clawmates/crates/cm-api/tests/mission_orchestrator.rs

//! End-to-end coverage for `mission_orchestrator::on_launch` — the
//! draft→running transition that materializes a team from a template,
//! inserts agents, seeds brains, records template lineage, and binds
//! members via team_members. Runs against a real Postgres (cm-testkit).
//!
//! What this test locks in:
//!   * Given a mission with `team_template_id` and no `team_id`,
//!     `on_launch` materializes exactly one team per role in the
//!     template.
//!   * The materialized team carries `template_id` + `template_version`
//!     + `risk_profile` + `mcp_bundles` from the template row.
//!   * Every role produces one `agents` row + one
//!     `agent_template_link` row (seeded=true).
//!   * `team_members` binds every claw to a topology node id.
//!   * The mission row's `team_id` gets updated.
//!   * Re-invoking is a no-op (returns the existing team_id, doesn't
//!     duplicate agents).

use cm_api::mission_orchestrator;
use cm_db::repo::{team_templates, users, workspaces};
use cm_domain::{Role, User, UserId, Workspace, WorkspaceId};
use serde_json::json;
use sqlx::Row;
use uuid::Uuid;

async fn seed_workspace(pool: &sqlx::PgPool) -> WorkspaceId {
    let ws = Workspace {
        id: WorkspaceId::new(),
        name: "Missions Test".into(),
        plan: "team".into(),
    };
    workspaces::insert(pool, &ws).await.unwrap();
    ws.id
}

async fn seed_owner(pool: &sqlx::PgPool, ws: WorkspaceId) -> UserId {
    let user = User {
        id: UserId::new(),
        workspace_id: ws,
        email: "[email protected]".into(),
        role: Role::Owner,
        display_name: "Owner".into(),
        created_at: time::OffsetDateTime::UNIX_EPOCH,
    };
    users::insert(pool, &user).await.unwrap();
    user.id
}

async fn seed_test_template(pool: &sqlx::PgPool) -> Uuid {
    let id = Uuid::now_v7();
    team_templates::upsert_builtin(
        pool,
        team_templates::UpsertBuiltin {
            id,
            key: "test_backend",
            name: "Test Backend Team",
            stack: vec!["rust".into(), "postgres".into()],
            default_topology: "pipeline",
            risk_profile: "medium",
            mcp_bundles: vec!["clawmates_skills".into()],
            version: 1,
            description: Some("Fixture template for orchestrator test"),
            config: json!({}),
            category: "development",
            roles: vec![
                team_templates::UpsertBuiltinRole {
                    slot: "planner",
                    order_idx: 0,
                    system_prompt: "Plan the feature. Break it into INT-XX items.",
                    skills: vec!["decompose-int-items".into()],
                    brain_seed: Some("# Planner\nBreak features into INT items."),
                    model: None,
                },
                team_templates::UpsertBuiltinRole {
                    slot: "coder",
                    order_idx: 1,
                    system_prompt: "Implement one INT item at a time.",
                    skills: vec!["write-rust-current-edition".into()],
                    brain_seed: Some("# Coder\nOne INT per commit."),
                    model: None,
                },
                team_templates::UpsertBuiltinRole {
                    slot: "reviewer",
                    order_idx: 2,
                    system_prompt: "Review each commit before merge.",
                    skills: vec!["code-review-checklist".into()],
                    brain_seed: None,
                    // The point of migration 0071: a reviewer that does NOT
                    // share a model with the coder it reviews.
                    model: Some("glm-4.7"),
                },
            ],
        },
    )
    .await
    .unwrap();
    id
}

async fn seed_mission(
    pool: &sqlx::PgPool,
    ws: WorkspaceId,
    template_id: Uuid,
    title: &str,
) -> Uuid {
    let id = Uuid::now_v7();
    sqlx::query(
        "INSERT INTO missions
           (id, workspace_id, title, template_kind, team_template_id, schedule, status, config)
         VALUES ($1, $2, $3, 'research_and_code', $4, '{\"kind\":\"one_shot\"}'::jsonb,
                 'draft', '{}'::jsonb)",
    )
    .bind(id)
    .bind(ws.as_uuid())
    .bind(title)
    .bind(template_id)
    .execute(pool)
    .await
    .unwrap();
    id
}

#[tokio::test]
async fn on_launch_materializes_team_from_template() {
    let pool = cm_testkit::test_pool().await;
    let ws = seed_workspace(&pool).await;
    let owner = seed_owner(&pool, ws).await;
    let template_id = seed_test_template(&pool).await;
    let mission_id = seed_mission(&pool, ws, template_id, "Test Mission").await;

    let team_id = mission_orchestrator::on_launch(&pool, ws, owner, mission_id, None)
        .await
        .expect("on_launch succeeds")
        .expect("returns a team id");

