chore: refactor tool handling (#4510)
# Tool System Refactor
- Centralizes tool definitions and execution in `core/src/tools/*`:
specs (`spec.rs`), handlers (`handlers/*`), router (`router.rs`),
registry/dispatch (`registry.rs`), and shared context (`context.rs`).
One registry now builds the model-visible tool list and binds handlers.
- Router converts model responses to tool calls; Registry dispatches
with consistent telemetry via `codex-rs/otel` and unified error
handling. Function, Local Shell, MCP, and experimental `unified_exec`
all flow through this path; legacy shell aliases still work.
- Rationale: reduce per‑tool boilerplate, keep spec/handler in sync, and
make adding tools predictable and testable.
Example: `read_file`
- Spec: `core/src/tools/spec.rs` (see `create_read_file_tool`,
registered by `build_specs`).
- Handler: `core/src/tools/handlers/read_file.rs` (absolute `file_path`,
1‑indexed `offset`, `limit`, `L#: ` prefixes, safe truncation).
- E2E test: `core/tests/suite/read_file.rs` validates the tool returns
the requested lines.
## Next steps:
- Decompose `handle_container_exec_with_params`
- Add parallel tool calls
2025-10-03 13:21:06 +01:00
|
|
|
#![cfg(not(target_os = "windows"))]
|
|
|
|
|
|
|
|
|
|
use codex_core::protocol::AskForApproval;
|
|
|
|
|
use codex_core::protocol::EventMsg;
|
|
|
|
|
use codex_core::protocol::InputItem;
|
|
|
|
|
use codex_core::protocol::Op;
|
|
|
|
|
use codex_core::protocol::SandboxPolicy;
|
|
|
|
|
use codex_protocol::config_types::ReasoningSummary;
|
|
|
|
|
use core_test_support::responses;
|
|
|
|
|
use core_test_support::responses::ev_assistant_message;
|
|
|
|
|
use core_test_support::responses::ev_completed;
|
|
|
|
|
use core_test_support::responses::ev_function_call;
|
2025-10-05 14:11:43 -07:00
|
|
|
use core_test_support::responses::ev_response_created;
|
chore: refactor tool handling (#4510)
# Tool System Refactor
- Centralizes tool definitions and execution in `core/src/tools/*`:
specs (`spec.rs`), handlers (`handlers/*`), router (`router.rs`),
registry/dispatch (`registry.rs`), and shared context (`context.rs`).
One registry now builds the model-visible tool list and binds handlers.
- Router converts model responses to tool calls; Registry dispatches
with consistent telemetry via `codex-rs/otel` and unified error
handling. Function, Local Shell, MCP, and experimental `unified_exec`
all flow through this path; legacy shell aliases still work.
- Rationale: reduce per‑tool boilerplate, keep spec/handler in sync, and
make adding tools predictable and testable.
Example: `read_file`
- Spec: `core/src/tools/spec.rs` (see `create_read_file_tool`,
registered by `build_specs`).
- Handler: `core/src/tools/handlers/read_file.rs` (absolute `file_path`,
1‑indexed `offset`, `limit`, `L#: ` prefixes, safe truncation).
- E2E test: `core/tests/suite/read_file.rs` validates the tool returns
the requested lines.
## Next steps:
- Decompose `handle_container_exec_with_params`
- Add parallel tool calls
2025-10-03 13:21:06 +01:00
|
|
|
use core_test_support::responses::sse;
|
|
|
|
|
use core_test_support::responses::start_mock_server;
|
|
|
|
|
use core_test_support::skip_if_no_network;
|
|
|
|
|
use core_test_support::test_codex::TestCodex;
|
|
|
|
|
use core_test_support::test_codex::test_codex;
|
|
|
|
|
use core_test_support::wait_for_event;
|
|
|
|
|
use pretty_assertions::assert_eq;
|
|
|
|
|
use serde_json::Value;
|
|
|
|
|
use wiremock::matchers::any;
|
|
|
|
|
|
|
|
|
|
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
2025-10-04 22:47:26 -07:00
|
|
|
#[ignore = "disabled until we enable read_file tool"]
|
chore: refactor tool handling (#4510)
# Tool System Refactor
- Centralizes tool definitions and execution in `core/src/tools/*`:
specs (`spec.rs`), handlers (`handlers/*`), router (`router.rs`),
registry/dispatch (`registry.rs`), and shared context (`context.rs`).
One registry now builds the model-visible tool list and binds handlers.
- Router converts model responses to tool calls; Registry dispatches
with consistent telemetry via `codex-rs/otel` and unified error
handling. Function, Local Shell, MCP, and experimental `unified_exec`
all flow through this path; legacy shell aliases still work.
- Rationale: reduce per‑tool boilerplate, keep spec/handler in sync, and
make adding tools predictable and testable.
Example: `read_file`
- Spec: `core/src/tools/spec.rs` (see `create_read_file_tool`,
registered by `build_specs`).
- Handler: `core/src/tools/handlers/read_file.rs` (absolute `file_path`,
1‑indexed `offset`, `limit`, `L#: ` prefixes, safe truncation).
- E2E test: `core/tests/suite/read_file.rs` validates the tool returns
the requested lines.
