hyperhive/hive-agent/src/prompt.rs

//! System-prompt renderer. Single `prompts/system.md` with
//! HTML-comment markers gating role-specific blocks; this module
//! assembles the final prompt (always "agent" role — there is only one
//! role). Marker grammar + placeholder substitution rules in
//! `docs/turn-loop/claude-invocation.md::On-boot files` (`claude-system-prompt.md`).

use std::path::{Path, PathBuf};

use anyhow::{Context, Result};

/// Assemble the system prompt for a given label + pronouns + optional hive /
/// swarm display names. Pure function — no I/O. Splits out from
/// [`write_system_prompt`] so the marker logic + substitution is unit-testable
/// in isolation. The caller supplies the template body so tests can pass an
/// inline fixture and production reads it once at harness startup via
/// [`hive_sh4re::assets::prompt_template`]
/// (`$HIVE_ASSETS_DIR/prompts/system.md`). Substitution placeholders +
/// marker grammar documented in
/// `docs/turn-loop/claude-invocation.md::On-boot files` (`claude-system-prompt.md`).
#[must_use]
pub fn render(
    template: &str,
    label: &str,
    operator_pronouns: &str,
    hive_name: Option<&str>,
    swarm_name: Option<&str>,
    docs_dir: Option<&str>,
) -> String {
    let body = filter_role_blocks(template, "agent");
    let qualified = crate::identity::qualify(label);
    let hive_identity = hive_name
        .filter(|n| !n.is_empty())
        .map_or(String::new(), |n| format!(" on hive `{n}`"));
    let swarm_identity = swarm_name
        .filter(|n| !n.is_empty())
        .map_or(String::new(), |n| format!(" in swarm `{n}`"));
    let rendered = body
        .replace("{label}", label)
        .replace("{qualified_label}", &qualified)
        .replace("{operator_pronouns}", operator_pronouns)
        .replace("{hive_identity}", &hive_identity)
        .replace("{swarm_identity}", &swarm_identity);
    // When the reference docs are mounted in-container (`hyperhive.docs.enable`
    // wires `HIVE_DOCS_DIR` + `claude --add-dir`), append a single pointer
    // sentence so the agent knows they exist. Additive: it doesn't replace the
    // agent's own memory/project instructions. Absent env → no change.
    match docs_dir.filter(|d| !d.is_empty()) {
        Some(dir) => format!(
            "{rendered}\n\nThe hyperhive reference docs (the repo `docs/` tree \
             describing this live system) are mounted read-only at `{dir}` — read \
             them (start at the index, then the topic file for the area you're \
             touching) rather than guessing.\n"
        ),
        None => rendered,
    }
}

/// Walk `template` line-by-line, stripping `<!-- role:X -->` /
/// `<!-- /role:X -->` marker lines and suppressing the lines inside a block
/// unless `X == target`. A close marker ends the current block. Production
/// `system.md` carries no markers today (single agent role — see the module
/// doc), so this is effectively a passthrough; the marker grammar stays wired
/// for a future manager / multi-role prompt.
fn filter_role_blocks(template: &str, target: &str) -> String {
    let mut out = String::with_capacity(template.len());
    // None = outside any block; Some(role) = inside role-tagged block.
    let mut active_role: Option<&str> = None;
    for line in template.lines() {
        let trimmed = line.trim();
        if let Some(role) = parse_open_marker(trimmed) {
            active_role = Some(role);
            continue;
        }
        if parse_close_marker(trimmed).is_some() {
            active_role = None;
            continue;
        }
        if active_role.is_none_or(|role| role == target) {
            out.push_str(line);
            out.push('\n');
        }
    }
    out
}

