@tencent-ai/agent-sdk 0.3.101 → 0.3.102

package/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tencent-ai/codebuddy-code",
-  "version": "2.69.0",
+  "version": "2.70.0",
   "description": "Use CodeBuddy, Tencent's AI assistant, right from your terminal. CodeBuddy can understand your codebase, edit files, run terminal commands, and handle entire workflows for you.",
   "main": "lib/node/index.js",
   "typings": "lib/node/index.d.ts",

package/cli/product.cloudhosted.json

@@ -404,6 +404,6 @@
     "ImageGen": true,
     "ScheduledTasks": true
   },
-  "commit": "985e7e77a8afb766fb5f3c9b3c3104eef1ff9978",
-  "date": "2026-03-30T14:25:41.521Z"
+  "commit": "d8125410a5d7fe59126e157cd53143914cd75f08",
+  "date": "2026-03-31T08:09:41.720Z"
 }

package/cli/product.internal.json

@@ -534,6 +534,6 @@
       }
     }
   },
-  "commit": "985e7e77a8afb766fb5f3c9b3c3104eef1ff9978",
-  "date": "2026-03-30T14:25:41.536Z"
+  "commit": "d8125410a5d7fe59126e157cd53143914cd75f08",
+  "date": "2026-03-31T08:09:41.719Z"
 }

package/cli/product.ioa.json

@@ -892,6 +892,6 @@
       }
     }
   },
-  "commit": "985e7e77a8afb766fb5f3c9b3c3104eef1ff9978",
-  "date": "2026-03-30T14:25:41.524Z"
+  "commit": "d8125410a5d7fe59126e157cd53143914cd75f08",
+  "date": "2026-03-31T08:09:41.722Z"
 }

