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

//! Do a mission agent's pinned skills actually reach its prompt?
//!
//! Before this test the honest answer was no, for every skill and every role.
//! The catalogue's only delivery channel was the `clawmates_skills` MCP server,
//! and a mission claw could not reach it: `provision_claw` wrote a constant
//! bundle list, the runtime config defines no such bundle, and mission claws
//! run on `claude_cli`, which is text-only and cannot surface a tool call.
//!
//! So the skills were authored, bound, listed in the boot log as bound — and
//! structurally unreadable. That is why this is a test and not a comment: the
//! failure produced no error anywhere, and every layer reported success.

use cm_api::skill_delivery::Mode;
use cm_api::topology_exec::{MissionTap, ZeroClawDriveExecutor};
use cm_domain::{Agent, AgentId, AgentStatus, Role, User, UserId, Workspace, WorkspaceId};

/// `agents.managed_by` is a real FK, so the owner has to exist.
async fn seed_user(pool: &sqlx::PgPool, ws: WorkspaceId) -> UserId {
    let user = User {
        id: UserId::new(),
        workspace_id: ws,
        email: format!("owner-{}@example.com", Uuid::now_v7().simple()),
        role: Role::Owner,
        display_name: "Owner".into(),
        created_at: time::OffsetDateTime::UNIX_EPOCH,
    };
    cm_db::repo::users::insert(pool, &user).await.unwrap();
    user.id
}
use std::collections::HashMap;
use uuid::Uuid;

/// A claw with one template-bound, pinned skill. Returns its runtime alias.
async fn seed_claw_with_pinned_skill(pool: &sqlx::PgPool, body: &str) -> (String, WorkspaceId) {
    let ws = Workspace {
        id: WorkspaceId::new(),
        name: "Skill Delivery Test".into(),
        plan: "team".into(),
    };
    cm_db::repo::workspaces::insert(pool, &ws).await.unwrap();

    let user = seed_user(pool, ws.id).await;
    let agent = Agent {
        id: AgentId::new(),
        workspace_id: ws.id,
        name: "Scout".into(),
        job_title: "researcher".into(),
        system_prompt: String::new(),
        avatar: String::new(),
        accent: String::new(),
        wallpaper: String::new(),
        managed_by: user,
        status: AgentStatus::Online,
    };
    cm_db::repo::agents::insert(pool, &agent, &cm_domain::AccessPolicy::default())
        .await
        .unwrap();

    // A template with one role, and a skill pinned to it.
    let template_id = Uuid::now_v7();
    sqlx::query(
        "INSERT INTO team_templates (id, key, name, description, category, stack,
                                     default_topology, risk_profile, mcp_bundles, version)
         VALUES ($1, $2, 'Delivery Test', 'test', 'research', '{}',
                 'pipeline', 'research_readonly', '{}', 1)",
    )
    .bind(template_id)
    .bind(format!("delivery_test_{}", template_id.simple()))
    .execute(pool)
    .await
    .unwrap();

    sqlx::query(
        "INSERT INTO template_roles (template_id, slot, order_idx, system_prompt)
         VALUES ($1, 'researcher', 0, 'you research')",
    )
    .bind(template_id)
    .execute(pool)
    .await
    .unwrap();

    let skill_id = Uuid::now_v7();
    sqlx::query(
        "INSERT INTO skills
           (id, workspace_id, name, title, author, description, when_to_use,
            tags, source_kind, current_version, body)
         VALUES ($1, NULL, $2, $2, 'system',
                 'a procedure the agent must follow', 'always', '{}',
                 'builtin', 1, $3)",
    )
    .bind(skill_id)
    .bind(format!("delivery-test-skill-{}", skill_id.simple()))
    .bind(body)
    .execute(pool)
    .await
    .unwrap();

    sqlx::query(
        "INSERT INTO template_role_skills (template_id, slot, skill_id, pin_in_context, order_idx)
         VALUES ($1, 'researcher', $2, true, 0)",
    )
    .bind(template_id)
    .bind(skill_id)
    .execute(pool)
    .await
    .unwrap();

    cm_db::repo::agent_template_link::upsert(
        pool,
        agent.id.as_uuid(),
        template_id,
        1,
        "researcher",
    )
    .await
    .unwrap();

    (
        cm_api::runtime_provision::claw_alias(agent.id.as_uuid()),
        ws.id,
    )
}

fn executor(pool: &sqlx::PgPool, workspace_id: WorkspaceId) -> ZeroClawDriveExecutor {
    executor_for(pool, workspace_id, Uuid::now_v7())
}

fn executor_for(
    pool: &sqlx::PgPool,
    workspace_id: WorkspaceId,
    mission_id: Uuid,
) -> ZeroClawDriveExecutor {
    ZeroClawDriveExecutor::new(
        "http://127.0.0.1:1".into(),
        "unused".into(),
        HashMap::new(),
        "default".into(),
    )
    .with_tap(MissionTap {
        pool: pool.clone(),
        workspace_id: workspace_id.as_uuid(),
        mission_id,
        phase_id: None,
        run_id: None,
    })
}

