ -3691,7 +3691,7 @@ window.__ModuleLoader__.load({
 		* exactly one and rejects the others, so the label states which one this model
 		* actually uses.
 		*/
-		function wireLabel(wire, t) {
+		function wireLabel$1(wire, t) {
 			if (wire === "anthropic") return t.wireAnthropic;
 			if (wire === "responses") return t.wireResponses;
 			return t.wireOpenai;
@@ -4120,7 +4120,7 @@ window.__ModuleLoader__.load({
 								items: (status?.models ?? []).map((model) => ({
 									id: model.id,
 									name: model.name,
-									hint: wireLabel(model.wire, t),
+									hint: wireLabel$1(model.wire, t),
 									enabled: model.enabled
 								})),
 								busy: busy !== null,
@@ -4277,15 +4277,6 @@ window.__ModuleLoader__.load({
 			});
 		}
 		//#endregion
-		//#region src/shared/kimi-code-contracts.ts
-		/** Every level, in escalating order; the settings card renders exactly these. */
-		const KIMI_CODE_REASONING_EFFORTS = [
-			"low",
-			"high",
-			"max",
-			"none"
-		];
-		//#endregion
 		//#region src/client/kimi-code/locales.ts
 		const NS_KIMI_CODE = "dsh-kimi-code";
 		const zh$10 = {
@@ -4336,10 +4327,13 @@ window.__ModuleLoader__.load({
 			wireAnthropic: "Anthropic",
 			wireOpenai: "OpenAI",
 			capVideo: "视频*",
+			capThinkingOnly: "只支持思考",
+			capEfforts: "档位 {list}",
 			capDynamicTools: "动态工具",
 			capImageOnly: "仅图片",
 			capNone: "—",
 			capVideoFootnote: "* 视频输入需先由 kimi_attach_video 工具挂载（本地绝对路径或 http(s) 链接）；直接粘贴的上传路径仍只支持图片。",
+			capThinkingOnlyFootnote: "* 「只支持思考」的模型不能关闭思考：请求里带 none 会被服务端拒绝（400），所以它的档位里没有「关闭思考」。",
 			capabilitiesTitle: "模型能力",
 			capColMedia: "多模态",
 			capColTools: "动态工具",
@@ -4350,13 +4344,16 @@ window.__ModuleLoader__.load({
 			speedRegular: "标准",
 			speedHighspeed: "高速 (约 6×)",
 			quotaCost: "额度倍率",
+			quotaUnknown: "未公布",
 			minimumPlan: "所需套餐",
 			enhanced: "思考设置",
 			defaultReasoningEffort: "默认思考档位",
-			defaultReasoningEffortHint: "Kimi Code 只接受 low / high / max 三档；none 表示关闭思考。切换档位会使上下文缓存失效，建议在同一会话中保持一致。",
+			defaultReasoningEffortHint: "可用档位跟随勾选的模型自己声明的能力（一个都没勾时按 low / high / max / none 全列）；none 表示关闭思考，只对允许关闭的模型有效。切换档位会使上下文缓存失效，建议在同一会话中保持一致。",
+			effortThinkingOnlyNote: "勾选的模型里有只支持思考模式的：{models}。它们没有「关闭思考」这一档，请求关闭思考会被服务端拒绝（400），所以这里不提供。",
+			effortNotOffered: "当前勾选的模型不接受",
 			cacheTtl: "上下文缓存时长",
-			cacheTtlHint: "Kimi 按前缀自动缓存，这里选择写入时长。1h 写入约为 5m 的两倍价，只有当同一前缀会在一小时内被反复读取才划算；档位在首次写入时锁定，之后无法改写。留空表示不指定，由 Kimi 自己决定（实测有效期约 5–30 分钟）。依据回合间隔选：间隔通常短于约 30 分钟就留空或选 5 分钟；调度、等子代理这类会出现长空闲的会话选 1 小时。",
-			cacheTtlDefault: "不指定（Kimi 默认）",
+			cacheTtlHint: "Kimi 按前缀自动缓存，这里选择写入档位（只有 5m / 1h 两档）。不传时服务端按 5 分钟档写入。1h 写入单价约为 5m 的两倍，只有当同一前缀会在一小时内被反复读取才划算。档位在首次写入时锁定，之后命中按原 TTL 续期，无法改写。依据回合间隔选：间隔通常短于约 30 分钟选 5 分钟；调度、等子代理这类会出现长空闲的会话选 1 小时。",
+			cacheTtlDefault: "不传（服务端按 5 分钟档写入）",
 			cacheTtl5m: "5 分钟",
 			cacheTtl1h: "1 小时",
 			defaultEffortAuto: "使用模型默认值",
@@ -4382,6 +4379,11 @@ window.__ModuleLoader__.load({
 			cacheFresh: "新处理 tokens",
 			cacheOutput: "输出 tokens",
 			cacheRequests: "请求数",
+			cacheWrite: "缓存写入",
+			cacheWrite5m: "5 分钟档",
+			cacheWrite1h: "1 小时档",
+			cacheWriteHint: "写入是独立计费项：1h 写入单价约为 5m 的两倍，命中后会按原 TTL 续期。分档显示 0 表示服务端没有回报该档的写入数（响应头缺失就是静默），不等于该档确实没写入。",
