hyperhive/swarm-queue-client/src/review_classifier.rs

//! The review classifier's try-out: the subject swarm-controller sends a run
//! on, and what travels each way.
//!
//! Three crates name these: the controller sends the request, the classifier
//! answers it, and the auth-callout responder grants the one subject to each.

use std::time::Duration;

use serde::{Deserialize, Serialize};

/// The subject a try-out request goes to. The controller is its one
/// publisher and the classifier its one subscriber; the classifier answers
/// on the request's reply subject.
pub const SUBJECT: &str = "$SWARM.review-classifier.try-out";

/// The queue group the classifier subscribes in, so a second instance shares
/// the requests instead of running each one twice.
pub const QUEUE_GROUP: &str = "review-classifier";

/// The most classifications one run carries.
pub const MAX_CLASSIFICATIONS: usize = 10;

/// The longest one classification's model run may take before it is stopped
/// and its row carries a timeout.
pub const CLASSIFICATION_DEADLINE: Duration = Duration::from_mins(3);

/// The longest a whole run may take: every classification at its deadline,
/// run one after another, plus a minute for the rest. The controller waits
/// this long for the reply, and the queue lets the classifier answer for
/// this long.
pub const RUN_DEADLINE: Duration = Duration::from_mins(31);

/// One run: the PR as the controller read it, and the classifications to
/// answer about it.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct TryOut {
    /// The swarm UI user who started the run, as the gateway named them.
    pub operator: String,
    /// `owner/name`.
    pub repo: String,
    pub pr: u64,
    /// The commit the commits and the diff were read at.
    pub head_sha: String,
    /// Oldest first.
    pub commits: Vec<Commit>,
    /// The PR's unified diff, as the forge serves it.
    pub diff: String,
    pub classifications: Vec<Classification>,
}

/// One commit of the PR.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct Commit {
    pub sha: String,
    /// The full message, subject and body.
    pub message: String,
}

/// One yes/no rule to check the PR against.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[cfg_attr(feature = "schema", derive(utoipa::ToSchema))]
pub struct Classification {
    pub name: String,
    /// The yes/no question the model answers about the PR.
    pub description: String,
    pub polarity: Polarity,
    /// The certainty, 0 to 100, a verdict needs to count.
    pub threshold: u8,
}

/// Which verdict is the wanted one.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[cfg_attr(feature = "schema", derive(utoipa::ToSchema))]
#[serde(rename_all = "lowercase")]
pub enum Polarity {
    /// A match is the wanted outcome.
    Positive,
    /// A match is a violation.
    Negative,
}

/// The classifier's answer to one [`TryOut`].
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[serde(tag = "state", rename_all = "kebab-case")]
pub enum Reply {
    Done {
        rows: Vec<Row>,
        overall: Overall,
    },
    /// Nothing ran to a verdict: no API key, or every classification failed.
    Failed {
        error: String,
    },
}

/// One classification's result, as the result table shows it.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[cfg_attr(feature = "schema", derive(utoipa::ToSchema))]
pub struct Row {
    pub name: String,
    pub polarity: Polarity,
    pub verdict: Verdict,
    pub certainty: u8,
    pub threshold: u8,
    /// Whether the row counts toward the overall verdict: applicable, and
    /// its certainty reached the threshold.
    pub counted: bool,
    /// For a counted row, whether the verdict is on the wanted side of the
    /// polarity. `false` for every row that is not counted.
    pub passed: bool,
    pub reason: String,
    /// Why this classification has no answer: a runtime error, a timeout, or
    /// an answer that did not validate. Such a row reads `not-applicable`,
    /// certainty 0 and an empty reason, and is never counted; key off this
    /// field, not off the verdict.
    #[serde(default, skip_serializing_if = "Option::is_none")]
    pub error: Option<String>,
}

#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[cfg_attr(feature = "schema", derive(utoipa::ToSchema))]
#[serde(rename_all = "kebab-case")]
pub enum Verdict {
    Match,
    NoMatch,
    NotApplicable,
}

#[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
#[cfg_attr(feature = "schema", derive(utoipa::ToSchema))]
#[serde(rename_all = "kebab-case")]
pub enum Overall {
    Approve,
    RequestChanges,
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn the_wire_spells_the_enums_as_the_api_does() {
        let row = Row {
            name: "datetime".to_owned(),
            polarity: Polarity::Positive,
            verdict: Verdict::NotApplicable,
            certainty: 95,
            threshold: 70,
            counted: false,
            passed: false,
            reason: "The PR adds no timestamp.".to_owned(),
            error: None,
        };
        let json = serde_json::to_value(Reply::Done {
            rows: vec![row],
            overall: Overall::RequestChanges,
        })
        .expect("encodes");
        assert_eq!(json["state"], "done");
        assert_eq!(json["overall"], "request-changes");
        assert_eq!(json["rows"][0]["polarity"], "positive");
        assert_eq!(json["rows"][0]["verdict"], "not-applicable");
        assert!(json["rows"][0].get("error").is_none());
    }

    #[test]
    fn the_run_deadline_covers_every_classification_at_its_deadline() {
        let all = CLASSIFICATION_DEADLINE * u32::try_from(MAX_CLASSIFICATIONS).expect("small");
        assert!(RUN_DEADLINE > all);
    }
}