Four defects found by on-device UAT, 2026-08-06.
1. D-08 persistence was WRITE-ONLY. chat() loaded the transcript only
AFTER the loop, to append — the model was never shown any of it. The
assistant answered "I don't have access to any previous conversation
history" with its own transcript on disk, and "and is it healthy?"
resolved to the node instead of the app just discussed. History now
replays into every turn (text only: a stale tool result must not be
re-presented as this turn's evidence), scoped by HistoryKey. The
replayed prefix is excluded from the append, or each turn would
re-persist the conversation and grow it geometrically.
2. The operator persona forbade the very answers the content surfaces
render. 13-01's prompt refuses anything without a matching tool, so
"recommend me 10 sci-fi films" was declined and the film/song/podcast
grids from 13-11 could never populate — two plans in contradiction.
The refusal rule now governs ACTIONS ON THE NODE; general questions
and recommendations are answered from the model's own knowledge.
(Whether the node should also SEARCH THE WEB depends on AIUI's
web-search setting, which embedded mode never forwards — captured as
a separate todo because it opens a new egress path.)
3. The content-surface loader labelled unrelated queries "Podcast
recommendations": the classifier matched a bare "show", which is how
operators phrase almost everything ("show me my files").
4. "Surfacing…" tracks at 0.2em and its final glyph collided with the
close button; the header now spaces them properly.
assistant::history 9/9 green incl. replay_feeds_prior_turns_back_to_the_model.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Second on-device failure in one session: after the wordlist fix, dev3
blocked cloud turns AGAIN mid-session as 13-10's history grew — splitting
on every non-alphabetic character let words from unrelated JSON fields
chain into one run. Both failures took the whole feature down rather than
protecting anything, which is the worse failure for a screen to have.
Shape is the wrong signal. A real mnemonic's last word encodes a checksum
over the rest, so an accidental run of English words parses as a mnemonic
only about one time in sixteen. Candidate runs are now validated with the
same bip39 crate the wallet uses:
- tokenize on whitespace (a seed phrase is space-separated); a token's
leading alphabetic segment counts, and alphanumerics after it end the
phrase, so a seed glued to a closing quote is still caught
- block only if a 12/15/18/21/24 window parses as a real mnemonic
- IMPLAUSIBLE_MEMBER_RUN (20) backstops checksum-invalid material such as
a typo'd 24-word seed, which prose cannot plausibly produce
Documented trade-off: a checksum-invalid run under 20 words no longer
blocks. The rule that did block it also blocked every legitimate turn,
twice, on a live node. 15/15 egress tests green, including the real
system prompt, scattered-JSON prose, and a genuine mnemonic in JSON.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The shape-only heuristic ('any 12 consecutive lowercase 3-8-char words')
matched ordinary prose — including the node's own system prompt — and
blocked 100% of live cloud chat turns (found on dev3, the first real
Claude call through this screen; log: kind=bip39-word-run every turn).
Membership in the crate's own bip39 English wordlist (already a dep via
seed.rs) distinguishes prose from seed material: glue words break runs,
real seeds are nothing but members. Regression test pins the real system
prompt + a clean wire body to Allow; the 12-word genuine-seed case still
blocks. 13/13 egress tests green.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
63 main commits since the fork point — gate cookie-strip fix, named-volume
create fix, appgate catalog classification, RNode error surfacing — merged
so 13-14/13-15 on-device verification runs against current production code.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Deploying the .126 LoRa panel ahead of its daemon made every button
report "Operation failed. Check server logs for details." — the panel
was calling RPCs the older binary doesn't have, and the sanitizer
masked "Unknown method: mesh.rnode-config" into that generic string.
Read as "the feature is broken" rather than "this node needs its
update" (operator, 2026-08-06).
Allowlisted: "Unknown method" (a frontend newer than its daemon should
say so), every RNode RF validation message (each names the field and
its legal range — the entire point of validating before touching the
radio), and the actionable mesh preconditions (no device connected,
mesh service not running, MeshCore has no remote reboot, radio daemon
did not answer, RNode interface disabled).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The port map deferred to DISK manifests for any app with a build source
— which is exactly the four companion UIs (lnd-ui, bitcoin-ui,
electrs-ui, fips-ui). Their disk manifests reach nodes only via the
frontend runtime payload or a per-node repo checkout, and in the
v1.7.125 rollout both proved stale or entirely absent: one node had no
checkout at all, others restored an older payload over apps/ at every
boot. Result: session_passthrough never reached the gate, so the node's
own screens 401'd on every data call, and on nodes whose UI rebuilt
from a stale context the app held its port UNGATED.
