On a Buzz relay, channel membership is server-side: another member can add you,
the relay writes you into the kind-39002 roster, and you can read and post
immediately. The relay then addresses you a kind-44100 naming who did it.
Amethyst funnelled every 44100 into BuzzDmChannels — treating it as a DM — which
silently subscribed you to that channel's messages, while the Messages list
(which reads the self-published kind-10009) showed no row for it. A channel could
therefore be joined, streaming, and invisible at the same time: the channel
screen offered no Join button and accepted posts, the RelayGroups screen listed
it from the relay's 39000 directory, messages arrived — and Messages had nothing.
Nothing here is auto-accepted any more. 44100 carries `{"type","channel_id",
"actor"}`, and the relay emits the SAME kind for a self-join with `actor == you`,
so the actor is the only thing separating "I joined this" from "somebody put me
here". Channels are classified by the `t` tag on their 39000 (stream/forum/dm/
workflow — read through a dedicated accessor because on buzz the type shares the
tag name with real hashtags): only `t = dm` belongs in the DM list, everything
else becomes a pending invite that subscribes to nothing.
The prompt appears on both surfaces, driven by one state holder so they cannot
disagree — Notifications, in the same header slot as the missing-inbox-relay
prompt, and Messages > New Requests, beside the pending DMs it is the exact
analogue of. Rendered as a list row rather than a modal: these arrive in bursts
when somebody sets up a workspace, and a blocking dialog on cold start would be
miserable. It is also the spam surface, so Ignore stays cheap.
Three actions, and Ignore is deliberately not Leave:
- Show -> writes the group into kind-10009 (Account.follow), after which the
ordinary joined-group path owns it and it syncs to other devices.
No kind-9021: the relay already has you in the roster, so this
records only your decision to surface it.
- Ignore -> local, reversible display choice. You stay in the roster and can
still open and post.
- Leave -> kind-9022 LeaveRequestEvent, the one that actually removes you.
A kind-44101 removal now withdraws any pending prompt, so the relay taking the
membership away cannot leave a card offering an action that would fail.
The invites section is passed as the chatroom feed's header rather than stacked
beside it: the collapsing top bar draws over that area, so a header outside the
list renders underneath it. It shows in the empty state too, otherwise an account
with no pending DMs would have no way to reach the prompt.
Verified end to end on device: "straycat added you to personalized-knowledge-
graphs" rendered on both surfaces, and Show republished kind-10009 with the
channel appended.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Audit of the compressed-proof work found one real defect and one coverage gap.
Defect: a hostile BOLT12 proof/offer can carry a 9+ byte `invoice_amount`
(or any tu64 field) that parses as a valid TLV. `TlvStream.tu64` then called
the strict `Bolt12Values.tu64`, which throws `require(size <= 8)`. On the
`amy bolt12 verify` path (`Bolt12ZapActions.validate`, no surrounding catch)
that surfaced as an uncaught exception and abnormal exit instead of a clean
`Invalid`; the Android ingest path was already contained by LocalCache's broad
catch. Make the nullable stream accessor `TlvStream.tu64` return null for an
over-8-byte value so every amount read (invoice_amount, invreq_amount, offer
amount) degrades to a clean rejection. Regression-tested at the codec level.
Coverage: the writer's `proof_note` (1005) branch and the `with_note` vector's
note were never exercised. Add a `Bolt12PayerProof.proofNote()` reader and
thread the vector's note through the writer round-trip so 1005 is asserted.
The forged-proof, DoS, and reconstruction-accounting paths were reviewed and
found sound (the reconstructed root is only ever a BIP-340 message; the NIP
offer-binding gate still pins invoice_node_id to the offer's issuer).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SpgpWLKzgD7vS9Fs4CXTR3
The File Sync / Import flow (and the mirror-on-upload fan-out) copy blobs
across the user's Blossom servers with BUD-04 `PUT /mirror`, but not every
server implements that endpoint. Blossom has no capability-discovery
mechanism, so a target without /mirror just answered 404/405/501 and the
whole copy was silently counted as failed.
Detect the "endpoint absent" statuses (404/405/501) as a typed
BlossomMirrorUnsupportedException — distinct from a mirror the server
understood but rejected (400/403/413/…) — and add BlossomClient.mirrorOrUpload,
which falls back to downloading the blob and re-uploading it (PUT /upload)
when mirror is unsupported. The downloaded bytes are verified against the
expected sha256 before re-upload, since a Blossom server is untrusted and
could substitute content, and the same t=upload auth is reused.
Wire every mirror path through mirrorOrUpload: the app-level
BlossomMirrorQueue (sync-all + import sweep), the blob manager's per-blob
mirror (including the paid-mirror retry), and UploadOrchestrator's
mirror-on-upload. Task now carries the descriptor content-type so the
fallback upload preserves the MIME.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0168TWLTgrMxUR6yjjCCiBLS
Real BOLT12 wallets emit selective-disclosure payer proofs: `invreq_metadata`
is always withheld and other invoice fields may be elided for privacy, with
`proof_omitted_tlvs` / `proof_missing_hashes` / `proof_leaf_hashes` carrying
enough to rebuild the invoice signature's merkle root. The verifier previously
reported these as unsupported (cryptoVerified = false), so a zap paid through a
real wallet never counted locally.
