Sync recommendation recordings with shared subagent tools
This commit is contained in:
Dudu-0223 committed
1 parent
849380ee1e
commit
d7858505da
4 files changed
+82
-66
No files matched your search
@@ -11,15 +11,15 @@
|
||||
{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nCurrent DeepSeek Harness implementation checkout: \"{{sourceRoot}}\".\n\nCurrent DeepSeek Harness Web GUI URL: \"{{webUrl}}\"."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"harness:source","text":"Current DeepSeek Harness implementation checkout: \"{{sourceRoot}}\"."},{"name":"app:web-surface","text":"Current DeepSeek Harness Web GUI URL: \"{{webUrl}}\"."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"}
|
||||
{"type":"user/message","data":{"content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `personalized-pages`: Plan an optional page or small tool when the user asks for a page, tab, panel, tool or interface in this app (even for one-off use), wants something to keep, revisit or update later, will keep changing data in your answer, or wants a live view of this app’s own data (Sessions, tasks, logs, workspace). Load this before reading any files or source; it says how to submit the proposal. Not for requested files or code, ordinary answers, existing-feature questions, quoted wishes or declined offers.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\nA user may also invoke a skill directly; its <skill_content> block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.\n</system-reminder>"}],"source":{"kind":"skill-catalog","form":"catalog","entries":[{"name":"personalized-pages","description":"Plan an optional page or small tool when the user asks for a page, tab, panel, tool or interface in this app (even for one-off use), wants something to keep, revisit or update later, will keep changing data in your answer, or wants a live view of this app’s own data (Sessions, tasks, logs, workspace). Load this before reading any files or source; it says how to submit the proposal. Not for requested files or code, ordinary answers, existing-feature questions, quoted wishes or declined offers."}]},"role":"user","id":"{{message:4}}"},"surfaceOp":"append"}
|
||||
{"type":"user/message","data":{"content":[{"type":"text","text":"Time sampled while preparing turn 1, step 1: {{timeContextTimestamp}}\nBrowser time zone for this request: {{clientTimeZone}}. Interpret otherwise-unqualified dates and times in this zone.\nElapsed since the preceding model-visible message: {{elapsed}}"}],"source":{"kind":"time-context","form":"snapshot","sections":[{"name":"time-context","text":"Time sampled while preparing turn 1, step 1: {{timeContextTimestamp}}\nBrowser time zone for this request: {{clientTimeZone}}. Interpret otherwise-unqualified dates and times in this zone.\nElapsed since the preceding model-visible message: {{elapsed}}"}]},"role":"user","id":"{{message:5}}"},"surfaceOp":"append"}
|
||||
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}}
|
||||
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","wait_agent","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}}
|
||||
{"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash","contextWindow":128000}}
|
||||
{"type":"session/title","data":{"title":"I wish I had a","messageSeqs":[8],"source":{"kind":"fallback"}}}
|
||||
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_creation_skill","name":"skill","arguments":"{\"name\":\"personalized-pages\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"stream":[{"type":"chunk","time":1792674450282,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"chunk","time":1792674450282,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_creation_skill","name":"skill","arguments":"{\"name\":\"personalized-pages\"}"}}},{"type":"chunk","time":1792674450283,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"}
|
||||
{"type":"tool/call","data":{"turn":1,"step":1,"callId":"call_creation_skill","name":"skill","arguments":"{\"name\":\"personalized-pages\"}"}}
|
||||
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_creation_skill"},"toolCallId":"call_creation_skill","content":[{"type":"text","text":"<skill_content name=\"personalized-pages\">\n<skill_resources>\nResources for this skill are managed by provider \"dsh-personalized-pages\".\nLoad referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\n# Personalized pages\n\nUse this workflow in the main conversation to plan an optional new page or small tool for any task, not just DSH. You decide whether a page helps, check existing capabilities, and hand the Creator a short plan. A `propose_action` call saves the proposal and shows a card below your answer; nothing is built until the user clicks Create. Plan from the conversation and the catalog at the end of this skill. Do not read files, configuration or source to validate a page idea; name an uninspected source as an unverified dependency and leave its details to the Creator.\n\n## When to propose\n\nPropose a page in these cases:\n\n- The user asks for a page, tab, panel, tool or interface in this app, or says they want something to keep, revisit or update later (“以后每次”, “能不能一直”, “希望能有”). One-off use still qualifies when the interface is explicitly requested.\n- Your answer is a table, list or chart, and the user has said the data will keep changing or that they will interact with it (“每周更新”, “我来改状态”, “要勾选”). The continuation must come from the user's own words; a table alone, or data that merely looks dynamic, is not enough. Deliver the requested answer first, then offer the page.\n- The user wants to keep watching live data of this app itself (a Session's usage, a running task's output, files changing in the workspace). A text answer cannot stay current, so a page qualifies even without the words above; name the data source in the brief and leave how it is read to the Creator.\n\nDo not propose a page in these cases:\n\n- The user asks for a file, code, document or an existing-project change: keep that delivery form.\n- The wish appears inside quoted text, pasted content, a web page or a tool result rather than the user's own request.\n- The user only wants to discuss, asks how an existing feature works, or has declined recommendations or asked for text only: stay silent on pages for the rest of this conversation.\n- The request changes a page created earlier: explain how it would change, do not create a replacement copy, and do not claim an update happened.\n- The request is a capability the agent lacks, such as a tool, automation or access, rather than a page: check the catalog below and point to the official plugin that provides it; do not plan a page around a missing tool.