diff --git a/CHANGELOG.md b/CHANGELOG.md
index b1cb6ebb..43255596 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,6 +10,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Changed
+
+- **Public share AI: default per-workspace hourly assistant cap lowered
+  300 → 100.** The limiter falls back to this default whenever
+  `SHARE_AI_WORKSPACE_MAX_PER_HOUR` is unset, so a `0.93.0` deployment that
+  never set the env var has its anonymous public-share assistant hourly cap
+  cut from 300 to 100 on upgrade. Set `SHARE_AI_WORKSPACE_MAX_PER_HOUR` to
+  keep the previous limit. (#62)
+
 ## [0.93.0] - 2026-06-21
 
 This release builds on the 0.91.0 AI foundation: admin-defined AI agent roles,
diff --git a/apps/client/public/locales/en-US/translation.json b/apps/client/public/locales/en-US/translation.json
index fc39a8d9..0f05d69f 100644
--- a/apps/client/public/locales/en-US/translation.json
+++ b/apps/client/public/locales/en-US/translation.json
@@ -1147,6 +1147,7 @@
   "Take a look at the current document": "Take a look at the current document",
   "AI agent is typing…": "AI agent is typing…",
   "{{name}} is typing…": "{{name}} is typing…",
+  "AI is typing…": "AI is typing…",
   "Send": "Send",
   "Stop": "Stop",
   "Chat menu": "Chat menu",
diff --git a/apps/client/public/locales/ru-RU/translation.json b/apps/client/public/locales/ru-RU/translation.json
index 4c40c4bf..816da5d6 100644
--- a/apps/client/public/locales/ru-RU/translation.json
+++ b/apps/client/public/locales/ru-RU/translation.json
@@ -672,6 +672,7 @@
   "Take a look at the current document": "Посмотри текущий документ",
   "AI agent is typing…": "AI-агент печатает…",
   "{{name}} is typing…": "{{name}} печатает…",
+  "AI is typing…": "AI печатает…",
   "Agent role": "Роль агента",
   "AI chat": "AI-чат",
   "AI chat is disabled for this workspace.": "AI-чат отключён для этого рабочего пространства.",
diff --git a/apps/client/src/features/ai-chat/components/message-list.tsx b/apps/client/src/features/ai-chat/components/message-list.tsx
index b4b4101d..487a7bb7 100644
--- a/apps/client/src/features/ai-chat/components/message-list.tsx
+++ b/apps/client/src/features/ai-chat/components/message-list.tsx
@@ -43,7 +43,7 @@ interface MessageListProps {
 const BOTTOM_THRESHOLD = 40;
 
 /**
- * Whether to show the standalone "AI agent is typing…" indicator. It bridges the
+ * Whether to show the standalone "AI is typing…" indicator. It bridges the
  * gap between sending and the first streamed content, so it shows only while a
  * turn is in flight AND the latest assistant message has nothing visible yet:
  *  - the last message is still the user's (assistant hasn't started a row), or
diff --git a/apps/client/src/features/ai-chat/components/role-cards.module.css b/apps/client/src/features/ai-chat/components/role-cards.module.css
index b47dfd95..94e7c2fb 100644
--- a/apps/client/src/features/ai-chat/components/role-cards.module.css
+++ b/apps/client/src/features/ai-chat/components/role-cards.module.css
@@ -4,7 +4,11 @@
   display: flex;
   flex-wrap: wrap;
   justify-content: center;
-  align-content: center;
+  /* flex-start keeps the first row reachable when the wrapped cards overflow and
+     the container scrolls. With align-content: center, an overflowing top row is
+     pushed out of the scrollable area and becomes unreachable. The parent Mantine
+     Center still vertically centers the whole block when it fits. */
+  align-content: flex-start;
   gap: 10px;
   /* Cap the height so a large number of roles scrolls instead of blowing out
      the empty chat area. */
@@ -21,7 +25,7 @@
   justify-content: center;
   gap: 4px;
   min-width: 140px;
-  max-width: 180px;
+  max-width: 200px;
   min-height: 90px;
   padding: 12px 10px;
   border-radius: var(--mantine-radius-md);
@@ -50,4 +54,8 @@
 .description {
   opacity: 0.8;
   line-height: 1.3;
+  /* Break long unbreakable tokens (URLs, long foreign words) in the
+     admin-configured description so they wrap instead of overflowing the card
+     width now that the line clamp no longer caps the text. */
+  overflow-wrap: anywhere;
 }
diff --git a/apps/client/src/features/ai-chat/components/role-cards.tsx b/apps/client/src/features/ai-chat/components/role-cards.tsx
index 2551bdbf..75bdd984 100644
--- a/apps/client/src/features/ai-chat/components/role-cards.tsx
+++ b/apps/client/src/features/ai-chat/components/role-cards.tsx
@@ -45,7 +45,7 @@ function RoleCard({
         {name}
       </Text>
       {description && (
-        <Text size="xs" lineClamp={3} className={classes.description}>
+        <Text size="xs" className={classes.description}>
           {description}
         </Text>
       )}
diff --git a/apps/client/src/features/ai-chat/components/show-typing-indicator.test.ts b/apps/client/src/features/ai-chat/components/show-typing-indicator.test.ts
index 5cc023d9..15ab75bc 100644
--- a/apps/client/src/features/ai-chat/components/show-typing-indicator.test.ts
+++ b/apps/client/src/features/ai-chat/components/show-typing-indicator.test.ts
@@ -5,7 +5,7 @@ import { showTypingIndicator } from "@/features/ai-chat/components/message-list.