Implement the lightning/bolts#1346 reader:
- Bolt12Merkle.reconstructRoot rebuilds the invoice root from the disclosed
LnLeaf hashes + supplied nonce leaves (proof_leaf_hashes) + omitted-field
markers + missing subtree hashes (consumed post-order DFS, smallest-to-largest).
Add emitMissingHashes as the writer dual, unify both on one tree builder.
- Fix two latent interop bugs the vectors exposed: the nonce leaf hashes the
record's type bytes (not the full encoded TLV), and the payer proof signs
under fieldname `proof_signature` (not `signature`).
- Bolt12PayerProof gains marker/leaf/missing accessors and the invoice-field
range predicate; the verifier reconstructs on every proof (type 0 is always
the implied first omitted leaf) and drops the Unsupported result.
- Add Bolt12ProofBuilder to mint spec-compliant proofs (tests + future interop),
and rewire Bolt12ProofFixture onto it.
Validated byte-for-byte against the draft's own conformance suite
(bolt12/payer-proof-test.json): all 5 valid vectors verify, all 23 invalid are
rejected, and the writer reproduces every vector's compression fields exactly.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SpgpWLKzgD7vS9Fs4CXTR3
A Concord community pinned to the bottom bar folded only a fraction of its
channels — Soapbox showed 1 of 12. The live subscription collapsed a
community's Control + Guestbook + rekey + every channel plane into ONE
kind-1059 filter per relay, and the channel list is folded from the Control
Plane. On an AUTH-gated relay that caps a REQ per filter (measured ~100
events/filter on relay.dreamith.to), the chatty Guestbook plane crowded the
channel-defining control editions out of the cap, so only a fraction of the
channels folded. On the strict relay.ditto.pub the collapsed multi-author
filter is refused wholesale until every author is authenticated.
- Split the Control Plane into its OWN filter, apart from the Guestbook /
rekey / channel planes (ConcordSubscriptionPlanner.controlIsolatedFilters),
so it gets an isolated per-filter budget. Both filters still ride the same
per-relay REQ (no extra socket).
- Add a COMPLETE-mode Control-Plane sweep (Account.syncConcordControlPlanes):
re-fetch the whole plane with no `since`, paging past the per-filter cap via
fetchAllPagesFromPool, so a forward cursor can never hide an edition and the
cap can never truncate the fold. Mounted account-wide, fired on load +
membership/held-epoch change + relay reconnect (not a wall-clock poll — the
persistent live subscription keeps a connected relay complete).
Mirrors Armada's plane-sweep design (one filter per plane scope, COMPLETE-mode
control). Verified on-device: Soapbox now folds all 12 channels.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- amy bolt12 verify: the id-only query with a <Bolt12ZapEvent> type crashed
with ClassCastException when the id pointed at a non-9736 event. Constrain
the filter to kind 9736 and cast defensively (query<Event>() as?), returning
a clean not_found instead.
- Bolt12ZapActions.decodeOffer/decodeProof: a parseable bech32 with an
over-8-byte amount TLV threw in tu64 on field read instead of honoring the
null contract; guarded the field extraction in runCatching. Adds a
malformed-amount regression test.
- Account.sendBolt12Zap: wrap the NWC response callback in try/catch/finally so
a post-payment receipt-assembly failure (e.g. a remote signer error) steps
progress and surfaces "paid, no receipt" instead of vanishing as an uncaught
coroutine exception.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SpgpWLKzgD7vS9Fs4CXTR3
Adds a BOLT12 zap (NIP-XX) command group over a new shared commons
Bolt12ZapActions (assembly-only, mirrors ZapActions):
bolt12 decode LNO1|LNP1 decode an offer or payer proof
bolt12 verify EVENT-ID validate a kind:9736 in the local store
bolt12 offer get/set read/publish a kind:10058 offer list
bolt12 intent … / zap … two-step out-of-band send (amy has no NWC
rail): intent prints the payer_note; zap
wraps the signed intent + settled proof
into a validated kind:9736 and publishes
Keeps cli a thin assembly layer — all logic is quartz's Bolt12ZapBuilder/
Validator/codecs via commons Bolt12ZapActions. Adds Bolt12ZapActionsTest;
updates README + ROADMAP. Interop harness and NWC-fetched proofs remain TODO.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SpgpWLKzgD7vS9Fs4CXTR3
NIP-03 OpenTimestamps attestations (kind 1040) were stored loosely in the main
note cache and found via a full-cache scan, with their blockchain verdicts held
in a separate, id-keyed VerificationStateCache LRU. Nothing tied either to the
lifecycle of the note being timestamped, so a deleted/pruned note leaked its
attestations, and consume(OtsEvent) invalidated the attestation's own
(observer-less) flow instead of the target's — so a live-arriving proof never
pinged the target's UI.
Mirror the recent edits→Note migration:
- Note gains a `timestamps` child collection (like `edits`/`reactions`), wired
into clearChildLinks/removeNote, so an attestation survives exactly as long as
its target and is collected when the target is pruned or deleted.
- consume(OtsEvent) anchors the proof on its target via the `e` tag and
invalidates the target's `ots` flow; unlinkAndRemove detaches it symmetrically.
- Each attestation memoizes its own verdict in `Note.otsVerification`, so the
result shares the note's lifecycle. This replaces VerificationStateCache
(deleted) and the full-cache scan: the OTS pill now folds `note.timestamps`
via the new Note.earliestOtsVerifiedTime / cacheVerifyOts helpers.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014D5fenZbAhCbDiwv7Rtpvj
Every chat composer in Amethyst already had a picture/media attach button
(SelectFromGallery) except the minichat "thread" screen — the kind-1111
reply composer opened from the "N replies" chip — which was text-only. This
brings it to parity with every other chat.