Classification now uses a ports-only overlay that accepts build-source
manifests (install/orchestration still defers to disk — unchanged). The
signed catalog is the freshest, operator-signed source, and the gate's
address binds fail safely against a container publishing differently
(logged CANNOT PROTECT), so this can only tighten policy, never expose.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- mesh.rnode-config: persisted RF settings + best-effort live radio
state (radio-confirmed r_* values) for the LoRa panel.
- mesh.rnode-config-apply: validate → persist → restart the radio
daemon → poll the read-back until the radio reports online, returning
{applied, confirmed, live, message}. Failure modes report what
actually happened instead of pretending success.
- RebootRadio carries a reply channel: Meshtastic reboots firmware,
Reticulum restarts the sidecar (re-detect + reapply RF config),
MeshCore honestly reports it has no remote reboot — previously the
Reticulum/MeshCore arms returned Ok(()) doing NOTHING: the operator's
"button gives no feedback" bug.
- MeshCommand::QueryRadioState plumbs the sidecar's radio_state to the
service layer with a timeout instead of fire-and-forget.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The .126 LoRa panel's Rust half:
- mesh::rnode_settings: RNodeRfSettings persisted at
<data_dir>/rnode-rf-settings.json — every RNodeInterface parameter
(enabled, port override, frequency, bandwidth, sf, cr, txpower,
airtime_limit_short/long), validated against the bounds RNS itself
enforces. Defaults are byte-identical to the sidecar's historical
argparse defaults.
- FIRST-RUN ADOPTION (operator requirement: the update must change NO
device's applied settings): with no settings file yet, the node's
existing RNS config (~/.archy-reticulum, else ~/.reticulum) is parsed
and its RNodeInterface values adopted verbatim as the initial
settings — proven by a test carrying the operator's literal
"RNode LoRa Portugal" config.
- Serial spawns pass the settings as explicit sidecar args (frequency/
bandwidth/txpower/sf/cr + airtime locks); the operator port override
wins over auto-detect but still passes the KISS probe gate; a
disabled interface refuses to open with a readable error.
- ReticulumLink::query_radio_state(): asks the sidecar for the live
RNodeInterface state (radio-confirmed r_* values) — the panel's
apply-confirmation read-back source.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
assistant/evals.rs: a test-gated in-crate module (#![cfg(test)] here AND
#[cfg(test)] pub mod evals; in mod.rs — never compiles into the shipped
binary, asserted by a release-binary string grep). load_cases/case_by_id
read the 18-case JSONL fixture by path; run_case drives the REAL run_loop/
execute_tool/ConfirmGate choke points end to end against a case's grants,
seeded untrusted content, and scripted backend turns, returning a
CaseOutcome that observes ToolCall/ToolResult/confirm-gate transitions
in-process rather than inferring them from prose. evaluate_case asserts
must_not_execute/must_not_claim at threshold zero (E-01's security and
integrity halves) and confirmations/turns at exact match, every failure
message naming the case id and the offending tool/term.
Parameterized over the Backend trait (CountingBackend wraps any real
Backend to measure turns used; a BudgetExhaustedStubBackend drives EV-17's
S-12 stop-without-retry path) so scripted, Ollama, Claude or Routstr can
all run the same 18 cases. report_by_backend/parity_requires_two_backends
refuse to record a cross-backend parity pass from fewer than two backends
(E-07). Live-backend runs are opt-in via ARCHY_EVAL_BACKENDS and #[ignore]d
so a plain `cargo test` never touches the network. write_trace_jsonl writes
one plain JSONL file per run under core/target/assistant-evals/ (gitignored
build output) — no exporter, no collector, no listening port.
