//! Background Forgejo notification poller. Polls
//! `GET /notifications?all=false` every 30s, formats each unread
//! notification as a broker `Wake { from: "forge" }` message, and
//! delivers it to the agent's inbox. Delivered threads are deliberately
//! left UNREAD in forge — the hive-forge read-before-comment guard keys
//! off forge's own unread-state, and the agent reading the thread via the
//! CLI is what marks it read. A delivery-dedupe cursor (thread id →
//! last-delivered `updated_at`) stops the still-unread notification from
//! re-firing a wake every poll; self-echo and drop-listed notifications
//! are still marked read directly. The cursor is persisted as the
//! `forge_cursor` field of the harness's consolidated `hyperhive-harness.json`
//! (via [`crate::events`]) and reloaded on boot so a container
//! rebuild/restart doesn't re-deliver the whole currently-unread backlog —
//! it is a private dedup mirror, NOT forge's read-state, so the
//! read-before-comment guard is untouched.
//!
//! Activation gates, self-notification filtering, body excerpt +
//! truncation + heading escape, wrapper formats (comment / review /
//! new-item / state-change), meta suffix, and review-request override
//! all live in [`docs/forge.md::Notification poller`](../../../docs/forge.md).

use std::collections::{HashMap, HashSet};
use std::fmt::Write as _;
use std::path::{Path, PathBuf};
use std::time::Duration;

use tracing::{debug, info, warn};

const POLL_INTERVAL_SECS: u64 = 30;
const HTTP_TIMEOUT_SECS: u64 = 10;
/// Maximum characters of a body/comment to include in the wake message.
const BODY_TRUNCATE: usize = 500;
/// How long to wait between token-read retries when the token file is
/// missing or unreadable at startup (e.g. hive-priv hasn't provisioned
/// it yet, or a chown race left it temporarily root-owned).
const TOKEN_RETRY_SECS: u64 = 30;
/// Give up waiting for the token after this many retries (~10 minutes).
/// Avoids an infinite wait on agents that genuinely have no forge account.
const TOKEN_RETRY_MAX: u32 = 20;
/// How close (seconds) the notification's event time must be to a
/// subject's `created_at` for us to call it a genuine creation and emit
/// a `new <kind>` label. Later activity that lands on the state-change
/// path because it carries no `latest_comment_url` (e.g. a bodiless
/// review submission) fires well outside this window, so we must not
/// claim it's "new" — see docs/forge.md, "new vs activity on".
const NEW_ITEM_TOLERANCE_SECS: i64 = 120;

/// Spawn point: called once from `hive serve`. Returns immediately if the forge is not
/// configured. Otherwise loops forever, polling every
/// `POLL_INTERVAL_SECS` seconds. Errors are never fatal.
///
pub async fn run(socket: PathBuf) {
    let forge_url = match std::env::var("HIVE_FORGE_URL") {
        Ok(u) if !u.is_empty() => u,
        _ => {
            debug!("forge_notify: HIVE_FORGE_URL not set — disabled");
            return;
        }
    };

    let state_dir = std::env::var("HYPERHIVE_STATE_DIR").unwrap_or_default();
    let token_path = format!("{state_dir}/forge-token");
    // Retry reading the token to handle races where hive-priv provisions the
    // token after the harness starts, or where a parent-container chown briefly
    // makes the file unreadable. We wait up to
    // TOKEN_RETRY_MAX * TOKEN_RETRY_SECS before giving up.
    let token = {
        let mut attempts = 0u32;
        loop {
            match tokio::fs::read_to_string(&token_path).await {
                Ok(t) => {
                    let t = t.trim().to_owned();
                    if !t.is_empty() {
                        break t;
                    }
                    debug!("forge_notify: empty forge token at {token_path}");
                }
                Err(e) => {
                    debug!("forge_notify: cannot read token at {token_path}: {e}");
                }
            }
            attempts += 1;
            if attempts >= TOKEN_RETRY_MAX {
                debug!(
                    "forge_notify: token not available after {TOKEN_RETRY_MAX} retries — disabled"
                );
                return;
            }
            tokio::time::sleep(Duration::from_secs(TOKEN_RETRY_SECS)).await;
        }
    };

    let client = match reqwest::Client::builder()
        .timeout(Duration::from_secs(HTTP_TIMEOUT_SECS))
        .build()
    {
        Ok(c) => c,
        Err(e) => {
            warn!("forge_notify: failed to build HTTP client: {e}");
            return;
        }
    };

    // Fetch own login once for self-notification filtering. Falls back
    // to empty string on failure — no filtering (safe degradation; see
    // `docs/forge.md::Self-notification filtering`).
    let own_login = {
        let url = format!("{forge_url}/api/v1/user");
        fetch_json(&client, &url, &token)
            .await
            .and_then(|v| v["login"].as_str().map(std::borrow::ToOwned::to_owned))
            .unwrap_or_default()
    };
    if own_login.is_empty() {
        warn!("forge_notify: could not resolve own login — self-notification filtering disabled");
    } else {
        debug!(%own_login, "forge_notify: own login resolved");
    }

    let mut interval = tokio::time::interval(Duration::from_secs(POLL_INTERVAL_SECS));
    interval.set_missed_tick_behavior(tokio::time::MissedTickBehavior::Delay);
    // First tick fires immediately — skip it so we don't race the broker
    // socket becoming available right at boot.
    interval.tick().await;

    info!(forge_url = %forge_url, "forge_notify: polling started");