 /**
  * Pure-helper tests for the typing-indicator bridging logic that the internal
  * chat and the public share widget now share. This is the behavior that decides
- * whether the animated "AI agent is typing…" placeholder shows in the gap
+ * whether the animated "AI is typing…" placeholder shows in the gap
  * between sending and the first streamed token.
  */
 const msg = (
diff --git a/apps/client/src/features/ai-chat/components/typing-indicator.tsx b/apps/client/src/features/ai-chat/components/typing-indicator.tsx
index 27373a3e..9dce2a7d 100644
--- a/apps/client/src/features/ai-chat/components/typing-indicator.tsx
+++ b/apps/client/src/features/ai-chat/components/typing-indicator.tsx
@@ -19,8 +19,10 @@ interface TypingIndicatorProps {
  * the real assistant message once content starts arriving.
  *
  * Mirrors the assistant row layout in MessageItem (the dimmed label), so it reads
- * as the assistant's bubble taking shape. The label and typing line use the
- * configured identity name when provided, otherwise the generic "AI agent".
+ * as the assistant's bubble taking shape. The dimmed label uses the configured
+ * identity name when provided (otherwise the generic "AI agent"), while the
+ * typing line is always the generic "AI is typing…" (it never includes the
+ * role/identity name).
  */
 export default function TypingIndicator({ assistantName }: TypingIndicatorProps) {
   const { t } = useTranslation();
@@ -38,7 +40,7 @@ export default function TypingIndicator({ assistantName }: TypingIndicatorProps)
           <span />
         </span>
         <Text size="sm" c="dimmed">
-          {name ? t("{{name}} is typing…", { name }) : t("AI agent is typing…")}
+          {t("AI is typing…")}
         </Text>
       </Group>
     </Box>
diff --git a/docs/backlog/ai-chat-stream-integration-coverage.md b/docs/backlog/ai-chat-stream-integration-coverage.md
new file mode 100644
index 00000000..c9c24cbb
--- /dev/null
+++ b/docs/backlog/ai-chat-stream-integration-coverage.md
@@ -0,0 +1,33 @@
+# Отложенные интеграционные тесты `AiChatService.stream`
+
+Статус: **открыто.** Это остаток от прежнего документа
+`feature-test-coverage-deferred.md` (хвост тест-плана PR #49). Два из трёх
+его разделов уже закрыты новой интеграционной обвязкой против реального
+Postgres/Redis (`apps/server/test/integration/`, PR #115):
+
+- ✅ **Раздел 1 — repo-тесты против БД.** Закрыт `ai-agent-roles-repo`,
+  `ai-chat-repo-find-by-creator`, `page-template-references-cascade`,
+  `workspace-repo-update-setting` (`*.int-spec.ts`).
+- ✅ **Раздел 2 — достоверность Lua-окна cost-cap против реального Redis.**
+  Закрыт `public-share-workspace-limiter.int-spec.ts`.
+- ⬜ **Раздел 3 (ниже) — полная интеграция `AiChatService.stream`.** Всё ещё
+  не реализован; держим запись открытой, чтобы тест-долг не потерялся при
+  удалении исходного документа.
+
+## Полная интеграция `AiChatService.stream` (рефактор R1-stream)
+
+`apps/server/src/core/ai-chat/ai-chat.service.ts`. В PR #49 извлечён и
+покрыт только чистый `buildErrorAssistantRecord`. Полные интеграционные
+сценарии всё ещё отложены:
+
+- **Запись чата, упавшего на первом ходу** (`onError`) — ассистентская
+  запись об ошибке должна сохраняться, даже когда первый ход стрима падает.
+- **Жизненный цикл external-MCP клиентов** — клиенты закрываются и при
+  `throw`, и при `onFinish` (нет утечки соединений).
+- **Анти-tamper: история восстанавливается из БД, а не из `body.messages`** —
+  клиент не может подменить историю через тело запроса.
+
+Эти сценарии требуют сидирования SDK `streamText` (инъекция/seam колбэков
+`onError` / `onFinish` / `onAbort` + `res.hijack`). Отложено, чтобы не
+дестабилизировать 287-строчный `stream()`; делать вместе с выносом testable
+turn-pipeline.