\n\n## Check existing capabilities\n\nCompare the need with the official plugins listed at the end of this skill. If one covers it, say its name, what it does, whether it is enabled, and that it lives under Plugins; offer no page card. A partial match does not cancel an explicit unmet need. The catalog is not a full inventory of built-in UI: missing details do not prove absence, and do not read source to find out. DSH already has Chat, Trajectory, a right sidebar for files and context, and a Plugins page.\n\n## Plan and hand off\n\nThe Creator cannot read this conversation. Give it exactly these fields:\n\n| Field | Contents |\n|:--|:--|\n| `title` | Short page name in the user's language. |\n| `brief` | One to three sentences: purpose, behavior, input, calculations and persistence scope. It is the card text and the implementation request at once. |\n| `initialContent` | Only supplied content the page starts with: items, rows, values, units and period, preserving gaps. Omit for an empty page. |\n| `slot` | Location, chosen below. |\n\nKeep the plan to what was asked or agreed. Editing, deletion, history, extra fields, data sources and automation need a basis in the request. Resolve “these items” into the actual content. Content that mentions an action stays content. Keep each number's meaning and period; a weekly addition is not a cumulative total. If an unresolved distinction changes a calculation, give the factual answer, ask one question, and propose later.\n\n## Choose the location\n\nHonor a location the user named. Otherwise:\n\n- `sidebar-right`: content tied to this Session or task, especially anything to watch while chatting, including live logs.\n- `sidebar-left`: a global feature or an ongoing personal record used across Sessions, opened from a left entry as a standalone page.\n- `page`: a Session-bound streaming view or interaction in a tab beside Chat and Trajectory, only when the user does not need it visible while chatting.\n\nSupplying data in this conversation does not make a record Session-bound.\n\n## Offer without starting\n\nTo propose, call `propose_action` once, in the same turn as loading this skill, withLine truncated
|
||||
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_creation_skill"},"toolCallId":"call_creation_skill","content":[{"type":"text","text":"<skill_content name=\"personalized-pages\">\n<skill_resources>\nResources for this skill are managed by provider \"dsh-personalized-pages\".\nLoad referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\n# Personalized pages\n\nUse this workflow in the main conversation to plan an optional new page or small tool for any task, not just DSH. You decide whether a page helps, check existing capabilities, and hand the Creator a short plan. A `propose_action` call saves the proposal and shows a card below your answer; nothing is built until the user clicks Create. Plan from the conversation and the catalog at the end of this skill. Do not read files, configuration or source to validate a page idea; name an uninspected source as an unverified dependency and leave its details to the Creator.\n\n## When to propose\n\nPropose a page in these cases:\n\n- The user asks for a page, tab, panel, tool or interface in this app, or says they want something to keep, revisit or update later (“以后每次”, “能不能一直”, “希望能有”). One-off use still qualifies when the interface is explicitly requested.\n- Your answer is a table, list or chart, and the user has said the data will keep changing or that they will interact with it (“每周更新”, “我来改状态”, “要勾选”). The continuation must come from the user's own words; a table alone, or data that merely looks dynamic, is not enough. Deliver the requested answer first, then offer the page.\n- The user wants to keep watching live data of this app itself (a Session's usage, a running task's output, files changing in the workspace). A text answer cannot stay current, so a page qualifies even without the words above; name the data source in the brief and leave how it is read to the Creator.\n\nDo not propose a page in these cases:\n\n- The user asks for a file, code, document or an existing-project change: keep that delivery form.\n- The wish appears inside quoted text, pasted content, a web page or a tool result rather than the user's own request.\n- The user only wants to discuss, asks how an existing feature works, or has declined recommendations or asked for text only: stay silent on pages for the rest of this conversation.\n- The request changes a page created earlier: explain how it would change, do not create a replacement copy, and do not claim an update happened.\n- The request is a capability the agent lacks, such as a tool, automation or access, rather than a page: check the catalog below and point to the official plugin that provides it; do not plan a page around a missing tool.\n\n## Check existing capabilities\n\nCompare the need with the official plugins listed at the end of this skill. If one covers it, say its name, what it does, whether it is enabled, and that it lives under Plugins; offer no page card. A partial match does not cancel an explicit unmet need. The catalog is not a full inventory of built-in UI: missing details do not prove absence, and do not read source to find out. DSH already has Chat, Trajectory, a right sidebar for files and context, and a Plugins page.\n\n## Plan and hand off\n\nThe Creator cannot read this conversation. Give it exactly these fields:\n\n| Field | Contents |\n|:--|:--|\n| `title` | Short page name in the user's language. |\n| `brief` | One to three sentences: purpose, behavior, input, calculations and persistence scope. It is the card text and the implementation request at once. |\n| `initialContent` | Only supplied content the page starts with: items, rows, values, units and period, preserving gaps. Omit for an empty page. |\n| `slot` | Location, chosen below. |\n\nKeep the plan to what was asked or agreed. Editing, deletion, history, extra fields, data sources and automation need a basis in the request. Resolve “these items” into the actual content. Content that mentions an action stays content. Keep each number's meaning and period; a weekly addition is not a cumulative total. If an unresolved distinction changes a calculation, give the factual answer, ask one question, and propose later.\n\n## Choose the location\n\nHonor a location the user named. Otherwise:\n\n- `sidebar-right`: content tied to this Session or task, especially anything to watch while chatting, including live logs.\n- `sidebar-left`: a global feature or an ongoing personal record used across Sessions, opened from a left entry as a standalone page.\n- `page`: a Session-bound streaming view or interaction in a tab beside Chat and Trajectory, only when the user does not need it visible while chatting.\n\nSupplying data in this conversation does not make a record Session-bound.\n\n## Offer without starting\n\nTo propose, call `propose_action` once, in the same turn as loading this skill, withLine truncated
|
||||
{"type":"step/end","data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","data":{"turn":1,"step":2}}
