lkn
/
ollie
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Document external plan-and-execute integrations

This commit is contained in:
Ollie Agent 2026-08-16 20:07:25 +02:00
parent 3e1697d074
commit 7b8f6942c6
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
doc/architecture.md
View File

@ -54,6 +54,19 @@ An MCP server can remain an optional external dependency. A bridge tool can invo
Capabilities are not compiled into the agent loop as provider-specific or framework-specific tool objects. Tool behavior lives in external executables or metadata-only commands, and toolsrv owns discovery, loading, execution, sandboxing, and process state. See [`architecture-tools.md`](architecture-tools.md) and [`architecture-toolsrv.md`](architecture-toolsrv.md).
### No built-in plan-and-execute workflow
Ollie does not implement a planner/executor subsystem, task graph, scheduler, or workflow engine. Planning is agent state; execution is the normal tool loop. Ollie does not own task dependencies, retries, compensation, or durable workflow semantics.
Those concerns belong at the composition boundary. A system such as [Beads](https://github.com/steveyegge/beads) can expose task creation, dependency queries, updates, and completion through a tool. The external system owns the durable task graph and workflow semantics; toolsrv executes the tool; Ollie supplies the agent, sessions, prompts, and 9P observation/control surface.
```text
Ollie agent
└─ toolsrv → Beads/task-graph tool → external durable state
```
This preserves a clean boundary: Ollie remains useful without Beads, while agents can use Beads or another task system when durable plan-and-execute behavior adds value.
### No external coordination protocol
Ollie does not expose a workflow engine, message bus, actor framework, or master coordinator as an external integration boundary. The runtime does contain an internal session event bus for agent and session observers; it is an implementation detail, not a public coordination API. External multi-agent coordination uses sessions, agents, `prompt`, `chat`, `statewait`, `feed`, and `ctl` files. Hub-and-spoke, pipeline, scatter-gather, peer, reactive, and self-directed workflows are scripts or agent conventions over those files.