+			unknownMetric: "暂无",
 			cacheHint: "同一会话内：系统提示与工具列表一旦变化会使缓存整体失效，因此保持工具集合稳定、把新增内容追加在末尾，命中率最高。",
 			cacheExpired: "本会话已空闲超过缓存有效期，下一轮将重新处理约 {tokens} 个 token。",
 			cacheDrift: "最近前缀状态",
@@ -4459,10 +4461,13 @@ window.__ModuleLoader__.load({
 			wireAnthropic: "Anthropic",
 			wireOpenai: "OpenAI",
 			capVideo: "Video*",
+			capThinkingOnly: "Thinking only",
+			capEfforts: "Levels {list}",
 			capDynamicTools: "Dynamic tools",
 			capImageOnly: "Images",
 			capNone: "—",
 			capVideoFootnote: "* Video input is attached with the kimi_attach_video tool (an absolute local path or an http(s) URL); the paste/upload path still accepts images only.",
+			capThinkingOnlyFootnote: "* A \"thinking only\" model cannot switch thinking off: a request carrying none is rejected by the service with HTTP 400, so \"thinking off\" is not among its levels.",
 			capabilitiesTitle: "Capabilities",
 			capColMedia: "Multimodal",
 			capColTools: "Dynamic tools",
@@ -4473,13 +4478,16 @@ window.__ModuleLoader__.load({
 			speedRegular: "Regular",
 			speedHighspeed: "HighSpeed (~6x)",
 			quotaCost: "Quota cost",
+			quotaUnknown: "Not published",
 			minimumPlan: "Required plan",
 			enhanced: "Thinking",
 			defaultReasoningEffort: "Default thinking level",
-			defaultReasoningEffortHint: "Kimi Code accepts only low / high / max; none disables thinking. Switching the level invalidates the context cache, so keep it steady within a session.",
+			defaultReasoningEffortHint: "The levels offered follow what the checked models declare (all of low / high / max / none when none is checked); none disables thinking and only applies to models that allow it. Switching the level invalidates the context cache, so keep it steady within a session.",
+			effortThinkingOnlyNote: "Some checked models think at every level: {models}. They have no \"thinking off\" — the service rejects that request with HTTP 400 — so it is not offered here.",
+			effortNotOffered: "not accepted by the checked models",
 			cacheTtl: "Context cache duration",
-			cacheTtlHint: "Kimi caches prefixes automatically; this chooses the write duration. A 1h write costs about twice a 5m one and only pays off when the same prefix is re-read within the hour. The tier is locked when first written and cannot be changed afterwards. Leave unset to send no cache field and let Kimi decide (measured lifetime is roughly 5-30 minutes). Choose by the gap between turns: leave unset or use 5 minutes when turns are normally less than about 30 minutes apart, and pick 1 hour for a session that idles for long stretches, such as dispatch work waiting on subagents.",
-			cacheTtlDefault: "Unset (Kimi default)",
+			cacheTtlHint: "Kimi caches prefixes automatically; this chooses the write tier, and there are only two (5m and 1h). Unset sends no cache field, and the service then writes at the 5-minute tier. A 1h write costs about twice a 5m one and only pays off when the same prefix is re-read within the hour. The tier is locked at the first write, and later hits renew it under that original TTL. Choose by the gap between turns: 5 minutes when turns are normally less than about 30 minutes apart, 1 hour for a session that idles for long stretches, such as dispatch work waiting on subagents.",