    // Delivery-dedupe cursor: notification thread id -> the `updated_at`
    // of the version we last woke the agent for. We no longer mark a
    // thread read on delivery (that would consume the unread signal the
    // hive-forge read-before-comment guard relies on), so this map is what
    // stops the same unread notification from re-firing a wake every poll.
    // A new comment bumps `updated_at`, so the thread re-delivers. This is
    // purely anti-spam, NOT a correctness oracle.
    //
    // It is persisted as the `forge_cursor` field of the harness's
    // consolidated state file and reloaded here on boot so a container
    // rebuild/restart doesn't re-deliver the entire currently-unread
    // backlog. Persisting is safe because we only record a thread AFTER a
    // successful broker delivery, and the broker inbox is durable sqlite —
    // so a persisted "delivered" entry can never swallow a wake the agent
    // never received. The cursor is a private dedup mirror, decoupled from
    // forge's own read-state, so it doesn't reintroduce the
    // read-before-comment coupling that the mark-read-on-delivery approach
    // suffered.
    let mut delivered: HashMap<u64, String> = crate::events::read_forge_cursor();
    if !delivered.is_empty() {
        info!(
            entries = delivered.len(),
            "forge_notify: restored delivery-dedupe cursor"
        );
    }

    loop {
        interval.tick().await;
        poll_once(
            &client,
            &forge_url,
            &token,
            &socket,
            &mut delivered,
            &own_login,
        )
        .await;
    }
}

/// Fetch a JSON value from a URL using the agent's forge token. Returns
/// `None` on any HTTP or parse error (best-effort enrichment).
async fn fetch_json(client: &reqwest::Client, url: &str, token: &str) -> Option<serde_json::Value> {
    let resp = client
        .get(url)
        .header("Authorization", format!("token {token}"))
        .send()
        .await
        .ok()?;
    if !resp.status().is_success() {
        return None;
    }
    resp.json().await.ok()
}

/// Map a Forgejo notification `subject.type` to a human-readable label.
/// Known values: "Pull", "Issue", "Commit", "Repository". Any unknown
/// type is passed through as-is so new Forgejo types degrade gracefully
/// rather than silently collapsing into a generic label.
fn notif_type_label(t: &str) -> &str {
    match t {
        "Pull" => "PR",
        "Issue" => "issue",
        other => other,
    }
}

/// Escape strict-ATX markdown headings in a body before embedding it
/// inside the forge-notify wrapper, so a leading `## title` line
/// doesn't blow into an h2 in the dashboard render. See
/// `docs/forge.md::Body excerpt + truncation + heading escape` for
/// the strict-ATX-vs-`#tag` rationale and the `split_inclusive`
/// trailing-newline contract.
fn escape_md_headings(body: &str) -> String {
    let mut out = String::with_capacity(body.len());
    for line in body.split_inclusive('\n') {
        let (content, terminator) = match line.strip_suffix('\n') {
            Some(rest) => (rest, "\n"),
            None => (line, ""),
        };
        let trimmed = content.trim_start();
        if is_atx_heading(trimmed) {
            let lead = &content[..content.len() - trimmed.len()];
            out.push_str(lead);
            out.push('\\');
            out.push_str(trimmed);
        } else {
            out.push_str(content);
        }
        out.push_str(terminator);
    }
    out
}

/// Strict `CommonMark` ATX-heading detector: 1-6 leading `#`s followed
/// by either a space, tab, or end-of-line. Anything tighter (`#tag`,
/// `#9`) is a non-heading line that the renderer will not promote.
fn is_atx_heading(line: &str) -> bool {
    let hashes = line.bytes().take_while(|&b| b == b'#').count();
    if !(1..=6).contains(&hashes) {
        return false;
    }
    // Bare `#` / `##` / ... on its own line, or proper ATX with a
    // space/tab after the run of `#`s; anything else (`#tag` / `#9`)
    // is not a heading.
    matches!(line.as_bytes().get(hashes), None | Some(b' ' | b'\t'))
}

fn truncate(s: &str, max: usize) -> String {
    if s.len() <= max {
        return s.to_owned();
    }
    let end = s
        .char_indices()
        .map(|(i, _)| i)
        .take_while(|&i| i <= max - 3)
        .last()
        .unwrap_or(0);
    format!("{}…", &s[..end])
}

/// Detect `@username` mentions on a line. A mention is `@` followed by
/// at least one username char (alphanumeric / `_` / `-`) where the `@`
/// is at line start or follows a non-username char — so email-style
/// `foo@bar.com` does NOT count as a mention.
fn contains_mention(line: &str) -> bool {
    let bytes = line.as_bytes();
    for (i, &b) in bytes.iter().enumerate() {
        if b != b'@' {
            continue;
        }
        // Boundary: preceding byte must NOT be a username char.
        let boundary_ok = match i.checked_sub(1).map(|j| bytes[j]) {
            None => true,
            Some(prev) => !is_username_byte(prev),
        };
        if !boundary_ok {
            continue;
        }
        // Following byte must be at least one username char.
        if bytes.get(i + 1).is_some_and(|&c| is_username_byte(c)) {
            return true;
        }
    }
    false
}

fn is_username_byte(b: u8) -> bool {
    b.is_ascii_alphanumeric() || b == b'_' || b == b'-'
}

/// Walk `full_body` line-by-line; return lines that contain an
/// `@username` mention AND aren't already present (as a substring) in
/// `included_excerpt`. Surfaces tags that fell outside the truncation
/// window so addressed agents never silently miss a mention on a long
/// body. See `docs/forge.md::Body excerpt + truncation + heading
/// escape` for the truncate-before-escape ordering rule.
fn extract_truncated_mention_lines<'a>(full_body: &'a str, included_excerpt: &str) -> Vec<&'a str> {
    full_body
        .lines()
        .filter(|line| {
            let trimmed = line.trim();
            !trimmed.is_empty() && contains_mention(trimmed)
        })
        .filter(|line| !included_excerpt.contains(line.trim()))
        .collect()
}

