Serve an event's full stored body over HTTP (closes #157)

Capping the event log page at 8 KB of body per event left no
in-app way to see a larger one: storage keeps it, but no route
served it, so a payload over the cap was reachable only by an
operator with filesystem access. GitHub pull_request and
multi-commit push payloads, expanded Stripe events and Shopify
orders all routinely clear 8 KB, which is exactly when the tool
is supposed to be useful.

GET /source/{sourceID}/logs/{eventID}/body now serves one whole
body, and the truncation marker links to it when — and only
when — a body was actually cut.

The response is deliberately inert. Its bytes are chosen by
whoever can reach the public receiver and it hands them back
inside the operator's own authenticated origin, so it goes out
as application/octet-stream with Content-Disposition: attachment
and nosniff, and the filename is built from a parsed uuid rather
than from anything in the request. The application CSP is no
help on this path: script-src allows 'unsafe-inline' from
'self', so a document served from this origin could run its own
script.

It is also bounded. database/sql exposes no incremental handle
on a SQLite blob, so scanning the column would materialise the
whole body whatever wraps it; instead the body is read in 64 KiB
ranges with substr over a blob cast and each range is written
straight to the ResponseWriter, never through renderTemplate.
Peak resident body bytes is the chunk, not the payload, which is
the memory profile the render cap was introduced to protect.

The ownership check the log page applies is extracted as
ownedWebhook and shared with the download, so the two cannot
drift apart. A webhook owned by someone else and one that does
not exist are the same 404.