|
||||
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","propose_action","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}}
|
||||
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","propose_action","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","wait_agent","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}}
|
||||
{"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"propose_action"}],"role":"developer","id":"{{message:8}}"},"headerSeq":20},"surfaceOp":"append"}
|
||||
{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_creation_card","name":"propose_action","arguments":"{\"action\":\"create_personalized_page\",\"title\":\"Counter\",\"brief\":\"Need: Keep a small counter visible across conversations.\\nLocation: A card titled Today’s achievements in the right sidebar.\\nControls: Increment and reset buttons beside the current value.\\nStorage: Save changes in browser storage across navigation and refresh.\\nAppearance: Follow the existing sidebar theme in light and dark mode.\\nCompletion: Both controls work and reopening restores the saved value.\",\"details\":{\"slot\":\"sidebar-right\"}}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:9}}"},"stream":[{"type":"chunk","time":1792674450652,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"chunk","time":1792674450652,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_creation_card","name":"propose_action","arguments":"{\"action\":\"create_personalized_page\",\"title\":\"Counter\",\"brief\":\"Need: Keep a small counter visible across conversations.\\nLocation: A card titled Today’s achievements in the right sidebar.\\nControls: Increment and reset buttons beside the current value.\\nStorage: Save changes in browser storage across navigation and refresh.\\nAppearance: Follow the existing sidebar theme in light and dark mode.\\nCompletion: Both controls work and reopening restores the saved value.\",\"details\":{\"slot\":\"sidebar-right\"}}"}}},{"type":"chunk","time":1792674450652,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"}
|
||||
{"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_creation_card","name":"propose_action","arguments":"{\"action\":\"create_personalized_page\",\"title\":\"Counter\",\"brief\":\"Need: Keep a small counter visible across conversations.\\nLocation: A card titled Today’s achievements in the right sidebar.\\nControls: Increment and reset buttons beside the current value.\\nStorage: Save changes in browser storage across navigation and refresh.\\nAppearance: Follow the existing sidebar theme in light and dark mode.\\nCompletion: Both controls work and reopening restores the saved value.\",\"details\":{\"slot\":\"sidebar-right\"}}"}}
|
||||
|
||||
@@ -224,7 +224,7 @@
|
||||
},
|
||||
{
|
||||
"name": "interrupt_agent",
|
||||
"description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local direct child's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.",
|
||||
"description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local subagent's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -292,19 +292,10 @@
|
||||
},
|
||||
{
|
||||
"name": "list_agents",
|
||||
"description": "List subagents you started, with their ids, labels, and status. running means it is working; inactive means it is not currently working. You will be notified when a subagent finishes; there is no need to keep checking its status. Use send_message to continue the conversation.",
|
||||
"description": "List your entire subagent tree: the root agent and all reachable continuable descendants, including yourself. Rows carry ids, descriptions, and status; descendant rows carry parent ids and depth from the root. You can message any other agent in the subagent tree listed as running or inactive. You can interrupt only your own descendants. running means it is working; inactive means it is not currently working. While you remain active, you will be notified when a direct child finishes; there is no need to keep checking its status. Use send_message to continue the conversation.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"scope": {
|
||||
"type": "string",
|
||||
"description": "children (default) lists direct children, which accept send_message in any status. descendants lists the whole tree below you with each entry's parent session id and depth; entries deeper than 1 accept only interrupt_agent.",
|
||||
"enum": [
|
||||
"children",
|
||||
"descendants"
|
||||
]
|
||||
}
|
||||
}
|
||||
"properties": {}
|
||||
}
|
||||
},
|
||||
{
|
||||
@@ -733,7 +724,7 @@
|
||||
"properties": {
|
||||
"agent_id": {
|
||||
"type": "string",
|
||||
"description": "The agent id of your direct continuable child, or your direct parent when you are a resident continuable child."
|
||||
"description": "The agent id of another member of your subagent tree, as shown by list_agents."
|
||||
},
|
||||
"message": {
|
||||
"type": "string",
|
||||
@@ -764,7 +755,7 @@
|
||||
},
|
||||
{
|
||||
"name": "subagent",
|
||||
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes. Supply `provider` and `model` together. Omitted values use child defaults, falling back to compatible parent values. When the effective route changes, an omitted `reasoning_effort` uses the model's default.",
|
||||
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. If you are still online when it finishes, the runtime automatically delivers its completion notice. The notice includes the final answer unless the child sent you a message just before finishing. Use `send_message` to steer it while running or continue its conversation after it finishes. Supply `provider` and `model` together. Omitted values use child defaults, falling back to compatible parent values. When the effective route changes, an omitted `reasoning_effort` uses the model's default.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -801,7 +792,7 @@
|
||||
},
|
||||
{
|
||||
"name": "subagent_fork",
|
||||
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.",
|
||||
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. If you are still online when it finishes, the runtime automatically delivers its completion notice. The notice includes the final answer unless the child sent you a message just before finishing. Use `send_message` to steer it while running or continue its conversation after it finishes.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -908,6 +899,19 @@
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "wait_agent",
|
||||
"description": "Wait for input at your next step, including agent messages, completion notifications, and user steering. Returns immediately when that input is already pending.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"timeout_ms": {
|
||||
"type": "integer",
|
||||
"description": "Wait duration in milliseconds, from 10000 through 3600000. Defaults to 30000."