/// A mission row carrying an explicit delivery arm.
async fn seed_mission_on_arm(pool: &sqlx::PgPool, ws: WorkspaceId, arm: Option<&str>) -> Uuid {
    let mission = Uuid::now_v7();
    sqlx::query(
        "INSERT INTO missions (id, workspace_id, title, template_kind, status, skill_delivery)
         VALUES ($1, $2, 'arm', 'research_only', 'running', $3)",
    )
    .bind(mission)
    .bind(ws.as_uuid())
    .bind(arm)
    .execute(pool)
    .await
    .unwrap();
    mission
}

// ── The index arm ───────────────────────────────────────────────────
//
// Trigger — did the agent reach for the skill? — cannot exist while every body
// is handed over unasked. These tests cover the arm that makes it a question,
// and the one guarantee the control arm needs: that it did not change.

#[tokio::test]
async fn the_index_arm_sends_the_uri_and_withholds_the_body() {
    let pool = cm_testkit::test_pool().await;
    const MARKER: &str = "Never review a paper from its title alone.";
    let (alias, ws) = seed_claw_with_pinned_skill(&pool, MARKER).await;
    let mission = seed_mission_on_arm(&pool, ws, Some("index")).await;

    let text = executor_for(&pool, ws, mission)
        .pinned_skills_text(&alias)
        .await
        .expect("an indexed skill is still delivered — as an entry, not a body");

    assert!(
        !text.contains(MARKER),
        "the BODY is what the index withholds; leaving it in delivers both \
         arms at once and measures neither. Got:\n{text}"
    );
    assert!(
        text.contains("uri=\"skill:global/delivery-test-skill-"),
        "an entry without a fetchable uri names a procedure the agent cannot \
         obtain — worse than inlining it. Got:\n{text}"
    );
    assert!(
        text.contains("When to use: always"),
        "`when_to_use` is the only thing the agent can judge relevance from, \
         and judging relevance is the entire axis. Got:\n{text}"
    );
    // The scorer counts delivered skills by the marker, in both arms.
    assert_eq!(
        cm_api::topology_exec::skill_names_in(&text).len(),
        1,
        "an indexed skill must still count as delivered:\n{text}"
    );
}

#[tokio::test]
async fn an_unrecorded_arm_delivers_bodies() {
    let pool = cm_testkit::test_pool().await;
    const MARKER: &str = "Never review a paper from its title alone.";
    let (alias, ws) = seed_claw_with_pinned_skill(&pool, MARKER).await;

    // Every mission that ran before the column existed, plus any row whose
    // value is unreadable, plus a turn with no mission row at all. All three
    // resolve to the arm that needs nothing installed to work.
    for arm in [None, Some("nonsense")] {
        let mission = seed_mission_on_arm(&pool, ws, arm).await;
        let text = executor_for(&pool, ws, mission)
            .pinned_skills_text(&alias)
            .await
            .unwrap();
        assert!(
            text.contains(MARKER),
            "skill_delivery={arm:?} must deliver the body — an index arm \
             selected by accident hands out uris behind a door that may not \
             be installed. Got:\n{text}"
        );
    }
}

#[tokio::test]
async fn a_pinned_skill_body_reaches_the_turn_prompt() {
    let pool = cm_testkit::test_pool().await;
    const MARKER: &str = "Never review a paper from its title alone.";
    let (alias, ws) = seed_claw_with_pinned_skill(&pool, MARKER).await;

    let text = executor(&pool, ws)
        .pinned_skills_text(&alias)
        .await
        .expect("a claw with a pinned template skill must produce skill text");

    assert!(
        text.contains(MARKER),
        "the default arm delivers the BODY. It is the control in the delivery \
         A/B, so it has to stay what production has always sent; the index arm \
         is selected per mission and tested separately. Got:\n{text}"
    );
}

#[tokio::test]
async fn an_agent_with_no_pinned_skills_adds_nothing() {
    let pool = cm_testkit::test_pool().await;
    let ws = Workspace {
        id: WorkspaceId::new(),
        name: "No Skills".into(),
        plan: "team".into(),
    };
    cm_db::repo::workspaces::insert(&pool, &ws).await.unwrap();
    let user = seed_user(&pool, ws.id).await;
    let agent = Agent {
        id: AgentId::new(),
        workspace_id: ws.id,
        name: "Bare".into(),
        job_title: "researcher".into(),
        system_prompt: String::new(),
        avatar: String::new(),
        accent: String::new(),
        wallpaper: String::new(),
        managed_by: user,
        status: AgentStatus::Online,
    };
    cm_db::repo::agents::insert(&pool, &agent, &cm_domain::AccessPolicy::default())
        .await
        .unwrap();

    let alias = cm_api::runtime_provision::claw_alias(agent.id.as_uuid());
    assert!(
        executor(&pool, ws.id)
            .pinned_skills_text(&alias)
            .await
            .is_none(),
        "an agent with no bound skills must add no section at all — an empty \
         `# Your skills` heading tells the model it has skills and then shows \
         it none"
    );
}

