- Refactored the initSandboxV2 function to return a structured result, consolidating the runner, computer, configuration, cleanup function, loading message ID, and roles into a single return type. - Updated the Stream method to utilize the new sandboxV2InitResult structure, improving clarity and reducing complexity in handling sandbox initialization. - Introduced role management enhancements, allowing for pre-resolved role connectors to be passed through the request, streamlining connector resolution during execution. - Adjusted various components to support the new roles structure, ensuring consistent handling across the agent's sandbox operations. - Added logging for connector resolution and role management, improving diagnostics and traceability during sandbox execution. - Updated .gitignore to include tools/TOOL-REGISTRATION.md for better project organization.
1.5 KiB
1.5 KiB
| name | description |
|---|---|
| yao-process | Yao process execution expert. ALWAYS invoke this skill when the user needs to call a Yao process, query data models, run scripts, or check process permissions. Do not call processes without checking this skill first. |
Process Tools
Two tools for Yao process execution, called via bash.
process_call
Execute a Yao Process by its fully qualified name.
tai tool process_call '{"name": "models.user.Find", "args": [1, {}]}'
| Parameter | Type | Required | Description |
|---|---|---|---|
name |
string | yes | Process name (e.g. models.user.Find) |
args |
array | no | Positional arguments |
process_allowed
Check which processes are permitted, or verify a specific process.
# List all allowed rules
tai tool process_allowed '{}'
# Check a specific process
tai tool process_allowed '{"name": "models.user.Find"}'
| Parameter | Type | Required | Description |
|---|---|---|---|
name |
string | no | Process name to check. Omit to list all rules. |
Workflow
- Use process_allowed to check what is permitted
- Use doc_inspect (from yao-doc skill) to understand the process signature
- Use process_call to execute
Guidelines
- Always check documentation before calling an unfamiliar process
- A 403 error means the process is not in the allowed list
- Process names follow the pattern
group.id.Method(e.g.models.user.Find,scripts.auth.Check) - Rules use prefix matching:
models.*matches all model processes