//! Task-card parser — Slice 5.
//!
//! Watches `run_events` payloads for the INT-XX marker protocol
//! (see skills/foundation/int-xx-marker-protocol.md) and materializes
//! `mission_tasks` rows with typed state so the mission canvas Tasks
//! tab can render a status timeline.
//!
//! Recognized markers (case-sensitive, on their own line):
//!   TASK: INT-NN — <title>       → status='created'
//!   WORK: INT-NN                 → status='working'
//!   HANDOFF: INT-NN              → status='validating'
//!   TEST_PASS: INT-NN            → status='validating' (unchanged if already validating+)
//!   TEST_FAIL: INT-NN — <reason> → status='failed'
//!   REVIEW_APPROVE: INT-NN       → status='validating'
//!   REVIEW_BLOCK: INT-NN — <reason> → status='failed'
//!   COMPLETED: INT-NN            → status='complete'
//!
//! Uses UPSERT keyed on (phase_id, external_id) so the same INT
//! progressing through states updates a single row; state transitions
//! are monotonic where reasonable (once complete, only failed can
//! demote — but the loop-once semantics of INT items mean this rarely
//! matters in practice).

use serde_json::Value;
use sqlx::PgPool;
use sqlx::Row;
use uuid::Uuid;

use cm_db::repo::missions::UpsertTask;

/// A parsed marker from a single run-event payload.
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct Marker {
    pub int_id: String, // "INT-05"
    pub kind: MarkerKind,
    pub title: Option<String>,
}

#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum MarkerKind {
    Task,
    PlanComplete,
    Work,
    Handoff,
    TestPass,
    TestFail,
    ReviewApprove,
    ReviewBlock,
    Completed,
}

impl MarkerKind {
    /// The status this marker implies. Preferences monotonic forward
    /// motion — the UPSERT layer may still overwrite prior states.
    pub fn status(&self) -> &'static str {
        match self {
            // The planner finished specifying; no work has started, so the item
            // is in the same state a fresh TASK leaves it in. A distinct status
            // would need a column value the UI does not render, and inventing
            // one to look complete is how a status stops meaning anything.
            MarkerKind::Task | MarkerKind::PlanComplete => "created",
            MarkerKind::Work => "working",
            MarkerKind::Handoff | MarkerKind::TestPass | MarkerKind::ReviewApprove => "validating",
            MarkerKind::TestFail | MarkerKind::ReviewBlock => "failed",
            MarkerKind::Completed => "complete",
        }
    }
}

/// Line-scanner over the raw text of a run's output. Cheap enough to
/// re-run per event; the UPSERT layer collapses duplicates.
pub fn parse(text: &str) -> Vec<Marker> {
    let mut out = Vec::new();
    for line in text.lines() {
        let trimmed = line.trim();
        if let Some(m) = parse_line(trimmed) {
            out.push(m);
        }
    }
    out
}

/// `INT-` followed by at least one digit and nothing else.
fn is_int_id(id: &str) -> bool {
    match id.strip_prefix("INT-") {
        Some(rest) => !rest.is_empty() && rest.chars().all(|c| c.is_ascii_digit()),
        None => false,
    }
}

fn parse_line(line: &str) -> Option<Marker> {
    // Match `<KIND>: INT-NN` (rest optional). Strict on the colon and
    // the INT- prefix — anything laxer starts matching prose.
    let (kind_str, rest) = line.split_once(':')?;
    let kind = match kind_str.trim() {
        "TASK" => MarkerKind::Task,
        // Documented in `skills/foundation/int-xx-marker-protocol.md` since the
        // skill was written, and never implemented here. Agents that followed
        // the skill exactly emitted it and were silently ignored — observed on
        // a live mission, found by the Skill-Use measurement. Implemented
        // rather than removed from the skill: the planner needs a way to say
        // it is done specifying, and agents already emit this one.
        "PLAN_COMPLETE" => MarkerKind::PlanComplete,
        "WORK" => MarkerKind::Work,
        "HANDOFF" => MarkerKind::Handoff,
        "TEST_PASS" => MarkerKind::TestPass,
        "TEST_FAIL" => MarkerKind::TestFail,
        "REVIEW_APPROVE" => MarkerKind::ReviewApprove,
        "REVIEW_BLOCK" => MarkerKind::ReviewBlock,
        "COMPLETED" => MarkerKind::Completed,
        _ => return None,
    };
    let rest = rest.trim();
    let (id_tok, tail) = match rest.split_once(char::is_whitespace) {
        Some((a, b)) => (a, Some(b.trim())),
        None => (rest, None),
    };
    let int_id = id_tok.trim_end_matches(&[',', ';', '.'][..]).to_string();
    // Strictly `INT-<digits>`. `starts_with("INT-")` alone accepted range forms
    // like `INT-01..02`, which parse into an id matching no real item — so a
    // task card appeared for something that did not exist while the two items
    // it was meant to cover stayed open. Observed live. Rejecting is right:
    // the marker is ignored, which is visible, instead of creating a plausible
    // row, which is not.
    if !is_int_id(&int_id) {
        return None;
    }
    // Title: after the id + any of ` — / – / - ` separators
    let title = tail.and_then(|t| {
        let t = t.trim_start_matches(['—', '–', '-', ':'].as_slice()).trim();
        if t.is_empty() {
            None
        } else {
            Some(t.to_string())
        }
    });
    Some(Marker {
        int_id,
        kind,
        title,
    })
}

