@xmanrui/dsh-im 4.14.0 → 4.16.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (69) hide show
  1. package/README.en.md +10 -2
  2. package/README.md +17 -6
  3. package/lib/client.js +1980 -616
  4. package/lib/index.js +303 -293
  5. package/package.json +6 -2
  6. package/plugin-src/client/access-policy-settings.js +6 -0
  7. package/plugin-src/client/channels/feishu/index.js +16 -4
  8. package/plugin-src/client/channels/wecom-app/api.js +124 -0
  9. package/plugin-src/client/channels/wecom-app/index.js +612 -0
  10. package/plugin-src/client/channels/wecom-app/styles.js +25 -0
  11. package/plugin-src/client/delivery-settings.js +7 -0
  12. package/plugin-src/client/i18n.js +64 -1
  13. package/plugin-src/client/index.js +21 -0
  14. package/plugin-src/client/model-setting.js +135 -69
  15. package/plugin-src/client/session-channel-logos.js +241 -0
  16. package/plugin-src/client/styles.js +22 -7
  17. package/plugin-src/host/channels/dingtalk/index.mjs +8 -15
  18. package/plugin-src/host/channels/discord/index.mjs +8 -10
  19. package/plugin-src/host/channels/feishu/index.mjs +8 -15
  20. package/plugin-src/host/channels/office/index.mjs +9 -5
  21. package/plugin-src/host/channels/qq/index.mjs +8 -15
  22. package/plugin-src/host/channels/shared/access-policy-production.mjs +1 -1
  23. package/plugin-src/host/channels/shared/model-setting-rpc.mjs +1 -2
  24. package/plugin-src/host/channels/shared/startup-error.mjs +53 -0
  25. package/plugin-src/host/channels/shared/startup.mjs +47 -0
  26. package/plugin-src/host/channels/shared/workspace-rpc.mjs +1 -0
  27. package/plugin-src/host/channels/slack/index.mjs +8 -10
  28. package/plugin-src/host/channels/telegram/index.mjs +8 -10
  29. package/plugin-src/host/channels/wecom/index.mjs +8 -15
  30. package/plugin-src/host/channels/wecom/rpc.mjs +6 -1
  31. package/plugin-src/host/channels/wecom-app/index.mjs +33 -0
  32. package/plugin-src/host/channels/wecom-app/production.mjs +217 -0
  33. package/plugin-src/host/channels/wecom-app/rpc.mjs +225 -0
  34. package/plugin-src/host/channels/weixin/index.mjs +8 -15
  35. package/plugin-src/host/channels/whatsapp/index.mjs +8 -15
  36. package/plugin-src/host/delivery-adapter.mjs +4 -0
  37. package/plugin-src/host/delivery-suggestions.mjs +4 -0
  38. package/plugin-src/host/index.mjs +21 -2
  39. package/plugin-src/host/session-title-prefix.mjs +122 -0
  40. package/scripts/verify-model-setting.mjs +54 -0
  41. package/scripts/verify-session-channel-logos.mjs +59 -0
  42. package/scripts/verify-session-title-prefix.mjs +149 -0
  43. package/src/channels/feishu/bridge.mjs +305 -12
  44. package/src/channels/feishu/feishu-cards.mjs +38 -0
  45. package/src/channels/feishu/feishu-channel.mjs +88 -20
  46. package/src/channels/feishu/plugin-controller.mjs +1 -0
  47. package/src/channels/feishu/repair-manager.mjs +3 -2
  48. package/src/channels/shared/bot-workspace-store.mjs +11 -3
  49. package/src/channels/shared/command-catalog.mjs +102 -0
  50. package/src/channels/shared/i18n-en/feishu.mjs +14 -2
  51. package/src/channels/shared/i18n-en/shared-a.mjs +3 -0
  52. package/src/channels/shared/i18n-en/shared-c.mjs +9 -0
  53. package/src/channels/shared/i18n-en/wecom-app.mjs +33 -0
  54. package/src/channels/shared/i18n-en.mjs +2 -0
  55. package/src/channels/shared/model-setting.mjs +43 -8
  56. package/src/channels/shared/session-channel-labels.mjs +26 -0
  57. package/src/channels/shared/text-harness-bridge.mjs +2 -26
  58. package/src/channels/telegram/telegram-api.mjs +18 -6
  59. package/src/channels/telegram/telegram-runtime.mjs +34 -32
  60. package/src/channels/wecom/send-error.mjs +31 -0
  61. package/src/channels/wecom/wecom-bridge.mjs +59 -17
  62. package/src/channels/wecom-app/callback-server.mjs +471 -0
  63. package/src/channels/wecom-app/config-store.mjs +240 -0
  64. package/src/channels/wecom-app/harness-client.mjs +11 -0
  65. package/src/channels/wecom-app/state-store.mjs +107 -0
  66. package/src/channels/wecom-app/wecom-app-api.mjs +432 -0
  67. package/src/channels/wecom-app/wecom-app-bridge.mjs +1059 -0
  68. package/src/channels/wecom-app/wecom-app-controller.mjs +440 -0
  69. package/src/channels/wecom-app/wecom-app-runtime.mjs +221 -0
package/README.en.md CHANGED
@@ -60,6 +60,8 @@ Connect IM bots to DeepSeek Harness by scanning a QR code, using an App Manifest
60
60
 