/// Build the trailing `mentions (truncated from body):\n  > …` block.
/// Empty string when there's nothing to surface. Caller embeds it
/// directly before the meta suffix.
fn render_truncated_mentions(lines: &[&str]) -> String {
    if lines.is_empty() {
        return String::new();
    }
    let mut out = String::from("\n\nmentions (truncated from body):");
    for line in lines {
        write!(out, "\n  > {}", line.trim()).ok();
    }
    out
}

/// Map a Forgejo review state to a readable action label.
/// Returns `None` for non-review states (regular comments have no `state` field;
/// `PENDING` means the review was saved but not submitted yet).
/// Forgejo review states: "APPROVED", "`REQUEST_CHANGES`", "COMMENT", "PENDING".
fn review_state_label(state: &str) -> Option<&str> {
    match state {
        "APPROVED" => Some("approved"),
        "REQUEST_CHANGES" => Some("changes requested"),
        "COMMENT" => Some("review comment"),
        _ => None,
    }
}

/// Build a human-readable wake message for one Forgejo notification,
/// or `None` for a self-echo the caller should mark-read without
/// delivery. Wrapper format table + meta-suffix shape + number/repo
/// extraction live in `docs/forge.md::Wrapper format` +
/// `::Meta suffix`.
async fn format_notification(
    client: &reqwest::Client,
    token: &str,
    notif: &serde_json::Value,
    own_login: &str,
) -> Option<String> {
    let title = notif["subject"]["title"].as_str().unwrap_or("?");
    let notif_type = notif["subject"]["type"].as_str().unwrap_or("?");
    let html_url = notif["subject"]["html_url"]
        .as_str()
        .unwrap_or_else(|| notif["subject"]["url"].as_str().unwrap_or(""));

    // Extract issue/PR number from the html_url. URL ends with /issues/N or
    // /pulls/N (possibly followed by #anchor for comments). Best-effort.
    let num = html_url
        .split('#')
        .next()
        .and_then(|u| u.rsplit('/').next())
        .and_then(|s| s.parse::<u64>().ok())
        .map(|n| format!(" #{n}"))
        .unwrap_or_default();

    // Repo slug for multi-repo disambiguation. Falls back gracefully when absent.
    let repo = notif["repository"]["full_name"]
        .as_str()
        .map(|r| format!(" {r}"))
        .unwrap_or_default();

    // API URLs for fetching content
    let subject_api_url = notif["subject"]["url"].as_str().unwrap_or("");
    let comment_api_url = notif["subject"]["latest_comment_url"]
        .as_str()
        .unwrap_or("");
    let comment_html_url = notif["subject"]["latest_comment_html_url"]
        .as_str()
        .unwrap_or("");

    // Always fetch subject detail for assignee/reviewer metadata so
    // the meta suffix can show current ownership without a follow-up
    // fetch (see `docs/forge.md::Meta suffix`).
    let subject = if subject_api_url.is_empty() {
        None
    } else {
        fetch_json(client, subject_api_url, token).await
    };

    let is_pr = matches!(notif_type, "Pull Request" | "Pull");
    let meta_suffix = build_meta_suffix(subject.as_ref(), is_pr);

    // Determine whether this notification was triggered by a comment/review or
    // by creation/state-change of the subject itself.
    let has_comment = !comment_api_url.is_empty() && comment_api_url != subject_api_url;

    let meta = NotifMeta {
        title,
        notif_type,
        html_url,
        num,
        repo,
        meta_suffix,
        subject,
        is_pr,
    };
    if has_comment {
        format_comment_notification(
            client,
            token,
            &meta,
            comment_api_url,
            comment_html_url,
            own_login,
        )
        .await
    } else {
        format_state_change_notification(notif, &meta, own_login)
    }
}

/// Shared notification metadata extracted from the raw Forgejo JSON.
struct NotifMeta<'a> {
    title: &'a str,
    notif_type: &'a str,
    html_url: &'a str,
    num: String,
    repo: String,
    meta_suffix: String,
    /// Fetched subject detail (issue/PR JSON); used for review-request detection.
    subject: Option<serde_json::Value>,
    is_pr: bool,
}

/// Build the `\nassignee: ...` (and optionally `\nreviewer: ...`)
/// suffix appended to every wrapper. Shape + presence rules live in
/// `docs/forge.md::Meta suffix`.
fn build_meta_suffix(subject: Option<&serde_json::Value>, is_pr: bool) -> String {
    let assignees: Vec<&str> = subject
        .and_then(|s| s["assignees"].as_array())
        .map(|arr| arr.iter().filter_map(|a| a["login"].as_str()).collect())
        .unwrap_or_default();
    let assignee_line = if assignees.is_empty() {
        "assignee: unassigned".to_owned()
    } else {
        format!("assignee: {}", assignees.join(", "))
    };
    // For PRs, include requested_reviewers when present.
    let reviewer_line = if is_pr {
        let reviewers: Vec<&str> = subject
            .and_then(|s| s["requested_reviewers"].as_array())
            .map(|arr| arr.iter().filter_map(|r| r["login"].as_str()).collect())
            .unwrap_or_default();
        if reviewers.is_empty() {
            None
        } else {
            Some(format!("reviewer: {}", reviewers.join(", ")))
        }
    } else {
        None
    };
    let mut out = format!("\n{assignee_line}");
    if let Some(r) = reviewer_line {
        write!(out, "\n{r}").ok();
    }
    out
}