- quartz: ChannelChat.imageReply() — a kind-1111 thread reply carrying
encrypted image imeta(s), combining reply()'s NIP-22 pointers with
imageMessage()'s ciphertext-URL/imeta handling (+ round-trip test).
- commons: ConcordActions.buildChannelImageReply().
- Account.sendMinichatReply() now accepts imetas and routes per backend:
Concord sends an encrypted image reply; NIP-28/NIP-29 public chats append
the URL to the content and carry a plaintext imeta on the comment; Buzz
appends the URL to the stream message content.
- Extract toConcordImeta()/toPlainImetas() into a shared UploadImetas.kt so
the minichat and Concord composers build imeta the same way.
- MinichatScreen: add the SelectFromGallery leading icon + ChatFileUpload
dialog, encrypting only when the backend is end-to-end (Concord).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01D8FD5xm8nyEKzd8dk9VfT1
Audit of the three edit paths (feed 1010 / Buzz 40003 / Concord 3302) found:
1. Bug (feed regression): a deleted edit kept overlaying its message. Edits
anchor on the target's Note.edits with no `replyTo` back-link, and
removeNote didn't cover `edits`, so unlinkAndRemove never dropped them — the
old cache-scan resolver dropped deleted edits for free, Note.edits did not.
Fix: removeNote now also removeEdit()s, and unlinkAndRemove resolves the
edit's `e`-tag target and unlinks it there (editedTargetIdOf covers all
three kinds). New test: deleting an edit un-overlays and unlinks it.
2. Perf: every chat row ran two edits-flow collectors (observeConcordEdit +
observeBuzzEdit). A message is only ever one kind, so they're merged into a
single observeChatEdit that resolves latestConcordEdit() ?: latestBuzzEdit()
— one collector per row, dispatched by the winning edit's event type.
3. Nits: latestBuzzEdit now tie-breaks by idHex (deterministic on same-second
edits, matching Concord); dropped a redundant takeIf in latestConcordEdit.
The author check stays at read time on purpose: an edit can be consumed before
its target loads (author unknown), so an attach-time gate would wrongly drop
early-arriving legit edits.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013HdLnAa4Pa1pFV9FTYVTB6
The payment-hash dedup kept the LOWER amount and OR'd cryptoVerified across
entries. Because a payer proof publishes its proof_preimage, once a BOLT12 zap
is public anyone can replay its payment hash in a compressed (unverifiable)
proof with a 1-msat amount; the merge would keep that amount AND inherit the
verified flag, driving the counted total to ~zero and mislabeling a fabricated
amount as verified.
Per the NIP, dedup by invoice_payment_hash applies among *validated* proofs.
Only a crypto-verified proof has a signature-bound amount, so a verified entry
now always wins over an unverified duplicate; the lower-amount rule applies only
between entries of the same verification status. Adds a two-order regression
test for the replay-griefing case.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SpgpWLKzgD7vS9Fs4CXTR3
Downloads and keeps kind 10058 fresh the way the per-user relay/payment lists do,
so a recipient's BOLT12 offer is available for discovery before a zap.
- LocalCache consumes 10058 as an addressable note (consumeBaseReplaceable),
keyed by Address(10058, pubkey, "").
- User gains a pinned bolt12OfferListNote + bolt12OfferList()/bolt12Offers()
accessors — this is how a payer reads a recipient's offers.
- Bolt12OfferListState: the logged-in user's own offer list as live account state
(a StateFlow<List<String>> of offers), persisted across restarts and published
via saveOffers() — cloned from NipA3PaymentTargetsState. Wired into Account
(bolt12OfferList + saveBolt12Offers), AccountSettings (backup + updater), and
LocalPreferences (persist/restore).
- Subscriptions: kind 10058 added to FilterUserMetadataForKey (fetches OTHER
users' offers — the key edit for zap recipients) and to the account's
FilterAccountInfoAndListsFromKey (fetches your own at login).
Editor UI and the payment intent follow next.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SpgpWLKzgD7vS9Fs4CXTR3
All three edit kinds now anchor on the message they edit via the same
Note.edits collection, instead of each maintaining its own store:
- Feed edits (kind 1010): consume(TextNoteModificationEvent) calls
editedNote.addEdit(note); findLatestModificationForNote folds note.edits
(author-only, NIP-40 expiry) instead of scanning the whole cache. Drops
the O(all-notes) scan and the 20-entry modificationCache LRU;
cachedModificationEventsForNote is now synchronous (no Loading state).
- Buzz edits (kind 40003): consume(StreamMessageEditEvent) calls
target.addEdit(note); observeBuzzEdit reads note.edits (newest by
created_at, no author gate — Buzz's own rule). Removes the channel-keyed
BuzzWorkspaceState edit store, its editUpdates/editFor/effectiveContentFor/
addEdit and the pruneEdits reaping (edits now prune with their message).
- Concord edits (kind 3302): already on note.edits.
Each reader keeps its own semantics by filtering note.edits on its event
type; the shared field only unifies storage + lifecycle, so an edit lives
exactly as long as the message it edits. Buzz edit tests rewritten against
note.edits (6/6 green).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013HdLnAa4Pa1pFV9FTYVTB6
Sweep of Kotlin compiler warnings in every module's main source sets
(quartz, commons, cli, desktopApp, amethyst, nappletHost).
