diff --git a/docs/en/configuration/config-files.md b/docs/en/configuration/config-files.md
index 303886e360..2e093baf29 100644
--- a/docs/en/configuration/config-files.md
+++ b/docs/en/configuration/config-files.md
@@ -38,6 +38,13 @@ api_key = ""
 provider = "managed:kimi-code"
 model = "kimi-for-coding"
 max_context_size = 262144
+capabilities = [ "thinking", "always_thinking", "image_in", "video_in", "tool_use" ]
+
+[models."kimi-code/kimi-for-coding-highspeed"]
+provider = "managed:kimi-code"
+model = "kimi-for-coding-highspeed"
+max_context_size = 262144
+capabilities = [ "thinking", "always_thinking", "image_in", "video_in", "tool_use" ]
 
 [thinking]
 enabled = true
@@ -52,8 +59,13 @@ reserved_context_size = 50000
 max_running_tasks = 4
 keep_alive_on_exit = false
 
-# [experimental]
-# micro_compaction = false  # disabled: micro compaction has been removed
+[services.moonshot_search]
+base_url = "https://api.kimi.com/coding/v1/search"
+api_key = ""
+
+[services.moonshot_fetch]
+base_url = "https://api.kimi.com/coding/v1/fetch"
+api_key = ""
 
 [[permission.rules]]
 decision = "allow"
@@ -127,7 +139,7 @@ Each entry in the `models` table defines a model alias (the name used in `defaul
 | `model` | `string` | Yes | Model identifier sent to the server when calling the API |
 | `max_context_size` | `integer` | Yes | Maximum context length in tokens; must be at least 1 |
 | `max_output_size` | `integer` | No | Per-request output token cap (maps to `max_tokens`). Currently only the `anthropic` provider honors it. When set for a Claude model, this explicit value overrides the built-in server-side maximum |
-| `capabilities` | `array<string>` | No | Capability tags to add explicitly: `thinking`, `image_in`, `video_in`, `audio_in`, `tool_use`. Unioned with the capabilities auto-detected by the provider — entries can only be added, never removed |
+| `capabilities` | `array<string>` | No | Capability tags to add explicitly: `thinking`, `always_thinking`, `image_in`, `video_in`, `audio_in`, `tool_use`. Unioned with the capabilities auto-detected by the provider — entries can only be added, never removed |
 | `support_efforts` | `array<string>` | No | Thinking effort levels declared by the model catalog. Managed and open-platform refreshes may rewrite this field; to pin it manually, set `[models."<alias>".overrides] support_efforts` instead |
 | `default_effort` | `string` | No | Default thinking effort for the model. Managed and open-platform refreshes may rewrite this field; to pin it manually, set `[models."<alias>".overrides] default_effort` instead |
 | `display_name` | `string` | No | Name shown in the UI; falls back to `model` when unset |
diff --git a/docs/en/release-notes/changelog.md b/docs/en/release-notes/changelog.md
index 9b8d8ab93c..ab6868f1b8 100644
--- a/docs/en/release-notes/changelog.md
+++ b/docs/en/release-notes/changelog.md
@@ -6,6 +6,18 @@ outline: 2
 
 This page documents the changes in each Kimi Code CLI release.
 
+## 0.23.5 (2026-07-10)
+
+### Polish
+
+- Retry provider 429, overload, and other transient errors more reliably, honoring the server Retry-After delay, and surface retries in `-p --output-format stream-json`.
+
+### Bug Fixes
+
+- Stop unsupported image formats (AVIF, BMP, TIFF, ICO, …) from breaking sessions at every entry point — including remote image URLs and images mislabeled by a tool — and recover an already-stuck session by dropping the offending image and retrying, so one such image can no longer make every later request fail.
+- web: Fix the "Turn finished" desktop notification and completion sound firing twice per turn.
+- web: Hide the internal image-compression note so it no longer renders as user message text.
+
 ## 0.23.4 (2026-07-10)
 
