swarm containers: run the claude-code the hive pins for agents
This commit is contained in:
parent
1302288474
commit
a169947f15
6 changed files with 65 additions and 2 deletions
|
|
@ -7,6 +7,9 @@ agent's harness installs them from there.
|
|||
|
||||
Where it runs and how it's enabled: [`services.md`](services.md#claude-login-minter).
|
||||
|
||||
The service runs the `claude-code` that `services.hyperhive.c0re.claudeCodePackage`
|
||||
pins for agents, and its container's own nixpkgs' where the hive pins none.
|
||||
|
||||
## What happens on a login
|
||||
|
||||
1. The agent publishes `needs_login` in its turn-state header, and its card
|
||||
|
|
|
|||
|
|
@ -135,6 +135,9 @@ config) and an empty directory of its own. The prompt reaches it on stdin as
|
|||
one user message in `--input-format stream-json`, so that it can carry content
|
||||
blocks (see [Shared context](#shared-context)).
|
||||
|
||||
The `claude` is the one `services.hyperhive.c0re.claudeCodePackage` pins for
|
||||
agents, or its container's own nixpkgs' where the hive pins none.
|
||||
|
||||
On the ACP runtime, each classification is one prompt on a new `opencode acp`
|
||||
session. Its config and opencode's state live in a directory of its own,
|
||||
removed after it. Its working directory is one empty directory that every
|
||||
|
|
|
|||
Loading…
Reference in a new issue