The second half of the llama.cpp work: a session can now name a downloaded
model and talk to it. `llama-server` is spawned through the same transport
as any other driver, polled until the model is loaded, then driven over its
OpenAI-compatible streaming endpoint and translated into the same events
the Claude driver emits -- so the transcript, the SSE stream and the phone
need to know nothing new.
**The conversation is rebuilt from the transcript, not held in the driver.**
llama-server is stateless between requests, so the whole history goes with
every one, and the obvious place to keep it is a Vec in the driver. That
fails the requirement: memory in a driver is invisible to a second device
and gone on restart, and this app is meant to work across devices. Reading
it back also means the model is prompted with exactly what the phone was
shown -- including a reply that was interrupted half way, which is in the
transcript because the deltas were already emitted.
That leaves the Claude driver as the odd one out rather than this one: the
CLI's memory of a conversation is a cache in front of the same transcript,
not a second truth. Said so at the top of llama.rs, because it is the sort
of inconsistency that gets "fixed" in the wrong direction.
Session settings arrive as a driver-interpreted `params` map rather than
new typed fields, so the shared schema does not grow one dialect's
vocabulary. Context size, gpu layers and threads become server flags;
temperature and the rest ride on each request, so changing them need not
reload a model.
**Also fixes an orphan this feature would have created.** Drivers set
kill_on_drop, which covers a session being deleted -- but nothing drops on
the way out of a SIGTERM, so signalling the server left its children
running. For the Claude CLI that is untidy; for a llama-server holding a
model it is gigabytes belonging to nobody. The server now stops its
sessions on SIGTERM and SIGINT. Found by killing a test server and noticing
two 600 MB processes still resident.
Remote llama sessions are refused rather than half-working: the model is
reached over HTTP, and forwarding that port to an ssh host is the "reach
this port" operation the transport does not have yet.
Verified end to end against a real model: downloaded Qwen3-0.6B Q8_0
through the app's own download route, spawned a session on it, and held a
two-turn conversation -- "my favourite colour is teal" then "what is my
favourite colour?", answered "teal", which is the transcript replay doing
its job. Token counts arrive. An earlier attempt with the IQ2_XXS quant
produced fluent nonsense, which turned out to be the quantisation rather
than the pipeline: llama-cli produces the same from that file directly.
Four unit tests cover the fold and the path guard.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017xn8nHw1tw1R6PtiY1eEtw
The same move, for the same reason: this file is written and read by hand,
and JSON has no comments to say why a host is configured the way it is.
Both house rules come across with it, in config.rs's `format` module and
nowhere else -- a file is the *body* of the config, so no outer parentheses
and nothing indented for them, and `Some` is implicit, which is what makes
`skip_serializing_if` on every optional field load-bearing rather than
tidiness.
The switch is outright: there is no reader for the old format. That is
invisible everywhere except here, because this file holds the enrolled
token hashes -- starting empty leaves the phone unable to talk to the
server and looks, from the phone, like the config having been lost. So a
config.json left beside the new file is named in the log and left alone,
rather than read or deleted.
One wart, documented at DriverKind: the kebab-case spelling is the string
the phone compares against, so it stays, and the file pays for it with
`kind: r#claude-cli` -- a hyphen is not a RON identifier. Renaming the
variant would change what an already-installed build is talking to.
Verified: cargo test, cargo clippy --all-targets, and a real start against
a scratch state directory -- a hand-typed config with comments and a bare
`port: 2222` loads, and what the server writes back sits at column 0 with
no Some(...) in it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017xn8nHw1tw1R6PtiY1eEtw
gen-dev-cert.sh is gone. The server ensures its own certificates on start,
which removes a setup step to remember, a dependency on whatever openssl
was installed, and a second place for the "which addresses?" answer to
live -- the leaf now covers every local IPv4 plus loopback and the
emulator's host alias, so nobody maintains a hardcoded IP.
The split that mattered in the script is kept and now enforced by tests:
the CA is generated once and left alone, because the app pins it and
replacing it strands every installed copy; the leaf is cheap and reissued
every start, so covering a new address is a restart. Both are written
owner-only into a directory outside the repo.
