Built-in tools for planning, memory, widgets, and sub-agent completion.
Overview
Internal tools are enabled by default. Configure them with internalTools:
1from inferencesh import inference, internal_tools2 3client = inference(api_key="inf_...")4agent = client.agent({5 "core_app_ref": "infsh/claude-sonnet-4@latest",6 "internal_tools": internal_tools()7 .plan(True)8 .memory(True)9 .widget(True)10 .build()11})Available Internal Tools
| Category | Tools | Scope |
|---|---|---|
| Plan | plan_create, plan_update, plan_load | All agents |
| Memory | memory_set, memory_get, memory_getall | All agents |
| Widget | widget | Top-level only |
| Finish | finish | Sub-agents only |
Plan Tools
Help agents organize multi-step tasks:
plan_create
Create a new plan with steps:
code
1Agent creates: ["Research topic", "Write outline", "Draft content"]plan_update
Update step status (pending, in_progress, completed, failed):
code
1Agent marks step 1 as completedplan_load
Load the current plan to see progress.
Example conversation:
code
1User: "Write me a blog post about AI"2 3Agent: [calls plan_create with steps]4> Plan created:5> [ ] Research AI trends6> [ ] Create outline 7> [ ] Write draft8> [ ] Review and polish9 10Agent: [calls plan_update to mark step 1 in progress]11> Plan updated:12> [/] Research AI trends ← in progress13> [ ] Create outline14> ...Memory Tools
Persist data across messages in a chat session:
memory_set
Store a key-value pair:
code
1Agent calls: memory_set(key="user_preference", value="dark mode")memory_get
Retrieve a value:
code
1Agent calls: memory_get(key="user_preference")2Returns: "dark mode"memory_getall
Get all stored memories:
code
1Returns: {"user_preference": "dark mode", "last_topic": "AI"}Use cases:
- Remember user preferences
- Store intermediate results
- Track conversation context
Widget Tool
Render interactive UI elements (top-level agents only):
widget
Create UI components:
- Forms with inputs
- Buttons and actions
- Cards and layouts
- Status displays
Example widget call:
json
1{2 "type": "ui",3 "title": "Order Confirmation",4 "children": [5 {"type": "text", "value": "Your order is ready"},6 {"type": "badge", "label": "confirmed", "variant": "secondary"},7 {"type": "row", "children": [8 {"type": "button", "label": "Track Order", "action": "track"},9 {"type": "button", "label": "Cancel", "action": "cancel", "variant": "destructive"}10 ]}11 ]12}See the Widget System documentation for full component reference.
Finish Tool
For sub-agents to report completion (sub-agents only):
finish
Report status and result back to parent agent:
json
1{2 "status": "succeeded", // or "failed", "cancelled"3 "result": "Research complete. Found 5 key trends..."4}With custom output schema:
1# Sub-agent configured with output_schema2agent = client.agent({3 "core_app_ref": "...",4 "output_schema": {5 "type": "object",6 "properties": {7 "summary": {"type": "string"},8 "confidence": {"type": "number"}9 }10 }11})Configuration Examples
1# Disable all internal tools2internal_tools().none().build()3 4# Enable only memory5internal_tools().plan(False).memory(True).widget(False).build()6 7# Enable all8internal_tools().all().build()Scope Rules
| Tool Category | Top-level Agent | Sub-agent |
|---|---|---|
| Plan | ✓ | ✓ |
| Memory | ✓ | ✓ |
| Widget | ✓ | ✗ |
| Finish | ✗ | ✓ |