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
This commit is contained in:
jif-oai
2025-10-03 13:21:06 +01:00
committed by GitHub
parent 69cb72f842
commit 33d3ecbccc
48 changed files with 5288 additions and 2006 deletions

View File

@@ -0,0 +1,121 @@
use crate::client_common::tools::ResponsesApiTool;
use crate::client_common::tools::ToolSpec;
use crate::codex::Session;
use crate::function_tool::FunctionCallError;
use crate::openai_tools::JsonSchema;
use crate::tools::context::ToolInvocation;
use crate::tools::context::ToolOutput;
use crate::tools::context::ToolPayload;
use crate::tools::registry::ToolHandler;
use crate::tools::registry::ToolKind;
use async_trait::async_trait;
use codex_protocol::plan_tool::UpdatePlanArgs;
use codex_protocol::protocol::Event;
use codex_protocol::protocol::EventMsg;
use std::collections::BTreeMap;
use std::sync::LazyLock;
pub struct PlanHandler;
pub static PLAN_TOOL: LazyLock<ToolSpec> = LazyLock::new(|| {
let mut plan_item_props = BTreeMap::new();
plan_item_props.insert("step".to_string(), JsonSchema::String { description: None });
plan_item_props.insert(
"status".to_string(),
JsonSchema::String {
description: Some("One of: pending, in_progress, completed".to_string()),
},
);
let plan_items_schema = JsonSchema::Array {
description: Some("The list of steps".to_string()),
items: Box::new(JsonSchema::Object {
properties: plan_item_props,
required: Some(vec!["step".to_string(), "status".to_string()]),
additional_properties: Some(false.into()),
}),
};
let mut properties = BTreeMap::new();
properties.insert(
"explanation".to_string(),
JsonSchema::String { description: None },
);
properties.insert("plan".to_string(), plan_items_schema);
ToolSpec::Function(ResponsesApiTool {
name: "update_plan".to_string(),
description: r#"Updates the task plan.
Provide an optional explanation and a list of plan items, each with a step and status.
At most one step can be in_progress at a time.
"#
.to_string(),
strict: false,
parameters: JsonSchema::Object {
properties,
required: Some(vec!["plan".to_string()]),
additional_properties: Some(false.into()),
},
})
});
#[async_trait]
impl ToolHandler for PlanHandler {
fn kind(&self) -> ToolKind {
ToolKind::Function
}
async fn handle(
&self,
invocation: ToolInvocation<'_>,
) -> Result<ToolOutput, FunctionCallError> {
let ToolInvocation {
session,
sub_id,
call_id,
payload,
..
} = invocation;
let arguments = match payload {
ToolPayload::Function { arguments } => arguments,
_ => {
return Err(FunctionCallError::RespondToModel(
"update_plan handler received unsupported payload".to_string(),
));
}
};
let content = handle_update_plan(session, arguments, sub_id.to_string(), call_id).await?;
Ok(ToolOutput::Function {
content,
success: Some(true),
})
}
}
/// This function doesn't do anything useful. However, it gives the model a structured way to record its plan that clients can read and render.
/// So it's the _inputs_ to this function that are useful to clients, not the outputs and neither are actually useful for the model other
/// than forcing it to come up and document a plan (TBD how that affects performance).
pub(crate) async fn handle_update_plan(
session: &Session,
arguments: String,
sub_id: String,
_call_id: String,
) -> Result<String, FunctionCallError> {
let args = parse_update_plan_arguments(&arguments)?;
session
.send_event(Event {
id: sub_id.to_string(),
msg: EventMsg::PlanUpdate(args),
})
.await;
Ok("Plan updated".to_string())
}
fn parse_update_plan_arguments(arguments: &str) -> Result<UpdatePlanArgs, FunctionCallError> {
serde_json::from_str::<UpdatePlanArgs>(arguments).map_err(|e| {
FunctionCallError::RespondToModel(format!("failed to parse function arguments: {e}"))
})
}