restic-manager/internal/server/http/host_credentials.go

package http

import (
	"context"
	"encoding/json"
	"errors"
	"log/slog"
	stdhttp "net/http"
	"time"

	"github.com/go-chi/chi/v5"
	"github.com/oklog/ulid/v2"

	"gitea.dcglab.co.uk/steve/restic-manager/internal/api"
	"gitea.dcglab.co.uk/steve/restic-manager/internal/server/ws"
	"gitea.dcglab.co.uk/steve/restic-manager/internal/store"
)

func nowUTC() time.Time { return time.Now().UTC() }

// hostRepoCredsView is the body of GET /api/hosts/{id}/repo-credentials.
// Password is always redacted; the UI uses this to pre-fill an edit
// form with the URL/username already populated.
type hostRepoCredsView struct {
	RepoURL      string `json:"repo_url"`
	RepoUsername string `json:"repo_username,omitempty"`
	HasPassword  bool   `json:"has_password"`
}

// handleGetHostCredentials returns a redacted view of the host's repo
// creds for UI display. 404 if no credential has ever been set.
func (s *Server) handleGetHostCredentials(w stdhttp.ResponseWriter, r *stdhttp.Request) {
	if !s.authedUser(r) {
		writeJSONError(w, stdhttp.StatusUnauthorized, "unauthorized", "")
		return
	}
	hostID := chi.URLParam(r, "id")
	if hostID == "" {
		writeJSONError(w, stdhttp.StatusBadRequest, "missing_id", "")
		return
	}
	enc, err := s.deps.Store.GetHostCredentials(r.Context(), hostID)
	if err != nil {
		if errors.Is(err, store.ErrNotFound) {
			writeJSONError(w, stdhttp.StatusNotFound, "not_set", "")
			return
		}
		writeJSONError(w, stdhttp.StatusInternalServerError, "internal", "")
		return
	}
	plain, err := s.deps.AEAD.Decrypt(enc, []byte("host:"+hostID))
	if err != nil {
		writeJSONError(w, stdhttp.StatusInternalServerError, "decrypt_failed", "")
		return
	}
	var blob repoCredsBlob
	if err := json.Unmarshal(plain, &blob); err != nil {
		writeJSONError(w, stdhttp.StatusInternalServerError, "internal", "")
		return
	}
	writeJSON(w, stdhttp.StatusOK, hostRepoCredsView{
		RepoURL:      blob.RepoURL,
		RepoUsername: blob.RepoUsername,
		HasPassword:  blob.RepoPassword != "",
	})
}

// hostRepoCredsRequest is the body of PUT /api/hosts/{id}/repo-credentials.
// Operator can edit any subset; missing fields preserve the existing
// value (so changing only the password doesn't require resending the URL).
//
// We model this as plaintext on the wire because the wire is HTTPS to
// the proxy. The values are AEAD-encrypted before they touch SQLite,
// and only ever leave the server again inside the authenticated WS
// `config.update` push.
type hostRepoCredsRequest struct {
	RepoURL      *string `json:"repo_url,omitempty"`
	RepoUsername *string `json:"repo_username,omitempty"`
	RepoPassword *string `json:"repo_password,omitempty"`
}

// handleSetHostCredentials lets an operator/admin update a host's
// repo creds. Any fields the operator sends overwrite the
// corresponding fields in the existing blob; the others are
// preserved. Re-encrypts under host_id and pushes a config.update
// over the WS if the agent is connected.
func (s *Server) handleSetHostCredentials(w stdhttp.ResponseWriter, r *stdhttp.Request) {
	if !s.authedUser(r) {
		writeJSONError(w, stdhttp.StatusUnauthorized, "unauthorized", "")
		return
	}
	hostID := chi.URLParam(r, "id")
	if hostID == "" {
		writeJSONError(w, stdhttp.StatusBadRequest, "missing_id", "")
		return
	}
	if _, err := s.deps.Store.GetHost(r.Context(), hostID); err != nil {
		writeJSONError(w, stdhttp.StatusNotFound, "host_not_found", "")
		return
	}

	var req hostRepoCredsRequest
	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
		writeJSONError(w, stdhttp.StatusBadRequest, "invalid_json", err.Error())
		return
	}