 ### Features
diff --git a/docs/zh/configuration/config-files.md b/docs/zh/configuration/config-files.md
index 9cc6ace34f..23545d7f26 100644
--- a/docs/zh/configuration/config-files.md
+++ b/docs/zh/configuration/config-files.md
@@ -38,6 +38,13 @@ api_key = ""
 provider = "managed:kimi-code"
 model = "kimi-for-coding"
 max_context_size = 262144
+capabilities = [ "thinking", "always_thinking", "image_in", "video_in", "tool_use" ]
+
+[models."kimi-code/kimi-for-coding-highspeed"]
+provider = "managed:kimi-code"
+model = "kimi-for-coding-highspeed"
+max_context_size = 262144
+capabilities = [ "thinking", "always_thinking", "image_in", "video_in", "tool_use" ]
 
 [thinking]
 enabled = true
@@ -52,8 +59,13 @@ reserved_context_size = 50000
 max_running_tasks = 4
 keep_alive_on_exit = false
 
-# [experimental]
-# micro_compaction = false  # disabled: micro compaction has been removed
+[services.moonshot_search]
+base_url = "https://api.kimi.com/coding/v1/search"
+api_key = ""
+
+[services.moonshot_fetch]
+base_url = "https://api.kimi.com/coding/v1/fetch"
+api_key = ""
 
 [[permission.rules]]
 decision = "allow"
@@ -127,7 +139,7 @@ KIMI_BASE_URL = "https://api.moonshot.ai/v1"
 | `model` | `string` | 是 | 调用 API 时实际传给服务端的模型 ID |
 | `max_context_size` | `integer` | 是 | 最大上下文长度（token 数），必须 ≥ 1 |
 | `max_output_size` | `integer` | 否 | 单次请求的输出 token 上限（对应 `max_tokens`）。目前仅 `anthropic` 供应商读取。为 Claude 模型设置后，这个显式值会覆盖内置的服务端最大值 |
-| `capabilities` | `array<string>` | 否 | 显式追加的能力标签：`thinking`、`image_in`、`video_in`、`audio_in`、`tool_use`。与供应商自动识别的能力取并集，只能追加不能移除 |
+| `capabilities` | `array<string>` | 否 | 显式追加的能力标签：`thinking`、`always_thinking`、`image_in`、`video_in`、`audio_in`、`tool_use`。与供应商自动识别的能力取并集，只能追加不能移除 |
 | `support_efforts` | `array<string>` | 否 | 模型目录声明的 Thinking 档位。managed 和 open-platform 刷新可能会改写该字段；如需手动固定，请改用 `[models."<alias>".overrides] support_efforts` |
 | `default_effort` | `string` | 否 | 模型的默认 Thinking 档位。managed 和 open-platform 刷新可能会改写该字段；如需手动固定，请改用 `[models."<alias>".overrides] default_effort` |
 | `display_name` | `string` | 否 | UI 中显示的名称，未设时回退到 `model` |
diff --git a/docs/zh/release-notes/changelog.md b/docs/zh/release-notes/changelog.md
index 98ff34285a..eef2673ed9 100644
--- a/docs/zh/release-notes/changelog.md
+++ b/docs/zh/release-notes/changelog.md
@@ -6,6 +6,18 @@ outline: 2
 
 本页记录 Kimi Code CLI 每个版本的变更内容。
 
+## 0.23.5（2026-07-10）
+
+### 优化
+
+- 优化 provider 429、过载等瞬时错误的重试可靠性，遵循服务端 Retry-After 等待时间，并在 `-p --output-format stream-json` 输出中展示重试事件。
+
+### 修复
+
+- 修复 AVIF、BMP、TIFF、ICO 等不支持的图片格式导致会话中断的问题，覆盖远程图片 URL、工具误标格式等所有入口。已卡住的会话会自动丢弃问题图片并重试，单张异常图片不再导致后续请求全部失败。
+- web: 修复 “Turn finished” 桌面通知与完成提示音每轮触发两次的问题。
+- web: 修复内部的图片压缩说明被当作用户消息文本显示的问题。
+
 ## 0.23.4（2026-07-10）
 
 ### 新功能