61
61
  Other IM platforms can be added through the same channel-adapter structure.
62
62
 
63
+ 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).
64
+
63
65
  All nine built-in channels 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. 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.
64
66
 
65
67
  ### Results after a reply timeout
@@ -130,8 +132,14 @@ Use the proxy URL required by your network and restart the Host after changing i
130
132
  | --- | --- |
131
133
  | Bot workspace | Each bot stores its workspace independently. New bots start with the Host's current working directory, which can later be changed from the bot card. |
132
134
  | Model | Every bot in all nine IM channels can choose a model directly below its workspace, or follow the Host default. A change applies only to later new Sessions; send `/new` and then an ordinary message in the current chat to use it. |
135
+ | Reasoning effort | Explicitly choose an effort supported by the selected model, or follow the model default. Levels, descriptions, and defaults come from DSH. Switching models restores the new model's default effort. Each bot saves its own choice, which applies only to later new Sessions. |
133
136
  | Agent Preset | Each bot can choose an Agent Preset on its settings card. When none is chosen, new Sessions follow the Host's `agent-presets.default`. A channel-level `config.agentPreset` is only the default for later new bots on that channel. Changing the preset never modifies or clears existing Sessions; if the current chat already has a Session, send `/new` and then a regular message to create one with the new selection. |
134
137
  | Context enhancement | Open settings from a bot card to enable groups and DMs independently. Both switches default to off, including for existing bots after an upgrade. |
138
+ | Session channel identity | Sessions from all nine IM channels and AI Office on the local Host are marked with their source. The Web Session list and search results display channel logos in place of prefixes such as “WeChat ·”, preserving DSH's automatic title generation and updates. Existing Sessions receive the prefix when next loaded. |
139
+
140
+ Channel prefixes are appended after DSH produces a title, preserving its complete text and automatic/manual source without pinning automatic titles or making additional model calls. Regeneration, refresh, and restarts do not stack prefixes; actual manual renames retain DSH's normal pinning behavior. This feature uses the current Host's Session events; an explicit remote `harnessBaseUrl` requires the plugin on the destination Host.
141
+
142
+ Logos are a dsh-im browser enhancement and require no changes to DSH. The adapter preserves original text nodes, clicks, menus, and dragging; copied titles, screen readers, and other surfaces retain the textual channel name. Unrecognized DSH page structures, unsupported browsers, or image-loading failures keep the text prefix. Unloading the plugin restores the original display.
135
143
 
136
144
  ### Proactive delivery
137
145
 
@@ -179,7 +187,7 @@ See the [Proactive Delivery Guide](PROACTIVE_DELIVERY.en.md) ([简体中文](PRO
179
187
  | `/batch` | Start batch input in a direct chat and collect up to 10 text messages. |
180
188
  | `/send` | Submit the collected messages, in order, as one input. |
181
189
  | `/cancel` | Cancel batch input and discard its collected messages. |
182
- | `/repair` | In a Feishu direct chat, incrementally repair the card callback and permissions required for media and the native Slash Command panel. |
190
+ | `/repair` | In a Feishu direct chat, incrementally repair the card callback and permissions required for media, group bot mentions, and the native Slash Command panel. |
183
191
  | `/compact` | Immediately compact older context in the Session bound to the current chat. |
184
192
  | `/workspace <workspace index or absolute path>`, `/ws <workspace index or absolute path>` | Switch the current bot's Harness workspace by `/workspacelist` index or absolute path. |
185
193
  | `/workspacelist`, `/workspaces`, `/wsl` | List workspace absolute paths that still exist on the current Harness Host. |
@@ -200,7 +208,7 @@ DingTalk menus use a shared template built into the plugin; no template setup is
200
208
 