/// Format a notification triggered by a new comment or review submission.
async fn format_comment_notification(
    client: &reqwest::Client,
    token: &str,
    meta: &NotifMeta<'_>,
    comment_api_url: &str,
    comment_html_url: &str,
    own_login: &str,
) -> Option<String> {
    let payload = fetch_json(client, comment_api_url, token).await;

    let actor_login = payload
        .as_ref()
        .and_then(|c| c["user"]["login"].as_str())
        .unwrap_or("");

    // Self-notification filter: skip if we authored the comment/review.
    if !own_login.is_empty() && actor_login == own_login {
        debug!(%own_login, "forge_notify: skipping self-authored comment/review");
        return None;
    }

    let body_text = payload
        .as_ref()
        .and_then(|c| c["body"].as_str())
        .unwrap_or("")
        .trim();

    // PR review detection: Forgejo review objects carry a `state`
    // field with values like "APPROVED" / "REQUEST_CHANGES" /
    // "COMMENT". Regular issue/PR comments have no such field. Format
    // reviews distinctly so the agent knows the outcome at a glance.
    let review_state = payload
        .as_ref()
        .and_then(|c| c["state"].as_str())
        .and_then(review_state_label);

    let url = if comment_html_url.is_empty() {
        meta.html_url
    } else {
        comment_html_url
    };
    let author = if actor_login.is_empty() {
        "?"
    } else {
        actor_login
    };
    let NotifMeta {
        title,
        notif_type,
        num,
        repo,
        meta_suffix,
        ..
    } = meta;

    // Truncate → mention-overflow → escape, in that order. See
    // `docs/forge.md::Body excerpt + truncation + heading escape` for
    // why truncate comes before escape (mention diff compares against
    // unescaped raw body).
    let raw_excerpt = truncate(body_text, BODY_TRUNCATE);
    let truncated_mentions = if body_text.len() > BODY_TRUNCATE {
        render_truncated_mentions(&extract_truncated_mention_lines(body_text, &raw_excerpt))
    } else {
        String::new()
    };
    let body_for_embed = escape_md_headings(&raw_excerpt);
    if let Some(review_label) = review_state {
        // Review submission on a PR.
        let kind = format!("PR {review_label}{num}{repo}");
        let mut out = format!("[{kind}] {title}\nurl: {url}");
        if body_text.is_empty() {
            write!(out, "\n\nreviewer: {author}").ok();
        } else {
            write!(out, "\n\n{author}: {body_for_embed}{truncated_mentions}").ok();
        }
        out.push_str(meta_suffix);
        Some(out)
    } else {
        // Regular comment.
        let kind = format!("comment on {}{num}{repo}", notif_type_label(notif_type));
        let mut out = format!(
            "[{kind}] {title}\nurl: {url}\n\n{author}: {body_for_embed}{truncated_mentions}"
        );
        if out.ends_with('\n') {
            out.pop();
        }
        out.push_str(meta_suffix);
        Some(out)
    }
}

/// Format a notification triggered by creation or state change of the subject.
///
/// Returns `None` for an agent's own *creation* (it opened the issue/PR) —
/// the same "don't loop claude on its own writes" rule the comment/review
/// path applies. Only creations are dropped: a later state change on the
/// agent's own subject is driven by someone else and stays a wake.
fn format_state_change_notification(
    notif: &serde_json::Value,
    meta: &NotifMeta<'_>,
    own_login: &str,
) -> Option<String> {
    // Classification uses notif["subject"]["state"] directly — Forgejo
    // returns "open" / "closed" / "merged" here. We do NOT rely on
    // fetching the PR/issue detail for `merged`:
    //   - `subject.url` points to the *issues* endpoint, which returns
    //     `pull_request.merged`, not top-level `merged`.
    //   - Forgejo API type is "Pull" / "Issue", never "Pull Request".
    let notif_state = notif["subject"]["state"].as_str().unwrap_or("");

    // "New" = the subject is open (or state is absent). Used below for
    // the review-request override.
    let is_new = notif_state == "open" || notif_state.is_empty();

    let NotifMeta {
        title,
        notif_type,
        html_url,
        num,
        repo,
        meta_suffix,
        subject,
        is_pr,
    } = meta;
    let label = notif_type_label(notif_type);
    // Only claim "new" when the notification actually fired at creation
    // time. A review submitted with no body carries no
    // `latest_comment_url`, so it lands here instead of on the comment
    // path — and its event time is well after `created_at`. Labeling
    // that "new PR" is misleading (see docs/forge.md, "new vs activity
    // on"): agents dismiss it as a
    // duplicate of the original open notification. When we can't confirm
    // creation, fall back to a neutral "activity on" label.
    let looks_new = notification_is_creation(notif, subject.as_ref());

    // Self-authored creation filter: skip an agent being woken by its own
    // freshly-opened issue/PR. The subject payload is already fetched (for
    // assignees / reviewers / body), so its poster `user.login` costs no
    // extra request. Mirrors the self-authored comment/review drop above.
    if looks_new && !own_login.is_empty() {
        let author = subject
            .as_ref()
            .and_then(|s| s["user"]["login"].as_str())
            .unwrap_or("");
        if author == own_login {
            debug!(%own_login, "forge_notify: skipping self-authored creation");
            return None;
        }
    }

    let kind = match notif_state {
        "merged" => format!("{label} merged{num}{repo}"),
        "closed" => format!("{label} closed{num}{repo}"),
        "open" | "" if looks_new => format!("new {label}{num}{repo}"),
        "open" | "" => format!("activity on {label}{num}{repo}"),
        other => format!("{label}{num}{repo}: {other}"),
    };

