Sync public snapshot from freebuff-private

Source: CodebuffAI/freebuff-private@0399f19c3f67baef5967917302cfcca055d3876e

Author: github-actions[bot]

README.md

@@ -34,8 +34,8 @@ Freebuff includes a curated model catalog. The regular picker currently offers:
 
 | Model                       | Access                  | Best for                                                          |
 | --------------------------- | ----------------------- | ----------------------------------------------------------------- |
-| **DeepSeek V4 Flash 07/31** | Full access             | The default everywhere in full mode; fast coding and tool use     |
-| **GPT-5.6 Luna**            | Full access             | Strong all-around with native images; two sessions a day          |
+| **GPT-5.6 Luna**            | Full access             | The default in full mode; strong all-around with native images    |
+| **DeepSeek V4 Flash 07/31** | Full access             | Fast coding and tool use; pauses during peak hours                |
 | **MiMo 2.5**                | Full and limited access | The limited-mode default; balanced performance with image support |
 | **DeepSeek V4 Pro**         | Full access             | Deepest reasoning; one session a day                              |
 

README.zh-CN.md

@@ -34,8 +34,8 @@ Freebuff 提供经过筛选的模型目录。常规模型选择器目前包括
 
 | 模型                        | 访问范围       | 适用场景                                         |
 | --------------------------- | -------------- | ------------------------------------------------ |
-| **DeepSeek V4 Flash 07/31** | 完整访问       | 完整模式下所有平台的默认模型；快速编程和工具调用 |
-| **GPT-5.6 Luna**            | 完整访问       | 综合能力强，原生支持图像；每天两次会话           |
+| **GPT-5.6 Luna**            | 完整访问       | 完整模式下的默认模型；综合能力强，原生支持图像   |
+| **DeepSeek V4 Flash 07/31** | 完整访问       | 快速编程和工具调用；高峰时段暂停                 |
 | **MiMo 2.5**                | 完整和受限访问 | 受限模式的默认模型；均衡性能并支持图像           |
 | **DeepSeek V4 Pro**         | 完整访问       | 推理最深入；每天一次会话                         |
 

bun.lock

@@ -58,6 +58,25 @@ export function isFreebuffSubscriptionPremiumModelId(modelId: string): boolean {
   return FREEBUFF_SUBSCRIPTION_PREMIUM_MODEL_IDS.includes(modelId)
 }
 
+/**
+ * The DeepSeek models a plan's peak-hours pause applies to.
+ *
+ * Named explicitly rather than matched on an id prefix: a prefix would sweep in
+ * any future `deepseek/*` id automatically, and silently pausing a model nobody
+ * decided to pause is the kind of change that should require an edit here.
+ */
+export const FREEBUFF_SUBSCRIPTION_PEAK_PAUSED_MODEL_IDS: readonly string[] =
+  Object.freeze([
+    FREEBUFF_DEEPSEEK_V4_PRO_MODEL_ID,
+    FREEBUFF_DEEPSEEK_V4_FLASH_MODEL_ID,
+  ])
+
+export function isFreebuffSubscriptionPeakPausedModelId(
+  modelId: string,
+): boolean {
+  return FREEBUFF_SUBSCRIPTION_PEAK_PAUSED_MODEL_IDS.includes(modelId)
+}
+
 export function isFreebuffSubscriptionModelId(modelId: string): boolean {
   return FREEBUFF_SUBSCRIPTION_MODEL_IDS.includes(modelId)
 }

common/src/constants/freebuff-subscriptions.ts

@@ -81,6 +81,9 @@ export interface FreebuffSubscriptionTierOffer {
   current: boolean
   /** True when this tier is above the caller's current one. */
   upgrade: boolean
+  /** True when it is below. A downgrade is SCHEDULED for the next renewal
+   *  rather than applied now, so clients must not word it as immediate. */
+  downgrade: boolean
 }
 
 /**
@@ -122,6 +125,9 @@ export interface FreebuffSubscriptionInfo {
   status?: string
   /** True when the subscription lapses at period end. */
   cancelAtPeriodEnd?: boolean
+  /** Tier this drops to at the next renewal, when a downgrade is scheduled.
+   *  Absent in the ordinary case — every subscription not mid-downgrade. */
+  pendingTierId?: string
   /** The full catalog, current tier flagged. Drives every upgrade CTA. */
   tiers: FreebuffSubscriptionTierOffer[]
   /**

common/src/types/freebuff-session.ts

@@ -19,7 +19,7 @@ freebuff
 
 ## Why Freebuff?
 
-**Choice of leading models** — The regular CLI picker includes DeepSeek, GPT-5.6 Luna, and MiMo, with DeepSeek V4 Flash 07/31 selected by default.
+**Choice of leading models** — The regular CLI picker includes DeepSeek, GPT-5.6 Luna, and MiMo, with GPT-5.6 Luna selected by default.
 
 **Fast** — 5–10× speed up. 3–5× tokens per second compared to Claude, plus context gathering in seconds.
 
@@ -29,7 +29,7 @@ freebuff
 
 **How can it be free?** Freebuff is supported by text ads.
 
-**What models do you use?** In full mode, the regular picker includes DeepSeek V4 Flash 07/31, GPT-5.6 Luna, MiMo 2.5, and DeepSeek V4 Pro. DeepSeek V4 Flash 07/31 is the CLI default, and the picker falls back to MiMo 2.5 once your daily premium sessions are used up. Limited mode uses MiMo 2.5. These limits are temporary and exist because the providers serving DeepSeek now charge more than free mode can carry: V4 Pro is one session a day, GPT-5.6 Luna is two sessions a day, and models may serve from a quantized (Q8_0) build.
+**What models do you use?** In full mode, the regular picker includes DeepSeek V4 Flash 07/31, GPT-5.6 Luna, MiMo 2.5, and DeepSeek V4 Pro. GPT-5.6 Luna is the CLI default, and the picker falls back to MiMo 2.5 once your daily premium sessions are used up. Limited mode uses MiMo 2.5. These limits are temporary and exist because the providers serving DeepSeek now charge more than free mode can carry: V4 Pro is one session a day, GPT-5.6 Luna is two sessions a day, and models may serve from a quantized (Q8_0) build.
 
 **Which countries is Freebuff available in?** All countries. Freebuff runs in "full" mode in the US, Canada, UK, EU, and other select countries, and in "limited" mode everywhere else (or while using a VPN). See [freebuff.com](https://freebuff.com) for the full list.