internal/handlers/event_body.go

@@ -0,0 +1,251 @@
+package handlers
+
+import (
+	"errors"
+	"net/http"
+	"strconv"
+
+	"github.com/go-chi/chi"
+	"github.com/google/uuid"
+	"gorm.io/gorm"
+	"sneak.berlin/go/webhooker/internal/database"
+)
+
+// bodyChunkBytes is how much of a stored body is resident at
+// once while it is being written to the client. The event log
+// page caps what it renders at maxRenderedBodyBytes, so this
+// route is the only way to reach a whole body and by
+// construction serves the largest ones in the system. Reading
+// it in fixed chunks keeps the peak a property of this constant
+// rather than of the payload.
+const bodyChunkBytes = 64 * 1024
+
+// eventBodySizeColumn measures a stored body the same way
+// eventLogColumns cuts one: the cast to blob makes length count
+// bytes rather than characters, so Content-Length matches what
+// substr will actually hand back.
+const eventBodySizeColumn = "length(cast(body as blob))"
+
+// eventBodyChunkQuery reads one byte range of a stored body.
+// substr over a blob is 1-indexed over bytes. The soft-delete
+// predicate is spelled out because Raw bypasses GORM's default
+// scope, and it is what stops a reaped event still being
+// downloadable.
+const eventBodyChunkQuery = "SELECT substr(cast(body as blob), ?, ?) " +
+	"FROM events WHERE id = ? AND webhook_id = ? AND deleted_at IS NULL"
+
+// errShortBodyRead reports that a chunk query returned nothing
+// while bytes were still owed, which means the row went away
+// mid-download.
+var errShortBodyRead = errors.New("stored body ended early")
+
+// HandleEventBodyDownload serves one event's stored body in
+// full, which the event log page cannot: it caps each rendered
+// body at maxRenderedBodyBytes.
+//
+// The bytes are attacker-supplied — anyone who can reach the
+// public receiver chooses them — and this route hands them back
+// inside the operator's own authenticated origin, so the
+// response is deliberately not renderable. Content-Disposition
+// makes the browser download rather than display it, and the
+// octet-stream type plus nosniff stop it being interpreted as
+// HTML or script. Without those a stored payload would execute
+// as the logged-in operator. The application's CSP does not
+// help here: script-src allows 'unsafe-inline' from 'self', so
+// a document served from this origin could run its own inline
+// script.
+func (h *Handlers) HandleEventBodyDownload() http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		webhook, ok := h.ownedWebhook(w, r)
+		if !ok {
+			return
+		}
+
+		// Parsing the id before use serves two purposes: a
+		// malformed id can never reach the SQL or the response
+		// header, and the canonical form below is drawn from
+		// uuid's own fixed alphabet rather than from the
+		// request, so the Content-Disposition value cannot be
+		// steered by a client.
+		eventID, err := uuid.Parse(chi.URLParam(r, "eventID"))
+		if err != nil {
+			http.NotFound(w, r)
+
+			return
+		}
+
+		h.serveEventBody(w, r, webhook, eventID.String())
+	}
+}
+
+// serveEventBody writes the named event's stored body to w.
+//
+// The event must belong to webhook, which is what keeps this
+// route from reading any event in the system by id alone. Two
+// things enforce that and they are not equally strong. The
+// operative one is that events live in a per-webhook SQLite
+// file, so a sibling webhook's event is not in the database
+// being queried at all. The webhook_id predicate on every query
+// below is the second guard, and it is currently redundant
+// against that isolation; it is there so the scoping survives
+// any future change that puts more than one webhook's events in
+// one file.
+func (h *Handlers) serveEventBody(
+	w http.ResponseWriter,
+	r *http.Request,
+	webhook database.Webhook,
+	eventID string,
+) {
+	if !h.dbMgr.DBExists(webhook.ID) {
+		http.NotFound(w, r)
+
+		return
+	}
+
+	webhookDB, err := h.dbMgr.GetDB(webhook.ID)
+	if err != nil {
+		h.serverError(w, "failed to get webhook database", err)
+
+		return
+	}
+
+	size, found, err := eventBodySize(webhookDB, webhook.ID, eventID)
+	if err != nil {
+		h.serverError(w, "failed to size event body", err)
+
+		return
+	}
+
+	// A miss is a 404 whether the event belongs to another
+	// webhook or does not exist at all, so the response does
+	// not report which.
+	if !found {
+		http.NotFound(w, r)
+
+		return
+	}
+
+	setEventBodyHeaders(w, eventID, size)
+
+	err = writeEventBody(w, webhookDB, webhook.ID, eventID, size)
+	if err != nil {
+		// The status and Content-Length are already committed,
+		// so the client sees a short download. There is no way
+		// to report a 500 from here; the log is the record.
+		h.log.Error(
+			"failed to write event body",
+			"webhook_id", webhook.ID,
+			"event_id", eventID,
+			"error", err,
+		)
+	}
+}
+
+// eventBodySize returns the stored size in bytes of an event's
+// body and whether the event exists within the webhook. The
+// size is read separately from the body so Content-Length can
+// be set before any bytes are written.
+func eventBodySize(
+	webhookDB *gorm.DB,
+	webhookID, eventID string,
+) (int64, bool, error) {
+	var size int64
+
+	result := webhookDB.Model(&database.Event{}).
+		Select(eventBodySizeColumn).
+		Where(
+			"id = ? AND webhook_id = ?", eventID, webhookID,
+		).
+		Limit(1).
+		Scan(&size)
+	if result.Error != nil {
+		return 0, false, result.Error
+	}
+
+	if result.RowsAffected == 0 {
+		return 0, false, nil
+	}
+
+	return size, true, nil
+}
+
+// setEventBodyHeaders applies the response headers that make
+// this route safe to hand attacker-supplied bytes through. See
+// HandleEventBodyDownload for why they are a security control
+// and not a formatting choice.
+//
+// nosniff is also set by the global SecurityHeaders middleware.
+// It is repeated here so the guarantee belongs to the route
+// that needs it rather than to a middleware someone could
+// reorder or scope away.
+func setEventBodyHeaders(
+	w http.ResponseWriter,
+	eventID string,
+	size int64,
+) {
+	w.Header().Set("Content-Type", "application/octet-stream")
+	w.Header().Set("X-Content-Type-Options", "nosniff")
+	w.Header().Set(
+		"Content-Disposition",
+		`attachment; filename="webhooker-event-`+eventID+`.bin"`,
+	)
+	w.Header().Set("Content-Length", strconv.FormatInt(size, 10))
+}
+
+// writeEventBody copies size bytes of the event's stored body to
+// w in bodyChunkBytes-sized reads.
+//
+// This is where the route earns its memory bound. database/sql
+// exposes no incremental handle on a SQLite BLOB, so scanning
+// the column would materialise the whole body regardless of the
+// wrapper around it; reading byte ranges instead keeps the
+// resident cost at one chunk. Nothing goes through
+// renderTemplate, which buffers a whole response before writing
+// it.
+//
+// There is deliberately no wrapping read transaction. These
+// per-webhook databases run in SQLite's default journal mode,
+// not WAL, so a read lock held for the length of a slow client's
+// download would block the receiver from recording new events.
+// The cost of that choice is that a body deleted mid-download
+// ends the response short, which is reported as an error rather
+// than passed off as a complete file.
+func writeEventBody(
+	w http.ResponseWriter,
+	webhookDB *gorm.DB,
+	webhookID, eventID string,
+	size int64,
+) error {
+	// Flushing each chunk keeps the claim above true at the
+	// socket as well as in this loop. A ResponseWriter that
+	// cannot flush is not an error: net/http's own output
+	// buffer is a fixed size either way.
+	flusher := http.NewResponseController(w)
+
+	for written := int64(0); written < size; {
+		var chunk []byte
+
+		err := webhookDB.Raw(
+			eventBodyChunkQuery,
+			written+1, bodyChunkBytes, eventID, webhookID,
+		).Row().Scan(&chunk)
+		if err != nil {
+			return err
+		}
+
+		if len(chunk) == 0 {
+			return errShortBodyRead
+		}
+
+		n, err := w.Write(chunk)
+		written += int64(n)
+
+		if err != nil {
+			return err
+		}
+
+		_ = flusher.Flush()
+	}
+
+	return nil
+}