`bdrive hooks install` detects the agent platforms in use — Claude Code
(.claude/), Codex (.codex/), Gemini CLI (.gemini/), Hermes (~/.hermes/) —
and idempotently merges beardrive's turn-boundary sync hooks into each
platform's own hook config (JSON for claude/codex/gemini, YAML for
hermes), preserving existing hooks. All four pipe hook JSON with a
session_id, so one POSIX-sh hook command serves every platform: pull at
turn start, push after edits, changes stamped "<agent> session <id>".
Bare `bdrive hooks` prints the detection/registration table.
The beardrive skill now runs it automatically after `bdrive init`, and
/beardrive:install's hand-maintained settings.json block is replaced by
the command, so the hook content has one source of truth in the binary.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt
`bdrive sync --note <text>` stamps session context onto every op the cycle
commits and persists it in the volume store (note.json, --note-ttl default
30m) so the daemon's own scans stamp it too — winning the race between
one-shot hook syncs and the 3s daemon scan. The plugin sync hook extracts
session_id from hook stdin JSON and passes it automatically, so history
links every change to the Claude Code session that made it. Conflict-copy
ops keep their own note; expired/cleared notes stop applying.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt
The initial import was latency-bound: the push loop uploaded blobs strictly
serially, doing an Exists round-trip then a Put per blob (~2-3N sequential
round-trips against the hub).
- Upload unique blobs in parallel (errgroup, 16 in flight) — the main win.
- Drop the separate Exists round-trip: the backend's Put is idempotent and
the hub already skips content it has (reported during signing), so the
check was redundant.
- Session.OnProgress emits upload progress (done/total files + bytes) from
the push phase; the CLI renders an in-place bar on a TTY and periodic
percentage lines otherwise, wired into `bdrive init`'s initial cycle and
`bdrive sync`. The daemon stays silent.
Multi-device convergence tests pass with -race; new TestPushProgress covers
the progress emission.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
BearDrive is now hub-based only. Clients sync through a `bdrive web` hub
over https and never talk to object storage directly.
- Remove the `bdrive remote` / `bdrive remote set` command entirely. Wiring a
folder's remote is `bdrive init` (always a hub); switching hubs is
`bdrive login <url>` then re-`init`. Object storage stays as the *hub's*
backing store (`bdrive web s3://…`), never a client remote.
- Reposition README, CLAUDE.md, and the beardrive skill from
"no server required / direct-to-bucket" to hub-based; section 2 of the
skill is now "storing a hub's data" (server-side), and the stale
`init --remote` / `remote set` examples are fixed.
BREAKING: direct client-to-bucket sync is no longer supported.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
- New `bdrive logout` clears the saved token + account (folders untouched);
`--forget` also drops the remembered server. Switching hubs is
`bdrive login <new-url>` then re-`init`.
- `remote set --help` now explains the two remote kinds — object storage
(s3/gs/file) vs a bdrive hub (https://<server>) — with examples, instead of
leading with only s3://. (The https:// hub scheme was already accepted.)
- Docs updated (README, CLAUDE.md, SKILL.md).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
Wire a `database` block in bdrive web config: {driver: file|sqlite|postgres,
dsn}. Default file, unchanged (existing per-registry paths honored). sqlite
or postgres routes all five hub registries through the SQL MetaStore.
Verified: signup + project + invite round-trip survives a restart on BOTH
file and sqlite; the sqlite DB holds real relational tables/rows (not JSON
blobs). Docs: a "choosing a database" section (README), the persistence
architecture note (CLAUDE.md), and a config mention (SKILL.md).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
A hub on a public URL could be signed up to with any fake email. Make the
safe posture the default and turn the dangerous ones into startup errors.
Three supported postures:
- invite-only (NEW default): allow_signup defaults false. A valid org
invite link bootstraps an account even when self-signup is closed — the
only way in. pageLogin/pageSignup detect a /join/<token> target via
BuiltinAuth.InviteValid (wired to OrgDB.ValidInvite) and offer account
creation; signupInvited skips the domain/approval/verification gates and
activates immediately (the owner's invite is the vetting).
- approval-gated: allow_signup + require_approval (no SMTP needed).
- domain-restricted + verified: allow_signup + allowed_domains +
require_verification (needs smtp).
Hardening:
- BuiltinAuth.ValidateSignupPolicy (run at hub startup in web.go) refuses to
boot an open hub with no gate, or require_verification without a mailer
(the link would otherwise only reach the server log).
- handleAdminPolicy rejects enabling verification without SMTP; the UI
toggle is disabled with clearer copy in that case.
Tests: TestValidateSignupPolicy, TestInviteBootstrapsAccountWhenSignupClosed,
TestPolicyVerificationNeedsMailer. Verified end to end in the running hub
(outside-domain invitee onboards via a link; direct signup stays closed).
Docs updated (README, CLAUDE.md, SKILL.md).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
Fixes the two round-2 majors.
User: on mobile the per-file actions (Share/History/Upload/Download) are
now icon buttons in the header — reachable again (round 2 wrongly hid
them). Search tolerates simple English plurals (ideas→idea), the
no-matches state states what search covers, the sidebar shows the hub
brand instead of the raw device name, and history-row downloads carry a
download attribute. Logged-out loads redirect to sign-in from /api/config
instead of firing 401-ing API calls.