Two things the tests caught. DirBuilder's mode applies only when the
directory is created, so a directory that already existed kept whatever
permissions it had while holding a private key -- the mode is now set
explicitly, in the session directories too. And loading the leaf into the
real RustlsConfig needs the crypto provider installed, which main does but
tests don't.
Verified end to end: deleted the certs, started the server, watched it
generate a CA and warn that installed apps now pin the wrong one, rebuilt
the APK against the new CA, and reinstalled -- the emulator connects over
a certificate that never existed as a pasted constant.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017xn8nHw1tw1R6PtiY1eEtw
GET /usage serves the numbers behind Claude Code's /usage, read with the
CLI's own stored OAuth credentials (nothing to configure). The endpoint
is undocumented, so parsing is defensive -- the generic limits[] array
becomes labeled window bars, unknown kinds surface under their raw name,
and any failure degrades to an 'unavailable' snapshot with the reason.
One UsageProvider per paid service behind a caching monitor that
enforces the >=180s minimum poll regardless of phone refreshes; no
background polling at all. ureq (rustls) does the outbound call, with
the process-level CryptoProvider now chosen explicitly in main -- ureq
brings ring while axum-server brings aws-lc-rs, and with both in the
graph rustls refuses to guess.
App: a Usage screen off the session list -- per-window bars colored by
utilization with relative reset times. Verified live: 74%/26%/16%
windows rendered against the real endpoint.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017xn8nHw1tw1R6PtiY1eEtw
Inbound: POST /sessions/{id}/attachments stores a picked photo under the
session; message attachmentIds become base64 image blocks in the
stream-json user message (verified live: an uploaded red PNG answered
"Red."). Outbound: image parts in tool results are decoded into the
session's files/ dir and referenced by Image events -- the transcript
stays lean -- and GET /sessions/{id}/files/{ref} serves them (verified
via the Read tool round-tripping the same PNG). The app grows an attach
button (system photo picker, upload-on-pick) and renders Image events
inline with an authenticated pinned fetch. Sent attachments are echoed
into the transcript as Image events so every device shows them.
Attachments and files are addressed under their session (a deviation
from PLAN.md's original bare /attachments -- recorded there) so their
lifecycle is the session directory's: deleting the session is still the
complete path out.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017xn8nHw1tw1R6PtiY1eEtw
The second driver behind the same trait: claude -p with stream-json both
ways, the hidden --permission-prompt-tool stdio flag (without which no
permission ever reaches a client), text deltas streamed from raw API
events, tool_use/tool_result mapped to tool events, and can_use_tool
control requests surfaced as Question events -- plain permissions as
Allow/Deny, AskUserQuestion as one Question per sub-question with the
chosen labels sent back in updatedInput.answers keyed by question text
(wire shapes pinned by live probes against CLI 2.1.237, recorded in the
module doc). The CLI session id is persisted per session dir, so a
backend restart respawns with --resume and loses nothing. set_model
rides the control protocol and persists through the manager; the spawn
screen grows model/cwd/permission-mode fields.
Also: the dev CA now carries proper keyUsage/basicConstraints
extensions (strict verifiers reject it otherwise) -- regenerated and
re-pinned before any real phone has installed the app.
Verified: 20 unit tests + clippy clean; scripted end-to-end over the
HTTP API (AskUserQuestion round trip, Bash permission allow, streaming,
restart with --resume remembering earlier work, delete); and on the
emulator, a live haiku session asking Tea-or-coffee and acknowledging
the tapped answer.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017xn8nHw1tw1R6PtiY1eEtw
The whole pipe behind one Driver trait and a common event model:
spawn/list/delete sessions, message + question answering, append-only
JSONL transcripts whose sequence numbers are the phone's resume cursor
(surviving backend restarts), bearer-token middleware wrapping every
route including the fallback, wg0-only binding that fails closed, and
first-run token enrollment via a terminal QR.
Verified: cargo test (10), clippy clean, and curl end-to-end over pinned
TLS -- auth rejection, spawn, streamed SSE replay/resume, /question
round trip, restart continuing seq numbers, delete removing everything.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017xn8nHw1tw1R6PtiY1eEtw
irisandClaude Opus 5