package/cli/product.json

@@ -682,11 +682,11 @@
     },
     {
       "name": "tool-slashcommand-description",
-      "template": "Execute a slash command within the main conversation\n\n**IMPORTANT - Intent Matching:**\nBefore starting any task, CHECK if the user's request matches one of the slash commands listed below. This tool exists to route user intentions to specialized workflows.\n\nHow slash commands work:\nWhen you use this tool or when a user types a slash command, you will see <command-message>{name} is running…</command-message> followed by the expanded prompt. For example, if .codebuddy/commands/foo.md contains \"Print today's date\", then /foo expands to that prompt in the next message.\n\nUsage:\n- `command` (required): The slash command to execute, including any arguments\n- Example: `command: \"/review-pr 123\"`\n\nIMPORTANT: Only use this tool for custom slash commands that appear in the Available Commands list below. Do NOT use for:\n- Built-in CLI commands (like /help, /clear, etc.)\n- Commands not shown in the list\n- Commands you think might exist but aren't listed\n{%- if truncatedCustomCommands.length > 0 %}\n\nAvailable Commands:\n{%- for command in truncatedCustomCommands %}\n- {{command.name}} {{command.argumentHint}}: {{command.description}}\n{%- endfor %}\n{%- if truncatedCustomCommands.length < customCommands.length %}\n\n(Showing {{truncatedCustomCommands.length}} of {{customCommands.length}} commands due to token limits)\n{%- endif %}\n{%- endif %}\n\nNotes:\n- When a user requests multiple slash commands, execute each one sequentially and check for <command-message>{name} is running…</command-message> to verify each has been processed\n- Do not invoke a command that is already running. For example, if you see <command-message>foo is running…</command-message>, do NOT use this tool with \"/foo\" - process the expanded prompt in the following message\n- Only custom slash commands with descriptions are listed in Available Commands. If a user's command is not listed, ask them to check the slash command file and consult the docs.\n"
+      "template": "Execute a slash command within the main conversation\n\nThis tool supports both **custom slash commands** and **built-in commands**. Use it to execute slash commands on behalf of the user.\n\nUsage:\n- `command` (required): The slash command to execute, including any arguments\n- Example: `command: \"/model list\"`, `command: \"/model gpt-4o\"`, `command: \"/config list\"`, `command: \"/context\"`\n\n## Built-in Commands\n\nYou can call these built-in commands when the user's intent matches. All built-in commands support a parameter mode for model-driven calls. Without parameters they open an interactive panel (TUI only).\n\n**Information queries (no approval needed):**\n- `/help` - Show help and available commands\n- `/status` - Show version, model, account, API connectivity, and tool statuses\n- `/todos` - Display the current session's todo list\n- `/plan` - Preview the current plan file content\n- `/skills` - List available skills\n- `/tasks` - List and manage background tasks\n- `/model list` - List all available models with current selection\n- `/resume list` - List all available sessions (id, time, summary)\n- `/resume <session-id>` - Resume a specific session\n- `/config list` - List current settings\n- `/config get <key>` - Get a specific setting value\n\n**Configuration changes (needs approval):**\n- `/model <model-id>` - Switch the AI model (e.g., `/model gpt-4o`)\n- `/model:text-to-image list` - List available text-to-image models\n- `/model:text-to-image <model-id>` - Switch the text-to-image model\n- `/model:image-to-image list` - List available image-to-image models\n- `/model:image-to-image <model-id>` - Switch the image-to-image model\n- `/config set <key> <value>` - Change a setting (e.g., `/config set theme dark`)\n- `/clear` - Start a fresh conversation\n- `/rename <name>` - Rename the current conversation\n- `/theme` - Configure theme\n- `/output-style` - Set the output style\n\nDo NOT use this tool for commands not listed above (e.g., /exit, /login, /vim, etc.).\n{%- if truncatedCustomCommands.length > 0 %}\n\n## Custom Commands\n{%- for command in truncatedCustomCommands %}\n- {{command.name}} {{command.argumentHint}}: {{command.description}}\n{%- endfor %}\n{%- if truncatedCustomCommands.length < customCommands.length %}\n\n(Showing {{truncatedCustomCommands.length}} of {{customCommands.length}} commands due to token limits)\n{%- endif %}\n{%- endif %}\n\nNotes:\n- When a user requests multiple slash commands, execute each one sequentially and check for <command-message>{name} is running…</command-message> to verify each has been processed\n- Do not invoke a command that is already running. For example, if you see <command-message>foo is running…</command-message>, do NOT use this tool with \"/foo\" - process the expanded prompt in the following message\n"
     },
     {
       "name": "tool-skill-description",