201
209
  - **Image understanding**: all nine built-in channels 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.
202
210
  - **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.
203
- - **Choose a model from a bot card**: every bot card in all nine IM channels offers the Host's available models directly below the workspace, plus an option to follow the default. The selection is stored per bot and used only for later new Sessions; existing Sessions and replies already in progress are unchanged.
211
+ - **Choose a model and reasoning effort from a bot card**: every bot card in all nine IM channels 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.
204
212
  - **Choose an Agent Preset from a bot card**: every bot card can select one of the Host's existing Agent Presets, or follow the Host default. The change applies only to that bot and only to later new Sessions; existing Sessions and replies already in progress are left unchanged.
205
213
  - **Check the connection and send a test message**: when a bot is online, clicking **Check connection** verifies the platform connection and sends a “DeepSeek Harness connection test succeeded” message to the bot's most recently remembered direct conversation; WhatsApp uses the account's self-chat. The test neither creates a Harness Session nor invokes the model. The bot must have received at least one direct message before it has a remembered test target; otherwise the page reports that no test conversation is available yet.
206
214
  - **Retry a connection or remove an integration**: when a bot is offline, its card action changes to **Retry connection**. Use **Remove integration** when the bot is no longer needed. Each action affects only the selected bot and leaves other bots and channels unchanged.
package/README.md CHANGED
@@ -37,7 +37,7 @@
37
37
 
38
38
  ## 简介
39
39
 
40
- 通过扫码、App Manifest 或已有机器人凭据把 IM 机器人接入 DeepSeek Harness,并让本机 Harness 主动连接公网 AI Office。一个插件、一个设置入口,统一管理九种 IM 渠道和 AI Office Connector。**每个 IM 渠道都支持接入多个机器人**,各机器人的连接状态、工作区、模型和会话绑定彼此独立。
40
+ 通过扫码、App Manifest 或已有机器人凭据把 IM 机器人接入 DeepSeek Harness,并让本机 Harness 主动连接公网 AI Office。一个插件、一个设置入口,统一管理十种 IM 渠道和 AI Office Connector。**每个 IM 渠道都支持接入多个机器人**,各机器人的连接状态、工作区、模型和会话绑定彼此独立。
41
41
 
42
42
  Connect IM bots to DeepSeek Harness by scanning a QR code, using an App Manifest, or entering existing bot credentials, and let the local Harness connect outward to a public AI Office. One plugin and one settings entry manage nine multi-bot IM channels and the AI Office Connector.
43
43
 
@@ -55,25 +55,30 @@ Connect IM bots to DeepSeek Harness by scanning a QR code, using an App Manifest
55
55
  | 微信 | 使用微信扫码绑定机器人 | 腾讯 iLink 长轮询收发消息;等待 Harness 回答时显示“正在输入”,最终回复按 1,800 字符分段发送 |
56
56
  | 钉钉 | 扫码创建机器人,或使用 Client ID + Client Secret 手动绑定 | 钉钉 Stream 长连接;通过 AI Card 流式显示回答 |
57
57
  | 企业微信 | 使用企业微信 App 扫码创建智能机器人,或使用 Bot ID + Secret 手动绑定 | 官方 WebSocket 长连接;原生显示“正在思考中”、工具执行进度和流式回答 |
58
+ | 企业微信应用 | 在企业微信管理后台创建自建应用,填写企业 ID、AgentId、Secret、Token、EncodingAESKey(可选代理地址) | HTTP 回调接收;私聊支持流式回复(微信端不支持时自动改为分段文本),支持图片输入与结果文件回传;成员的微信关注该企业的微信插件后可在微信中直接使用 |
58
59
  | QQ | 使用手机 QQ 扫码创建机器人,或使用 AppID + AppSecret 手动绑定 | WebSocket 长连接;私聊显示“正在输入”并以单条 Markdown 回复,群聊被 @ 后只发送最终答案 |
59
60
  | Slack | 使用预置 App Manifest 创建应用,再填写 Bot Token(`xoxb-`)和 App Token(`xapp-`) | Socket Mode 长连接;私聊直接回复,频道被 @ 后响应,优先使用官方流式消息 API |
60
61
  | Telegram | 使用 @BotFather 生成的 Bot Token | Bot API 长轮询;默认私聊直接响应、群聊被提及或回复时响应,也可为每个机器人独立启用私聊白名单安全模式;私聊通过 Rich Message Draft 流式预览并持久化最终富消息,群聊和 Topic 原位完成占位消息,平台不支持时回退为普通文字 |
61
62
  | Discord | 使用 Developer Portal 生成的 Bot Token | Gateway v10 长连接;私信直接回复;服务器文字/公告频道首次 @ 后创建原生 Thread,后续在线程中无需重复 @,并通过编辑消息流式显示回答 |
62
63
  | WhatsApp | 使用手机 WhatsApp 扫码关联设备 | WhatsApp Web 长连接;默认仅响应账号自聊,也可切换到指定联系人或开放响应模式;显示已读和“正在输入”,通过每秒编辑同一条消息显示工具进度和逐步生成的回答,长回复自动分段,编辑失败时回退为完整文字回复 |
63
64
 