/// `<!-- role:agent -->` → `Some("agent")`. Anything else returns
/// None. Whitespace inside the marker is tolerated so a future
/// author's `<!--role:foo-->` (no spaces) still parses; the dashboard
/// markdown renderer is equally lenient. Close tags (`/role:...`)
/// can't accidentally match — the `strip_prefix("role:")` rejects
/// the leading slash before we'd ever see it.
fn parse_open_marker(line: &str) -> Option<&str> {
    let inside = line.strip_prefix("<!--")?.strip_suffix("-->")?.trim();
    let role = inside.strip_prefix("role:")?.trim();
    Some(role)
}

/// `<!-- /role:agent -->` → `Some("agent")`. Mirror of
/// [`parse_open_marker`] for the closing tag.
fn parse_close_marker(line: &str) -> Option<&str> {
    let inside = line.strip_prefix("<!--")?.strip_suffix("-->")?.trim();
    inside.strip_prefix("/role:").map(str::trim)
}

/// Write the assembled prompt to a stable path next to the harness
/// socket and return the path. The Rust harness passes this path to
/// `claude --system-prompt-file` so the per-turn prompts only carry
/// the role + tools instructions in the system slot; per-turn prompts
/// become much smaller (just the wake-message body).
///
/// # Errors
///
/// Returns an error if the system prompt file cannot be written.
pub async fn write_system_prompt(_socket: &Path, label: &str) -> Result<PathBuf> {
    let parent = crate::paths::config_dir();
    tokio::fs::create_dir_all(&parent).await.ok();
    let pronouns = std::env::var("HIVE_OPERATOR_PRONOUNS").unwrap_or_else(|_| "she/her".to_owned());
    let template_path = hive_sh4re::assets::prompt_template();
    let template = tokio::fs::read_to_string(&template_path)
        .await
        .with_context(|| {
            format!(
                "read claude system prompt template from {}",
                template_path.display()
            )
        })?;
    // Surface hive + swarm display names in the prompt opener when
    // configured. Both `None` falls back to the non-identity wording
    // verbatim (single-hive deployments see no diff).
    let hive_name = crate::identity::hive_name();
    let swarm_name = crate::identity::swarm_name();
    // `hyperhive.docs.enable` sets HIVE_DOCS_DIR (and the harness passes it to
    // claude via `--add-dir`); when present, render() appends a pointer line.
    let docs_dir = std::env::var("HIVE_DOCS_DIR")
        .ok()
        .filter(|d| !d.is_empty());
    let body = render(
        &template,
        label,
        &pronouns,
        hive_name.as_deref(),
        swarm_name.as_deref(),
        docs_dir.as_deref(),
    );
    let path = parent.join("claude-system-prompt.md");
    tokio::fs::write(&path, body).await?;
    tracing::info!(path = %path.display(), "wrote claude system prompt");
    Ok(path)
}

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

    // The production template lives at `$HIVE_ASSETS_DIR/prompts/system.md`
    // and is loaded at runtime. The unit tests below want to assert
    // against the actual production wording (so the renderer + tool
    // surface stay honest), so they resolve the same path at test
    // runtime via two fallbacks:
    //   1. `$HIVE_ASSETS_DIR/prompts/system.md` — the runtime contract
    //      production uses. The flake's `checks.cargo-test` derivation
    //      sets this to the `hyperhive-assets` output so `cargo test`
    //      inside the nix sandbox finds the file without needing
    //      `prompts/` in the cargo source tree. `packages.default`
    //      explicitly does NOT carry the assets dep, so a prompt edit
    //      doesn't bust the binary derivation — only this test check.
    //   2. `env!("CARGO_MANIFEST_DIR")/prompts/system.md` — for plain
    //      `cargo test --workspace` from a checked-out repo where the
    //      env var isn't set; `env!` is a compile-time string lookup,
    //      no file open at compile, so this still doesn't pull
    //      `prompts/` into the build hash.
    // The combined effect is that the flake's `cleanSrc` no longer
    // unions `./hive-agent/prompts` — tweaks to system.md don't bust
    // the cargo cache anymore.
    static PRODUCTION_TEMPLATE: LazyLock<String> = LazyLock::new(|| {
        let path = match std::env::var("HIVE_ASSETS_DIR") {
            Ok(v) if !v.is_empty() => format!("{v}/prompts/system.md"),
            _ => concat!(env!("CARGO_MANIFEST_DIR"), "/prompts/system.md").to_owned(),
        };
        std::fs::read_to_string(&path)
            .unwrap_or_else(|e| panic!("read production prompt template at {path}: {e}"))
    });

    const SAMPLE: &str = "\
shared opener
<!-- role:agent -->
agent-only line
<!-- /role:agent -->
<!-- role:manager -->
manager-only line
<!-- /role:manager -->
shared closer
";