	// Merge with the existing row, if any.
	existing := repoCredsBlob{}
	if cur, err := s.deps.Store.GetHostCredentials(r.Context(), hostID); err == nil {
		plain, err := s.deps.AEAD.Decrypt(cur, []byte("host:"+hostID))
		if err != nil {
			writeJSONError(w, stdhttp.StatusInternalServerError, "decrypt_failed", "")
			return
		}
		_ = json.Unmarshal(plain, &existing)
	} else if !errors.Is(err, store.ErrNotFound) {
		writeJSONError(w, stdhttp.StatusInternalServerError, "internal", "")
		return
	}

	if req.RepoURL != nil {
		existing.RepoURL = *req.RepoURL
	}
	if req.RepoUsername != nil {
		existing.RepoUsername = *req.RepoUsername
	}
	if req.RepoPassword != nil {
		existing.RepoPassword = *req.RepoPassword
	}
	if existing.RepoURL == "" || existing.RepoPassword == "" {
		writeJSONError(w, stdhttp.StatusBadRequest, "missing_field",
			"repo_url and repo_password must end up non-empty")
		return
	}

	enc, err := s.encryptRepoCreds(existing, []byte("host:"+hostID))
	if err != nil {
		writeJSONError(w, stdhttp.StatusInternalServerError, "internal", "")
		return
	}
	if err := s.deps.Store.SetHostCredentials(r.Context(), hostID, enc); err != nil {
		writeJSONError(w, stdhttp.StatusInternalServerError, "internal", "")
		return
	}

	_ = s.deps.Store.AppendAudit(r.Context(), store.AuditEntry{
		ID:         ulid.Make().String(),
		Actor:      "user",
		Action:     "host.repo_credentials_set",
		TargetKind: ptr("host"),
		TargetID:   &hostID,
		TS:         nowUTC(),
	})

	// Push to the agent if it's connected. Errors here are non-fatal:
	// the next reconnect will pick the row up via the hello handler.
	if s.deps.Hub != nil && s.deps.Hub.Connected(hostID) {
		_ = s.pushRepoCredsToAgent(r.Context(), hostID, existing)
	}

	w.WriteHeader(stdhttp.StatusNoContent)
}

// pushRepoCredsToAgent serializes blob into a config.update envelope
// and ships it down the agent's WS. Returns an error from the hub
// (no-op if not connected — caller is expected to check first when it
// matters).
func (s *Server) pushRepoCredsToAgent(ctx context.Context, hostID string, blob repoCredsBlob) error {
	env, err := api.Marshal(api.MsgConfigUpdate, "", api.ConfigUpdatePayload{
		RepoURL:      blob.RepoURL,
		RepoUsername: blob.RepoUsername,
		RepoPassword: blob.RepoPassword,
	})
	if err != nil {
		return err
	}
	sendCtx, cancel := context.WithTimeout(ctx, 5*time.Second)
	defer cancel()
	if err := s.deps.Hub.Send(sendCtx, hostID, env); err != nil {
		slog.Warn("push repo creds: hub send failed", "host_id", hostID, "err", err)
		return err
	}
	return nil
}

// onAgentHello runs synchronously inside the WS handler immediately
// after a successful hello. It loads the host's encrypted creds (if
// any), decrypts, and ships them down the conn as a config.update so
// the agent has them before any command.run lands.
//
// The conn argument is used directly (rather than via the hub) so we
// don't race a brand-new register against an old still-closing conn.
func (s *Server) onAgentHello(ctx context.Context, hostID string, conn *ws.Conn) {
	s.pushRepoCredsOnHello(ctx, hostID, conn)
	// Push the current schedule set in the same on-hello window so
	// the agent's local cron is in sync before any command.run lands.
	// An empty schedule list is a valid push: it tells the agent to
	// drop any cron entries left over from a previous deployment.
	// Always runs, even when the host has no repo credentials yet.
	s.pushScheduleSetOnConn(ctx, hostID, conn)
	// Auto-init the repo if we've never landed a successful init job
	// against this host. Restic treats "config file already exists"
	// as a soft success, so re-enrolment against a populated repo
	// just no-ops. Skipped silently when the host has no creds yet —
	// the next hello after the operator binds creds will dispatch.
	s.maybeAutoInit(ctx, hostID, conn)
}

