Files
beardrive/internal/remote/remote.go
Snow LeeandClaude Fable 5 2ce714ac4d feat(sync): agent read reporting — read-log, spool, hub report, hook matchers
Phase 3 of the read heatmap: `bdrive read-log` parses any platform's hook
event JSON from stdin and queues in-project file reads (mount-relative,
ignore/include-filtered) in a per-volume spool — no network on the hook
path. The sync cycle drains the spool best-effort to the hub's new
POST /api/p/<id>/reads via the remote ReadReporter capability (https
backend only); a failed report retries next cycle and never fails or
offlines the cycle. `bdrive hooks install` now registers a third hook per
platform on its read-tool matcher (claude Read, codex read_file
best-effort, gemini read_file|read_many_files, hermes read_file), each
idempotent on its own marker so sync-only configs upgrade in place. Agent
reads land as agent traffic in the heat view, actor = device id.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt
2026-07-11 14:49:02 -07:00

88 lines
3.0 KiB
Go

// Package remote abstracts the cloud object store a volume syncs through.
// beardrive is provider-agnostic: any backend that can put/get/list immutable
// objects works. Built-in schemes:
//
// file:///abs/path local or network-drive directory (also used in tests)
// s3://bucket/prefix Amazon S3 (or S3-compatible via AWS_ENDPOINT_URL)
// gs://bucket/prefix Google Cloud Storage
// https://host:4173 a bdrive web server brokering one of the above —
// the device needs no storage credentials at all
//
// Remote layout: blobs/<sha256> for content, journal/<device>.jsonl for op
// logs. Each device writes only its own journal, so there are no concurrent
// writers per object and no server-side coordination is needed.
package remote
import (
"context"
"fmt"
"io"
"net/url"
"strings"
"time"
)
type Object struct {
Key string
Size int64
}
// SignedPut is a presigned direct-upload request: whoever holds the URL can
// PUT that one object until Expires, without ever seeing storage credentials.
type SignedPut struct {
URL string // upload here
Method string // always "PUT"
Headers map[string]string // headers that must be sent verbatim (they are signed)
Expires time.Time
}
// PutSigner is implemented by backends that can mint presigned upload URLs
// so clients write to storage directly. Backends without that capability
// (file://) simply don't implement it, and callers fall back to uploading
// through the server.
type PutSigner interface {
SignPut(ctx context.Context, key string, size int64, ttl time.Duration) (*SignedPut, error)
}
type Backend interface {
Put(ctx context.Context, key string, r io.Reader, size int64) error
Get(ctx context.Context, key string) (io.ReadCloser, error)
List(ctx context.Context, prefix string) ([]Object, error)
Exists(ctx context.Context, key string) (bool, error)
Close() error
}
// ReadEvent is one agent file read reported to the hub for its read heatmap.
type ReadEvent struct {
Path string `json:"path"`
Time time.Time `json:"time,omitzero"`
}
// ReadReporter is the optional read-telemetry capability, in the PutSigner
// mold: backends that sync through a hub report the device's agent reads so
// the heat view can split human from agent traffic. Object-store backends
// simply don't implement it — there is no hub to tell.
type ReadReporter interface {
ReportReads(ctx context.Context, reads []ReadEvent) error
}
// Open creates a backend from a remote URL.
func Open(ctx context.Context, raw string) (Backend, error) {
u, err := url.Parse(raw)
if err != nil {
return nil, fmt.Errorf("invalid remote %q: %w", raw, err)
}
switch u.Scheme {
case "file":
return newLocal(u.Path)
case "s3":
return newS3(ctx, u.Host, strings.Trim(u.Path, "/"))
case "gs":
return newGCS(ctx, u.Host, strings.Trim(u.Path, "/"))
case "http", "https":
return newHTTPBackend(raw)
default:
return nil, fmt.Errorf("unsupported remote scheme %q (supported: file://, s3://, gs://, https://)", u.Scheme)
}
}