+			cacheTtlDefault: "Unset (service writes at the 5-minute tier)",
 			cacheTtl5m: "5 minutes",
 			cacheTtl1h: "1 hour",
 			defaultEffortAuto: "Use the model default",
@@ -4506,6 +4514,11 @@ window.__ModuleLoader__.load({
 			cacheFresh: "Fresh tokens",
 			cacheOutput: "Output tokens",
 			cacheRequests: "Requests",
+			cacheWrite: "Cache writes",
+			cacheWrite5m: "5-minute tier",
+			cacheWrite1h: "1-hour tier",
+			cacheWriteHint: "A write is billed separately: a 1h write costs about twice a 5m one, and a hit renews the entry under its original TTL. A tier showing 0 means the service did not report a write for it (a missing response header is silence), not that nothing was written there.",
+			unknownMetric: "n/a",
 			cacheHint: "Within one session: any change to the system prompt or the tool list invalidates the whole prefix cache, so keep the tool set stable and append new material at the tail for the best hit rate.",
 			cacheDrift: "Last prefix state",
 			cacheDriftFirst: "First request (cache cold)",
@@ -4541,6 +4554,95 @@ window.__ModuleLoader__.load({
 			"en-US": en$10
 		};
 		//#endregion
+		//#region src/shared/kimi-code-contracts.ts
+		/** Every level, in escalating order; the settings card renders exactly these. */
+		const KIMI_CODE_REASONING_EFFORTS = [
+			"low",
+			"high",
+			"max",
+			"none"
+		];
+		//#endregion
+		//#region src/client/kimi-code/labels.ts
+		/**
+		* Name of the request/response dialect a model is served over.
+		*
+		* @param wire - dialect the adapter reports for this model.
+		* @param t - dictionary of the card rendering it.
+		*/
+		function wireLabel(wire, t) {
+			return wire === "anthropic" ? t.wireAnthropic : t.wireOpenai;
+		}
+		/** Human label for one thinking level. */
+		function effortLabel(effort, t) {
+			switch (effort) {
+				case "low": return t.effortLow;
+				case "high": return t.effortHigh;
+				case "max": return t.effortMax;
+				case "none": return t.effortNone;
+				default: return effort;
+			}
+		}
+		/**
+		* Thinking levels one model publishes, in the order the card renders them.
+		*
+		* The ladder is read, never assumed: a model that declares no levels gets an
+		* empty list, and the picker then offers none of them rather than the generic
+		* four. `none` is dropped for a thinking-only model — the host already strips
+		* it, and filtering again is what keeps an older host, or a live catalog that
+		* says nothing about thinking, from putting "thinking off" back on a menu whose
+		* request the service answers with HTTP 400.
+		*
+		* @param model - one entry from the model directory.
+		*/
+		function effortLadder(model) {
+			const declared = model.reasoningEfforts ?? [];
+			const known = KIMI_CODE_REASONING_EFFORTS.filter((effort) => declared.includes(effort));
+			return model.thinkingType === "only" ? known.filter((effort) => effort !== "none") : known;
+		}
+		/**
+		* Whether one model may be asked to stop reasoning.