    // Team row exists with template lineage stamped.
    let team_row = sqlx::query(
        "SELECT template_id, template_version, risk_profile, mcp_bundles
         FROM teams WHERE id = $1",
    )
    .bind(team_id)
    .fetch_one(&pool)
    .await
    .unwrap();
    let stamped_template_id: Uuid = team_row.get("template_id");
    let stamped_version: i32 = team_row.get("template_version");
    let stamped_risk: String = team_row.get("risk_profile");
    assert_eq!(stamped_template_id, template_id);
    assert_eq!(stamped_version, 1);
    assert_eq!(stamped_risk, "medium");

    // One agent per role — three total.
    let agent_count: i64 =
        sqlx::query_scalar("SELECT count(*)::bigint FROM team_members WHERE team_id = $1")
            .bind(team_id)
            .fetch_one(&pool)
            .await
            .unwrap();
    assert_eq!(agent_count, 3, "expected one member per role");

    // Every member has a matching agents row + role_slot binding.
    let member_slots: Vec<String> = sqlx::query_scalar(
        "SELECT tm.role FROM team_members tm
         JOIN agents a ON a.id = tm.claw_id
         WHERE tm.team_id = $1
         ORDER BY tm.role",
    )
    .bind(team_id)
    .fetch_all(&pool)
    .await
    .unwrap();
    assert_eq!(member_slots, vec!["coder", "planner", "reviewer"]);

    // Every claw has an agent_template_link row with seeded=true.
    let seeded_count: i64 = sqlx::query_scalar(
        "SELECT count(*)::bigint FROM agent_template_link atl
         JOIN team_members tm ON tm.claw_id = atl.agent_id
         WHERE tm.team_id = $1
           AND atl.template_id = $2",
    )
    .bind(team_id)
    .bind(template_id)
    .fetch_one(&pool)
    .await
    .unwrap();
    assert_eq!(
        seeded_count, 3,
        "expected every claw to have seeded lineage"
    );

    // Mission row was updated to point at the new team.
    let bound_team_id: Uuid = sqlx::query_scalar("SELECT team_id FROM missions WHERE id = $1")
        .bind(mission_id)
        .fetch_one(&pool)
        .await
        .unwrap();
    assert_eq!(bound_team_id, team_id);
}

#[tokio::test]
async fn on_launch_is_idempotent() {
    let pool = cm_testkit::test_pool().await;
    let ws = seed_workspace(&pool).await;
    let owner = seed_owner(&pool, ws).await;
    let template_id = seed_test_template(&pool).await;
    let mission_id = seed_mission(&pool, ws, template_id, "Idempotency Mission").await;

    let team_a = mission_orchestrator::on_launch(&pool, ws, owner, mission_id, None)
        .await
        .unwrap()
        .unwrap();
    let team_b = mission_orchestrator::on_launch(&pool, ws, owner, mission_id, None)
        .await
        .unwrap()
        .unwrap();
    assert_eq!(
        team_a, team_b,
        "second invocation should return the same team_id"
    );

    // Still exactly three agents — no duplication.
    let agent_count: i64 =
        sqlx::query_scalar("SELECT count(*)::bigint FROM team_members WHERE team_id = $1")
            .bind(team_a)
            .fetch_one(&pool)
            .await
            .unwrap();
    assert_eq!(agent_count, 3);
}

#[tokio::test]
async fn on_launch_no_template_hard_fails() {
    let pool = cm_testkit::test_pool().await;
    let ws = seed_workspace(&pool).await;
    let owner = seed_owner(&pool, ws).await;

    // Mission with no team_template_id.
    let mission_id = Uuid::now_v7();
    sqlx::query(
        "INSERT INTO missions
           (id, workspace_id, title, template_kind, schedule, status, config)
         VALUES ($1, $2, 'no template', 'refactor', '{\"kind\":\"one_shot\"}'::jsonb,
                 'draft', '{}'::jsonb)",
    )
    .bind(mission_id)
    .bind(ws.as_uuid())
    .execute(&pool)
    .await
    .unwrap();

    let result = mission_orchestrator::on_launch(&pool, ws, owner, mission_id, None).await;
    let err = result.expect_err("no template + no team must be a hard error");
    assert!(
        err.contains("no team_template_id") && err.contains("config.phase_teams"),
        "unexpected error message: {err}"
    );