Admin: a hub-admin "Signup & access" settings screen (⚙ Admin in the
sidebar) toggles email verification and admin approval live — persisted to
auth.json and surviving restart — while the domain allowlist and admin
list are shown read-only (deliberately server-config-owned so a browser
session can't widen access). Pending approvals live on the same screen.
Config toggles are now *bool so an explicit config value pins the setting
each boot, else the UI-saved policy stands. Invite revoke confirms; role
change re-renders the panel.
Tests: policy persistence + reload, policy API admin-only.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
Makes a self-hosted hub safe to expose on a public URL and operable
without hand-editing JSON — addressing the blocker/major findings from
the persona usability evaluations.
Signup gating (config auth block, all optional):
- allowed_domains: signup email must match (e.g. only @runbear.io)
- require_verification: email-link activation before sign-in (reuses mailer)
- require_approval: hub admins approve new accounts (admins list)
- brand shown on the sign-in page; allow_signup:false already hid Sign up
Accounts carry a Status (active/unverified/pending); non-active accounts
cannot authenticate.
Admin lifecycle (endpoints + web UI):
- org: rename, member role change, member remove (last-owner guarded),
invite list + revoke
- project: create (web), rename, delete (from the org panel)
- hub admins: approve/deny pending signups (sidebar bell + panel)
- org-wide public-share audit with revoke
UX: onboarding empty-state (explains invites, paste-invite + create-project)
instead of a blank sidebar; visible "Search ⌘K" button; toasts replace
blocking alert(); responsive layout with an off-canvas sidebar; joining
via #join now survives a logged-out click (token carried through login).
Web uploads are attributed to the signed-in account, not the server.
Login/signup are rate-limited per IP.
Tests: domain/verification/approval gates, auth rate limit, org+project
lifecycle, owner-only guards, invite→join→role→remove over HTTP.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
Rendered-markdown share pages get a small "Shared with BearDrive" footer
linking to the repo — the shell template only, so shared raw HTML is
still served byte-for-byte and the /s/ sandbox CSP is unchanged. All
/s/* responses now sit behind a per-IP token bucket (default 120 req/min
sustained + burst, tunable via "share_rpm" in the web config) so the one
unauthenticated surface of a hub can't be scraped into a free CDN.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
Every hub project now belongs to exactly one org (file-backed orgs.json,
same load-at-open + atomic-rewrite discipline as the other registries).
Membership (email -> owner|member) gates every per-project route: the
viewer APIs, uploads, history, blobs, shares management, and the device
sync store proxy; /api/projects lists only your orgs' projects, and
project names are now scoped per org. Public share links (/s/) stay
public by design.
Design choices, per the simplest-consistent rule:
- Migration: a pre-org hub sweeps all org-less projects into a "default"
org at startup; ALL existing accounts join it (they could all see every
project before, so anything narrower would lock someone out), oldest
account as owner. Zero manual steps.
- An account in no org that creates a project gets a fresh org named
after itself, so nobody is ever blocked from starting to sync.
- Invites are expiring multi-use links (default 7 days): an owner mints
/#join/<token>, any signed-in account that opens it joins as member.
The web UI shows the org in a sidebar footer (members on click,
Invite button for owners).
bdrive init needed no changes: its connect-existing flow lists projects
through the now-filtered API.
Tests: OrgDB + migration units; a 403/access matrix over every
per-project route; invite mint/redeem flow; and a multi-device syncer
test proving a device holding an org-B token can neither pull org A's
files nor push into its store (sync degrades to Offline, never partial).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
Share links (bdrive share <file>, or the web UI's Share button):
- Mint an unguessable public URL (/s/<token>) anyone can open — no
account. HTML renders as a page, markdown gets a standalone shell,
PDFs open inline; ?download=1 attaches.
- Sandboxed: /s/* responses carry CSP `sandbox allow-scripts` + nosniff
and never see auth cookies, so shared content's scripts run in an
opaque origin and can't touch hub sessions.
- Links serve the file's LATEST synced content and live until revoked;
--expires makes self-destructing ones; --list/--revoke manage them.
Re-sharing a file returns the same link. File-backed shares.json.
- CLI resolves the project by walking up to .bdrive/ from the shared
file, warns when the hub address is private (LAN-only links), and
hints when the file hasn't synced yet.
/beardrive:install (plugin command) — team onboarding driven by Claude:
- Ensures the bdrive binary, signs in (bdrive login), runs bdrive init
(whole folder or a shared subfolder like wiki/).
- Asks before appending a CLAUDE.md section that teaches agents to put
shareable artifacts in the shared folder and mint URLs with bdrive
share; asks before registering project-level hooks in
.claude/settings.json: blocking pull at UserPromptSubmit, async push
on PostToolUse Write|Edit — teammates sync with or without the plugin.
- Fix: the plugin hook script still checked for the old `.bdrive` file
and was a silent no-op since the directory change; now checks -d.