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "web_fetch",
|
||||
"description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.",
|
||||
@@ -1294,7 +1298,7 @@
|
||||
},
|
||||
{
|
||||
"name": "interrupt_agent",
|
||||
"description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local direct child's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.",
|
||||
"description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local subagent's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -1362,19 +1366,10 @@
|
||||
},
|
||||
{
|
||||
"name": "list_agents",
|
||||
"description": "List subagents you started, with their ids, labels, and status. running means it is working; inactive means it is not currently working. You will be notified when a subagent finishes; there is no need to keep checking its status. Use send_message to continue the conversation.",
|
||||
"description": "List your entire subagent tree: the root agent and all reachable continuable descendants, including yourself. Rows carry ids, descriptions, and status; descendant rows carry parent ids and depth from the root. You can message any other agent in the subagent tree listed as running or inactive. You can interrupt only your own descendants. running means it is working; inactive means it is not currently working. While you remain active, you will be notified when a direct child finishes; there is no need to keep checking its status. Use send_message to continue the conversation.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"scope": {
|
||||
"type": "string",
|
||||
"description": "children (default) lists direct children, which accept send_message in any status. descendants lists the whole tree below you with each entry's parent session id and depth; entries deeper than 1 accept only interrupt_agent.",
|
||||
"enum": [
|
||||
"children",
|
||||
"descendants"
|
||||
]
|
||||
}
|
||||
}
|
||||
"properties": {}
|
||||
}
|
||||
},
|
||||
{
|
||||
@@ -1835,7 +1830,7 @@
|
||||
"properties": {
|
||||
"agent_id": {
|
||||
"type": "string",
|
||||
"description": "The agent id of your direct continuable child, or your direct parent when you are a resident continuable child."
|
||||
"description": "The agent id of another member of your subagent tree, as shown by list_agents."
|
||||
},
|
||||
"message": {
|
||||
"type": "string",
|
||||
@@ -1866,7 +1861,7 @@
|
||||
},
|
||||
{
|
||||
"name": "subagent",
|
||||
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes. Supply `provider` and `model` together. Omitted values use child defaults, falling back to compatible parent values. When the effective route changes, an omitted `reasoning_effort` uses the model's default.",
|
||||
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. If you are still online when it finishes, the runtime automatically delivers its completion notice. The notice includes the final answer unless the child sent you a message just before finishing. Use `send_message` to steer it while running or continue its conversation after it finishes. Supply `provider` and `model` together. Omitted values use child defaults, falling back to compatible parent values. When the effective route changes, an omitted `reasoning_effort` uses the model's default.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -1903,7 +1898,7 @@
|
||||
},
|
||||
{
|
||||
"name": "subagent_fork",
|
||||
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.",
|
||||
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. If you are still online when it finishes, the runtime automatically delivers its completion notice. The notice includes the final answer unless the child sent you a message just before finishing. Use `send_message` to steer it while running or continue its conversation after it finishes.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -2010,6 +2005,19 @@
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "wait_agent",
|
||||
"description": "Wait for input at your next step, including agent messages, completion notifications, and user steering. Returns immediately when that input is already pending.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"timeout_ms": {
|
||||
"type": "integer",
|
||||
"description": "Wait duration in milliseconds, from 10000 through 3600000. Defaults to 30000."