Genuine code fixes:
- Drop unnecessary !!/safe-calls and redundant elvis/casts (OkHttp's
now-non-null `body`, smart-cast callbacks, non-null String receivers).
- Remove provably-redundant conditions (`canvas == null` after a
non-null content check; `account != null` implied by `canModerate`).
- Migrate deprecated kotlinx.collections.immutable persistent ops
(add/remove/put/addAll -> adding/removing/putting/addingAll).
- Migrate LocalClipboardManager -> LocalClipboard (+ scoped setText),
ContextCompat.startActivity -> context.startActivity, TabRow ->
SecondaryTabRow, and @ConsistentCopyVisibility on a private-ctor data class.
- Delete dead ReceiveDialog.onGenerate param (never invoked).
- Fix a platform-Boolean type-mismatch on a ThreadLocal read.
Deprecations with no available successor are narrowly @Suppress-ed with
a reason: androidx.security.crypto (EncryptedSharedPreferences/MasterKey),
androidx.privacysandbox.ui, WebView.databaseEnabled, BluetoothDevice
.connectGatt, media3 setEnableAudioTrackPlaybackParams, FirebaseMessaging
.token, and InputMethodManager.SHOW_IMPLICIT.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015Xb9YbBqhdZsHxMzitmyvn
LocalCache.notes is a soft cache, and a Concord rumor is decrypted exactly
once per session (the community session dedups re-delivered wraps), so a
kind-3302 edit left orphaned there could be GC'd on navigation and never
re-downloaded — the message would silently revert to its pre-edit text.
Resetting the channel EOSE doesn't help: the re-delivered wrap is swallowed
by the session's isNew dedup, so its rumor never re-emits.
Fix it the way reactions/replies already survive: attach the edit to the
message it edits. consume(ConcordChatEditEvent) now calls target.addEdit(note),
so the edit is held for exactly as long as its channel-retained message (and
released with it via clearChildLinks). observeConcordEdit reads note.edits
directly — author-matching, latest by CORD-02 §4 send time — instead of
scanning/observing the soft cache.
- Note: new hard-held `edits` collection + addEdit/removeEdit, wired into
clearChildLinks like the other child-event links.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013HdLnAa4Pa1pFV9FTYVTB6
Verified against the Concord v2 reference client (Soapbox Armada,
src/concord-v2/lib/kinds.ts): a chat message edit is a dedicated KIND_EDIT =
3302 rumor, NOT a kind-1010 modification. It names the target with a single
`e` tag (no `k` — Armada adds `k` only to deletes), carries the replacement
text, and rides the channel/epoch binding. The fold applies only edits
authored by the original message's author (latest by CORD-02 §4 send time
`created_at*1000 + ms`), non-destructively.
The prior commit used kind-1010 TextNoteModificationEvent, which would not
interop with Armada. Corrected:
- New ConcordChatEditEvent (kind 3302) in quartz, registered in EventFactory;
ChannelChat.edit now builds it. orderingMs() honors the `ms` remainder tag.
- LocalCache.consume(ConcordChatEditEvent) wires the edit to its target note
and invalidates the edits flow; findLatestConcordEditForNote returns the
author-matching kind-3302 edits ordered by send time (latest wins).
- observeConcordEdit reads that finder instead of the kind-1010 machinery.
Send/compose/action-sheet plumbing is unchanged (it routes through
ChannelChat.edit). Note: Amethyst does not yet emit the `ms` remainder tag on
Concord rumors (a pre-existing, message-wide gap), so its own edits order at
one-second granularity; received Armada edits are ordered at full precision.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013HdLnAa4Pa1pFV9FTYVTB6
Brings feed-post-style edits to Concord chat. A Concord message rumor is a
standard kind-9 event, so an edit reuses Amethyst's native kind-1010
TextNoteModificationEvent: a channel/epoch-bound rumor that e-tags the target
and carries the replacement text, wrapped and published on the same channel
plane as any other Chat Plane rumor. Receivers overlay the newest edit through
the existing shared machinery (LocalCache.findLatestModificationForNote), which
only applies edits authored by the original message's author, so a member can't
rewrite someone else's message. Clients that don't understand kind-1010 keep
showing the original text, so it degrades gracefully.
- ChannelChat.edit + ConcordActions.buildChannelEdit build/wrap the edit rumor.
- Account.editConcordChannelMessage gates to my own kind-9 messages and
publishes the wrap (local echo + relays), mirroring reactToConcordMessage so
the edit never leaks the private rumor id onto public relays.
- The chat bubble overlays the newest edit (RenderConcordEditedNote) with an
"(edited)" marker, matching the Buzz kind-40003 edit presentation.
- The long-press action sheet offers Edit on my own Concord messages; the
composer enters edit mode with an editing banner and publishes the edit on
send. The former onWantsToEditBuzz callback is generalized to
onWantsToEditChatMessage, shared by the Buzz and Concord surfaces.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013HdLnAa4Pa1pFV9FTYVTB6
Concord fetched a channel's messages only when its screen was open (the history
pager mounts on the channel screen), so an un-opened channel showed "No messages
yet" in the community list and never appeared in the Messages inbox — unlike
NIP-28 / NIP-29, which preload a last-message per room. Add a one-shot warm
drain, `Account.warmConcordChannelPreviews`, triggered on community-screen open
and app-wide per subscribed community from the account preload (both debounced
so the cold-boot fold burst warms once).
