hyperhive/hive-c0re/src/workers/knowledge.rs

//! Hive-wide knowledge repository management.
//!
//! `internal/knowledge` on the forge is cloned to
//! [`LOCAL_DIR`] and bind-mounted read-only into every agent container
//! at `/knowledge`. Agents read documents from it directly and
//! contribute by forking the repo and opening PRs — they never write
//! to the bind-mounted path inside the container.
//!
//! hive-c0re maintains the local clone. A Forgejo webhook notifies it
//! on push to main so agents always see an up-to-date snapshot. The
//! webhook is auto-created by [`ensure_webhook`] at startup. A
//! periodic pull in `main.rs` provides a fallback cadence.

use std::collections::BTreeMap;

use anyhow::{Context, Result};
use forgejo_api::structs::{CreateHookOption, CreateHookOptionConfig, CreateHookOptionType};

use crate::forge::forge_git_url;

pub const ORG: &str = "internal";
pub const REPO: &str = "knowledge";

/// Host-side path for the local clone. Also referenced from
/// `lifecycle.rs` (bind-mount source) and the dashboard webhook handler.
/// The literal lives in [`crate::paths`]; re-exported here under the name
/// this module and its consumers have always used.
pub use crate::paths::KNOWLEDGE_DIR as LOCAL_DIR;

/// In-container mount point for the knowledge repo. Bind-mounted
/// read-only from [`LOCAL_DIR`] into every agent container.
pub const CONTAINER_MOUNT: &str = "/knowledge";

/// Default README pushed to a freshly created `internal/knowledge` repo.
/// Short explanation + empty table-of-contents with an HTML comment instructing contributors
/// to add entries when they create new files.
const README_CONTENT: &str = "\
# knowledge

Hive-wide reference documents: conventions, runbooks, and anything that \
every agent should know.

## How to contribute

1. Fork this repo into your own namespace on the forge.
2. Create a branch, add or update a document.
3. Open a pull request — the operator reviews and merges.
4. Every agent container updates automatically on merge.

Do **not** push directly to `main` — agents have read-only access.

## Contents

<!-- Add an entry here each time you create a new document:
- [Title](path/to/file.md) - one-line description
-->
";

/// Clone `internal/knowledge` to [`LOCAL_DIR`] if it is not already a git
/// repository. `core_token` authenticates the HTTPS clone so private repos
/// work. Idempotent — skips if `LOCAL_DIR/.git` exists.
///
/// When the upstream repo is empty (freshly created), seeds it with a
/// README.md before returning so the local clone is always non-empty and
/// agents see a useful starting document.
///
/// Called once at hive-c0re startup after `forge::ensure_all`.
pub async fn ensure_local_clone(core_token: &str) -> Result<()> {
    let git_dir = std::path::Path::new(LOCAL_DIR).join(".git");
    if git_dir.exists() {
        tracing::debug!("knowledge: local clone already present at {LOCAL_DIR}");
        return Ok(());
    }
    std::fs::create_dir_all(LOCAL_DIR).context("create knowledge local dir")?;
    let url = forge_git_url(core_token, &format!("{ORG}/{REPO}"));
    let out = tokio::process::Command::new("git")
        .args(["clone", &url, LOCAL_DIR])
        .output()
        .await
        .context("git clone knowledge repo")?;
    if !out.status.success() {
        let stderr = String::from_utf8_lossy(&out.stderr).trim().to_owned();
        anyhow::bail!("git clone {ORG}/{REPO} failed: {stderr}");
    }
    tracing::info!("knowledge: cloned {ORG}/{REPO} to {LOCAL_DIR}");
    // If the repo is brand new (no commits), seed it with a README.
    let head_out = tokio::process::Command::new("git")
        .args(["-C", LOCAL_DIR, "rev-parse", "HEAD"])
        .output()
        .await
        .context("git rev-parse HEAD")?;
    if !head_out.status.success() {
        seed_readme(core_token).await?;
    }
    Ok(())
}

/// Write the initial README.md, commit, and push to `internal/knowledge`.
/// Called only when the upstream repo is empty.
async fn seed_readme(core_token: &str) -> Result<()> {
    let readme = std::path::Path::new(LOCAL_DIR).join("README.md");
    std::fs::write(&readme, README_CONTENT).context("write README.md")?;
    // Set a minimal git identity for the seed commit.
    for (k, v) in [("user.email", "core@hive"), ("user.name", "hive-c0re")] {
        let out = tokio::process::Command::new("git")
            .args(["-C", LOCAL_DIR, "config", k, v])
            .output()
            .await
            .with_context(|| format!("git config {k}"))?;
        if !out.status.success() {
            let stderr = String::from_utf8_lossy(&out.stderr).trim().to_owned();
            anyhow::bail!("git config {k} failed: {stderr}");
        }
    }
    for args in [
        vec!["add", "README.md"],
        vec!["commit", "-m", "init: seed README"],
    ] {
        let out = tokio::process::Command::new("git")
            .args(["-C", LOCAL_DIR].iter().chain(args.iter()))
            .output()
            .await
            .with_context(|| format!("git {args:?}"))?;
        if !out.status.success() {
            let stderr = String::from_utf8_lossy(&out.stderr).trim().to_owned();
            anyhow::bail!("git {args:?} failed: {stderr}");
        }
    }
    let url = forge_git_url(core_token, &format!("{ORG}/{REPO}"));
    let out = tokio::process::Command::new("git")
        .args(["-C", LOCAL_DIR, "push", &url, "HEAD:main"])
        .output()
        .await
        .context("git push knowledge README")?;
    if out.status.success() {
        tracing::info!("knowledge: seeded README.md and pushed to {ORG}/{REPO}");
        Ok(())
    } else {
        let stderr = String::from_utf8_lossy(&out.stderr).trim().to_owned();
        anyhow::bail!("git push {ORG}/{REPO} failed: {stderr}")
    }
}