+		*
+		* Read from the model's own declaration rather than assumed: `only` is the one
+		* value that makes the question a hard no — the service answers a
+		* disabled-thinking request with HTTP 400 and names the model — while `no`
+		* describes a model that never reasons, so there is no switch to offer either.
+		* `both`, and a registry that says nothing about the id, keep the switch,
+		* because that is what this line offered before the flag existed and the
+		* service, not the card, is the authority on refusing a level.
+		*
+		* @param model - one entry from the model directory.
+		*/
+		function canDisableThinking(model) {
+			return model.thinkingType !== "only" && model.thinkingType !== "no";
+		}
+		/**
+		* Thinking levels a conversation can actually be set to.
+		*
+		* The setting is one level for the whole line, so the three thinking levels are
+		* the union of what the CHECKED models declare: a level no checked model
+		* declares would be stored and then rejected on the first turn. "Thinking off"
+		* is not one of those declared levels on most rows — it is a switch, not a
+		* ladder rung — so it is decided by {@link canDisableThinking} instead, and it
+		* disappears exactly when every checked model refuses to be switched off.
+		*
+		* With nothing checked there is no model to narrow it down and the full ladder
+		* is offered.
+		*
+		* @param models - every model in the directory, checked or not.
+		*/
+		function effortOptions(models) {
+			const enabled = models.filter((model) => model.enabled);
+			if (enabled.length === 0) return [...KIMI_CODE_REASONING_EFFORTS];
+			const declared = new Set(enabled.flatMap((model) => effortLadder(model)));
+			const switchable = enabled.some((model) => canDisableThinking(model));
+			return KIMI_CODE_REASONING_EFFORTS.filter((effort) => effort === "none" ? switchable : declared.has(effort));
+		}
+		/** Models that reason at every level, and so have no "thinking off". */
+		function thinkingOnlyModels(models) {
+			return models.filter((model) => model.thinkingType === "only");
+		}
+		//#endregion
 		//#region src/client/kimi-code/KimiModelCapabilities.tsx
 		/**
 		* Capability table for the Kimi model list.
@@ -4564,54 +4666,71 @@ window.__ModuleLoader__.load({
 			const t = useLineDict(NS_KIMI_CODE, zh$10);
 			return /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("div", {
 				className: "dsha-cap-table",
-				children: [/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("table", { children: [/* @__PURE__ */ (0, react_jsx_runtime.jsx)("thead", { children: /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("tr", { children: [
-					/* @__PURE__ */ (0, react_jsx_runtime.jsx)("th", { children: t.capabilitiesTitle }),
-					/* @__PURE__ */ (0, react_jsx_runtime.jsx)("th", { children: t.capColMedia }),
-					/* @__PURE__ */ (0, react_jsx_runtime.jsx)("th", { children: t.capColTools }),
-					/* @__PURE__ */ (0, react_jsx_runtime.jsx)("th", { children: t.capColNotes })
-				] }) }), /* @__PURE__ */ (0, react_jsx_runtime.jsx)("tbody", { children: models.map((model) => {
-					return /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("tr", { children: [
-						/* @__PURE__ */ (0, react_jsx_runtime.jsx)("td", {
-							title: [
-								model.id,
-								model.wire === "anthropic" ? t.wireAnthropic : t.wireOpenai,
-								...model.defaultReasoningEffort ? [t.defaultReasoningEffort + ": " + model.defaultReasoningEffort] : [],
-								...model.maxInputTokens === void 0 ? [] : [t.capInputCap.replace("{tokens}", String(model.maxInputTokens))],
-								...model.minimumPlan ? [t.capPlan.replace("{plan}", model.minimumPlan)] : [],
-								...model.quotaMultiplier === null ? [] : [`${t.quotaCost}: ${formatMultiplier(model.quotaMultiplier)}`]
-							].join(" · "),