    #[test]
    fn filter_keeps_shared_and_target_role() {
        let agent = filter_role_blocks(SAMPLE, "agent");
        assert!(agent.contains("shared opener"));
        assert!(agent.contains("agent-only line"));
        assert!(!agent.contains("manager-only line"));
        assert!(agent.contains("shared closer"));
        // Marker lines themselves are stripped — no `<!--` left behind.
        assert!(!agent.contains("<!--"));
    }

    #[test]
    fn filter_for_manager_picks_manager_block() {
        let manager = filter_role_blocks(SAMPLE, "manager");
        assert!(manager.contains("shared opener"));
        assert!(!manager.contains("agent-only line"));
        assert!(manager.contains("manager-only line"));
        assert!(manager.contains("shared closer"));
        assert!(!manager.contains("<!--"));
    }

    #[test]
    fn parse_open_marker_handles_whitespace_variants() {
        assert_eq!(parse_open_marker("<!-- role:agent -->"), Some("agent"));
        assert_eq!(parse_open_marker("<!--role:agent-->"), Some("agent"));
        assert_eq!(parse_open_marker("<!-- role:manager -->"), Some("manager"));
        // Close tags must NOT match open-tag parser.
        assert_eq!(parse_open_marker("<!-- /role:agent -->"), None);
        // Non-markers pass through (return None).
        assert_eq!(parse_open_marker("just text"), None);
        assert_eq!(parse_open_marker("<!-- not a role -->"), None);
    }

    #[test]
    fn parse_close_marker_handles_whitespace_variants() {
        assert_eq!(parse_close_marker("<!-- /role:agent -->"), Some("agent"));
        assert_eq!(parse_close_marker("<!--/role:manager-->"), Some("manager"));
        // Open tags must NOT match close-tag parser.
        assert_eq!(parse_close_marker("<!-- role:agent -->"), None);
        assert_eq!(parse_close_marker("just text"), None);
    }

    #[test]
    fn render_substitutes_label_and_pronouns() {
        // Real template's first agent line — keeps the renderer
        // honest about the {label} / {operator_pronouns} pair the
        // harness already relied on.
        let rendered = render(&PRODUCTION_TEMPLATE, "alice", "they/them", None, None, None);
        assert!(rendered.contains("hyperhive agent `alice`"));
        assert!(rendered.contains("**they/them** pronouns"));
        assert!(!rendered.contains("{label}"));
        assert!(!rendered.contains("{operator_pronouns}"));
    }

    #[test]
    fn render_no_role_markers_in_output() {
        // No raw role markers should survive into the rendered prompt.
        let rendered = render(&PRODUCTION_TEMPLATE, "alice", "she/her", None, None, None);
        assert!(!rendered.contains("<!-- role:"));
        assert!(!rendered.contains("<!-- /role:"));
        // Shared tools appear.
        assert!(rendered.contains("mcp__hyperhive__recv"));
        assert!(rendered.contains("mcp__hyperhive__ask"));
    }

    #[test]
    fn render_uses_agent_opener() {
        let rendered = render(&PRODUCTION_TEMPLATE, "alice", "she/her", None, None, None);
        assert!(rendered.starts_with("You are hyperhive agent"));
    }