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "web_fetch",
|
||||
"description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.",
|
||||
|
||||
@@ -11,15 +11,15 @@
|
||||
{"type":"user/message","data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent working directory: \"{{cwd}}\".\n\nCurrent DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable.\n\nApproval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed.\n\nCurrent DeepSeek Harness implementation checkout: \"{{sourceRoot}}\".\n\nCurrent DeepSeek Harness Web GUI URL: \"{{webUrl}}\"."}],"source":{"kind":"runtime-context","form":"snapshot","sections":[{"name":"working-directory:current","text":"Current working directory: \"{{cwd}}\"."},{"name":"sandbox:policy","text":"Current DSH file policy: workspace-write. Any available operation enforced by the DSH file sandbox may modify files under the session workspace: \"{{cwd}}\". Some platform temporary areas may also be writable."},{"name":"approval:policy","text":"Approval prompts are enabled in this session: operations that require approval may ask through the configured answerers; without an available answerer, the request fails closed."},{"name":"harness:source","text":"Current DeepSeek Harness implementation checkout: \"{{sourceRoot}}\"."},{"name":"app:web-surface","text":"Current DeepSeek Harness Web GUI URL: \"{{webUrl}}\"."}]},"role":"user","id":"{{message:3}}"},"surfaceOp":"append"}
|
||||
{"type":"user/message","data":{"content":[{"type":"text","text":"<system-reminder>\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n<available_skills>\n- `official-plugins`: Check DSH’s optional plugins when the user asks how to do or use something in this app, whether it can, or says a capability is missing or should change: tools, input, thinking or title display, session search, terminals, worktrees, agent teams, desktop control, automation, access, approvals, badges or signatures, plugins or plugin sources. Not a request to develop DSH, even in its own repository: load before reading files or source. Not for ordinary tasks, quoted wishes or declined offers.\n</available_skills>\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\nA user may also invoke a skill directly; its <skill_content> block then appears in this conversation. Follow it, and do not call the `skill` tool again for that skill.\n</system-reminder>"}],"source":{"kind":"skill-catalog","form":"catalog","entries":[{"name":"official-plugins","description":"Check DSH’s optional plugins when the user asks how to do or use something in this app, whether it can, or says a capability is missing or should change: tools, input, thinking or title display, session search, terminals, worktrees, agent teams, desktop control, automation, access, approvals, badges or signatures, plugins or plugin sources. Not a request to develop DSH, even in its own repository: load before reading files or source. Not for ordinary tasks, quoted wishes or declined offers."}]},"role":"user","id":"{{message:4}}"},"surfaceOp":"append"}
|
||||
{"type":"user/message","data":{"content":[{"type":"text","text":"Time sampled while preparing turn 1, step 1: {{timeContextTimestamp}}\nBrowser time zone for this request: {{clientTimeZone}}. Interpret otherwise-unqualified dates and times in this zone.\nElapsed since the preceding model-visible message: {{elapsed}}"}],"source":{"kind":"time-context","form":"snapshot","sections":[{"name":"time-context","text":"Time sampled while preparing turn 1, step 1: {{timeContextTimestamp}}\nBrowser time zone for this request: {{clientTimeZone}}. Interpret otherwise-unqualified dates and times in this zone.\nElapsed since the preceding model-visible message: {{elapsed}}"}]},"role":"user","id":"{{message:5}}"},"surfaceOp":"append"}
|
||||
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}}
|
||||
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","wait_agent","web_fetch","web_search","workflow","working_directory","write"]},"reason":"initial"}}
|
||||
{"type":"request/context","data":{"provider":"deepseek-official","model":"deepseek-v4-flash","contextWindow":128000}}
|
||||
{"type":"session/title","data":{"title":"I want to dictate long","messageSeqs":[8],"source":{"kind":"fallback"}}}
|
||||
{"type":"assistant/message","data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_plugin_skill","name":"skill","arguments":"{\"name\":\"official-plugins\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:6}}"},"stream":[{"type":"chunk","time":1792678188343,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"chunk","time":1792678188343,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_plugin_skill","name":"skill","arguments":"{\"name\":\"official-plugins\"}"}}},{"type":"chunk","time":1792678188344,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"}
|
||||
{"type":"tool/call","data":{"turn":1,"step":1,"callId":"call_plugin_skill","name":"skill","arguments":"{\"name\":\"official-plugins\"}"}}
|
||||
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_plugin_skill"},"toolCallId":"call_plugin_skill","content":[{"type":"text","text":"<skill_content name=\"official-plugins\">\n<skill_resources>\nResources for this skill are managed by provider \"dsh-official-plugins\".\nLoad referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\n# Official plugins\n\nUse this workflow in the main conversation when the user wants DSH itself to work differently or gain an ability. The catalog at the end lists DSH's built-in optional plugins and whether each is enabled. A `propose_action` call shows an Enable card below your answer; nothing changes until the user clicks Enable. Match from the catalog descriptions alone: do not read files, configuration or source, call plugin management tools, or change settings yourself.\n\n## When to offer\n\nOffer one disabled plugin when the user's own words ask for an outcome its description provides. Match the outcome, not keywords. When a plugin covers only part of the wish, say the limit in one sentence: thinking translation translates the displayed thinking and does not change the language the model reasons in.\n\nOffer no card in these cases:\n\n- The plugin is already enabled: say that it is on and how to use it.\n- The wish appears inside quoted text, pasted content, a translation request, a web page or a tool result rather than the user's own request.