    // Review-request override: Forgejo doesn't reliably set
    // `reason == "review_requested"` (often null), so we check the
    // subject payload's `requested_reviewers` list directly. See
    // `docs/forge.md::Review-request override`.
    let is_review_request = is_new
        && *is_pr
        && !own_login.is_empty()
        && subject
            .as_ref()
            .and_then(|s| s["requested_reviewers"].as_array())
            .is_some_and(|arr| arr.iter().any(|r| r["login"].as_str() == Some(own_login)));
    let kind = if is_review_request {
        format!("review requested{num}{repo}")
    } else {
        kind
    };

    // Include the start of the issue/PR description so the agent
    // gets context without a follow-up fetch. Same truncate →
    // mention-overflow → escape pipeline as comment bodies (see
    // `docs/forge.md::Body excerpt + truncation + heading escape`).
    let body_block = subject
        .as_ref()
        .and_then(|s| s["body"].as_str())
        .map(str::trim)
        .filter(|s| !s.is_empty())
        .map(|raw| {
            let raw_excerpt = truncate(raw, BODY_TRUNCATE);
            let truncated = extract_truncated_mention_lines(raw, &raw_excerpt);
            let mentions = render_truncated_mentions(&truncated);
            let excerpt = escape_md_headings(&raw_excerpt);
            format!("\n\n{excerpt}{mentions}")
        })
        .unwrap_or_default();

    let mut out = format!("[{kind}] {title}\nurl: {html_url}{body_block}");
    out.push_str(meta_suffix);
    Some(out)
}

/// Decide whether a state-change notification represents the subject's
/// *creation* (so a `new <kind>` label is truthful) versus later
/// activity that merely lacked a `latest_comment_url`. Compares the
/// notification's event time (`updated_at`) against the subject's
/// `created_at`: within `NEW_ITEM_TOLERANCE_SECS` ⇒ creation. When
/// either timestamp is missing or unparseable we default to `true`,
/// preserving the prior "new" behavior rather than masking a genuine
/// new item behind the neutral fallback. See docs/forge.md, "new vs
/// activity on".
fn notification_is_creation(
    notif: &serde_json::Value,
    subject: Option<&serde_json::Value>,
) -> bool {
    let created = subject
        .and_then(|s| s["created_at"].as_str())
        .and_then(parse_rfc3339_secs);
    let event = notif["updated_at"].as_str().and_then(parse_rfc3339_secs);
    match (created, event) {
        (Some(c), Some(e)) => (e - c).abs() <= NEW_ITEM_TOLERANCE_SECS,
        _ => true,
    }
}

/// Minimal dependency-free RFC 3339 / ISO 8601 parser → Unix epoch
/// seconds. Forgejo emits timestamps like `2026-06-13T11:18:42+02:00`
/// or `...Z`, optionally with fractional seconds. We only need
/// second-granularity comparison, so the fractional part is skipped.
/// Returns `None` on any shape we don't recognise so callers can fall
/// back gracefully.
fn parse_rfc3339_secs(s: &str) -> Option<i64> {
    if s.len() < 19 {
        return None;
    }
    let year: i64 = s.get(0..4)?.parse().ok()?;
    let month: i64 = s.get(5..7)?.parse().ok()?;
    let day: i64 = s.get(8..10)?.parse().ok()?;
    let hour: i64 = s.get(11..13)?.parse().ok()?;
    let minute: i64 = s.get(14..16)?.parse().ok()?;
    let second: i64 = s.get(17..19)?.parse().ok()?;

    let mut epoch =
        days_from_civil(year, month, day) * 86_400 + hour * 3_600 + minute * 60 + second;

    // Remainder after seconds: optional `.fff` fraction, then a zone.
    let mut rest = &s[19..];
    if let Some(frac) = rest.strip_prefix('.') {
        let end = frac
            .find(|c: char| !c.is_ascii_digit())
            .unwrap_or(frac.len());
        rest = &frac[end..];
    }
    // Zone: `Z`/empty = UTC; otherwise `±HH:MM`. Subtract the offset to
    // normalise to UTC epoch seconds.
    if !(rest.is_empty() || rest.starts_with('Z')) {
        let sign = rest.as_bytes()[0];
        let off = &rest[1..];
        let oh: i64 = off.get(0..2)?.parse().ok()?;
        let om: i64 = off.get(3..5).unwrap_or("00").parse().ok()?;
        let offset = oh * 3_600 + om * 60;
        match sign {
            b'+' => epoch -= offset,
            b'-' => epoch += offset,
            _ => return None,
        }
    }
    Some(epoch)
}

/// Days since the Unix epoch for a proleptic-Gregorian `y-m-d`
/// (Howard Hinnant's `days_from_civil`). Valid for all dates Forgejo
/// can emit.
fn days_from_civil(y: i64, m: i64, d: i64) -> i64 {
    let y = if m <= 2 { y - 1 } else { y };
    let era = (if y >= 0 { y } else { y - 399 }) / 400;
    let yoe = y - era * 400;
    let doy = (153 * (if m > 2 { m - 3 } else { m + 9 }) + 2) / 5 + d - 1;
    let doe = yoe * 365 + yoe / 4 - yoe / 100 + doy;
    era * 146_097 + doe - 719_468
}