    // Inline fixture for the {hive_identity} / {swarm_identity}
    // placeholders. Cargo's `cargo test` resolves `PRODUCTION_TEMPLATE`
    // against `$HIVE_ASSETS_DIR/prompts/system.md`, which the flake
    // builds at derivation time — a fresh placeholder added on the
    // source side isn't in the shipped asset until the flake rebuilds,
    // so PRODUCTION_TEMPLATE can't be the fixture here. The string
    // below carries just enough of the opener shape to exercise the
    // substitution logic; nothing here depends on the production
    // template's flavor markers.
    const IDENTITY_FIXTURE: &str = "\
You are hyperhive agent `{label}` (qualified: `{qualified_label}`){hive_identity}{swarm_identity} in a multi-agent system. Pronouns: **{operator_pronouns}**.
";

    #[test]
    fn render_substitutes_hive_identity_when_set() {
        let rendered = render(
            IDENTITY_FIXTURE,
            "alice",
            "she/her",
            Some("pr1ma"),
            None,
            None,
        );
        assert!(rendered.contains("on hive `pr1ma`"), "{rendered}");
        // swarm clause stays absent when only hive is set.
        assert!(!rendered.contains("in swarm"));
        // No raw placeholder leaks.
        assert!(!rendered.contains("{hive_identity}"));
        assert!(!rendered.contains("{swarm_identity}"));
    }

    #[test]
    fn render_substitutes_swarm_identity_when_set() {
        let rendered = render(
            IDENTITY_FIXTURE,
            "ruth",
            "she/her",
            None,
            Some("constellat1on"),
            None,
        );
        assert!(rendered.contains("in swarm `constellat1on`"));
        assert!(!rendered.contains("on hive"));
    }

    #[test]
    fn render_substitutes_both_when_both_set() {
        let rendered = render(
            IDENTITY_FIXTURE,
            "iris",
            "she/her",
            Some("pr1ma"),
            Some("constellat1on"),
            None,
        );
        // Order: hive then swarm, both inline before "in a multi-agent
        // system" — keeps the opener grammar intact.
        assert!(rendered.contains("on hive `pr1ma` in swarm `constellat1on`"));
    }

    #[test]
    fn render_omits_identity_when_unset() {
        // None / None must round-trip the non-identity opener verbatim
        // — single-hive deployments see zero diff.
        let rendered = render(IDENTITY_FIXTURE, "alice", "she/her", None, None, None);
        assert!(!rendered.contains("on hive"));
        assert!(!rendered.contains("in swarm"));
        assert!(!rendered.contains("{hive_identity}"));
        assert!(!rendered.contains("{swarm_identity}"));
    }

    #[test]
    fn render_treats_empty_identity_as_none() {
        // Defensive: an env var set to empty string round-trips
        // through `identity::hive_name()` as None (the accessor
        // filters empty), but `render` should still no-op on a
        // direct `Some("")` from a test fixture or a future caller.
        let rendered = render(
            IDENTITY_FIXTURE,
            "alice",
            "she/her",
            Some(""),
            Some(""),
            None,
        );
        assert!(!rendered.contains("on hive"));
        assert!(!rendered.contains("in swarm"));
    }

    #[test]
    fn render_appends_docs_pointer_when_docs_dir_set() {
        let rendered = render(
            &PRODUCTION_TEMPLATE,
            "alice",
            "she/her",
            None,
            None,
            Some("/run/hive-docs"),
        );
        // Key on a phrase unique to the pointer sentence — "reference docs"
        // alone also appears in the /knowledge blurb of the base template.
        assert!(
            rendered.contains("mounted read-only at `/run/hive-docs`"),
            "expected docs pointer sentence with the dir:\n{rendered}"
        );
    }

    #[test]
    fn render_no_docs_pointer_when_docs_dir_absent_or_empty() {
        for docs in [None, Some("")] {
            let rendered = render(&PRODUCTION_TEMPLATE, "alice", "she/her", None, None, docs);
            assert!(
                !rendered.contains("mounted read-only at"),
                "docs pointer must not appear for {docs:?}:\n{rendered}"
            );
        }
    }
}