## Next steps:
- Decompose `handle_container_exec_with_params`
- Add parallel tool calls
2025-10-03 13:21:06 +01:00
|
|
|
async fn read_file_tool_returns_requested_lines() -> anyhow::Result<()> {
|
|
|
|
|
skip_if_no_network!(Ok(()));
|
|
|
|
|
|
|
|
|
|
let server = start_mock_server().await;
|
|
|
|
|
|
|
|
|
|
let TestCodex {
|
|
|
|
|
codex,
|
|
|
|
|
cwd,
|
|
|
|
|
session_configured,
|
|
|
|
|
..
|
|
|
|
|
} = test_codex().build(&server).await?;
|
|
|
|
|
|
|
|
|
|
let file_path = cwd.path().join("sample.txt");
|
|
|
|
|
std::fs::write(&file_path, "first\nsecond\nthird\nfourth\n")?;
|
|
|
|
|
let file_path = file_path.to_string_lossy().to_string();
|
|
|
|
|
|
|
|
|
|
let call_id = "read-file-call";
|
|
|
|
|
let arguments = serde_json::json!({
|
|
|
|
|
"file_path": file_path,
|
|
|
|
|
"offset": 2,
|
|
|
|
|
"limit": 2,
|
|
|
|
|
})
|
|
|
|
|
.to_string();
|
|
|
|
|
|
|
|
|
|
let first_response = sse(vec![
|
2025-10-05 14:11:43 -07:00
|
|
|
ev_response_created("resp-1"),
|
chore: refactor tool handling (#4510)
# Tool System Refactor
- Centralizes tool definitions and execution in `core/src/tools/*`:
specs (`spec.rs`), handlers (`handlers/*`), router (`router.rs`),
registry/dispatch (`registry.rs`), and shared context (`context.rs`).
One registry now builds the model-visible tool list and binds handlers.
- Router converts model responses to tool calls; Registry dispatches
with consistent telemetry via `codex-rs/otel` and unified error
handling. Function, Local Shell, MCP, and experimental `unified_exec`
all flow through this path; legacy shell aliases still work.
- Rationale: reduce per‑tool boilerplate, keep spec/handler in sync, and
make adding tools predictable and testable.
Example: `read_file`
- Spec: `core/src/tools/spec.rs` (see `create_read_file_tool`,
registered by `build_specs`).
- Handler: `core/src/tools/handlers/read_file.rs` (absolute `file_path`,
1‑indexed `offset`, `limit`, `L#: ` prefixes, safe truncation).
- E2E test: `core/tests/suite/read_file.rs` validates the tool returns
the requested lines.
## Next steps:
- Decompose `handle_container_exec_with_params`
- Add parallel tool calls
2025-10-03 13:21:06 +01:00
|
|
|
ev_function_call(call_id, "read_file", &arguments),
|
|
|
|
|
ev_completed("resp-1"),
|
|
|
|
|
]);
|
|
|
|
|
responses::mount_sse_once_match(&server, any(), first_response).await;
|
|
|
|
|
|
|
|
|
|
let second_response = sse(vec![
|
|
|
|
|
ev_assistant_message("msg-1", "done"),
|
|
|
|
|
ev_completed("resp-2"),
|
|
|
|
|
]);
|
|
|
|
|
responses::mount_sse_once_match(&server, any(), second_response).await;
|
|
|
|
|
|
|
|
|
|
let session_model = session_configured.model.clone();
|
|
|
|
|
|
|
|
|
|
codex
|
|
|
|
|
.submit(Op::UserTurn {
|
|
|
|
|
items: vec![InputItem::Text {
|
|
|
|
|
text: "please inspect sample.txt".into(),
|
|
|
|
|
}],
|
|
|
|
|
final_output_json_schema: None,
|
|
|
|
|
cwd: cwd.path().to_path_buf(),
|
|
|
|
|
approval_policy: AskForApproval::Never,
|
|
|
|
|
sandbox_policy: SandboxPolicy::DangerFullAccess,
|
|
|
|
|
model: session_model,
|
|
|
|
|
effort: None,
|
|
|
|
|
summary: ReasoningSummary::Auto,
|
|
|
|
|
})
|
|
|
|
|
.await?;
|
|
|
|
|
|
|
|
|
|
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
|
|
|
|
|
|
|
|
|
|
let requests = server.received_requests().await.expect("recorded requests");
|
|
|
|
|
let request_bodies = requests
|
|
|
|
|
.iter()
|
|
|
|
|
.map(|req| req.body_json::<Value>().unwrap())
|
|
|
|
|
.collect::<Vec<_>>();
|
|
|
|
|
assert!(
|
|
|
|
|
!request_bodies.is_empty(),
|
|
|
|
|
"expected at least one request body"
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
let tool_output_item = request_bodies
|
|
|
|
|
.iter()
|
|
|
|
|
.find_map(|body| {
|
|
|
|
|
body.get("input")
|
|
|
|
|
.and_then(Value::as_array)
|
|
|
|
|
.and_then(|items| {
|
|
|
|
|
items.iter().find(|item| {
|
|
|
|
|
item.get("type").and_then(Value::as_str) == Some("function_call_output")
|
|
|
|
|
})
|
|
|
|
|
})
|
|
|
|
|
})
|
|
|
|
|
.unwrap_or_else(|| {
|
|
|
|
|
panic!("function_call_output item not found in requests: {request_bodies:#?}")
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
assert_eq!(
|
|
|
|
|
tool_output_item.get("call_id").and_then(Value::as_str),
|
|
|
|
|
Some(call_id)
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
let output_text = tool_output_item
|
|
|
|
|
.get("output")
|
|
|
|
|
.and_then(|value| match value {
|
|
|
|
|
Value::String(text) => Some(text.as_str()),
|
|
|
|
|
Value::Object(obj) => obj.get("content").and_then(Value::as_str),
|
|
|
|
|
_ => None,
|
|
|
|
|
})
|
|
|
|
|
.expect("output text present");
|
|
|
|
|
assert_eq!(output_text, "L2: second\nL3: third");
|
|
|
|
|
|
|
|
|
|
Ok(())
|
|
|
|
|
}
|