4 Commits

Author SHA1 Message Date
7f657ab099 feat(mesh): optional plain-TCP Reticulum interface (radio-less Aurora interop)
Adds an additive, loopback-only TCP server/client interface to
reticulum-daemon and the Rust mesh wiring, alongside the unchanged serial
RNode path. Aurora (~/aurora) already speaks standard RNS/LXMF over plain
TCP by default, the same way Sideband already proved interop over LoRa
(docs/RETICULUM-TRANSPORT-PROGRESS.md gates #2/#3) — this closes the gap so
that interop is provable without scarce LoRa hardware, and gives archy a
path to eventually be dialed by an Aurora client.

Verified: daemon TCP transport round-trip, bidirectional LXMF DM against a
scripted RNS/LXMF stand-in for Aurora's Dart stack (content + dest-hash
match both directions), cargo check/test -p archipelago green (108 mesh
tests, 0 regressions), and a real MeshService::start() end-to-end test
spawning the daemon in TCP client mode with no serial probe.

TCP server mode is hard-gated to loopback in both Python and Rust — WAN/LAN
exposure is a deliberate future decision, not part of this change.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-03 18:08:35 +00:00
archipelago
469b0203b7 fix(reticulum-daemon): die with parent to stop RNode-jamming pile-ups
The daemon ships as a PyInstaller one-file binary; its direct parent is the
bootloader, which the Rust supervisor (mesh/reticulum.rs Drop) stops via
start_kill() == SIGKILL. SIGKILL can't be forwarded, so the Python child was
orphaned on every link recreation and kept holding the RNode serial port.
These stale daemons piled up (9 seen on one node), all clutching /dev/ttyUSB0
and garbling the RNode so it silently stopped transmitting (txb frozen,
interface status False).

Set PR_SET_PDEATHSIG(SIGTERM) at daemon startup so the kernel signals us when
the parent exits; our existing SIGTERM handler then shuts down cleanly and
frees the port. Linux-only, best-effort, no-op elsewhere.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-01 16:14:55 -04:00
archipelago
0eb5c258f5 fix(mesh): Meshtastic 3ccc pkc_capable pill + Sideband image interop + critical CBOR wire-bloat fix
Merges in the meshtastic agent's now-finished work alongside this session's
continuation: stock-peer (3ccc) PKI-capability is now stamped through
get_contacts -> refresh_contacts -> MeshPeer.pkc_capable, so a directed DM to/from
a PKC-capable stock Meshtastic peer correctly shows the E2E pill on the Sent row,
not just received messages. Confirmed live: .198 sees "Meshtastic 3ccc" with
pkc_capable=true.

Also fixes two real interop/correctness bugs found while live-testing the
Reticulum <-> Sideband link:
  - Receive: the daemon only ever read LXMF's plain-text content, silently
    dropping native FIELD_IMAGE/FIELD_FILE_ATTACHMENTS fields — a stock
    Sideband/NomadNet photo vanished into a blank-space message. Now decoded
    into the same ContentInline typed envelope our own attachments use.
  - Send: images to a non-archy (stock) peer now use native LXMF FIELD_IMAGE
    instead of our own opaque CBOR wire format, which Sideband can't decode.
  - Root cause of a garbled MC-chunk-fragment bug: TypedEnvelope.v/.sig (the
    OUTER wrapper every message type uses) serialized raw bytes as a CBOR
    array-of-integers instead of a native byte string, bloating every
    message on the wire ~2-3.5x — enough to push even a tiny ReadReceipt
    over the 140-byte single-frame chunking threshold. Root-caused by
    reading ciborium's deserializer source directly (deserialize_bytes only
    works within its internal scratch buffer; deserialize_byte_buf streams
    unbounded).

Frontend: consolidated the attach/record buttons into a single animated "+"
menu (was overflowing the compose row).

857/857 tests pass. Verified live across all 5 deploy-roster nodes.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-06-30 22:07:45 -04:00
archipelago
f54c853128 feat(mesh): Reticulum LoRa hardware gates pass + RNS Resource transfer + image/voice attachments
Phase 0 gates #2/#3 (two-node LXMF-over-LoRa, external Sideband interop) passed
on real hardware (.116's flashed Heltec V3 RNode <-> a phone-flashed RNode running
Sideband) — RNS announce, encrypted DM round-trip, and contact binding all verified
live. Fixed two bugs found in the process: the Reticulum send path wasn't stamping
outbound messages as E2E despite LXMF being unconditionally encrypted, and the
per-message transport pill collapsed Meshcore/Meshtastic into one generic "lora"
color instead of distinguishing the three radio transports.

Built on top of that link: a Columba-style image/file send experience —
compression-quality presets with a real transfer-time estimate (mesh.transport-advice,
now device-throughput-aware), receive-side thumbnail previews + auto-render for
already-local attachments, and async voice messages, all reusing the existing
ContentRef/ContentInline attachment pipeline. The headline addition is genuine RNS
Resource transfer support (daemon-side RNS.Link + RNS.Resource, Rust-side
send_resource/resource_recv plumbing, a new "resource-mesh" transport-advice tier)
so compressed photos up to 2MB now actually transfer over LoRa for Reticulum peers
instead of always falling back to Tor past the small inline-chunk cap.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-06-30 19:57:01 -04:00