Tests: share creation gating, public access + sandbox headers, dedupe,
latest-content semantics, revoke, expiry, markdown/download variants,
list filtering, registry persistence. Docs updated (README sharing +
Claude Code sections, SKILL.md, CLAUDE.md).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
Authentication (previous phase, now landed together with its follow-ups):
- Email+password+name accounts behind an AuthProvider interface; the OSS
server ships BuiltinAuth only (file-backed auth.json: bcrypt password
hashes + SHA-256 token digests, plaintext never stored; server-owned
/auth/* pages; managed deployments can swap in another provider).
- bdrive login: loopback-callback browser flow (sign-up on the page, the
terminal finishes itself) with a device-code fallback for headless
machines; long-lived revocable device tokens in settings.json.
- Password reset via plain SMTP (stdlib) with a log-link fallback when no
SMTP is configured.
Move-proof projects:
- .bdrive is now a directory; config.json carries a stable mount id.
The volume store (~/.bdrive/volumes/<mount-id>/) and registry are keyed
by that id — never the folder path — so renames/moves are free.
- The daemon re-reads the project config each tick and exits cleanly
(propagating nothing) when its folder vanishes; the registry self-heals
and the next bdrive command at the new location resumes with zero
spurious changes.
bdrive init is the front door (mnt/umnt removed; bdrive stop pauses):
- Interactive on a TTY (create new / connect existing project from the
server's list; whole folder / shared subfolder via the include list),
full flag bypass (--name/--project/--shared/--yes), never prompts
without a TTY. Runs the login flow first when there is no session.
Default server: beardrive.ai (config.DefaultServer).
Web history (revert-ready):
- Hubs now always require auth; journal ops carry the signed-in account
(user/user_name) alongside the git/OS fallback author.
- File-backed device registry: per-device name, OS, account, and the
public IP the server observed, joined into history at read time.
- GET /api/p/<id>/history?path=|prefix= (newest first) and
GET /api/p/<id>/blob?sha= stream any exact version — blobs are retained
forever, so the next phase's revert is re-putting an old blob.
- UI: History button (file versions or project feed), per-folder history
shortcut, view/download of any past version.
Tests: auth flows (callback, device-code, reset single-use, persistence,
gating), history API + device registry, folder-move survival, registry
self-heal, ops-carry-account; docs (README/SKILL/CLAUDE) updated.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
The web server (bdrive web) becomes a full sync hub, and client devices
get one-command onboarding — without ever seeing storage info or holding
cloud credentials:
- bdrive web -c config.json: server configurable from a JSON file
(remote/addr/upload/upload_ttl/projects_db); explicit flags win.
- Hub mode: pointing bdrive web at a storage root hosts many projects,
each under <root>/<project-id>/ (remote.Prefixed). Projects live in a
file-backed registry (projects.json — loaded at open, rewritten
atomically per change) with create-or-join-by-name semantics.
- Per-project APIs: /api/projects (list/create/get) and
/api/p/<id>/{tree,file,render,download,upload/*,store/*}. The web UI
grows a project list with per-project browsing and hash deep links.
- Browser uploads and a store proxy for syncing devices: presigned
direct-to-storage PUTs when the backend can sign (S3 presign, GCS V4
signed URLs; expiring, credential-free), relayed through the server
otherwise. Journals are never presigned — only immutable blobs.
Blobs-before-journal and one-writer-per-journal invariants hold.
- https:// remote backend: a device syncs one hub project through
/api/p/<id>/store/* — mnt/sync/daemon/log all work unchanged.
- bdrive login <url>: verify a hub and remember it as the device default
(settings.json). bdrive init: create-or-join a project named after the
folder (--name/--project override), write .bdrive, seed a starter
.bdriveignore, mount, and start the daemon — one command per project.
- Hard-break rename: .beardrive->.bdrive, .beardriveignore->.bdriveignore,
~/.beardrive->~/.bdrive, BEARDRIVE_HOME->BDRIVE_HOME, temp/conflict
prefixes; old names are no longer read.
- Tests: presigning, project registry persistence, store API validation
and gating, project isolation over live HTTP, browser upload flows, and
two-device convergence through a hub (incl. read-only pull-only mode).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
One binary instead of two: cmd/bdrive-web becomes the `web` subcommand
(same flags and positional folder-or-URL argument). Measured cost of
carrying the webapp in the CLI: +1.4 MB on a ~56 MB binary (~2.4%) —
the cloud SDKs dominate either way. Drops the second goreleaser build
and the separate go install path.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HHEUaYfFHhmDvqLYw74Ehz
Product and project are BearDrive; the CLI binary is bdrive (bdrive mnt,
bdrive sync, ...), the web viewer is bdrive-web. All conventions follow
the full name: .beardrive settings file, .beardriveignore, ~/.beardrive
home, BEARDRIVE_HOME, .beardrive-conflict-* / .beardrive-tmp-* files.
Plugin/skill/marketplace renamed to beardrive (/beardrive:mount).
Module path is now github.com/runbear-io/beardrive — merge only after
renaming the GitHub repo, or go install breaks.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HHEUaYfFHhmDvqLYw74Ehz