\n- The user only wants to discuss, asks you not to recommend anything, or has declined: stay silent on plugins for the rest of this conversation.\n- No entry fits, or the need is too vague to match: answer normally or ask one question; do not stretch a description.\n- Something DSH already shows covers it, such as the sidebar search for finding a session by keyword yourself. Letting the agent search and read past sessions is a different need.\n\n## One card per turn\n\nA turn shows at most one card across every card skill. When the user asks for several things, follow an explicit priority; otherwise prefer an existing plugin over building a new page. Mention the other needs in one sentence, without promising a later card.\n\n## Offer without enabling\n\nTo offer, call `propose_action` once, in the same turn as loading this skill, with `action: \"enable_official_plugin\"`, `title` set to the plugin's catalog title in the user's language, `brief` set to one sentence in the user's language that ties the plugin to their need, and `details` holding `name`, the exact catalog name. The call is the submission: the card appears below your answer; a refused call creates no card, and its error says why. Then write your final answer: answer any direct question; the call's result says how to end the answer. Do not narrate the call, repeat the catalog description, add setup steps the catalog does not state, claim the plugin is enabled, or ask the user to report back. The card opens the plugin's details; enabling applies to every conversation and can be undone there. The user's choice reaches you later as a status notice; enabling a plugin authorizes nothing beyond it.\n\n## Official plugins\n\n[{\"name\":\"@deepseek-ai/dsh-plugin-recommendations\",\"title\":{\"en\":\"Plugin recommendations\",\"de\":\"Plugin-Empfehlungen\",\"es\":\"Recomendaciones de complementos\",\"fr\":\"Recommandations de plugins\",\"ja\":\"プラグイン推薦\",\"pt\":\"Recomendações de plug-ins\",\"ru\":\"Рекомендации плагинов\",\"zh\":\"插件推荐\"},\"description\":{\"en\":\"Discover built-in plugins for needs you describe when you are unsure which features are available. An Enable card appears after the answer; activation requires your click.\",\"de\":\"Entdecken Sie integrierte Plugins für Bedürfnisse, die Sie beschreiben, wenn Sie nicht wissen, welche Funktionen verfügbar sind. Nach der Antwort erscheint eine Karte zum Aktivieren; die Aktivierung erfordert Ihren Klick.\",\"es\":\"Descubre complementos integrados para las necesidades que describes cuando no sabes qué funciones están disponibles. Después de la respuesta aparece una tarjeta Habilitar; la activación requiere tu clic.\",\"fr\":\"Découvrez les plugins intégrés adaptés aux besoins que vous décrivez lorsque vous ne savez pas quelles fonctionnalités sont disponibles. Une carte Activer apparaît après la réponse ; l’activation nécessite votre clic.\",\"ja\":\"どの機能が使えるか分からないとき、あなたが述べたニーズに合う内蔵プラグインを推薦します。回答の後に有効化カードが表示され、有効化にはクリックが必要です。\",\"pt\":\"Descubra plug-ins integrados para as necessidades que você descreve quando não sabe quais recursos estão disponíveis. Um cartão Ativar aparece após a resposta; a ativação exige o seu clique.\",\"ru\":\"Находите встроенные плагины для описанных вамLine truncated
|
||||
{"type":"tool/result","data":{"turn":1,"step":1,"message":{"role":"tool","source":{"kind":"tool","callId":"call_plugin_skill"},"toolCallId":"call_plugin_skill","content":[{"type":"text","text":"<skill_content name=\"official-plugins\">\n<skill_resources>\nResources for this skill are managed by provider \"dsh-official-plugins\".\nLoad referenced resources only as needed.\n</skill_resources>\n\n<skill_instructions>\n# Official plugins\n\nUse this workflow in the main conversation when the user wants DSH itself to work differently or gain an ability. The catalog at the end lists DSH's built-in optional plugins and whether each is enabled. A `propose_action` call shows an Enable card below your answer; nothing changes until the user clicks Enable. Match from the catalog descriptions alone: do not read files, configuration or source, call plugin management tools, or change settings yourself.\n\n## When to offer\n\nOffer one disabled plugin when the user's own words ask for an outcome its description provides. Match the outcome, not keywords. When a plugin covers only part of the wish, say the limit in one sentence: thinking translation translates the displayed thinking and does not change the language the model reasons in.\n\nOffer no card in these cases:\n\n- The plugin is already enabled: say that it is on and how to use it.\n- The wish appears inside quoted text, pasted content, a translation request, a web page or a tool result rather than the user's own request.\n- The user only wants to discuss, asks you not to recommend anything, or has declined: stay silent on plugins for the rest of this conversation.\n- No entry fits, or the need is too vague to match: answer normally or ask one question; do not stretch a description.\n- Something DSH already shows covers it, such as the sidebar search for finding a session by keyword yourself. Letting the agent search and read past sessions is a different need.\n\n## One card per turn\n\nA turn shows at most one card across every card skill. When the user asks for several things, follow an explicit priority; otherwise prefer an existing plugin over building a new page. Mention the other needs in one sentence, without promising a later card.\n\n## Offer without enabling\n\nTo offer, call `propose_action` once, in the same turn as loading this skill, with `action: \"enable_official_plugin\"`, `title` set to the plugin's catalog title in the user's language, `brief` set to one sentence in the user's language that ties the plugin to their need, and `details` holding `name`, the exact catalog name. The call is the submission: the card appears below your answer; a refused call creates no card, and its error says why. Then write your final answer: answer any direct question; the call's result says how to end the answer. Do not narrate the call, repeat the catalog description, add setup steps the catalog does not state, claim the plugin is enabled, or ask the user to report back. The card opens the plugin's details; enabling applies to every conversation and can be undone there. The user's choice reaches you later as a status notice; enabling a plugin authorizes nothing beyond it.