-      "template": "Execute a skill within the main conversation\n\n<skills_instructions>\nWhen users ask you to perform tasks, check if any of the available skills below can help complete the task more effectively. Skills provide specialized capabilities and domain knowledge.\n\nWhen users ask you to run a \"slash command\" or reference \"/<something>\" (e.g., \"/commit\", \"/review-pr\"), they are referring to a skill. Use this tool to invoke the corresponding skill.\n\n<example>\nUser: \"run /commit\"\nAssistant: [Calls Skill tool with skill: \"commit\"]\n</example>\n\nHow to invoke:\n- Use this tool with the skill name and optional arguments\n- Examples:\n  - `skill: \"pdf\"` - invoke the pdf skill\n  - `skill: \"commit\", args: \"-m 'Fix bug'\"` - invoke with arguments\n  - `skill: \"review-pr\", args: \"123\"` - invoke with arguments\n  - `skill: \"ms-office-suite:pdf\"` - invoke using fully qualified name\n\nImportant:\n- When a skill is relevant, you must invoke this tool IMMEDIATELY as your first action\n- NEVER just announce or mention a skill in your text response without actually calling this tool\n- This is a BLOCKING REQUIREMENT: invoke the relevant Skill tool BEFORE generating any other response about the task\n- Only use skills listed in <available_skills> below\n- Do not invoke a skill that is already running\n- Do not use this tool for built-in CLI commands (like /help, /clear, etc.)\n- If you see a <command-name> tag in the current conversation turn, the skill has ALREADY been loaded - follow the instructions directly instead of calling this tool again\n</skills_instructions>\n\n<available_skills>\n{%- if skills and skills.length > 0 -%}\n{%- for skill in skills %}\n<skill>\n<name>\n{{skill.name}}\n</name>\n<description>\n{{skill.description}}\n</description>\n<location>\n{{skill.source}}\n</location>\n{%- if skill.allowedTools %}\n<allowed-tools>\n{{skill.allowedTools.join(', ')}}\n</allowed-tools>\n{%- endif %}\n</skill>\n{%- endfor -%}\n{%- endif %}\n</available_skills>\n"
+      "template": "Execute a skill or built-in command within the main conversation\n\n<skills_instructions>\nWhen users ask you to perform tasks, check if any of the available skills below can help complete the task more effectively. Skills provide specialized capabilities and domain knowledge.\n\nWhen users ask you to run a \"slash command\" or reference \"/<something>\" (e.g., \"/commit\", \"/review-pr\", \"/clear\", \"/model\"), they are referring to a skill or built-in command. Use this tool to invoke it.\n\n<example>\nUser: \"run /commit\"\nAssistant: [Calls Skill tool with skill: \"commit\"]\n</example>\n\n<example>\nUser: \"switch to gpt-4o\"\nAssistant: [Calls Skill tool with skill: \"model\", args: \"gpt-4o\"]\n</example>\n\n<example>\nUser: \"clear the conversation\"\nAssistant: [Calls Skill tool with skill: \"clear\"]\n</example>\n\nHow to invoke:\n- Use this tool with the skill name and optional arguments\n- Examples:\n  - `skill: \"pdf\"` - invoke the pdf skill\n  - `skill: \"commit\", args: \"-m 'Fix bug'\"` - invoke with arguments\n  - `skill: \"review-pr\", args: \"123\"` - invoke with arguments\n  - `skill: \"ms-office-suite:pdf\"` - invoke using fully qualified name\n  - `skill: \"model\", args: \"list\"` - list available AI models\n  - `skill: \"model\", args: \"gpt-4o\"` - switch AI model\n  - `skill: \"clear\"` - start a fresh conversation\n  - `skill: \"resume\", args: \"list\"` - list available sessions\n  - `skill: \"config\", args: \"set theme dark\"` - change a setting\n\nImportant:\n- When a skill is relevant, you must invoke this tool IMMEDIATELY as your first action\n- NEVER just announce or mention a skill in your text response without actually calling this tool\n- This is a BLOCKING REQUIREMENT: invoke the relevant Skill tool BEFORE generating any other response about the task\n- Do not invoke a skill that is already running\n- If you see a <command-name> tag in the current conversation turn, the skill has ALREADY been loaded - follow the instructions directly instead of calling this tool again\n</skills_instructions>\n\n<available_skills>\n{%- if skills and skills.length > 0 -%}\n{%- for skill in skills %}\n<skill>\n<name>\n{{skill.name}}\n</name>\n<description>\n{{skill.description}}\n</description>\n<location>\n{{skill.source}}\n</location>\n{%- if skill.allowedTools %}\n<allowed-tools>\n{{skill.allowedTools.join(', ')}}\n</allowed-tools>\n{%- endif %}\n</skill>\n{%- endfor -%}\n{%- endif %}\n</available_skills>\n"
     },
     {
       "name": "agent-statusline-instructions",
@@ -1480,6 +1480,6 @@
       "description": "Send a reply to a WeCom (企业微信) user. For text: pass text (markdown supported)."
     }
   ],
-  "commit": "985e7e77a8afb766fb5f3c9b3c3104eef1ff9978",
-  "date": "2026-03-30T14:25:41.537Z"
+  "commit": "d8125410a5d7fe59126e157cd53143914cd75f08",
+  "date": "2026-03-31T08:09:41.730Z"
 }

package/cli/product.selfhosted.json

@@ -293,6 +293,6 @@
     "DeferToolLoading": true,
     "ScheduledTasks": true
   },
-  "commit": "985e7e77a8afb766fb5f3c9b3c3104eef1ff9978",
-  "date": "2026-03-30T14:25:41.533Z"
+  "commit": "d8125410a5d7fe59126e157cd53143914cd75f08",
+  "date": "2026-03-31T08:09:41.703Z"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tencent-ai/agent-sdk",
-  "version": "0.3.101",
+  "version": "0.3.102",
   "description": "CodeBuddy Code SDK for JavaScript/TypeScript",
   "main": "lib/index.js",
   "typings": "lib/index.d.ts",