-							children: model.name
-						}),
-						/* @__PURE__ */ (0, react_jsx_runtime.jsx)("td", { children: /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
-							className: model.supportsVideo ? "dsha-cap-on" : "dsha-cap-off",
-							children: model.supportsVideo ? t.capVideo : t.capImageOnly
-						}) }),
-						/* @__PURE__ */ (0, react_jsx_runtime.jsx)("td", { children: model.supportsDynamicTools ? /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
-							className: "dsha-cap-on",
-							children: t.capDynamicTools
-						}) : model.supportsToolUse ? /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
-							className: "dsha-cap-off",
-							children: t.capNone
-						}) : /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
-							className: "dsha-cap-off",
-							children: t.capNoTools
-						}) }),
-						/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("td", {
-							className: "dsha-cap-notes",
-							children: [model.quotaMultiplier === null ? null : /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("span", {
-								className: "dsha-cap-cost",
-								children: [
-									t.quotaCost,
-									" ",
-									formatMultiplier(model.quotaMultiplier)
-								]
-							}), model.description ?? ""]
-						})
-					] }, model.id);
-				}) })] }), models.some((model) => model.supportsVideo) && /* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
-					className: "dsha-muted dsha-cap-footnote",
-					children: t.capVideoFootnote
-				})]
+				children: [
+					/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("table", { children: [/* @__PURE__ */ (0, react_jsx_runtime.jsx)("thead", { children: /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("tr", { children: [
+						/* @__PURE__ */ (0, react_jsx_runtime.jsx)("th", { children: t.capabilitiesTitle }),
+						/* @__PURE__ */ (0, react_jsx_runtime.jsx)("th", { children: t.capColMedia }),
+						/* @__PURE__ */ (0, react_jsx_runtime.jsx)("th", { children: t.capColTools }),
+						/* @__PURE__ */ (0, react_jsx_runtime.jsx)("th", { children: t.capColNotes })
+					] }) }), /* @__PURE__ */ (0, react_jsx_runtime.jsx)("tbody", { children: models.map((model) => {
+						const ladder = effortLadder(model);
+						return /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("tr", { children: [
+							/* @__PURE__ */ (0, react_jsx_runtime.jsx)("td", {
+								title: [
+									model.id,
+									wireLabel(model.wire, t),
+									...model.thinkingType === "only" ? [t.capThinkingOnly] : [],
+									...ladder.length === 0 ? [] : [t.capEfforts.replace("{list}", ladder.join(" / "))],
+									...model.defaultReasoningEffort ? [t.defaultReasoningEffort + ": " + model.defaultReasoningEffort] : [],
+									...model.maxInputTokens === void 0 ? [] : [t.capInputCap.replace("{tokens}", String(model.maxInputTokens))],
+									...model.minimumPlan ? [t.capPlan.replace("{plan}", model.minimumPlan)] : [],
+									...model.quotaMultiplier === null ? [] : [`${t.quotaCost}: ${formatMultiplier(model.quotaMultiplier)}`]
+								].join(" · "),
+								children: model.name
+							}),
+							/* @__PURE__ */ (0, react_jsx_runtime.jsx)("td", { children: /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+								className: model.supportsVideo ? "dsha-cap-on" : "dsha-cap-off",
+								children: model.supportsVideo ? t.capVideo : t.capImageOnly
+							}) }),
+							/* @__PURE__ */ (0, react_jsx_runtime.jsx)("td", { children: model.supportsDynamicTools ? /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+								className: "dsha-cap-on",
+								children: t.capDynamicTools
+							}) : model.supportsToolUse ? /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+								className: "dsha-cap-off",
+								children: t.capNone