\n\n## Official plugins\n\n[{\"name\":\"@deepseek-ai/dsh-plugin-recommendations\",\"title\":{\"en\":\"Plugin recommendations\",\"de\":\"Plugin-Empfehlungen\",\"es\":\"Recomendaciones de complementos\",\"fr\":\"Recommandations de plugins\",\"ja\":\"プラグイン推薦\",\"pt\":\"Recomendações de plug-ins\",\"ru\":\"Рекомендации плагинов\",\"zh\":\"插件推荐\"},\"description\":{\"en\":\"Discover built-in plugins for needs you describe when you are unsure which features are available. An Enable card appears after the answer; activation requires your click.\",\"de\":\"Entdecken Sie integrierte Plugins für Bedürfnisse, die Sie beschreiben, wenn Sie nicht wissen, welche Funktionen verfügbar sind. Nach der Antwort erscheint eine Karte zum Aktivieren; die Aktivierung erfordert Ihren Klick.\",\"es\":\"Descubre complementos integrados para las necesidades que describes cuando no sabes qué funciones están disponibles. Después de la respuesta aparece una tarjeta Habilitar; la activación requiere tu clic.\",\"fr\":\"Découvrez les plugins intégrés adaptés aux besoins que vous décrivez lorsque vous ne savez pas quelles fonctionnalités sont disponibles. Une carte Activer apparaît après la réponse ; l’activation nécessite votre clic.\",\"ja\":\"どの機能が使えるか分からないとき、あなたが述べたニーズに合う内蔵プラグインを推薦します。回答の後に有効化カードが表示され、有効化にはクリックが必要です。\",\"pt\":\"Descubra plug-ins integrados para as necessidades que você descreve quando não sabe quais recursos estão disponíveis. Um cartão Ativar aparece após a resposta; a ativação exige o seu clique.\",\"ru\":\"Находите встроенные плагины для описанных вамLine truncated
|
||||
{"type":"step/end","data":{"turn":1,"step":1}}
|
||||
{"type":"step/start","data":{"turn":1,"step":2}}
|
||||
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","propose_action","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}}
|
||||
{"type":"request/header","data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"tools":["ask_user_question","bash","create_goal","edit","get_goal","glob","grep","interrupt_agent","job_kill","job_list","job_output","list_agents","list_subagent_models","plugin_manager","present","propose_action","read","read_image","schedule_create","schedule_delete","schedule_list","schedule_update","send_message","skill","subagent","subagent_fork","todo_write","update_goal","wait_agent","web_fetch","web_search","workflow","working_directory","write"]},"reason":"change"}}
|
||||
{"type":"developer/message","data":{"turn":1,"step":2,"message":{"source":{"kind":"tool-registry"},"content":[{"type":"tool-addition","toolName":"propose_action"}],"role":"developer","id":"{{message:8}}"},"headerSeq":20},"surfaceOp":"append"}
|
||||
{"type":"assistant/message","data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"tool-call","id":"call_plugin_card","name":"propose_action","arguments":"{\"action\":\"enable_official_plugin\",\"title\":\"Voice input\",\"brief\":\"Speak long requests instead of typing them; transcription runs on this computer.\",\"details\":{\"name\":\"@deepseek-ai/dsh-experimental-voice-input-bundle\"}}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"{{message:9}}"},"stream":[{"type":"chunk","time":1792678188573,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}},{"type":"chunk","time":1792678188573,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_plugin_card","name":"propose_action","arguments":"{\"action\":\"enable_official_plugin\",\"title\":\"Voice input\",\"brief\":\"Speak long requests instead of typing them; transcription runs on this computer.\",\"details\":{\"name\":\"@deepseek-ai/dsh-experimental-voice-input-bundle\"}}"}}},{"type":"chunk","time":1792678188573,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}]},"surfaceOp":"append"}
|
||||
{"type":"tool/call","data":{"turn":1,"step":2,"callId":"call_plugin_card","name":"propose_action","arguments":"{\"action\":\"enable_official_plugin\",\"title\":\"Voice input\",\"brief\":\"Speak long requests instead of typing them; transcription runs on this computer.\",\"details\":{\"name\":\"@deepseek-ai/dsh-experimental-voice-input-bundle\"}}"}}
|
||||
|
||||
@@ -224,7 +224,7 @@
|
||||
},
|
||||
{
|
||||
"name": "interrupt_agent",
|
||||
"description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local direct child's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.",
|
||||
"description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local subagent's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -292,19 +292,10 @@
|
||||
},
|
||||
{
|
||||
"name": "list_agents",
|
||||
"description": "List subagents you started, with their ids, labels, and status. running means it is working; inactive means it is not currently working. You will be notified when a subagent finishes; there is no need to keep checking its status. Use send_message to continue the conversation.",
|
||||
"description": "List your entire subagent tree: the root agent and all reachable continuable descendants, including yourself. Rows carry ids, descriptions, and status; descendant rows carry parent ids and depth from the root. You can message any other agent in the subagent tree listed as running or inactive. You can interrupt only your own descendants. running means it is working; inactive means it is not currently working. While you remain active, you will be notified when a direct child finishes; there is no need to keep checking its status. Use send_message to continue the conversation.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"scope": {
|
||||
"type": "string",
|
||||
"description": "children (default) lists direct children, which accept send_message in any status. descendants lists the whole tree below you with each entry's parent session id and depth; entries deeper than 1 accept only interrupt_agent.",
|
||||
"enum": [
|
||||
"children",
|
||||
"descendants"
|
||||
]
|
||||
}
|
||||
}
|
||||
"properties": {}
|
||||
}
|
||||
},
|
||||
{
|
||||
@@ -733,7 +724,7 @@
|
||||
"properties": {
|
||||
"agent_id": {
|
||||
"type": "string",
|
||||
"description": "The agent id of your direct continuable child, or your direct parent when you are a resident continuable child."
|
||||
"description": "The agent id of another member of your subagent tree, as shown by list_agents."