/// Scan every event of a topology_run that has a mission_id set;
/// parse markers out of the event payload's `text` / `output` fields;
/// UPSERT each into `mission_tasks`.
///
/// Idempotent: re-running against the same run's events collapses
/// into the current-truth state (last marker per INT wins per pass).
pub async fn apply_for_run(pool: &PgPool, run_id: Uuid) -> Result<usize, String> {
    // Load the run + its mission binding. Bail cheaply if no mission.
    let run = sqlx::query(
        "SELECT mission_id, mission_phase_id
         FROM topology_runs WHERE id = $1",
    )
    .bind(run_id)
    .fetch_optional(pool)
    .await
    .map_err(|e| format!("load run: {e}"))?;
    let Some(run) = run else {
        return Ok(0);
    };
    let mission_id: Option<Uuid> = run.try_get("mission_id").ok().flatten();
    let phase_id: Option<Uuid> = run.try_get("mission_phase_id").ok().flatten();
    let (Some(mission_id), Some(phase_id)) = (mission_id, phase_id) else {
        return Ok(0);
    };

    // Read event payloads in order.
    let rows = sqlx::query(
        "SELECT payload
         FROM run_events WHERE run_id = $1
         ORDER BY seq ASC",
    )
    .bind(run_id)
    .fetch_all(pool)
    .await
    .map_err(|e| format!("load events: {e}"))?;

    let mut all_markers: Vec<Marker> = Vec::new();
    for r in rows {
        let payload: Value = r.get("payload");
        for text in extract_text_fields(&payload) {
            all_markers.extend(parse(&text));
        }
    }

    let mut applied = 0usize;
    for m in &all_markers {
        let title = m.title.clone().unwrap_or_else(|| m.int_id.clone());
        cm_db::repo::missions::upsert_task(
            pool,
            UpsertTask {
                mission_id,
                phase_id,
                external_id: &m.int_id,
                title: &title,
                assigned_agent_id: None,
                status: m.kind.status(),
                run_id: Some(run_id),
            },
        )
        .await
        .map_err(|e| format!("upsert_task {}: {e}", m.int_id))?;
        applied += 1;
    }
    Ok(applied)
}

/// Walk a payload's JSON tree and yield every string field named
/// `text`, `output`, `content`, or `message`. Handles the shapes we
/// see across ZeroClaw events (chunk / tool_result / done / final).
fn extract_text_fields(v: &Value) -> Vec<String> {
    fn walk(v: &Value, out: &mut Vec<String>) {
        match v {
            Value::Object(map) => {
                for (k, child) in map {
                    if matches!(k.as_str(), "text" | "output" | "content" | "message") {
                        if let Value::String(s) = child {
                            out.push(s.clone());
                        }
                    }
                    walk(child, out);
                }
            }
            Value::Array(items) => {
                for item in items {
                    walk(item, out);
                }
            }
            _ => {}
        }
    }
    let mut out = Vec::new();
    walk(v, &mut out);
    out
}

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

    #[test]
    fn parses_completed_marker() {
        let out = parse("COMPLETED: INT-05");
        assert_eq!(out.len(), 1);
        assert_eq!(out[0].int_id, "INT-05");
        assert_eq!(out[0].kind, MarkerKind::Completed);
    }

    #[test]
    fn parses_task_with_title() {
        let out = parse("TASK: INT-12 — wire the loader");
        assert_eq!(out[0].kind, MarkerKind::Task);
        assert_eq!(out[0].title.as_deref(), Some("wire the loader"));
    }

    #[test]
    fn parses_test_fail_with_reason() {
        let out = parse("TEST_FAIL: INT-03 — flake in async_setup");
        assert_eq!(out[0].kind, MarkerKind::TestFail);
        assert_eq!(out[0].title.as_deref(), Some("flake in async_setup"));
    }

    #[test]
    fn ignores_marker_inside_prose() {
        // Not on its own line + not starting with the exact kind:
        let out = parse("we should not TASK: INT-05 like this");
        assert!(out.is_empty());
    }

    #[test]
    fn scans_multiline_batch() {
        let src = "TASK: INT-01 — foo\nWORK: INT-01\nother text\nCOMPLETED: INT-01\n";
        let out = parse(src);
        assert_eq!(out.len(), 3);
        assert_eq!(out[2].kind, MarkerKind::Completed);
    }
}