+							}) : /* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+								className: "dsha-cap-off",
+								children: t.capNoTools
+							}) }),
+							/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("td", {
+								className: "dsha-cap-notes",
+								children: [model.quotaMultiplier === null ? /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("div", {
+									className: "dsha-cap-off",
+									children: [
+										t.quotaCost,
+										" ",
+										t.quotaUnknown
+									]
+								}) : /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("span", {
+									className: "dsha-cap-cost",
+									children: [
+										t.quotaCost,
+										" ",
+										formatMultiplier(model.quotaMultiplier)
+									]
+								}), model.description ?? ""]
+							})
+						] }, model.id);
+					}) })] }),
+					models.some((model) => model.supportsVideo) && /* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
+						className: "dsha-muted dsha-cap-footnote",
+						children: t.capVideoFootnote
+					}),
+					models.some((model) => model.thinkingType === "only") && /* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
+						className: "dsha-muted dsha-cap-footnote",
+						children: t.capThinkingOnlyFootnote
+					})
+				]
 			});
 		}
 		//#endregion
@@ -4630,14 +4749,15 @@ window.__ModuleLoader__.load({
 				return `${(cents / 100).toFixed(2)} ${code}`;
 			}
 		}
-		function effortLabel(effort, t) {
-			switch (effort) {
-				case "low": return t.effortLow;
-				case "high": return t.effortHigh;
-				case "max": return t.effortMax;
-				case "none": return t.effortNone;
-				default: return effort;
-			}
+		/**
+		* One token count as the card prints it.
+		*
+		* A reported zero prints as "0": zero writes is a reading, while a blank cell
+		* reads as "nothing was measured", and the two are different claims. Only a
+		* number this build cannot read at all falls back to "暂无".
+		*/
+		function tokenCount(value, t) {
+			return typeof value === "number" && Number.isFinite(value) ? value.toLocaleString() : t.unknownMetric;
 		}
 		/** Human label for the last request's prefix-drift cause. */
 		function driftLabel(cause, t) {
@@ -4984,8 +5104,13 @@ window.__ModuleLoader__.load({
 			});
 			const quota = status?.quota;
 			status?.account;
-			status?.models.filter((model) => model.enabled).length;
+			const models = status?.models ?? [];
+			models.filter((model) => model.enabled).length;
 			const loginPending = flow?.status === "pending";
+			const offeredEfforts = effortOptions(models);
+			const savedEffort = status?.defaultReasoningEffort ?? null;
+			const staleEffort = savedEffort !== null && !offeredEfforts.includes(savedEffort) ? savedEffort : null;
+			const thinkingOnly = thinkingOnlyModels(models.filter((model) => model.enabled));
 			return /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("div", {
 				className: "dsha-page",
 				children: [
@@ -5181,6 +5306,30 @@ window.__ModuleLoader__.load({
 											children: driftLabel(status.cache.lastDrift, t)
 										})]
 									}),
+									/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("div", {
+										className: "dsha-row",
+										children: [/* @__PURE__ */ (0, react_jsx_runtime.jsx)("span", {
+											className: "dsha-label",
+											children: t.cacheWrite
+										}), /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("span", {
+											className: "dsha-value",
+											children: [
+												tokenCount(status.cache.cacheWriteTokens, t),
+												" · ",
+												t.cacheWrite5m,
+												" ",
+												tokenCount(status.cache.cacheWrite5mTokens, t),
+												" · ",
+												t.cacheWrite1h,
+												" ",
+												tokenCount(status.cache.cacheWrite1hTokens, t)
+											]
+										})]
