@xmanrui/dsh-im 4.22.0 → 4.23.0

package/README.en.md

@@ -72,7 +72,7 @@ third-party gateway.
 
 Feishu group chats accept messages from other bots that explicitly mention the current bot by default, with no extra setting. Messages without that mention, mentions of only other members or everyone, self-sent messages, and bot DMs are still ignored, even in all-message mode. Group allowlists and command permissions still apply. The app needs the `im:message.group_at_msg.include_bot:readonly` tenant scope. New apps request it through the QR flow; existing or manually connected apps can use **Complete permissions** or `/repair` in a direct chat, scan the QR code, and complete any publication or approval required by Feishu. See the [Feishu message-event permissions](https://open.feishu.cn/document/server-docs/im-v1/message/events/receive).
 
-Built-in channels with image input support can send JPEG, PNG, and WebP images, plus GIFs sent as image files, with optional captions to Harness. Each image is limited to 5 MB, and images in one message are limited to 20 MB in total. iMessage's MVP supports text DMs only. Downloading images or files from Feishu user messages requires the `im:message:readonly` tenant scope, shown on the confirmation page as **Read direct and group messages**; Feishu currently offers no narrower image-only scope for that download endpoint. Apps created through the built-in QR flow request it by default; for existing or manually connected apps, click **Complete permissions** on the IM Bot settings page and scan the QR code to incrementally add that scope, `im:resource` for uploading bot-sent images or files, `application:app_slash_command:read` / `write` for the native command panel, and the card callback.
+Built-in channels with image input support can send JPEG, PNG, and WebP images, plus GIFs sent as image files, with optional captions to Harness. By default, original images can be up to 30 MB each, with up to 20 images per message. Originals are saved in the Session workspace; model copies are resized or compressed to 5 MB each and 20 MB total. Images that still exceed the budget, or are rejected by a non-vision model, are delivered as workspace files. These four limits can be changed under General settings → Attachments → Image input for subsequent messages. Originals follow attachment retention settings. Higher model limits increase request size, latency and model cost, and remain subject to platform and Host limits. iMessage's MVP supports text DMs only. Downloading images or files from Feishu user messages requires the `im:message:readonly` tenant scope, shown on the confirmation page as **Read direct and group messages**; Feishu currently offers no narrower image-only scope for that download endpoint. Apps created through the built-in QR flow request it by default; for existing or manually connected apps, click **Complete permissions** on the IM Bot settings page and scan the QR code to incrementally add that scope, `im:resource` for uploading bot-sent images or files, `application:app_slash_command:read` / `write` for the native command panel, and the card callback.
 
 ### Results after a reply timeout
 
@@ -221,7 +221,7 @@ DingTalk menus use a shared template built into the plugin; no template setup is
 
 ## Other features
 
-- **Image understanding**: built-in channels with image input support can send JPEG, PNG, WebP, and GIF files sent as images to Harness, with an optional text description. Each image is limited to 5 MB, and all images in one message are limited to 20 MB in total. iMessage's MVP supports text DMs only.
+- **Image understanding**: built-in channels with image input support can send JPEG, PNG, WebP, and GIF files sent as images to Harness, with an optional text description. Originals are saved in the workspace (default 30 MB per image, 20 images per message). Model copies are resized or compressed within configurable 5 MB per-image and 20 MB total budgets, with workspace-file fallback when necessary. Configure these limits in General settings → Attachments → Image input. iMessage's MVP supports text DMs only.
 - **Switch workspaces from a bot card**: every bot card on the settings page shows its current Harness workspace. Enter an existing absolute directory path directly or open the directory picker. Switching clears only that bot's old chat mappings; it never deletes, empties, or archives old Sessions. Replies already in progress may finish, while later messages use the new workspace.
 - **Default directory and ungrouped sessions**: bots using the default share `$DSH_HOME/im`, while retaining separate chat-to-Session mappings. The plugin creates no workspace group for this directory. Use `/sessions` to list its ungrouped sessions and `/session <Session ID>` or `/session N` to bind an ordinary session. New sessions in other directories use the existing workspace grouping mechanism; switching back to the default directory creates ungrouped sessions again. Existing bot directories are not migrated automatically.
 - **Choose a model and reasoning effort from a bot card**: every bot card in each IM channel offers model and effort controls below the workspace, with DSH-style provider groups, descriptions, and checkmarks. Select an available model and one of its supported efforts, or use the model default. Leaving the model unset follows the Host default. Settings are stored per bot and used only for later new Sessions; existing Sessions and replies already in progress are unchanged.
@@ -231,7 +231,7 @@ DingTalk menus use a shared template built into the plugin; no template setup is
 - **Manage multiple bots independently**: a channel can have multiple connected bots. Credentials, connection state, workspace, model, Agent Preset, and chat-to-Session mappings are kept separately for every bot, so card actions do not affect sibling bots.
 - **Streaming replies and progress**: the plugin uses each platform's available capabilities to show thinking state, tool progress, and incremental answers. Platforms without a native streaming API complete replies through message edits, card updates, or a final message.
 