65
+ 企业微信自建应用的回调基址、代理地址和企业可信 IP 配置,见[企业微信自建应用接入说明](docs/企业微信自建应用接入.md)。
66
+
64
67
  其他 IM 平台可继续按同一渠道适配器结构接入。
65
68
 
66
- 九个内置渠道均支持把 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。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。
69
+ 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)。
70
+
71
+ 十个内置渠道均支持把 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。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。
67
72
 
68
73
  ### 超时后的结果补发
69
74
 
70
- 九个渠道共用超时任务跟踪:收到“等待模型回复超时”后,插件会继续检查原任务,完成后向原聊天或线程补发最终文字;插件重启或连接恢复后也会继续检查。`/stop` 只停止当前聊天提交的对应回合,切换会话后不再向该聊天补发旧会话的结果。无需新增设置,正常回复流程保持原样。
75
+ 十个渠道共用超时任务跟踪:收到“等待模型回复超时”后,插件会继续检查原任务,完成后向原聊天或线程补发最终文字;插件重启或连接恢复后也会继续检查。`/stop` 只停止当前聊天提交的对应回合,切换会话后不再向该聊天补发旧会话的结果。无需新增设置,正常回复流程保持原样。
71
76
 
72
77
  补发仍受渠道发送权限和配额限制。明确发送失败最多尝试三次;发送结果不确定时保留记录并停止自动重试,避免重复消息。此机制恢复文字结果和终态通知,不重放问题、审批或文件工具调用。详见[延迟交付说明](docs/deferred-delivery.md)。
73
78
 
74
79
  ### 结果文件与图片回传
75
80
 
76
- 九个内置渠道均已实现把 Harness 可读取的文件作为渠道原生附件回传。已有文件和当前任务新生成的文件都可以直接发送;该能力对所有已连接机器人默认可用,无需开关或机器人白名单,原有文字、图片、流式回复、命令和会话行为保持不变。
81
+ 十个内置渠道均已实现把 Harness 可读取的文件作为渠道原生附件回传。已有文件和当前任务新生成的文件都可以直接发送;该能力对所有已连接机器人默认可用,无需开关或机器人白名单,原有文字、图片、流式回复、命令和会话行为保持不变。
77
82
 
78
83
  模型调用文件回传工具后,插件把指定文件交给当前渠道的原生接口。图片会优先以原生图片消息呈现;渠道不支持或明确拒绝图片发送时自动回退为文件附件,发送结果不确定时不会补发文件造成重复消息。插件不额外设置文件来源、创建时间、工作区边界、扩展名、内容、数量、大小或有效期规则;文件只需真实存在且可读取。渠道平台仍可能依据自身权限、配额、文件能力或账号等级拒绝发送,插件会按平台返回结果提示。
79
84
 