+									}),
+									/* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
+										className: "dsha-muted",
+										children: t.cacheWriteHint
+									}),
 									/* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
 										className: "dsha-muted",
 										children: t.cacheHint
@@ -5206,11 +5355,12 @@ window.__ModuleLoader__.load({
 								children: t.modelsHint
 							}),
 							/* @__PURE__ */ (0, react_jsx_runtime.jsx)(ModelChecklist, {
-								items: (status?.models ?? []).map((model) => ({
+								items: models.map((model) => ({
 									id: model.id,
 									name: model.name,
 									hint: [
-										model.wire === "anthropic" ? t.wireAnthropic : t.wireOpenai,
+										wireLabel(model.wire, t),
+										...model.thinkingType === "only" ? [t.capThinkingOnly] : [],
 										...model.supportsVideo ? [t.capVideo] : [],
 										...model.supportsDynamicTools ? [t.capDynamicTools] : [],
 										...model.minimumPlan ? [t.capPlan.replace("{plan}", model.minimumPlan)] : []
@@ -5226,7 +5376,7 @@ window.__ModuleLoader__.load({
 									list: t.modelsSection
 								}
 							}),
-							status !== null && status.models.length > 0 && /* @__PURE__ */ (0, react_jsx_runtime.jsx)(KimiModelCapabilities, { models: status.models })
+							status !== null && models.length > 0 && /* @__PURE__ */ (0, react_jsx_runtime.jsx)(KimiModelCapabilities, { models })
 						]
 					}),
 					/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("section", {
@@ -5250,15 +5400,30 @@ window.__ModuleLoader__.load({
 										const value = event.currentTarget.value;
 										handleUpdateEffort(value === "" ? null : value);
 									},
-									children: [/* @__PURE__ */ (0, react_jsx_runtime.jsx)("option", {
-										value: "",
-										children: t.defaultEffortAuto
-									}), KIMI_CODE_REASONING_EFFORTS.map((effort) => /* @__PURE__ */ (0, react_jsx_runtime.jsx)("option", {
-										value: effort,
-										children: effortLabel(effort, t)
-									}, effort))]
+									children: [
+										/* @__PURE__ */ (0, react_jsx_runtime.jsx)("option", {
+											value: "",
+											children: t.defaultEffortAuto
+										}),
+										offeredEfforts.map((effort) => /* @__PURE__ */ (0, react_jsx_runtime.jsx)("option", {
+											value: effort,
+											children: effortLabel(effort, t)
+										}, effort)),
+										staleEffort !== null && /* @__PURE__ */ (0, react_jsx_runtime.jsxs)("option", {
+											value: staleEffort,
+											children: [
+												effortLabel(staleEffort, t),
+												" · ",
+												t.effortNotOffered
+											]
+										})
+									]
 								})]
 							}),
+							thinkingOnly.length > 0 && /* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
+								className: "dsha-notice",
+								children: t.effortThinkingOnlyNote.replace("{models}", thinkingOnly.map((model) => model.name).join(" · "))
+							}),
 							/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("div", {
 								className: "dsha-pref-row",
 								children: [/* @__PURE__ */ (0, react_jsx_runtime.jsxs)("div", { children: [/* @__PURE__ */ (0, react_jsx_runtime.jsx)("strong", { children: t.cacheTtl }), /* @__PURE__ */ (0, react_jsx_runtime.jsx)("p", {
@@ -19071,10 +19236,13 @@ window.__ModuleLoader__.load({
 			wireAnthropic: "Anthropic",
 			wireOpenai: "OpenAI",
 			capVideo: "Видео*",
+			capThinkingOnly: "Только рассуждения",
+			capEfforts: "Уровни {list}",
 			capDynamicTools: "Динамические инструменты",
 			capImageOnly: "Изображения",
 			capNone: "—",
 			capVideoFootnote: "* Видео подключается инструментом kimi_attach_video (абсолютный локальный путь или ссылка http(s)); вставка и загрузка по-прежнему принимают только изображения.",