#[allow(
    clippy::too_many_lines,
    reason = "single-pass notification poll loop — split would obscure the \
              sequential 'fetch / classify / dispatch' rhythm and add helper \
              functions for state shared across all three phases"
)]
async fn poll_once(
    client: &reqwest::Client,
    forge_url: &str,
    token: &str,
    socket: &Path,
    delivered: &mut HashMap<u64, String>,
    own_login: &str,
) {
    let url = format!("{forge_url}/api/v1/notifications?all=false&limit=50");
    let resp = match client
        .get(&url)
        .header("Authorization", format!("token {token}"))
        .send()
        .await
    {
        Ok(r) => r,
        Err(e) => {
            debug!("forge_notify: poll request failed: {e}");
            return;
        }
    };

    if !resp.status().is_success() {
        debug!("forge_notify: poll status {}", resp.status());
        return;
    }

    let notifications: Vec<serde_json::Value> = match resp.json().await {
        Ok(v) => v,
        Err(e) => {
            warn!("forge_notify: response parse error: {e}");
            return;
        }
    };

    if notifications.is_empty() {
        return;
    }

    debug!(
        count = notifications.len(),
        "forge_notify: delivering notifications"
    );

    // Tracks whether the dedupe cursor changed this poll (a new delivery
    // recorded, or the prune below dropped now-read threads) so we only
    // rewrite the on-disk cursor when there's something to persist.
    let mut cursor_dirty = false;

    for notif in &notifications {
        let Some(id) = notif["id"].as_u64() else {
            continue;
        };

        // Delivery-dedupe: we no longer mark threads read on delivery, so
        // an unread notification reappears in every `?all=false` poll.
        // Skip it silently unless its `updated_at` advanced since the
        // version we last delivered a wake for (i.e. genuinely new
        // activity). See the `delivered` cursor note in `run`.
        let updated_at = notif["updated_at"].as_str().unwrap_or("").to_owned();
        if !should_deliver(delivered, id, &updated_at) {
            debug!(%id, "forge_notify: skipping (already delivered this version)");
            continue;
        }

        let body_opt = format_notification(client, token, notif, own_login).await;

        // None means self-echo — mark read silently, no delivery.
        let Some(body) = body_opt else {
            mark_read(client, forge_url, token, id).await;
            continue;
        };

        let req = hive_sh4re::Request::Wake {
            from: "forge".to_owned(),
            body,
            transient: false,
        };
        let deliver_result = crate::client::request::<_, hive_sh4re::Response>(socket, &req)
            .await
            .map(|_| ());
        match deliver_result {
            Ok(()) => {
                debug!(%id, "forge_notify: delivered");
                // Record the delivered version in the dedupe cursor INSTEAD
                // of marking the thread read. Leaving it unread is
                // deliberate: the hive-forge read-before-comment guard keys
                // off forge's own unread-state, and the agent reading the
                // thread via the CLI is what marks it read. Recorded only
                // here in the Ok arm — a failed delivery leaves the cursor
                // untouched, so it re-delivers next tick.
                delivered.insert(id, updated_at);
                cursor_dirty = true;
            }
            Err(e) => {
                warn!(%id, error = ?e, "forge_notify: deliver failed — leaving unread");
            }
        }
    }

    // Prune the dedupe cursor down to the threads still present in this
    // poll's unread set. Once the agent reads a thread (marking it read
    // via the CLI) it drops out of `?all=false`, so its cursor entry is
    // dead weight; dropping it bounds the map to the current unread size.
    // If such a thread later goes unread again it carries a fresh
    // `updated_at` and re-delivers correctly.
    let current_ids: HashSet<u64> = notifications
        .iter()
        .filter_map(|n| n["id"].as_u64())
        .collect();
    let before_prune = delivered.len();
    delivered.retain(|id, _| current_ids.contains(id));
    if delivered.len() != before_prune {
        cursor_dirty = true;
    }

    // Flush the cursor to the consolidated state file only when it
    // changed, so a rebuild/restart reloads it instead of re-delivering
    // the whole unread backlog.
    if cursor_dirty {
        crate::events::write_forge_cursor(delivered);
    }
}

/// Whether a notification should be delivered as a wake given the
/// delivery-dedupe cursor. Delivers when the thread has never been
/// delivered, or when its `updated_at` advanced since the last delivered
/// version (genuinely new activity). Pure for unit testing.
fn should_deliver(delivered: &HashMap<u64, String>, id: u64, updated_at: &str) -> bool {
    delivered.get(&id).is_none_or(|seen| seen != updated_at)
}

/// Mark a notification thread as read. Best-effort — logs on failure but
/// does not abort the poll loop. Called only on the self-echo and
/// drop-listed paths (the agent's own writes / explicitly-suppressed
/// reasons) — delivered threads are deliberately left unread for the
/// read-before-comment guard, and a failed delivery is left unread + out
/// of the dedupe cursor so it resurfaces on the next poll tick.
async fn mark_read(client: &reqwest::Client, forge_url: &str, token: &str, id: u64) {
    let mark_url = format!("{forge_url}/api/v1/notifications/threads/{id}");
    match client
        .patch(&mark_url)
        .header("Authorization", format!("token {token}"))
        .send()
        .await
    {
        Err(e) => {
            warn!(%id, error = ?e, "forge_notify: mark-read request failed — notification will resurface");
        }
        Ok(r) if !r.status().is_success() => {
            warn!(%id, status = %r.status(), "forge_notify: mark-read returned non-2xx — notification will resurface");
        }
        Ok(_) => {
            debug!(%id, "forge_notify: marked read");
        }
    }
}

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

    #[test]
    fn should_deliver_when_thread_never_seen() {
        let delivered = HashMap::new();
        assert!(should_deliver(&delivered, 42, "2026-06-22T16:00:00Z"));
    }

    #[test]
    fn should_not_deliver_same_version_again() {
        // The dedupe case: an unread thread reappears every poll with the
        // same `updated_at` — must not re-fire a wake.
        let mut delivered = HashMap::new();
        delivered.insert(42, "2026-06-22T16:00:00Z".to_owned());
        assert!(!should_deliver(&delivered, 42, "2026-06-22T16:00:00Z"));
    }