    // Mission stays with team_id NULL — no partial materialization.
    let team_id: Option<Uuid> = sqlx::query_scalar("SELECT team_id FROM missions WHERE id = $1")
        .bind(mission_id)
        .fetch_one(&pool)
        .await
        .unwrap();
    assert!(team_id.is_none());
}

/// Slice 5: an APPROVED roster outranks the team template.
///
/// The template gives every composed mission the same five roles on the same
/// image. A roster is the model's answer for THIS mission, and it is the only
/// path that carries a per-node backend — which is how a mission runs more than
/// one provider at all. If the template won, a heterogeneous roster would be
/// accepted, stored, and then silently ignored at launch.
#[tokio::test]
async fn an_approved_roster_outranks_the_template() {
    let pool = cm_testkit::test_pool().await;
    let ws = seed_workspace(&pool).await;
    let template_id = seed_test_template(&pool).await;
    let mission = seed_mission(&pool, ws, template_id, "roster beats template").await;

    // With no roster, the shape comes from the template — the behaviour every
    // composed mission had before this slice.
    let from_template = mission_orchestrator::composed_graph(&pool, mission, &["mission"])
        .await
        .expect("template graph")
        .expect("the template supplies a shape");
    let template_nodes = from_template["nodes"].as_array().unwrap().len();
    assert!(template_nodes >= 1);
    assert!(
        from_template["nodes"][0]["attrs"].get("backend").is_none(),
        "a template cannot express a per-node backend — that is the gap the roster fills"
    );

    // Approve a roster the way the route does: the built graph under
    // `config.roster`.
    let roster = cm_api::mission_roster::Roster {
        topology_kind: "pipeline".into(),
        members: vec![
            cm_api::mission_roster::RosterMember {
                role: "implementer".into(),
                backend: Some("claude".into()),
                rationale: None,
            },
            cm_api::mission_roster::RosterMember {
                role: "verifier".into(),
                backend: Some("kimi".into()),
                rationale: None,
            },
        ],
    };
    let graph = roster.graph().expect("a runnable graph");
    sqlx::query(
        "UPDATE missions SET config = jsonb_set(config, '{roster}', $2::jsonb, true) WHERE id = $1",
    )
    .bind(mission)
    .bind(&graph)
    .execute(&pool)
    .await
    .unwrap();

    let chosen = mission_orchestrator::composed_graph(&pool, mission, &["mission"])
        .await
        .expect("roster graph")
        .expect("the roster supplies a shape");
    let nodes = chosen["nodes"].as_array().unwrap();
    assert_eq!(nodes.len(), 2, "the roster's two nodes, not the template's");
    assert_eq!(nodes[0]["role"], "implementer");
    assert_eq!(nodes[0]["attrs"]["backend"], "claude");
    assert_eq!(nodes[1]["attrs"]["backend"], "kimi");
}

/// Migration 0071: a template role may name its own model, and the claw minted
/// for it must actually run on that model.
///
/// Before this, `mint_team_from_template` bound EVERY role to one literal — so a
/// template whose whole point is an independent reviewer minted a reviewer
/// sharing a model with the coder it reviews. That is the correlated failure the
/// cross-provider judge exists to break, reintroduced one layer down.
#[tokio::test]
async fn a_template_role_may_run_on_its_own_model() {
    let pool = cm_testkit::test_pool().await;
    let ws = seed_workspace(&pool).await;
    let user = seed_owner(&pool, ws).await;
    let template_id = seed_test_template(&pool).await;
    let mission = seed_mission(&pool, ws, template_id, "per-role models").await;

    mission_orchestrator::on_launch(&pool, ws, user, mission, None)
        .await
        .expect("launch");

    let rows: Vec<(String, Option<String>)> = sqlx::query_as(
        "SELECT job_title, model_binding FROM agents
          WHERE workspace_id = $1 AND deleted_at IS NULL
          ORDER BY job_title",
    )
    .bind(ws.as_uuid())
    .fetch_all(&pool)
    .await
    .unwrap();
    let by_role: std::collections::HashMap<_, _> = rows.into_iter().collect();

    assert_eq!(
        by_role.get("reviewer").and_then(|m| m.clone()).as_deref(),
        Some("glm-4.7"),
        "the reviewer must run the model its role names: {by_role:?}"
    );
    // And a role that names none still gets the mint's default, so every
    // template written before 0071 behaves exactly as it did.
    for silent in ["planner", "coder"] {
        assert_eq!(
            by_role.get(silent).and_then(|m| m.clone()).as_deref(),
            Some("claude-sonnet-5"),
            "{silent} named no model and must take the default"
        );
    }
}