#[test]
fn the_composed_prompt_carries_the_skill_and_omits_the_heading_when_empty() {
    let base = "You are the \"researcher\" agent.\n\nTask: read the papers";

    let with = cm_api::topology_exec::compose_turn_prompt(base, Some("## arxiv-daily\nDo not re-search."), Mode::Inline);
    assert!(with.contains("Task: read the papers"), "the base turn must survive");
    assert!(with.contains("Do not re-search."), "the skill body must be in the prompt");
    assert!(with.contains("# Your skills"), "the section needs a heading");

    for empty in [None, Some(""), Some("   \n ")] {
        let without = cm_api::topology_exec::compose_turn_prompt(base, empty, Mode::Inline);
        assert_eq!(
            without, base,
            "with no skills the prompt must be byte-identical to the base — an \
             empty heading announces skills the agent does not have"
        );
    }
}

// ── The other three tiers ───────────────────────────────────────────
//
// `topology_exec` injects per TURN and covers only the container tier. The
// composed-microVM, solo-microVM and direct-session paths in `phase_runner`
// share one task string built by `phase_task_text`, and until now that string
// carried no skill at all — so a mission on any of those tiers ran with the
// catalogue unreachable, exactly as the container tier did before e4942ce.

/// Bind a claw to a mission's crew so `phase_skills_text` can find it.
async fn seed_mission_with_crew(pool: &sqlx::PgPool, ws: WorkspaceId, agent: AgentId) -> Uuid {
    let mission = Uuid::now_v7();
    sqlx::query(
        "INSERT INTO missions (id, workspace_id, title, template_kind, status)
         VALUES ($1, $2, 'skill delivery', 'research_only', 'running')",
    )
    .bind(mission)
    .bind(ws.as_uuid())
    .execute(pool)
    .await
    .unwrap();

    let team = Uuid::now_v7();
    sqlx::query(
        "INSERT INTO teams (id, workspace_id, name, kind, lifecycle, graph)
         VALUES ($1, $2, 'crew', 'pipeline', 'permanent', '{}'::jsonb)",
    )
    .bind(team)
    .bind(ws.as_uuid())
    .execute(pool)
    .await
    .unwrap();
    sqlx::query("INSERT INTO team_members (team_id, claw_id, node_id, role) VALUES ($1, $2, 'researcher', 'researcher')")
        .bind(team)
        .bind(agent.as_uuid())
        .execute(pool)
        .await
        .unwrap();
    sqlx::query("INSERT INTO mission_teams (mission_id, team_id, purpose) VALUES ($1, $2, 'mission')")
        .bind(mission)
        .bind(team)
        .execute(pool)
        .await
        .unwrap();
    mission
}

#[tokio::test]
async fn the_microvm_and_session_tiers_get_the_skill_in_their_task_text() {
    let pool = cm_testkit::test_pool().await;
    const MARKER: &str = "Never review a paper from its title alone.";
    let (alias, ws) = seed_claw_with_pinned_skill(&pool, MARKER).await;
    let agent = AgentId::from(cm_api::runtime_provision::claw_from_alias(&alias).unwrap());
    let mission = seed_mission_with_crew(&pool, ws, agent).await;

    let skills = cm_api::phase_runner::phase_skills_text(&pool, mission)
        .await
        .expect("a mission whose crew holds a pinned skill must produce skill text");
    assert!(
        skills.contains(MARKER),
        "the pinned BODY must reach the phase task — these tiers run one \
         `claude -p` session with no per-turn injection, so this string is the \
         agent's only route to the procedure. Got:\n{skills}"
    );

    // All three tiers share this composition, so testing it once covers them.
    let composed = cm_api::topology_exec::compose_turn_prompt("Task: read the papers", Some(&skills), Mode::Inline);
    assert!(composed.contains(MARKER));
    assert!(composed.contains("Task: read the papers"));
}

#[tokio::test]
async fn a_mission_whose_crew_has_no_skills_adds_nothing() {
    let pool = cm_testkit::test_pool().await;
    let ws = Workspace {
        id: WorkspaceId::new(),
        name: "Bare Crew".into(),
        plan: "team".into(),
    };
    cm_db::repo::workspaces::insert(&pool, &ws).await.unwrap();
    let user = seed_user(&pool, ws.id).await;
    let agent = Agent {
        id: AgentId::new(),
        workspace_id: ws.id,
        name: "Bare".into(),
        job_title: "researcher".into(),
        system_prompt: String::new(),
        avatar: String::new(),
        accent: String::new(),
        wallpaper: String::new(),
        managed_by: user,
        status: AgentStatus::Online,
    };
    cm_db::repo::agents::insert(&pool, &agent, &cm_domain::AccessPolicy::default())
        .await
        .unwrap();
    let mission = seed_mission_with_crew(&pool, ws.id, agent.id).await;

    assert!(
        cm_api::phase_runner::phase_skills_text(&pool, mission)
            .await
            .is_none(),
        "a crew with no pinned skills must add no section — the empty-heading \
         rule has to hold on this path too"
    );
}