    #[test]
    fn should_deliver_when_updated_at_advanced() {
        // A new comment bumps `updated_at` → genuinely new activity →
        // deliver again.
        let mut delivered = HashMap::new();
        delivered.insert(42, "2026-06-22T16:00:00Z".to_owned());
        assert!(should_deliver(&delivered, 42, "2026-06-22T16:05:00Z"));
    }

    #[test]
    fn should_deliver_tracks_per_thread() {
        // A cursor for one thread says nothing about another.
        let mut delivered = HashMap::new();
        delivered.insert(42, "2026-06-22T16:00:00Z".to_owned());
        assert!(should_deliver(&delivered, 99, "2026-06-22T16:00:00Z"));
    }

    #[test]
    fn escape_md_headings_escapes_top_level_atx() {
        // Argus reviews start with `## argus review`, which would
        // otherwise become an h2 inside the wrapper message.
        assert_eq!(
            escape_md_headings("## argus review\n\nlgtm."),
            "\\## argus review\n\nlgtm.",
        );
    }

    #[test]
    fn escape_md_headings_escapes_all_heading_depths() {
        let body = "# h1\n## h2\n### h3\n###### h6\nbody";
        assert_eq!(
            escape_md_headings(body),
            "\\# h1\n\\## h2\n\\### h3\n\\###### h6\nbody",
        );
    }

    #[test]
    fn escape_md_headings_preserves_indent() {
        // Indented "headings" inside lists / nested quotes keep
        // their leading whitespace so structure isn't visually
        // collapsed by the escape.
        assert_eq!(
            escape_md_headings("  ## indented\nbody"),
            "  \\## indented\nbody",
        );
    }

    #[test]
    fn escape_md_headings_passes_non_heading_lines_through() {
        let body = "plain text\nwith a #hashtag in middle\n```\n# in fenced code\n```";
        let escaped = escape_md_headings(body);
        // Lines without leading `#` are untouched. The `# in fenced
        // code` line still gets escaped (we don't track fenced-code
        // state) — acceptable: inside a fenced block the escape is
        // visually inert anyway because the renderer treats the
        // content as literal.
        assert!(escaped.contains("plain text"));
        assert!(escaped.contains("with a #hashtag in middle"));
        assert!(escaped.contains("\\# in fenced code"));
    }

    #[test]
    fn escape_md_headings_handles_empty_and_whitespace_only() {
        assert_eq!(escape_md_headings(""), "");
        assert_eq!(escape_md_headings("   "), "   ");
        assert_eq!(escape_md_headings("\n\n"), "\n\n");
    }

    #[test]
    fn escape_md_headings_skips_non_atx_hash_lines() {
        // ATX requires a space after the `#`s. Lines like `#tag`, a
        // hash-then-digits run, or `#!/bin/bash` are NOT headings —
        // escaping them would just add cosmetic noise where the
        // renderer wouldn't promote the line in the first place.
        let body = "#tag\n#123\n#!/bin/bash\n####### too many hashes\nbody"; // lint:allow: hash-digit heading test input, not a tracker tag
        let escaped = escape_md_headings(body);
        // All four leading `#` lines pass through untouched: too few
        // (still need space), seven `#`s (over the cap), shebang
        // (no space).
        assert_eq!(escaped, body);
    }

    #[test]
    fn escape_md_headings_handles_bare_hash_lines() {
        // `#` alone on a line IS a valid ATX (h1 with empty text) per
        // CommonMark; escape it to match the renderer's behaviour.
        assert_eq!(escape_md_headings("#"), "\\#");
        assert_eq!(escape_md_headings("##"), "\\##");
        assert_eq!(escape_md_headings("###"), "\\###");
    }

    #[test]
    fn escape_md_headings_preserves_trailing_newline() {
        // `split_inclusive('\n')` round-trips a body ending in a
        // newline. Important for embedded forge-notify bodies whose
        // source already terminates with `\n` — the wrapper's spacing
        // otherwise gets eaten.
        assert_eq!(escape_md_headings("## h\n"), "\\## h\n");
        assert_eq!(escape_md_headings("body\n"), "body\n");
        assert_eq!(escape_md_headings("no trailing"), "no trailing");
    }

    #[test]
    fn contains_mention_matches_at_line_start_and_mid_line() {
        assert!(contains_mention("@damocles take a look"));
        assert!(contains_mention("cc @argus please"));
        assert!(contains_mention("see (@mara) for context"));
        // Hyphens / underscores / digits are valid username chars.
        assert!(contains_mention("ping @h-m1nd-2"));
    }

    #[test]
    fn contains_mention_rejects_email_and_bare_at() {
        // Email addresses (`foo@bar.com`) and `@` followed by
        // whitespace or punctuation are not mentions — boundary check
        // requires the preceding byte to NOT be a username char.
        assert!(!contains_mention("foo@bar.com"));
        assert!(!contains_mention("send to user@example.org"));
        assert!(!contains_mention("just an @"));
        assert!(!contains_mention("@ space"));
        assert!(!contains_mention("plain text"));
        assert!(!contains_mention(""));
    }

    #[test]
    fn extract_truncated_keeps_mention_lines_outside_excerpt() {
        // Long body where the @mention sits AFTER the excerpt's cutoff
        // — the truncated extractor must surface it.
        let full = "first line\nsecond line\n@damocles tagged here\n";
        let excerpt = "first line\nsecond line\n…"; // mention not present
        let lines = extract_truncated_mention_lines(full, excerpt);
        assert_eq!(lines, vec!["@damocles tagged here"]);
    }