Per channel (`ConcordSubscriptionPlanner.channelPreviewFilters`):
- never read -> the newest `previewLimit` (10) wraps: a preview plus a rough
sense of how busy the channel is, without pulling the whole backlog.
- read -> everything `since lastRead - 1` (capped at `catchUpLimit`): the unread
badge is accurate and the missed messages are cached for on-open; the `-1`
re-includes the last-read message (its created_at == lastRead) so a caught-up
channel still shows a preview, and unread stays exact (the count is strict `>`).
Filters group by relay into one REQ per relay (one filter per channel); the
wraps ingest through the normal cache path, and the always-on plane subscription
keeps them fresh afterward. Full history still pages in on open.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
From an adversarial audit of the BOLT12-zap feature.
Security / correctness:
- Offer↔invoice binding: `cryptoVerified=true` was asserted even when the offer had
no `offer_issuer_id` or used blinded paths — cases where the invoice's node key is
payer-chosen and can't be tied to the offer. An attacker could self-sign a "verified"
proof having paid nothing. Now cryptoVerified requires the invoice to be provably the
offer's (issuer_id present, no paths, invoice_node_id == issuer); unbindable proofs are
accepted but flagged unverified, not verified. Definite contradictions still hard-reject.
- Counting: `updateZapTotal` now counts ONLY crypto-verified BOLT12 zaps. An unverified
(compressed / unbindable) proof carries a self-chosen preimage+amount with no settled-
payment guarantee, so counting it let anyone inflate a note's total for free. Unverified
entries stay stored + shown (dimmed), never summed.
- Dedup: `innerAddBolt12Zap` now honors the NIP's "count the LOWER amount for the same
payment hash" rule (was order-dependent last-writer-wins, inflatable by re-publishing a
bigger amount tag). Keeps the stronger verification flag.
- Precision: divide millisats in BigDecimal, so fractional sats survive and match the
millisat-native lightning column (was integer `/1000`, flooring sub-sat zaps to 0).
Codec hardening (quartz):
- TLV length now range-checked (was a signed compare that let a high-bit BigSize length
slip through and get truncated by toInt()).
- BigSize enforces minimal encoding (also rejects >=2^63 values that read back negative).
- bech32 alphabet membership is O(1) via a lookup table (was O(32n) indexOf per char).
UI:
- ReusableZapButton's "you zapped" gate now includes bolt12Zaps (and nutzaps/onchain),
so a BOLT12-only zap correctly shows the zapped state.
- The reactions gallery renders the blank/unknown author for anonymous zaps, matching the
standalone card (was showing the throwaway ephemeral key's avatar).
Tests: validator issuer-less-offer downgrade; TLV non-minimal-BigSize + oversized-length
rejection; model lower-amount dedup (both orderings), verified-only counting, and
fractional-sat survival. NoteBolt12ZapTest 6→8, Bolt12ZapValidatorTest 11→12, TlvTest 6→8.
The audit also surfaced a NIP-level gap that is NOT fixable in code and is captured in the
plan doc: there is no offer↔recipient-identity binding, so even a crypto-verified proof
only proves payment to the *embedded* offer, not to the p-tagged recipient.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SpgpWLKzgD7vS9Fs4CXTR3
Speed:
- Bolt12ZapValidator reorders checks cheap-to-expensive: all structural, cross-event,
and payer-proof binding checks run first; the schnorr signature + proof crypto
verifications run only once an event has passed them. A malformed or mismatched
event now rejects with zero schnorr ops. Cannot change accept/reject, only which
reason a doubly-invalid event reports.
- validate() gains verifyEventSignature (default true); LocalCache.consume passes
false since the relay pipeline already verified the outer event — removing a
redundant schnorr on every ingested zap (3 verifies instead of 4).
- Bolt12Merkle precomputes SHA256("LnLeaf")/SHA256("LnBranch") once and hashes the
per-call "LnNonce"||first-tlv tag once per rootHash instead of once per record.
Tests:
- New validator rejections: preimage-mismatch, invalid-invoice-signature,
payer-tag-mismatch, proof-does-not-match-offer, plus the verifyEventSignature
skip-flag both ways (fixture gains corruptPaymentHash / breakInvoiceSignature).
- New commons NoteBolt12ZapTest: millisat→sat total, dedup by payment_hash,
verified-not-downgraded-by-unverified, remove-by-source, clearChildLinks, and
combined totals.
Docs: quartz/plans/2026-07-23-bolt12-zap-interop-vectors.md captures the two
upstream-gated follow-ups (vector-driven interop test + compressed-proof merkle
reconstruction) for when lightning/bolts#1346 merges.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SpgpWLKzgD7vS9Fs4CXTR3
Wires the receiving side of NIP-XX BOLT12 zaps (kind 9736) into every place a
NIP-57 lightning zap is counted or shown. Sending is intentionally left for
later. Modeled on the lightning-zap scheme (synchronous, the proof carries the
amount, counted the moment it validates) rather than the onchain scheme (async
chain backend, PENDING/CONFIRMED, CONFIRMED-only) — BOLT12 proof verification is
a self-contained synchronous check, so no resolver/backend is needed.
