zed/crates/acp_thread/Cargo.toml
Richard Feldman f0341c96a1
Some checks are pending
Congratsbot / check-author (push) Waiting to run
Congratsbot / congrats (push) Blocked by required conditions
run_tests / orchestrate (push) Waiting to run
run_tests / check_style (push) Waiting to run
run_tests / clippy_windows (push) Blocked by required conditions
run_tests / clippy_linux (push) Blocked by required conditions
run_tests / clippy_mac (push) Blocked by required conditions
run_tests / clippy_mac_x86_64 (push) Blocked by required conditions
run_tests / run_tests_windows (push) Blocked by required conditions
run_tests / run_tests_linux (push) Blocked by required conditions
run_tests / run_tests_mac (push) Blocked by required conditions
run_tests / miri_scheduler (push) Blocked by required conditions
run_tests / doctests (push) Blocked by required conditions
run_tests / check_workspace_binaries (push) Blocked by required conditions
run_tests / build_visual_tests_binary (push) Blocked by required conditions
run_tests / check_wasm (push) Blocked by required conditions
run_tests / check_dependencies (push) Blocked by required conditions
run_tests / check_docs (push) Blocked by required conditions
run_tests / check_licenses (push) Blocked by required conditions
run_tests / check_scripts (push) Blocked by required conditions
run_tests / check_postgres_and_protobuf_migrations (push) Blocked by required conditions
run_tests / extension_tests (push) Blocked by required conditions
run_tests / tests_pass (push) Blocked by required conditions
deploy_nightly_docs / deploy_docs (push) Has been skipped
Wrap agent terminal commands in macOS Seatbelt sandbox (#57431)
Stacked on top of #57430.

When the `sandboxing` feature flag is on (macOS only), agent-run
terminal commands are launched under `/usr/bin/sandbox-exec` with a
per-command Seatbelt policy:

- **Reads:** any path on the filesystem.
- **Writes:** each project worktree plus a per-command `$TMPDIR`.
- **Network:** blocked.

The model can request relaxations on individual calls via three new
input flags on the `terminal` tool:

- `allow_network: true`
- `allow_fs_write: true`
- `unsandboxed: true`

Each one triggers a separate always-prompt user approval (bypassing any
`always_allow` rules, since escalation is a stronger trust boundary than
the baseline command approval). The flags are silently ignored when
sandboxing is off, so the model can't surreptitiously change runtime
behavior by setting them in the no-op case.

The per-command tempdir is provisioned regardless of sandbox state so
the model can't infer whether the sandbox is in effect by looking at
`$TMPDIR`.

The Seatbelt config file's lifetime is tied to the `Terminal` entity via
an opaque RAII handle (`SandboxConfigHandle = Box<dyn Any + Send>`), so
cancellation paths drop it automatically.

### Notes for review

- The writable scope passed to the sandbox is the project's worktree
paths plus the per-command tempdir, **not** the resolved `cd` working
directory — `cd` is model-controlled, and using it as the writable scope
would let the model widen its own write permissions outside the project.
- The new tool flags are always present in the JSON schema (with
`#[serde(default)]`), even when the sandbox prompt section isn't
rendered. The system prompt only documents them when the section is
present, so the model shouldn't try to use them when it's not — but the
schema doesn't actively reject them, just ignores them.
- I opted not to add an end-to-end test for the escalation prompt path:
the existing `FakeThreadEnvironment` ignores the new params and toggling
the feature flag in tests is more wiring than felt worth it for a first
cut. The pure-function pieces (`sandbox_approval_title`, schema,
deserialization) are covered, and the sandbox crate itself has
end-to-end tests that actually invoke `sandbox-exec`.

Release Notes:

- N/A

---------

Co-authored-by: MartinYe1234 <52641447+MartinYe1234@users.noreply.github.com>
2026-05-27 21:38:17 +00:00

65 lines
1.6 KiB
TOML

[package]
name = "acp_thread"
version = "0.1.0"
edition.workspace = true
publish.workspace = true
license = "GPL-3.0-or-later"
[lints]
workspace = true
[lib]
path = "src/acp_thread.rs"
doctest = false
[features]
test-support = ["gpui/test-support", "project/test-support", "dep:parking_lot"]
[dependencies]
action_log.workspace = true
agent-client-protocol.workspace = true
async-channel.workspace = true
base64.workspace = true
anyhow.workspace = true
buffer_diff.workspace = true
chrono.workspace = true
collections.workspace = true
feature_flags.workspace = true
multi_buffer.workspace = true
file_icons.workspace = true
futures.workspace = true
gpui.workspace = true
itertools.workspace = true
language.workspace = true
language_model.workspace = true
log.workspace = true
markdown.workspace = true
parking_lot = { workspace = true, optional = true }
image.workspace = true
portable-pty.workspace = true
project.workspace = true
prompt_store.workspace = true
sandbox.workspace = true
serde.workspace = true
serde_json.workspace = true
settings.workspace = true
task.workspace = true
telemetry.workspace = true
terminal.workspace = true
text.workspace = true
ui.workspace = true
url.workspace = true
util.workspace = true
uuid.workspace = true
watch.workspace = true
urlencoding.workspace = true
[dev-dependencies]
env_logger.workspace = true
gpui = { workspace = true, "features" = ["test-support"] }
indoc.workspace = true
parking_lot.workspace = true
project = { workspace = true, "features" = ["test-support"] }
rand.workspace = true
util.workspace = true
settings.workspace = true