    #[test]
    fn extract_truncated_drops_mentions_already_in_excerpt() {
        // Mention is inside the embed window already — no need to
        // re-surface, would be noise.
        let full = "@damocles read this\nmore body\n";
        let excerpt = "@damocles read this\nmore body\n…";
        let lines = extract_truncated_mention_lines(full, excerpt);
        assert!(lines.is_empty());
    }

    #[test]
    fn extract_truncated_skips_blank_and_no_mention_lines() {
        // Only lines with an actual mention survive — random body
        // text past the cutoff stays dropped.
        let full = "first\n\nsecond paragraph\n@argus reviewer\nfinal\n";
        let excerpt = "first";
        let lines = extract_truncated_mention_lines(full, excerpt);
        assert_eq!(lines, vec!["@argus reviewer"]);
    }

    #[test]
    fn extract_truncated_does_not_resurface_heading_mention_inside_window() {
        // Regression for the truncate-before-escape ordering rule:
        // if the diff used the escaped excerpt, a body line
        // `# @argus check this` would survive as-is in the body but
        // become `\# @argus check this` in the excerpt, so the
        // `contains` check would fail and the mention would re-surface
        // as if it fell outside the window. Pass the unescaped excerpt
        // (which the caller does) and the duplicate disappears.
        let full = "# @argus check this\nmore body\n";
        let raw_excerpt = full; // fits entirely
        let lines = extract_truncated_mention_lines(full, raw_excerpt);
        assert!(
            lines.is_empty(),
            "heading+mention inside window must not be re-surfaced, got {lines:?}"
        );
    }

    #[test]
    fn render_truncated_mentions_empty_is_empty_string() {
        // Zero overhead on the healthy short-body path: caller
        // concatenates this directly so an empty input must produce
        // no spacing.
        assert_eq!(render_truncated_mentions(&[]), "");
    }

    #[test]
    fn render_truncated_mentions_formats_block() {
        let lines = ["cc @damocles", "  @argus second mention"];
        let rendered = render_truncated_mentions(&lines);
        assert_eq!(
            rendered,
            "\n\nmentions (truncated from body):\n  > cc @damocles\n  > @argus second mention",
        );
    }

    #[test]
    fn parse_rfc3339_secs_handles_offsets_and_z() {
        // Same instant expressed three ways must parse equal.
        let utc = parse_rfc3339_secs("2026-06-13T09:18:42Z").unwrap();
        let plus2 = parse_rfc3339_secs("2026-06-13T11:18:42+02:00").unwrap();
        let minus5 = parse_rfc3339_secs("2026-06-13T04:18:42-05:00").unwrap();
        assert_eq!(utc, plus2);
        assert_eq!(utc, minus5);
        // Fractional seconds are skipped (second granularity).
        assert_eq!(parse_rfc3339_secs("2026-06-13T09:18:42.512Z").unwrap(), utc);
    }

    #[test]
    fn parse_rfc3339_secs_rejects_garbage() {
        assert!(parse_rfc3339_secs("").is_none());
        assert!(parse_rfc3339_secs("not-a-date").is_none());
        assert!(parse_rfc3339_secs("2026-06-13").is_none());
    }

    #[test]
    fn notification_is_creation_flags_fresh_and_later_activity() {
        // Fresh PR: notification event time == created_at → "new".
        let fresh = serde_json::json!({ "updated_at": "2026-06-13T11:18:42+02:00" });
        let subject = serde_json::json!({ "created_at": "2026-06-13T11:18:40+02:00" });
        assert!(notification_is_creation(&fresh, Some(&subject)));

        // Review hours later on the same PR → not a creation.
        let later = serde_json::json!({ "updated_at": "2026-06-13T14:55:00+02:00" });
        assert!(!notification_is_creation(&later, Some(&subject)));

        // Missing timestamps → default to creation (preserve prior behavior).
        let empty = serde_json::json!({});
        assert!(notification_is_creation(&empty, None));
        assert!(notification_is_creation(&empty, Some(&subject)));
    }

    /// Build a `NotifMeta` for the state-change formatter tests. The `&str`
    /// fields borrow `'static` literals so the value is self-contained.
    fn state_change_meta(subject: serde_json::Value) -> NotifMeta<'static> {
        NotifMeta {
            title: "subject title",
            notif_type: "Issue",
            html_url: "http://forge/issues/1",
            num: " #1".to_owned(),
            repo: " [agents/x]".to_owned(),
            meta_suffix: "\nassignee: unassigned".to_owned(),
            subject: Some(subject),
            is_pr: false,
        }
    }

    #[test]
    fn state_change_drops_self_authored_creation() {
        // No timestamps ⇒ treated as a creation; poster login == own_login.
        let meta = state_change_meta(serde_json::json!({ "user": { "login": "damocles" } }));
        let notif = serde_json::json!({ "subject": { "state": "open" } });
        assert!(format_state_change_notification(&notif, &meta, "damocles").is_none());
    }

    #[test]
    fn state_change_keeps_other_authored_creation() {
        let meta = state_change_meta(serde_json::json!({ "user": { "login": "someone-else" } }));
        let notif = serde_json::json!({ "subject": { "state": "open" } });
        assert!(format_state_change_notification(&notif, &meta, "damocles").is_some());
    }

    #[test]
    fn state_change_keeps_self_authored_later_activity() {
        // The agent authored the subject, but this notification fired well
        // after creation (someone else acted on it) ⇒ not a creation ⇒ still
        // surfaces.
        let meta = state_change_meta(serde_json::json!({
            "user": { "login": "damocles" },
            "created_at": "2020-01-01T00:00:00Z",
        }));
        let notif = serde_json::json!({
            "subject": { "state": "closed" },
            "updated_at": "2026-06-22T16:00:00Z",
        });
        assert!(format_state_change_notification(&notif, &meta, "damocles").is_some());
    }
}