An agent harness built on aisuite's agent framework. Adds a coworker engine
with pluggable connectors (browser automation, integration tools), session
management, audit logging, and a permissions model, alongside a desktop GUI
surface (Tauri + React) and a multi-provider model layer with Ollama support.
Co-authored-by: Devika <dr.drp8226@gmail.com>
Add an observability layer for agent runs on top of the Agent API. The
runner now emits structured trace events for each step (model calls,
tool calls, tool-policy denials) and routes them to pluggable sinks,
with a trace store and viewer model for inspecting past runs.
- aisuite/tracing: trace sinks (in-memory, local JSONL), a JSONL trace
store, and a viewer data model for reconstructing runs
- aisuite/agents/runner: emit trace events and propagate run context
- aisuite/agents/context: ActiveRunContext to correlate nested runs
- Runner accepts trace_sinks; RunResult/RunStep carry trace data
- tests/agents: trace sink, viewer, trace-output, and tool-policy
denial integration coverage
Co-authored-by: Rohit <rohit.prasad15@gmail.com>
Introduce a high-level Agent abstraction for aisuite. An Agent pairs a
model with instructions, tools, and run settings, and a Runner drives
the multi-step tool-calling loop over any aisuite-supported provider.
- aisuite/agents: Runner (run_sync / continue_sync) plus typed
Agent, RunResult, RunState, and RunStep
- Tool policies (ToolPolicyContext / ToolPolicyDecision) to gate
which tools a run may invoke
- Continuation API to resume a finished run with new input
- aisuite/utils/tools: tool schema generation and execution helpers
- examples/agents/simple_agent.py: minimal end-to-end example
- tests/agents: runner, tool-policy, continuation, and OpenAI
integration coverage
Co-authored-by: Rohit <rohit.prasad15@gmail.com>
Rohit C Prasad