+			capThinkingOnlyFootnote: "* У модели с пометкой «только рассуждения» нельзя отключить рассуждения: запрос с none сервис отклоняет (HTTP 400), поэтому уровня «рассуждения выкл.» у неё нет.",
 			capabilitiesTitle: "Возможности",
 			capColMedia: "Мультимодальность",
 			capColTools: "Динамические инструменты",
@@ -19085,13 +19253,16 @@ window.__ModuleLoader__.load({
 			speedRegular: "Обычная",
 			speedHighspeed: "Ускоренная (~6×)",
 			quotaCost: "Множитель квоты",
+			quotaUnknown: "Не опубликовано",
 			minimumPlan: "Нужный тариф",
 			enhanced: "Рассуждения",
 			defaultReasoningEffort: "Уровень рассуждений по умолчанию",
-			defaultReasoningEffortHint: "Kimi Code принимает только low / high / max; none отключает рассуждения. Смена уровня сбрасывает кеш контекста, поэтому в пределах сессии держите его неизменным.",
+			defaultReasoningEffortHint: "Набор уровней следует тому, что заявляют отмеченные модели (если не отмечено ни одной — все четыре: low / high / max / none); none отключает рассуждения и действует только для моделей, которые это позволяют. Смена уровня сбрасывает кеш контекста, поэтому в пределах сессии держите его неизменным.",
+			effortThinkingOnlyNote: "Среди отмеченных моделей есть те, что рассуждают всегда: {models}. Уровня «рассуждения выкл.» у них нет — такой запрос сервис отклоняет (HTTP 400), поэтому здесь он не предлагается.",
+			effortNotOffered: "отмеченные модели это не принимают",
 			cacheTtl: "Время жизни кеша контекста",
-			cacheTtlHint: "Kimi кеширует префиксы автоматически, здесь выбирается время записи. Запись на 1 ч стоит примерно вдвое дороже записи на 5 мин и окупается, только если тот же префикс перечитывается в течение часа. Уровень фиксируется при первой записи и позже не меняется. Пустое значение — поле не отправляется, решает Kimi (измеренное время жизни — примерно 5–30 минут). Выбирайте по паузе между ходами: если она обычно короче ~30 минут, оставьте пусто или 5 минут; для сессий с долгим простоем, например диспетчера, ждущего субагентов, — 1 час.",
-			cacheTtlDefault: "Не задавать (по умолчанию Kimi)",
+			cacheTtlHint: "Kimi кеширует префиксы автоматически, здесь выбирается уровень записи, и их всего два: 5m и 1h. Пустое значение — поле не отправляется, и тогда сервис пишет на уровне 5 минут. Запись на 1 ч стоит примерно вдвое дороже записи на 5 мин и окупается, только если тот же префикс перечитывается в течение часа. Уровень фиксируется при первой записи, а попадания продлевают её по исходному TTL. Выбирайте по паузе между ходами: 5 минут, если она обычно короче ~30 минут; 1 час для сессий с долгим простоем, например диспетчера, ждущего субагентов.",
+			cacheTtlDefault: "Не передавать (сервис пишет на уровне 5 минут)",
 			cacheTtl5m: "5 минут",
 			cacheTtl1h: "1 час",
 			defaultEffortAuto: "Как в модели по умолчанию",
@@ -19117,6 +19288,11 @@ window.__ModuleLoader__.load({
 			cacheFresh: "Новые токены",
 			cacheOutput: "Выходные токены",
 			cacheRequests: "Запросы",
+			cacheWrite: "Запись в кеш",
+			cacheWrite5m: "Уровень 5 минут",
+			cacheWrite1h: "Уровень 1 час",
+			cacheWriteHint: "Запись — отдельная статья биллинга: запись на 1 ч стоит примерно вдвое дороже записи на 5 мин, а попадание продлевает её по исходному TTL. 0 на уровне означает, что сервис не сообщил запись для этого уровня (отсутствующий заголовок — молчание), а не то, что там ничего не записали.",
+			unknownMetric: "нет данных",
 			cacheHint: "В пределах одной сессии: любое изменение системного промпта или списка инструментов сбрасывает весь префиксный кеш, поэтому держите набор инструментов стабильным, а новое добавляйте в конец — так доля попаданий выше.",
 			cacheExpired: "Сессия простаивала дольше времени жизни кеша, поэтому следующий ход заново обработает около {tokens} токенов.",
 			cacheDrift: "Состояние последнего префикса",