docs(extending): scope the "no sandbox" claim, point at Docker cases

The bullet read as a blanket "Codeman has no sandbox", which is wrong and
undersells a headline feature. Two different axes were conflated:

- Integration code cannot be sandboxed by Codeman because Codeman never
  launches it. It is the reader's own process, started by them.
- Agent workloads are sandboxed per case via Docker cases, which is the
  documented isolation story.

Scopes the claim to integration code and links docs/docker-cases.md, noting
that an integration driving a Docker-backed session inherits that isolation
because it is a property of the session, not the caller.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Codeman maintainer
2026-08-06 08:46:22 +02:00
parent c2d973cb2d
commit 322f21ef9f
+11 -2
View File
@@ -242,5 +242,14 @@ require nothing of you but HTTP.
- **No in-process plugin runtime.** See the reasoning at the top of this page.
- **No build or startup hooks** for third-party code. Run your own process.
- **No per-plugin config or state directories.** Manage your own files.
- **No sandbox**, because there is nothing to sandbox. Your integration is your
process, with your permissions, talking HTTP.
- **No sandbox for integration code**, because Codeman never launches it. Your
integration is your own process, started by you, with your permissions,
talking HTTP.
That last point is about integration code specifically, not about Codeman.
Sandboxing lives on a different axis here: the thing worth isolating is the
**agent**, and you isolate it per case with
[Docker cases](docker-cases.md), which run the agent in a hardened container with
a bind-mounted workspace and seeded (not shared) credentials. An integration that
creates or drives a Docker-backed session inherits that isolation for free, since
it is a property of the session rather than of the caller.