-If WeChat setup, connection, or removal fails, expand **Diagnostic details** and choose **Copy diagnostics**. Include the steps, Desktop/Web mode, and actual DSH version in your report; use the `WX-CONN-…` reference to find the matching `[dsh-weixin]` Host log. Diagnostics distinguish network, credential, file, Harness, and WeChat service failures without including login tokens or QR contents. When removal succeeds but local cleanup fails, the page retains a cleanup warning. If no Host reference was received, also check the DSH management connection and startup logs.
+If setup, connection, or removal fails in WeChat, Feishu, DingTalk, Enterprise WeChat, QQ, Slack, Telegram, Discord, WhatsApp, Enterprise WeChat App, iMessage, Email, or AI Office, expand **Diagnostic details** and choose **Copy diagnostics**. Include the steps, Desktop/Web mode, and actual DSH version in your report; use the displayed `WX-CONN-…`, `DT-CONN-…`, or `IM-CONN-…` reference to find the matching channel Host log. Diagnostics preserve the failing stage, recognized underlying causes, HTTP status, and available timings. Multiple causes are listed together; unrecognized causes are explicitly marked **Unknown**. Login tokens, QR contents, and raw responses are excluded. When removal succeeds but local cleanup fails, the page retains a cleanup warning. Message failures keep their existing `MF-…` references. If the page cannot reach the DSH management API and has no Host reference, check the DSH management connection. Investigate network failures on the machine running DSH.
 
 Startup configuration validation failures also include `file`, `field`, and `issue`, identifying the first rejected field in `config.json` or `workspaces.json`. Field positions use zero-based entry order: `workspaces[0].value` means the first workspace entry's value without exposing its account identifier. The default directory is `DSH_HOME/integrations/dsh-weixin`, or `~/.dsh/integrations/dsh-weixin` when `DSH_HOME` is unset; custom plugin paths take precedence. Restart DSH after fixing the file. Refreshing the settings status does not reload configuration files.
 

package/README.md

@@ -75,7 +75,7 @@ Connect IM bots to DeepSeek Harness by scanning a QR code, using an App Manifest
 
 飞书群聊默认接收其他机器人明确 @ 当前机器人的消息，无需额外开关；未 @、仅 @ 其他成员或全体、机器人自身发送的消息和机器人私聊消息仍会忽略，即使群聊响应方式设为“全部”。消息仍受群聊白名单与命令权限约束。飞书应用需要租户权限 `im:message.group_at_msg.include_bot:readonly`（“获取群组中其他机器人和用户@当前机器人的消息”）；扫码新建应用会默认申请，已有或手动绑定的应用可点击“补全权限”或私聊执行 `/repair`，扫码并完成飞书要求的发布审批后生效。详见[飞书接收消息权限说明](https://open.feishu.cn/document/server-docs/im-v1/message/events/receive)。
 
-支持图片输入的内置渠道均支持把 JPEG、PNG、WebP 图片，以及以图片文件方式发送的 GIF，连同可选文字说明发送给 Harness；单张图片上限为 5 MB，单条消息中的图片总大小上限为 20 MB。iMessage 首版仅支持文本私聊，不包含在图片能力中。飞书下载用户消息中的图片或文件需要租户权限 `im:message:readonly`，确认页将其显示为“获取单聊、群组消息”；飞书目前没有为该下载接口提供仅限图片的更窄权限。扫码新建的应用会默认申请；已有或手动绑定的应用可私聊机器人执行 `/repair`，或在「IM机器人」设置页点击“补全权限”，扫码增量补全该权限、上传机器人图片或文件所需的 `im:resource`、原生命令面板所需的 `application:app_slash_command:read` / `write`，以及卡片回调。
+支持图片输入的内置渠道均支持把 JPEG、PNG、WebP 图片，以及以图片文件方式发送的 GIF，连同可选文字说明发送给 Harness；默认每张原图最多接收 30 MB、每条消息最多 20 张；原图保存到会话工作区，模型副本自动缩放或压缩到单张 5 MB、总计 20 MB 以内，仍超限或模型不支持图片时按文件交给模型处理。这四项限制可在「通用设置 → 附件 → 图片输入」调整，对后续消息生效；原图沿用附件保留时长。调高模型输入上限会增加请求体积、处理耗时和模型成本，也仍受平台及宿主限制。iMessage 首版仅支持文本私聊，不包含在图片能力中。飞书下载用户消息中的图片或文件需要租户权限 `im:message:readonly`，确认页将其显示为“获取单聊、群组消息”；飞书目前没有为该下载接口提供仅限图片的更窄权限。扫码新建的应用会默认申请；已有或手动绑定的应用可私聊机器人执行 `/repair`，或在「IM机器人」设置页点击“补全权限”，扫码增量补全该权限、上传机器人图片或文件所需的 `im:resource`、原生命令面板所需的 `application:app_slash_command:read` / `write`，以及卡片回调。
 