Model (commons):
- Bolt12ZapEntry + Note.bolt12Zaps map keyed by the proof's invoice_payment_hash
(the spec dedup key); addBolt12Zap/removeBolt12ZapBySource; folded into
updateZapTotal (millisats → sats) alongside lightning/onchain/nutzap amounts;
wired into clearChildLinks, moveAllReferencesTo, removeNote,
hasZapsBoostsOrReactions, hasZapped, and the isZappedBy family.
Ingestion (LocalCache):
- consume(Bolt12ZapEvent): validate synchronously via Bolt12ZapValidator, then
addBolt12Zap on the resolved targets (e / a / profile); computeReplyTo and
live-activity channel routing branches; dispatch case.
Subscriptions: added kind 9736 to every filter carrying LnZapEvent.KIND
(notifications, replies/reactions to notes & addresses, profile received-zaps,
live-activity goal + messages, nest room + collectors, notification dispatcher,
shared NotificationKinds, app-functions).
Aggregation / notifications: UserProfileZapsViewModel (mapper), NotificationSummaryState
(both passes), NotificationFeedFilter (kinds, zap-receipt detection, payer author
resolution, muted-thread + own-event gates), NotificationKinds own-event exception,
ThreadAssembler.anchorsItsOwnThread, and the commons live-activity aggregators
(RoomZapsState, LiveStreamTopZappers, NestViewModel).
UI: RenderBolt12Zap standalone card (styled like the lightning card, labeled
BOLT12) wired into NoteCompose + ThreadFeedView; Bolt12ZapGallery in the
reactions row (payer avatars + amounts, unverified/compressed proofs dimmed);
reaction-row counter gate; KindNames / KindDisplayName entries.
Note: validated BOLT12 zaps are counted immediately; a compressed proof whose
signatures aren't yet verifiable (pending lightning/bolts#1346 merkle
reconstruction) is stored with cryptoVerified=false and dimmed in the gallery.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SpgpWLKzgD7vS9Fs4CXTR3
Cancelling a proof-of-work mining job used to silently discard the post
(the sign+broadcast continuation only ran on a successfully mined
template). Users had no way to publish the note un-mined once they'd
started waiting.
Now abandoning a template post asks what to do instead of discarding:
- The × on the mining banner opens a dialog with "Send without PoW",
"Discard post", or tap-away to keep mining. Only shown for jobs that
carry a plain un-mined fallback (template posts); opaque work jobs
(reactions, reposts, anonymous posts, gift wraps) keep the direct
cancel since they have no template to fall back to.
- The mining foreground-service notification gains a "Send now" action
that publishes every eligible queued post without proof of work.
Implementation: the queue keeps the un-mined publish continuation
alongside the miner. sendWithoutPow() sets a flag the worker picks up on
its next isActive poll; the miner aborts and the plain template is
published through the same sign+broadcast path the mined template would
have used, off the worker pool. PoWJobState exposes canSendWithoutPow so
the UI knows which jobs support it.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012kLVFV7ps4HfXDDJPNqi82
- docs(dm): note the profile Reports tab also reads reportsNamingUser
- refactor(dm): push report-tag typing to quartz and simplify the warning stack
- fix(dm): narrow report indexing and address final review findings
- perf(dm): resolve a 1:1 chat row's counterpart once per row
fix(dm): dedupe reporter avatars and align warning card styling
feat(dm): warn in the room when the counterpart is reported by a follow
feat(dm): expose a report-warning flow per user
refactor(reports): extract reusable reportTypeLabel composable
feat(reports): index author-named reports even when they target an event
feat(reports): add pure DM report-warning classifier
feat(reports): add additive reportsNamingUser index to UserReportCache
Batch of correctness, performance, and code-quality fixes across the Buzz
workspace feature surfaced by a full audit of the branch's modified files:
- ChannelNewMessageViewModel: agent auto-invite ran inside createTemplate(),
which sendDraftSync() calls per keystroke — so @mentioning a member
published real kind-9000 invites while still typing. Move the invite to the
send path (sendPostSync) and stage the pending mentions instead.
- AgentConsoleViewModel: fix a decryptCache read/reload race by guarding
reloadFromCache (not refresh) under the mutex; bound observerSeen growth.
- BuzzNewDmViewModel: broaden start()'s catch so signer/IO/timeout failures
surface as an error instead of leaving Start stuck on "Sending"; rethrow
CancellationException.
- BuzzPresenceState / BuzzAgentActivityState: replace per-record full-map
copies with persistent maps (structural sharing) to cut GC churn; the
StateFlow now holds the map directly.
- RelayGroupChannelListScreen / RelayGroupMembersScreen / RelayGroupTopBar /
RenderBuzzNotes: correct remember/LaunchedEffect keys so state rebinds when
the relay or channel changes.
- RelayGroupDiscoveryFeedFilter: hoist joinedGroupIds() out of the per-item
matches() loop.
- RelayGroupChannel / BuzzWorkspaceStates: @Volatile the fields read off relay
dispatcher threads.
- BuzzInviteMinter: build the request URL through HttpUrl.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J8KBSw6smQRyXLiWHeDsZ8
A Buzz DM is a relay-authoritative NIP-29 group whose messages carry no `p`
tag, so nothing made them eligible for the Notifications tab and nothing
fetched them app-wide (discovery was scoped to the open DM inbox, which only
pulls 44100 + 39000 — never the message bodies). Two halves fix that:
- NotificationFeedFilter now early-accepts a group chat message (kind-9 or
kind-40002 — the deployed relay uses both) when it resolves to a `t=dm`
channel whose 39000 participants include me, honoring the same "Messages in
notifications" toggle and never notifying for my own message. LocalCache
gains `getRelayGroupChannelForContent`, the read-only reverse-lookup this
needs (same serving-relay-then-single-channel keying as the consume path).