/// Ensure a Forgejo push webhook for `internal/knowledge` exists and
/// points at hive-c0re's `/webhook/knowledge` endpoint. Idempotent —
/// lists existing hooks first and skips creation when one is already
/// targeting the correct URL.
///
/// `hive_domain` is the public domain name of the hive; the webhook URL is
/// `https://<hive_domain>/webhook/knowledge` (routed through the gateway,
/// avoiding the Forgejo SSRF guard that blocks loopback delivery).
///
/// `webhook_secret` is the HMAC secret Forgejo will attach as
/// `X-Hub-Signature-256` on each delivery; hive-c0re verifies this header
/// in [`crate::dashboard::webhook::post_webhook_knowledge`].
///
/// Called at startup alongside [`ensure_local_clone`]. No-op when the
/// core token is absent (forge not yet provisioned).
pub async fn ensure_webhook(
    core_token: &str,
    hive_domain: &str,
    webhook_secret: &str,
) -> Result<()> {
    // The typed client carries no per-request timeout, so each call is
    // wrapped in one: this runs as a detached startup task, and a forge
    // that accepts connections but never answers would otherwise hang
    // it forever (and the hourly pull fallback masks the missing hook).
    const HTTP_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);

    let target_url = format!("https://{hive_domain}/webhook/knowledge");
    let client = crate::forge::api(core_token)?;

    // List existing hooks — skip creation if ours is already there.
    // Best-effort like the raw-HTTP predecessor: a listing failure
    // falls through to the create attempt.
    let listed = tokio::time::timeout(HTTP_TIMEOUT, client.repo_list_hooks(ORG, REPO).all())
        .await
        .map_err(anyhow::Error::from)
        .and_then(|r| r.map_err(anyhow::Error::from));
    match listed {
        Ok(hooks) => {
            let already_exists = hooks.iter().any(|h| {
                h.config
                    .as_ref()
                    .and_then(|c| c.get("url"))
                    .map(String::as_str)
                    == Some(target_url.as_str())
            });
            if already_exists {
                tracing::debug!(%target_url, "knowledge: push webhook already configured");
                return Ok(());
            }
            // Delete stale hooks that point at our path but a different base
            // (e.g. old loopback hooks from before the SSRF-bypass migration).
            for h in &hooks {
                let hook_url = h
                    .config
                    .as_ref()
                    .and_then(|c| c.get("url"))
                    .map_or("", String::as_str);
                if hook_url.ends_with("/webhook/knowledge")
                    && hook_url != target_url
                    && let Some(id) = h.id
                {
                    tracing::info!(hook_url, "knowledge: deleting stale webhook (wrong base)");
                    let _ = tokio::time::timeout(
                        HTTP_TIMEOUT,
                        client.repo_delete_hook(ORG, REPO, id).send(),
                    )
                    .await;
                }
            }
        }
        Err(e) => {
            tracing::debug!(error = %e, "knowledge: listing hooks failed; attempting create");
        }
    }

    // Create the webhook.
    let mut additional = BTreeMap::new();
    additional.insert("secret".to_owned(), webhook_secret.to_owned());

    let hook = CreateHookOption {
        active: Some(true),
        authorization_header: None,
        branch_filter: None,
        config: CreateHookOptionConfig {
            content_type: "json".to_owned(),
            url: url::Url::parse(&target_url).context("parse webhook target url")?,
            additional,
        },
        events: Some(vec!["push".to_owned()]),
        r#type: CreateHookOptionType::Forgejo,
    };
    tokio::time::timeout(HTTP_TIMEOUT, client.repo_create_hook(ORG, REPO, hook))
        .await
        .map_err(anyhow::Error::from)
        .and_then(|r| r.map_err(anyhow::Error::from))
        .with_context(|| format!("create webhook for {ORG}/{REPO}"))?;
    tracing::info!(%target_url, "knowledge: push webhook created");
    Ok(())
}

/// Pull the latest changes in the local clone. Called from the webhook
/// handler on every push to `internal/knowledge` main, and periodically
/// from `main.rs` as a fallback. Uses `--ff-only` so a force-push to
/// the knowledge repo never wedges the local copy silently.
pub async fn pull() -> Result<()> {
    // Sanity: if the clone is missing (e.g. storage was wiped), refuse
    // to pull and let the caller decide whether to re-clone.
    let git_dir = std::path::Path::new(LOCAL_DIR).join(".git");
    if !git_dir.exists() {
        anyhow::bail!("knowledge: {LOCAL_DIR}/.git not found — clone first");
    }
    let out = tokio::process::Command::new("git")
        .args(["-C", LOCAL_DIR, "pull", "--ff-only"])
        .output()
        .await
        .context("git pull knowledge")?;
    if out.status.success() {
        let stdout = String::from_utf8_lossy(&out.stdout).trim().to_owned();
        tracing::info!(result = %stdout, "knowledge: pull succeeded");
        Ok(())
    } else {
        let stderr = String::from_utf8_lossy(&out.stderr).trim().to_owned();
        anyhow::bail!("git pull {ORG}/{REPO} failed: {stderr}")
    }
}