 ### 超时后的结果补发
 
@@ -224,7 +224,7 @@ Logo 由 dsh-im 的浏览器适配显示，无需修改 DSH。适配保留原始
 
 ## 其它功能
 
-- **图片识别**：支持图片输入的内置渠道都可以把 JPEG、PNG、WebP，以及以图片文件方式发送的 GIF 交给 Harness；图片可以附带文字说明。单张图片上限为 5 MB，单条消息中的图片总大小上限为 20 MB。iMessage 首版仅支持文本私聊。
+- **图片识别**：支持图片输入的内置渠道都可以把 JPEG、PNG、WebP，以及以图片文件方式发送的 GIF 交给 Harness；图片可以附带文字说明。默认每张原图最多接收 30 MB、每条消息最多 20 张；原图保存到会话工作区，模型副本自动缩放或压缩到单张 5 MB、总计 20 MB 以内，仍超限或模型不支持图片时按文件交给模型处理。这四项限制可在「通用设置 → 附件 → 图片输入」调整，对后续消息生效；原图沿用附件保留时长。调高模型输入上限会增加请求体积、处理耗时和模型成本，也仍受平台及宿主限制。iMessage 首版仅支持文本私聊。
 - **在机器人卡片切换工作区**：设置页中的每张机器人卡片都会显示当前 Harness 工作区。可以直接填写已有目录的绝对路径，也可以打开目录选择器。切换只清除该机器人的旧聊天映射，不会删除、清空或归档旧 Session；已经开始的回复可以继续完成，后续消息使用新工作区。
 - **默认目录与未分组会话**：所有使用默认值的机器人共用 `$DSH_HOME/im`，但各自保存聊天与会话的绑定。插件不会为该目录创建工作区分组；`/sessions` 可以列出该目录的未分组会话，`/session <Session ID>` 或 `/session N` 可以绑定普通会话。切换到其他目录后，新会话按现有机制加入对应工作区分组；切回默认目录后新会话归入「未分组」。已有机器人的目录不会自动迁移。
 - **在机器人卡片选择模型与思考强度**：每个 IM 渠道的每张机器人卡片都在工作区下方提供模型与思考强度入口，采用 DSH 风格的分组列表、档位说明和选中标记。先选择 Host 当前可用模型，再选择其支持的强度，或跟随模型默认；未选模型时整体跟随 Host 默认。设置按机器人独立保存，只用于之后新建的 Session；已有 Session 和正在生成的回复不受影响。
@@ -234,7 +234,7 @@ Logo 由 dsh-im 的浏览器适配显示，无需修改 DSH。适配保留原始
 - **多机器人独立管理**：同一渠道可以接入多个机器人。每个机器人分别保存凭据、连接状态、工作区、模型、Agent Preset 和聊天会话映射，卡片上的工作区、模型、Preset、连接检查、重试和移除操作互不影响。
 - **流式回复和进度提示**：插件会按各平台能力显示正在思考、工具执行和逐步生成的回答；不支持原生流式接口的平台会通过编辑消息、卡片更新或最终消息完成回复。
 
-微信扫码、连接或移除失败时，可展开页面中的「诊断详情」并点击「复制诊断信息」。反馈时附上操作步骤、Desktop/Web 运行方式和实际 DSH 版本；使用 `WX-CONN-…` 参考号查找同一次故障的 `[dsh-weixin]` Host 日志。诊断会区分网络、凭据、文件、Harness 和微信业务拒绝，不包含登录令牌或二维码内容。账号已移除但本机清理未完成时，页面会保留清理警告；若未取得 Host 参考号，请同时检查 DSH 管理连接和启动日志。
+微信、飞书、钉钉、企业微信、QQ、Slack、Telegram、Discord、WhatsApp、企业微信应用、iMessage、邮箱和 AI Office 的绑定、连接或移除失败时，可展开页面中的「诊断详情」并点击「复制诊断信息」。反馈时附上操作步骤、Desktop/Web 运行方式和实际 DSH 版本；使用页面中的 `WX-CONN-…`、`DT-CONN-…` 或 `IM-CONN-…` 参考号查找同一次故障的渠道 Host 日志。诊断会保留失败阶段、已识别的底层原因、HTTP 状态及可用的耗时等安全信息；多个原因会一并列出，无法识别时明确标为「暂未识别」，不包含登录令牌、二维码或原始响应内容。账号已移除但本机清理未完成时，页面会保留清理警告。消息故障沿用 `MF-…` 参考号；若页面提示 DSH 管理接口无法访问且没有 Host 参考号，请检查 DSH 管理连接。网络排查应以运行 DSH 的机器为准。
 
 微信启动配置校验失败时，诊断还会提供 `file`、`field`、`issue`，定位 `config.json` 或 `workspaces.json` 中第一个未通过校验的位置。字段中的序号从 0 开始，按文件条目顺序计数，例如 `workspaces[0].value` 表示第一条工作区配置的值，不包含真实账号标识。默认目录为 `DSH_HOME/integrations/dsh-weixin`（未设置 `DSH_HOME` 时为 `~/.dsh/integrations/dsh-weixin`），自定义路径以插件配置为准。修复后需要重启 DSH；页面「重新读取」仅查询状态，不会重新加载配置文件。