// maybeAutoInit dispatches a `restic init` job iff the host has no
// successful init in its history AND repo creds are bound (without
// them the runner can't talk to the repo). We rely on Restic's
// idempotent init for re-runs.
func (s *Server) maybeAutoInit(ctx context.Context, hostID string, conn *ws.Conn) {
	if _, err := s.deps.Store.GetHostCredentials(ctx, hostID); err != nil {
		// No creds bound yet — operator hasn't supplied them. The next
		// hello after creds land will pick this up.
		return
	}
	already, err := s.deps.Store.HasJobOfKind(ctx, hostID, string(api.JobInit))
	if err != nil {
		slog.Warn("auto-init: check job history", "host_id", hostID, "err", err)
		return
	}
	if already {
		return
	}
	jobID := ulid.Make().String()
	now := time.Now().UTC()
	if err := s.deps.Store.CreateJob(ctx, store.Job{
		ID:        jobID,
		HostID:    hostID,
		Kind:      string(api.JobInit),
		ActorKind: "system",
		CreatedAt: now,
	}); err != nil {
		slog.Warn("auto-init: persist job", "host_id", hostID, "err", err)
		return
	}
	env, err := api.Marshal(api.MsgCommandRun, jobID, api.CommandRunPayload{
		JobID: jobID,
		Kind:  api.JobInit,
	})
	if err != nil {
		slog.Warn("auto-init: marshal command.run", "host_id", hostID, "err", err)
		return
	}
	sendCtx, cancel := context.WithTimeout(ctx, 5*time.Second)
	defer cancel()
	if err := conn.Send(sendCtx, env); err != nil {
		slog.Warn("auto-init: send command.run", "host_id", hostID, "err", err)
		return
	}
	_ = s.deps.Store.AppendAudit(ctx, store.AuditEntry{
		ID:         ulid.Make().String(),
		Actor:      "system",
		Action:     "host.auto_init",
		TargetKind: ptr("host"),
		TargetID:   &hostID,
		TS:         now,
	})
	slog.Info("auto-init: dispatched", "host_id", hostID, "job_id", jobID)
}

// pushRepoCredsOnHello loads + decrypts + sends the host's repo
// credentials. Silent no-op when the host has nothing on file
// (the operator hasn't bound creds to it yet).
func (s *Server) pushRepoCredsOnHello(ctx context.Context, hostID string, conn *ws.Conn) {
	enc, err := s.deps.Store.GetHostCredentials(ctx, hostID)
	if err != nil {
		if !errors.Is(err, store.ErrNotFound) {
			slog.Warn("on-hello: load host creds", "host_id", hostID, "err", err)
		}
		return
	}
	plain, err := s.deps.AEAD.Decrypt(enc, []byte("host:"+hostID))
	if err != nil {
		slog.Error("on-hello: decrypt host creds", "host_id", hostID, "err", err)
		return
	}
	var blob repoCredsBlob
	if err := json.Unmarshal(plain, &blob); err != nil {
		slog.Error("on-hello: parse host creds", "host_id", hostID, "err", err)
		return
	}
	env, err := api.Marshal(api.MsgConfigUpdate, "", api.ConfigUpdatePayload{
		RepoURL:      blob.RepoURL,
		RepoUsername: blob.RepoUsername,
		RepoPassword: blob.RepoPassword,
	})
	if err != nil {
		slog.Error("on-hello: marshal config.update", "host_id", hostID, "err", err)
		return
	}
	sendCtx, cancel := context.WithTimeout(ctx, 5*time.Second)
	defer cancel()
	if err := conn.Send(sendCtx, env); err != nil {
		slog.Warn("on-hello: send config.update", "host_id", hostID, "err", err)
	}
}