Skip to main content

Agent profiles

knoxchat.agentProfile picks how the agent loop behaves after it is allowed to run: how stubborn it is with repeated tool calls, and what it runs to check an edit. It does not replace Ask / Edits / Auto or Plan.

Setting: default | systems | rust | auto (default: default). Change it in Knox: Open Knox Settings or settings.json.

GUI chat stays unlimited tool rounds. Stop with Cancel. Background jobs and /autonomous are capped (40 / rust 60 / systems 80, absolute 200). Details: Background agents.

When the resolved profile is systems or rust, the agent meter shows that chip.

What each profile does​

SettingDoom-loop afterPost-edit check
default3 identical / failing callsLSP diagnostics (knoxchat.enablePostEditVerification)
rust4cargo check --workspace --all-targets
systems5make (kernel / QEMU)
auto(resolved)systems on kernel/QEMU trees, rust on a root Cargo.toml, otherwise default

A doom-loop chip offers Change strategy (one-line instruction to pick a different approach). Stop any run with Cancel.

systems / rust ignore knoxchat.enablePostEditVerification (the compile oracle wins). A non-empty knoxchat.verifyCommand also skips LSP and selects command mode.

What auto looks at​

auto lists the workspace root (not nested folders) and classifies, first match wins:

  1. kernel — Kconfig (or Kconfig.*) plus arch/, Makefile, or Kbuild
  2. qemu — meson.build plus target/, accel/, or hw/
  3. cargo — root Cargo.toml (a nested rust/Cargo.toml does not count, so rust-for-linux stays systems)
  4. Otherwise default (app tree)

A kernel/QEMU tree that also has a root Cargo.toml stays systems. Explicit systems / rust / default are never changed. With Jev on, auto can be confirmed; that overlay still does not override an explicit setting.

Bare Makefile / CMakeLists.txt is not enough for systems (app repos often have those).

Workspace card​

On classified trees Knox injects a short Codebase Card on submit (not a dump of .config or lockfiles):

KindDetected from
kernel / qemuKconfig + arch, or meson + target/accel/hw
cargoroot Cargo.toml
editorthis KnoxCoder / VS Code fork (src/ + extensions/ + product.json / gulp)
nodepackage.json
pythonpyproject.toml, pytest.ini, requirements.txt, setup.py / setup.cfg
gogo.mod
cmakeCMakeLists.txt

Order if several match: kernel > qemu > cargo > editor > node > python > go > cmake. The editor fork wins over a bare Node package.json.

You do not paste this. /instructions is still the place to see token cost of rules and AGENTS.md.

After a red build​

If the verify command (or make / cargo test / npm test on the product path) is still red, Knox holds instead of treating the turn as done and keeps trying to fix. A hold chip can show on the last assistant message.

  • Same compiler-error signature: knoxchat.verifyMaxIterations (default 8) skips further auto-builds.
  • Extra no-tool “oracle still red” rounds cap at 8; 3 in a row with the same diagnostics stop that loop.

Set knoxchat.verifyMode to off if you do not want a post-edit oracle. diagnostics is LSP; command is knoxchat.verifyCommand (examples: make -j8, cargo check --workspace --all-targets). A non-empty verify command selects command.

Settings recap​

SettingEffect
knoxchat.agentProfiledefault / systems / rust / auto
knoxchat.enablePostEditVerificationLSP check + attempted fixes after mutating tools (ignored on systems/rust or when verifyCommand is set)
knoxchat.verifyCommandCompile oracle; empty = LSP on default
knoxchat.verifyModediagnostics / command / off
knoxchat.verifyMaxIterationsCircuit breaker for identical compiler errors (1–20, default 8)

Next​

Background agents · Permission modes · Inline edit (Cmd+I)