|
||||
},
|
||||
"message": {
|
||||
"type": "string",
|
||||
@@ -764,7 +755,7 @@
|
||||
},
|
||||
{
|
||||
"name": "subagent",
|
||||
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes. Supply `provider` and `model` together. Omitted values use child defaults, falling back to compatible parent values. When the effective route changes, an omitted `reasoning_effort` uses the model's default.",
|
||||
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. If you are still online when it finishes, the runtime automatically delivers its completion notice. The notice includes the final answer unless the child sent you a message just before finishing. Use `send_message` to steer it while running or continue its conversation after it finishes. Supply `provider` and `model` together. Omitted values use child defaults, falling back to compatible parent values. When the effective route changes, an omitted `reasoning_effort` uses the model's default.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -801,7 +792,7 @@
|
||||
},
|
||||
{
|
||||
"name": "subagent_fork",
|
||||
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.",
|
||||
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. If you are still online when it finishes, the runtime automatically delivers its completion notice. The notice includes the final answer unless the child sent you a message just before finishing. Use `send_message` to steer it while running or continue its conversation after it finishes.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -908,6 +899,19 @@
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "wait_agent",
|
||||
"description": "Wait for input at your next step, including agent messages, completion notifications, and user steering. Returns immediately when that input is already pending.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"timeout_ms": {
|
||||
"type": "integer",
|
||||
"description": "Wait duration in milliseconds, from 10000 through 3600000. Defaults to 30000."
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "web_fetch",
|
||||
"description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.",
|
||||
@@ -1294,7 +1298,7 @@
|
||||
},
|
||||
{
|
||||
"name": "interrupt_agent",
|
||||
"description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local direct child's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.",
|
||||
"description": "Ask a subagent to stop its current work. This call returns without waiting for it to stop. You can continue a local subagent's conversation later with send_message. External executions stop permanently and cannot receive follow-ups. Subagents it started will keep running.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -1362,19 +1366,10 @@
|
||||
},
|
||||
{
|
||||
"name": "list_agents",
|
||||
"description": "List subagents you started, with their ids, labels, and status. running means it is working; inactive means it is not currently working. You will be notified when a subagent finishes; there is no need to keep checking its status. Use send_message to continue the conversation.",
|
||||
"description": "List your entire subagent tree: the root agent and all reachable continuable descendants, including yourself. Rows carry ids, descriptions, and status; descendant rows carry parent ids and depth from the root. You can message any other agent in the subagent tree listed as running or inactive. You can interrupt only your own descendants. running means it is working; inactive means it is not currently working. While you remain active, you will be notified when a direct child finishes; there is no need to keep checking its status. Use send_message to continue the conversation.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"scope": {
|
||||
"type": "string",
|
||||
"description": "children (default) lists direct children, which accept send_message in any status. descendants lists the whole tree below you with each entry's parent session id and depth; entries deeper than 1 accept only interrupt_agent.",
|
||||
"enum": [
|
||||
"children",
|
||||
"descendants"
|
||||
]
|
||||
}
|
||||
}
|
||||
"properties": {}
|
||||
}
|
||||
},
|
||||
{
|
||||
@@ -1835,7 +1830,7 @@
|
||||
"properties": {
|
||||
"agent_id": {
|
||||
"type": "string",
|
||||
"description": "The agent id of your direct continuable child, or your direct parent when you are a resident continuable child."
|
||||
"description": "The agent id of another member of your subagent tree, as shown by list_agents."
|
||||
},
|
||||
"message": {
|
||||
"type": "string",
|
||||
@@ -1866,7 +1861,7 @@
|
||||
},
|
||||
{
|
||||
"name": "subagent",
|
||||
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes. Supply `provider` and `model` together. Omitted values use child defaults, falling back to compatible parent values. When the effective route changes, an omitted `reasoning_effort` uses the model's default.",
|
||||
"description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent returns its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. If you are still online when it finishes, the runtime automatically delivers its completion notice. The notice includes the final answer unless the child sent you a message just before finishing. Use `send_message` to steer it while running or continue its conversation after it finishes. Supply `provider` and `model` together. Omitted values use child defaults, falling back to compatible parent values. When the effective route changes, an omitted `reasoning_effort` uses the model's default.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -1903,7 +1898,7 @@
|
||||
},
|
||||
{
|
||||
"name": "subagent_fork",
|
||||
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. The runtime notifies you when it finishes. The child reports results with `send_message`; use `send_message` to steer it while running or continue its conversation after it finishes.",
|
||||
"description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn). Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive its result, not its intermediate steps. This tool starts an independently managed subagent and immediately returns its id. If you are still online when it finishes, the runtime automatically delivers its completion notice. The notice includes the final answer unless the child sent you a message just before finishing. Use `send_message` to steer it while running or continue its conversation after it finishes.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
@@ -2010,6 +2005,19 @@
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "wait_agent",
|
||||
"description": "Wait for input at your next step, including agent messages, completion notifications, and user steering. Returns immediately when that input is already pending.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"timeout_ms": {
|
||||
"type": "integer",
|
||||
"description": "Wait duration in milliseconds, from 10000 through 3600000. Defaults to 30000."
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "web_fetch",
|
||||
"description": "Fetch the content of a specific HTTP(S) URL and return it decoded to text.",
|
||||
|
||||
Reference in new issue
Block a user