codex/codex-rs/core/src/tools/handlers/plan.rs

use crate::client_common::tools::ResponsesApiTool;
use crate::client_common::tools::ToolSpec;
use crate::codex::Session;
use crate::codex::TurnContext;
use crate::function_tool::FunctionCallError;
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 crate::tools::spec::JsonSchema;
use async_trait::async_trait;
use codex_protocol::config_types::ModeKind;
use codex_protocol::models::FunctionCallOutputPayload;
use codex_protocol::models::ResponseInputItem;
use codex_protocol::plan_tool::UpdatePlanArgs;
use codex_protocol::protocol::EventMsg;
use serde_json::Value as JsonValue;
use std::collections::BTreeMap;
use std::sync::LazyLock;

pub struct PlanHandler;

pub struct PlanToolOutput;

const PLAN_UPDATED_MESSAGE: &str = "Plan updated";

impl ToolOutput for PlanToolOutput {
    fn log_preview(&self) -> String {
        PLAN_UPDATED_MESSAGE.to_string()
    }

    fn success_for_logging(&self) -> bool {
        true
    }

    fn to_response_item(&self, call_id: &str, _payload: &ToolPayload) -> ResponseInputItem {
        let mut output = FunctionCallOutputPayload::from_text(PLAN_UPDATED_MESSAGE.to_string());
        output.success = Some(true);

        ResponseInputItem::FunctionCallOutput {
            call_id: call_id.to_string(),
            output,
        }
    }

    fn code_mode_result(&self, _payload: &ToolPayload) -> JsonValue {
        JsonValue::Object(serde_json::Map::new())
    }
}

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,
        defer_loading: None,
        parameters: JsonSchema::Object {
            properties,
            required: Some(vec!["plan".to_string()]),
            additional_properties: Some(false.into()),
        },
        output_schema: None,
    })
});

#[async_trait]
impl ToolHandler for PlanHandler {
    type Output = PlanToolOutput;

    fn kind(&self) -> ToolKind {
        ToolKind::Function
    }

    async fn handle(&self, invocation: ToolInvocation) -> Result<Self::Output, FunctionCallError> {
        let ToolInvocation {
            session,
            turn,
            call_id,
            payload,
            ..
        } = invocation;

        let arguments = match payload {
            ToolPayload::Function { arguments } => arguments,
            _ => {
                return Err(FunctionCallError::RespondToModel(
                    "update_plan handler received unsupported payload".to_string(),
                ));
            }
        };

        handle_update_plan(session.as_ref(), turn.as_ref(), arguments, call_id).await?;

        Ok(PlanToolOutput)
    }
}

/// 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,
    turn_context: &TurnContext,
    arguments: String,
    _call_id: String,
) -> Result<String, FunctionCallError> {
    if turn_context.collaboration_mode.mode == ModeKind::Plan {
        return Err(FunctionCallError::RespondToModel(
            "update_plan is a TODO/checklist tool and is not allowed in Plan mode".to_string(),
        ));
    }
    let args = parse_update_plan_arguments(&arguments)?;
    session
        .send_event(turn_context, 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}"))
    })
}