- An always-on discovery (BuzzDmDiscoveryPreload) subscribes 44100 #p=me across
joined workspaces into the new BuzzDmChannels registry and fetches each DM's
39000 directory; BuzzDmJoinedChatTailFilterAssembler then keeps those
channels' recent messages warm app-wide (reusing the joined-group #h tail),
excluding hidden DMs. Both mount in LoggedInPage. This is what makes a Buzz
DM show on Notifications / in push without opening the conversation.
Tests: BuzzDmChannels registry; and a LocalCache resolution test proving a
40002 and a kind-9 message both resolve back to their DM channel (and a
non-dm channel does not).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Completes the deferred items from the moderation & safety plan:
- Thread + Profile feeds now pass the real hidden lambda (via LocalDesktopIAccount),
so mutes hide replies-in-thread and profile-tab notes live. Thread root stays shown.
- 'Always show sensitive content' toggle: new PreferencesSensitiveContentSettings
(commons/jvmMain, java.util.prefs) backs DesktopIAccount.showSensitiveContentSetting
(null=blur / true=show, never false) + setAlwaysShowSensitive; unit-tested.
- ModerationSettingsSection in the Content Filters settings: the toggle + management
lists for muted users (unmute), hidden words (add/remove), muted threads (unmute),
driven by the live hidden-users flow so removing an entry un-hides immediately.
- Profile header overflow (MoreVert): Mute/Unmute + Report… (reuses ReportNoteDialog)
for other users on writeable accounts.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Desktop DesktopIAccount.isHidden()/isAcceptable() were stubs (false / deletion-only)
and DesktopFeedFilters never consulted them, so muting/blocking a user did nothing.
- Add DesktopHiddenUsersState: assembles the kind-10000 mute list (users, hidden
words, muted threads) + kind-30000 block list into a live StateFlow<LiveHiddenUsers>,
decrypting the private section via the shared Mute/PeopleListDecryptionCache.
- Wire DesktopIAccount.isHidden/isAcceptable + the content-filter fields to it.
- Chain !note.isHiddenFor(...) into every note-rendering DesktopFeedFilter
(global/following/custom/profile/reads/search/notification + thread replies).
- DesktopFeedViewModel re-invalidates the feed when the choices change, so mutes
hide live without a restart.
- Subscribe to the account's kind-10000 mute list in Main.kt so it hydrates.
Reuses the shared commons LiveHiddenUsers + Note.isHiddenFor; the chatroom DM list
already called isAcceptable, so DMs now enforce mutes too.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Brings the Buzz community + member screens closer to Buzz's own clients:
- Presence dots (BuzzPresenceState → online green / away amber) overlaid
on DM-row and member-list avatars; offline/unknown shows nothing rather
than implying we track a peer we don't.
- Community view sections (Channels / Forums) are now collapsible, each
channel row carries an unread dot (relayGroupChannelHasUnreadFlow) and a
star toggle; starred channels float to the top. Stars persist
device-globally (BuzzChannelStars + BuzzChannelStarPreferences), mirroring
the joined-workspaces store.
- Canvas editing: the canvas screen gains an edit mode that publishes a
fresh kind-40100 CanvasEvent to the channel's host relay (last-write-wins);
the top-bar canvas button now shows on any Buzz channel so an empty one can
be created.
- Bot "Working…" indicator: a process-wide BuzzAgentActivityState, fed by a
members-screen observer (24200) subscription, lights a live "Working…" line
next to an agent currently emitting frames; tapping opens the community's
Agent Console. Owner-scoped by nature (frames are #p=owner).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J8KBSw6smQRyXLiWHeDsZ8
A Buzz community member (kind 13534 roster / 8000-8001 deltas) can read and post
across every channel on the relay, but `RelayGroupChannel.membershipOf()` read
only the per-channel NIP-29 roster (39001/39002), so a community member/admin who
wasn't explicitly added to a private channel resolved as NONE and was wrongly
gated (Join lock, hidden composer).
Add `BuzzCommunityMembership`, a per-relay registry fed by the relay-signed NIP-43
events, and consult it as a Buzz-only fallback in `membershipOf` (mapped to MEMBER
only, never channel ADMIN, to avoid over-granting per-channel moderation). Wire
`LocalCache.consume` for kinds 13534/8000/8001 to update the registry (LWW on
created_at) and poke the relay's channels so the gate re-renders live.
This complements the open-channel fix: open channels no longer require membership
at all, and members of private channels are now recognized community-wide.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A Buzz workspace channel you can participate in still showed a Join lock and
"invite-only — you need an invite to post": `RelayGroupChannel.membershipOf()`
reads only the per-channel NIP-29 roster (39001/39002), and the UI treated the
`closed` metadata tag as invite-only.
But Buzz's write gate (buzz-relay `check_channel_membership`) is *member OR
visibility=="open"*: an open (non-`private`) channel accepts kind-9 from any
authenticated relay member with no per-channel join, and Buzz stamps `closed`
onto every channel — so `isClosed()` says nothing about who may post; only
`isPrivate()` reflects the write ACL.
