docs(turn-loop): present managed-settings as current state, drop changelog phrasing

This commit is contained in:
damocles 2026-06-26 22:33:34 +02:00 committed by mara
commit c2ba841932

View file

@ -142,14 +142,13 @@ claude --print --verbose --output-format stream-json --model <name> \
# wake prompt piped over stdin
```
Static settings are no longer passed with `--settings`: hive-enforced
settings ship at `/etc/claude-code/managed-settings.json` (claude-code's
canonical managed-settings path — precedence #1, read-only,
un-overridable), wired in `nix/templates/harness-base.nix` from the
`prompts/claude-settings.json` asset. `effortLevel` is deliberately not
in that file — effort is controlled live via the `--effort` flag
(`HIVE_DEFAULT_EFFORT` / the per-agent UI slider), which managed scope
would otherwise lock.
Hive-enforced settings ship at `/etc/claude-code/managed-settings.json`
(claude-code's canonical managed-settings path — precedence #1,
read-only, un-overridable), wired in `nix/templates/harness-base.nix`
from the `prompts/claude-settings.json` asset. `effortLevel` is
deliberately not in that file — effort is controlled live via the
`--effort` flag (`HIVE_DEFAULT_EFFORT` / the per-agent UI slider), which
managed scope would otherwise lock.
`<name>` is read from `Bus::model()` on each turn. The initial
default is set by `hyperhive.model` in the agent's `agent.nix`