@@ -133,8 +138,14 @@ dsh web
133
138
  | --- | --- |
134
139
  | 机器人工作区 | 每个机器人独立保存工作区。新机器人默认使用 Host 当时的工作目录;之后可在机器人卡片中修改。 |
135
140
  | 模型 | 九个 IM 渠道的每个机器人都可在工作区下方独立选择模型;未选择时跟随 Host 默认。切换只影响之后新建的会话;当前聊天先发送 `/new`,再发送普通消息才会使用新选择。 |
141
+ | 思考强度 | 在模型下方显式选择该模型支持的思考强度,或跟随模型默认。档位、说明和默认值来自 DSH;切换模型后恢复新模型默认强度。每个机器人独立保存,只影响之后新建的会话。 |
136
142
  | Agent Preset | 每个机器人可在设置页卡片中选择 Agent Preset。未选择时跟随 Host 的 `agent-presets.default`;渠道级 `config.agentPreset` 只作为该渠道之后新接入机器人的默认值。切换不会修改或清空已有会话;若当前聊天已有会话,需先发送 `/new`,再发送一条普通消息,才会按新选择创建会话。 |
137
143
  | 上下文增强 | 从机器人卡片打开设置,分别决定群聊、私聊是否增强;两个开关默认均关闭,旧机器人升级后也不会自动开启。 |
144
+ | 会话渠道标识 | 本机 Host 的九个 IM 渠道与 AI Office 会话自动标记来源。Web 会话列表和搜索结果将「微信 ·」等前缀显示为渠道 Logo;保留 DSH 原有的自动标题生成与更新。已有会话在下次加载时补上。 |
145
+
146
+ 渠道前缀在 DSH 生成标题后追加,完整保留原始标题与自动/手动来源,不会将自动标题锁定为手动命名,也不会额外调用模型。重复生成、刷新或重启不会叠加前缀;真实的手动命名仍遵循 DSH 原有的锁定规则。此功能由当前 Host 的会话事件驱动,显式连接远程 `harnessBaseUrl` 时需在目标 Host 上安装该插件。
147
+
148
+ Logo 由 dsh-im 的浏览器适配显示,无需修改 DSH。适配保留原始文字节点和点击、菜单、拖拽操作;复制、读屏及其他界面仍保留文字渠道名。DSH 页面结构不匹配、浏览器不支持或图标加载失败时,自动保留文字前缀;插件卸载后恢复原始显示。
138
149
 
139
150
  ### 主动投递
140
151
 
@@ -182,7 +193,7 @@ dsh web
182
193
  | `/batch` | 在私聊中开启批量输入,最多收集 10 条纯文字消息。 |
183
194
  | `/send` | 将已收集的消息按原顺序作为一次输入提交。 |
184
195
  | `/cancel` | 取消批量输入并丢弃已收集的消息。 |
185
- | `/repair` | 在飞书私聊中增量修复卡片回调,并补全媒体与原生 Slash Command 面板所需的权限。 |
196
+ | `/repair` | 在飞书私聊中增量修复卡片回调,并补全媒体、群聊机器人 @ 消息与原生 Slash Command 面板所需的权限。 |
186
197
  | `/compact` | 立即压缩当前聊天绑定会话的较早上下文。 |
187
198
  | `/workspace <工作区序号或绝对路径>`、`/ws <工作区序号或绝对路径>` | 按 `/workspacelist` 序号或绝对路径切换当前机器人的 Harness 工作区。 |
188
199
  | `/workspacelist`、`/workspaces`、`/wsl` | 列出当前 Harness Host 上仍然存在的工作区绝对路径。 |
@@ -203,7 +214,7 @@ dsh web
203
214
 
204
215
  - **图片识别**:九个内置渠道都可以把 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。
205
216
  - **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。
206
- - **在机器人卡片选择模型**:九个 IM 渠道的每张机器人卡片都在工作区下方提供模型选择,可选 Host 当前可用模型或跟随默认。选择按机器人独立保存,只用于之后新建的 Session;已有 Session 和正在生成的回复不受影响。
217
+ - **在机器人卡片选择模型与思考强度**:九个 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。
207
218
  - **在机器人卡片选择 Agent Preset**:设置页中的每张机器人卡片都可以选择 Host 已有的 Agent Preset,或跟随 Host 默认。切换只作用于该机器人,并且只影响之后新建的会话;已有会话和正在生成的回复不受影响。
208
219
  - **检查连接并发送测试消息**:机器人在线时,点击卡片上的「检查连接」会检查平台连接,并向该机器人最近记录的私聊发送一条“DeepSeek Harness 连接测试成功”消息;WhatsApp 会发送到账号自聊。测试消息不会创建 Harness Session,也不会调用模型。机器人必须至少收到过一条私聊才能记住测试目标,否则页面会提示尚无可用的测试会话。
209
220
  - **重试连接和移除接入**:机器人离线时,卡片上的操作会变为「重试连接」;不再使用时可以点击「移除接入」。这些操作都只作用于所选机器人,不影响其他机器人或渠道。