Add `RelayGroupChannel.requiresMembershipToPost()` (Buzz open channels don't;
standard NIP-29 relays always do) + `canPost(pubkey)`, and route the composer,
threads FAB, top-bar Join button, and discovery Join button + invite-only badge
through it. Standard NIP-29 relays are unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A Concord community pinned to the bottom bar wouldn't load at all when its
private kind-13302 joined-communities list wasn't already cached: the tab and
its server screen stayed blank. The list often lives only on the community's
own relays (Armada/Vector publish it there, never to the user's outbox), and
the only fetch that looked beyond the outbox — importConcordCommunities — was
triggered solely from the Concord hub and never queried the community's relays.
Carry each pinned community's bootstrap relays on its BottomBarEntry.Concord
tab (captured from the joined-list entry at pin time) and:
- importConcordCommunities now takes extra relays and folds in the relays saved
on every pinned Concord tab, so the list is found where it actually lives;
- ConcordChannelPreload bootstraps app-wide: it fetches the list for any pinned
community we don't yet know, so the tab and server screen fill in without the
user ever opening the hub.
Once the list folds into the cache, ConcordChannelListState.liveCommunities
already surfaces it reactively (verified by a new late-arrival test) and the
plane preload picks the community up — so a late-arriving list with no local
backup now updates the tab and the Concord Channels screen.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RSiSXaHMEpuo3gcDuTZ24u
Kind 20001 is claimed by both BitChat's GeohashPresenceEvent and Buzz's
PresenceUpdateEvent. EventFactory's flat when(kind) could only route one, so
Buzz presence never materialized (parsed as a geohash event) in either
direction — this was the deferred "EventFactory collision".
Disambiguate inside the shared 20001 branch by BitChat's required `g` (geohash)
tag: present -> GeohashPresenceEvent, absent -> PresenceUpdateEvent. Verified
against the Buzz Rust ground truth (buzz-sdk build_presence_update + the relay's
synthesize_presence read form): Buzz presence carries the status in content plus
a `status` tag (client) or a `p` tag (relay-synthesized), never a `g` tag, and
BitChat presence always carries `g` with empty content. Both inbound parse
(EventDeserializer) and outbound signing (EventAssembler) route through this
factory, so one guard fixes both.
Make it usable, not just parseable: add BuzzPresenceState (process-wide latest
online/away/offline per subject, mirroring BuzzTypingState), a
PresenceUpdateEvent.subjectPubKey() accessor (the `p` tag or the author), and a
LocalCache branch that records presence and drops the ephemeral without storing
it. Tests cover both Buzz wire shapes, the BitChat guard, and latest-wins.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J8KBSw6smQRyXLiWHeDsZ8
- Auto-authenticate relays for Buzz workspaces the user explicitly joined:
their read-only #p=me channel/DM discovery is otherwise not first-party, so
the p-gated 44100/30622 reads were never served and workspaces stayed empty.
- Invite screen: two-state hand-off — join + pre-approve NIP-42, launch the
in-app window.nostr browser, then point back to the workspaces hub.
- DM inbox: add-member action (npub/hex dialog → kind-41011) alongside hide.
- Workspaces hub: leave-workspace overflow on each header.
- Elevate the Buzz surface with a shared BuzzBrand gradient design kit — hero
masthead with live workspace/channel stats, cohesive across screens.
- Drop the dead kind-41001 DM-conversation path: the deployed relay never
emits a queryable 41001, so BuzzDmRegistry is trimmed to the 30622 hidden
set and LocalCache stores DmCreatedEvent without registry bookkeeping.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J8KBSw6smQRyXLiWHeDsZ8
The earlier discovery layer read the NIP-29 joined list (kind-10009) and
kind-41001 — neither of which the deployed relay uses, so a joined workspace
rendered nothing. Rework it to the model live testing confirmed.
Enabling layer — persist joined workspaces:
- commons BuzzWorkspaces: process-wide set of joined workspace relays (Buzz
membership is server-side, so there's no join event to rebuild from). Joining
also marks the relay a Buzz dialect. Unit-tested.
- BuzzWorkspacePreferences: device-global DataStore that restores the set at
startup (so the app connects + authenticates + discovers on cold start) and
mirrors changes. Eager init in AppModules. BuzzInviteScreen now `join`s.
Quartz:
- BuzzChannelMetadata: read the relay's `t` channel-type tag ("stream"/"forum"/
"dm") and a DM's inlined `p` participants off kind-39000.
Discovery (both hubs now source from the relay's real signals):
- BuzzWorkspacesViewModel: fetch + live-subscribe kind-44100 member-added
notifications (#p=me) across joined relays → my channels; fetch each channel's
39000 metadata; keep the non-DM ones. BuzzWorkspacesScreen unions this with the
NIP-29 joined list.
- BuzzDmListViewModel: same 44100 discovery, kept where 39000 `t`=dm (participants
from the metadata `p` tags), minus the 30622 hidden set — replaces the dead
kind-41001 path.
- Account.openBuzzDm returns the relay-assigned channel id from the OK response
(`response:{channel_id}`); BuzzNewDmViewModel opens the chat from it instead of
polling 41001.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01J8KBSw6smQRyXLiWHeDsZ8
davotoula
Vitor PamplonaandClaude Opus 5
nrobi144andClaude Opus 4.8
vitorpamplonaandgithub-actions[bot]