herald/src/bot_actions/review.rs

use futures_util::stream::TryStreamExt;
use tokio::io::AsyncReadExt;
use tokio_util::io::StreamReader;
use tracing::instrument;

use crate::{
    bot::ReviewResult,
    consts::{BOT_PROCESS_MSG, MAX_DIFF_SIZE, REVIEW_PROMPT},
    gitea::{GiteaAPI, ReviewPayload},
    open_router::OpenRouterClient,
};

#[instrument(skip(gitea_api, open_router_client, http_client, review_payload))]
pub async fn exec_review(
    gitea_api: &GiteaAPI,
    open_router_client: &OpenRouterClient,
    http_client: &reqwest::Client,
    model: &str,
    review_payload: ReviewPayload,
) -> anyhow::Result<()> {
    tracing::info!(
        repo = %review_payload.repository.full_name,
        pr = review_payload.pull_request.number,
        action = %review_payload.action,
        "Starting review"
    );

    let new_comment = gitea_api
        .comment(
            &BOT_PROCESS_MSG.replace("{model}", model),
            &review_payload.repository.full_name,
            review_payload.pull_request.number,
        )
        .await?;

    let bot_result: Result<ReviewResult, anyhow::Error> = async {
        let git_diff =
            download_git_diff(http_client, &review_payload.pull_request.diff_url).await?;

        let diff_for_llm = format_diff_for_review(&git_diff);

        let bot_request = REVIEW_PROMPT
            .replace("{subject}", &review_payload.pull_request.title)
            .replace("{comment}", &review_payload.comment.body)
            .replace("{diff}", &diff_for_llm);

        let chat_result = open_router_client.chat(&bot_request).await?;
        let mut review_result = serde_json::from_str::<ReviewResult>(&chat_result.message)?;

        review_result.cost = chat_result.cost;

        let final_review_markdown = review_result_to_markdown(&review_result);

        gitea_api
            .post_pull_request_review(
                &review_result,
                &final_review_markdown,
                &review_payload.repository.full_name,
                review_payload.pull_request.number,
            )
            .await?;

        Ok(review_result)
    }
    .await;

    match bot_result {
        Ok(_) => {
            gitea_api
                .delete_comment(&review_payload.repository.full_name, new_comment.id)
                .await
        }
        Err(e) => {
            gitea_api
                .edit_comment(
                    &format!("Error while reviewing: {}", e),
                    &review_payload.repository.full_name,
                    new_comment.id,
                )
                .await
        }
    }
}

fn review_result_to_markdown(review_result: &ReviewResult) -> String {
    if review_result.reviews.is_empty() {
        return String::from("No issues found. ✅");
    }

    let mut md = String::from("## Review Feedback\n\n");

    md.push_str(&format!(
        "### {} issues found.\n\n",
        review_result.reviews.len()
    ));

    if !review_result.comment.is_empty() {
        md.push_str("\n---\n\n");
        md.push_str("### Summary\n\n");
        md.push_str(&review_result.comment);
        md.push('\n');
    }

    if let Some(cost) = review_result.cost {
        md.push_str("\n---\n\n");
        md.push_str(&format!("### Cost: ${}", cost));
        md.push('\n');
    }

    md
}

async fn download_git_diff(http_client: &reqwest::Client, url: &str) -> anyhow::Result<String> {
    let response = http_client.get(url).send().await?;
    let stream = response.bytes_stream().map_err(std::io::Error::other);

    let mut buf = Vec::with_capacity(MAX_DIFF_SIZE);
    StreamReader::new(stream)
        .take((MAX_DIFF_SIZE + 1) as u64)
        .read_to_end(&mut buf)
        .await?;

    if buf.len() > MAX_DIFF_SIZE {
        anyhow::bail!("Git diff exceeds the maximum allowed size of 1 Mo");
    }

    Ok(String::from_utf8_lossy(&buf).into_owned())
}

fn format_diff_for_review(git_diff: &str) -> String {
    let mut output = String::new();
    let mut current_file: Option<&str> = None;
    let mut new_line: u64 = 0;

    for line in git_diff.lines() {
        if let Some(rest) = line.strip_prefix("diff --git a/") {
            if let Some(end) = rest.find(' ') {
                current_file = Some(&rest[..end]);
            }
            new_line = 0;
            continue;
        }

        if line.starts_with("---") || line.starts_with("+++") {
            continue;
        }

        if line.starts_with("@@") && line.contains('+') {
            if let Some(start) = parse_hunk_new_start(line) {
                new_line = start;
            }
            continue;
        }

        let Some(filename) = current_file else {
            continue;
        };

        if line.starts_with(' ') {
            new_line += 1;
            continue;
        }

        if let Some(code) = line.strip_prefix('+') {
            use std::fmt::Write;
            let _ = writeln!(output, "{filename}:{new_line}:{code}");
            new_line += 1;
        }
    }

    output
}

fn parse_hunk_new_start(hunk_header: &str) -> Option<u64> {
    let plus_part = hunk_header.split('+').nth(1)?;
    let num_str = plus_part.split(|c: char| !c.is_ascii_digit()).next()?;
    num_str.parse::<u64>().ok()
}

#[cfg(test)]
#[test]
fn test_format_diff_for_review() {
    let diff = concat!(
        "diff --git a/src/foo.rs b/src/foo.rs\n",
        "--- a/src/foo.rs\n",
        "+++ b/src/foo.rs\n",
        "@@ -1,3 +1,6 @@\n",
        " fn main() {\n",
        "+    let x = 1;\n",
        "     println!(\"hello\");\n",
        "+    let y = 2;\n",
        "+    let z = 3;\n",
        " }\n",
        "diff --git a/src/bar.rs b/src/bar.rs\n",
        "--- a/src/bar.rs\n",
        "+++ b/src/bar.rs\n",
        "@@ -10,4 +10,6 @@\n",
        " old context\n",
        "+    let a = 10;\n",
        " more context\n",
        "+    let b = 20;\n",
    );

    let result = format_diff_for_review(diff);
    let expected = concat!(
        "src/foo.rs:2:    let x = 1;\n",
        "src/foo.rs:4:    let y = 2;\n",
        "src/foo.rs:5:    let z = 3;\n",
        "src/bar.rs:11:    let a = 10;\n",
        "src/bar.rs:13:    let b = 20;\n",
    );

    assert_eq!(result, expected);
}