Agents¶
An agent is a named execution profile that binds a model name and a list of tools. Agents don't do anything on their own — they are referenced in pipeline run statements or selected implicitly by workflow stage/review steps to declare which model and tools should handle a task.
Syntax¶
The model field is optional. When omitted, the agent uses the runtime default.
Example¶
tool web_search(query: String) -> List[Obj{title: String, url: String, snippet: String}] {}
agent planner {
model: "gpt-4.1"
, tools: [web_search]
}
-- model omitted — uses the selected adapter's default
agent writer {
tools: []
}
Rules¶
modelis optional. When omitted, the runtime uses the selected adapter's default model or the mock handler.AGL_OPENAI_MODELandAGL_ANTHROPIC_MODELprovide deployment-wide overrides (see Model mapping).toolsis required. Use[]for an empty tool list.- Tool names are identifiers and must be declared with
tooldefinitions in the DSL. - Agent names must be unique within a file.
- Duplicate tool names in the list are a parse error.
Using an agent¶
Reference an agent in a pipeline run statement with by:
When by is omitted for a standard task handled by a live adapter, the runtime uses that adapter's configured default model. Tasks declared by agent require an explicit agent binding.
In workflows, the agent is attached directly to the step:
Model resolution¶
| Situation | Model used |
|---|---|
by agent_name present, model declared |
agent_name.model from the DSL (mapped in anthropic mode) |
by agent_name present, model omitted |
Provider default or AGL_OPENAI_MODEL / AGL_ANTHROPIC_MODEL override |
by omitted, live provider mode |
Provider default or deployment override |
by omitted, mock mode |
no model needed |
Tools¶
Tools are identifiers that activate additional adapter behavior in live and anthropic mode.
Currently supported tools:
| Tool | Effect in live/anthropic mode |
|---|---|
web_search |
Exposes a typed search tool that model tasks may call at runtime |
fetch_url |
Fetches page content and exposes extracted text to model tasks |
In mock mode, tools are parsed and stored but do not trigger external network calls.