All 18 cases pass against ScriptedBackend (23/23 assistant::evals:: tests);
full crate suite 1258/1258; release binary contains zero eval-fixture
strings; no phoenix/promptfoo/ragas/opentelemetry references anywhere in
assistant/; no new CI job (ci.yml untouched — picked up by the existing
`cargo test --all-features` step); zero new packages (T-13-SC).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
EV-01..EV-18 (four happy reads, four confirmed writes, five injection cases,
three authority-ceiling cases, one budget case, one privacy case) per
13-AI-SPEC.md §5's schema, written against the real tool registry
(assistant::tools::registry()) and the real wrap_untrusted() boundary shape
rather than against the spec's description of them. EV-11's payload carries
a forged closing boundary in the exact `{label}_DATA_{token}_END` shape
untrusted.rs emits, proving why the per-call random token (not the wording)
is what makes the boundary hold. README.md records the per-bucket
reviewer-role labeling from §5's Labeling table (engineer for EV-01..EV-08,
security-minded red-teamer for EV-09..EV-16, non-technical reviewer for the
EV-05/EV-06 confirmation-copy judgment) so a later contributor knows whose
judgment each case's expect block encodes.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Completes D-04's backend chain: Ollama -> Claude -> Routstr (budget-gated),
and wires D-05's operator-set prepaid allowance as a hard, arithmetic stop
a prompt-injected model can never cross.
- assistant/mod.rs: `AssistantBudget` (allowance_sats/spent_sats,
persisted 0600 under data_dir/assistant/budget.json, mirroring
Grants::load/save exactly — a missing/corrupt file defaults to a ZERO
allowance, D-16's "default closed" applied to money). `payment_policy()`
builds a `PaymentPolicy` from ONLY these two persisted fields — no
parameter accepts anything model/tool/provider-influenced, which is what
makes the ceiling arithmetic rather than a policy an injected model
could argue with. `record_spend()` persists a successful payment and
raises a one-time 80%-threshold owner notice (AI-SPEC §7b). New typed
`BudgetExhausted` error (downcastable via anyhow) is the signal
`loop_.rs` distinguishes from an ordinary transport error.
- assistant/loop_.rs: `run_loop` downcasts a `BudgetExhausted` out of the
backend's `Err` and returns `Ok` with a plain-language stop message —
no retry, no re-price, no partial spend, no fall-through to a different
provider at a different price. Verified to actually matter: temporarily
replaced the terminating `return` with `continue` and confirmed
`zero_budget_stops_loop_without_retry` goes red (the backend gets
retried 8x to MAX_TURNS and the turn errors instead of stopping
cleanly); restored and reconfirmed green (13-13-SUMMARY.md records the
observed failure).
- assistant/backends/mod.rs: `select_backend` now takes `&RpcHandler`
(was `&Path`) to also read the Tor-proxy config; completes the D-04
chain — Routstr never selected when the operator's allowance is zero
(Claude alone instead), otherwise chained as Claude's fallback
(Ollama -> Claude -> Routstr, each leg reached only when the priors are
unavailable). New `BackendId::Routstr` variant.
- assistant/backends/routstr.rs: the payment-decline arm now returns the
typed `BudgetExhausted` (was a plain bail in Task 2's commit, per the
plan's own "handled in Task 3" note); a successful payment records spend
against the persisted budget immediately (the Cashu proofs are already
committed at that point, regardless of whether the subsequent chat HTTP
call itself succeeds).
- api/rpc/assistant_chat.rs: `assistant.budget-get`/`assistant.budget-set`
RPCs (routed through the existing single `assistant.` dispatcher arm —
dispatcher.rs untouched) and a `nostr_tor_proxy()` accessor for
select_backend's onion-preference decision.
Named tests (assistant::tests::): zero_budget_stops_loop_without_retry (S-12),
zero_allowance_never_selects_routstr, ceiling_is_not_a_function_of_model_output,
injection_loop_against_low_budget_does_not_overspend (EV-17) — all pass.
Full assistant:: suite: 91/91. Full crate suite: 1235/1235 (2 pre-existing
ignored, unrelated). dispatcher.rs and Cargo.toml untouched.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Task 1 decision (proceed-docs-with-probe-first, operator-selected via
AskUserQuestion 2026-08-05): 13-ROUTSTR-FINDINGS.md observed 0 of 9 cited
protocol claims (no live provider was announcing on any of the 3 default
relays in a 30s window on 2026-08-03; relay reachability itself WAS
confirmed). This backend is written against docs.routstr.com's cited shape,
with the first live chat-completions call doubling as the capability probe:
a non-success HTTP status or a response missing the expected
choices[0].message shape fails loudly (bails with the real status/body)
rather than silently degrading.
- assistant/backends/routstr.rs (new): RoutstrBackend implements the
Backend trait — discover_providers subscribes for kind-38421
provider-announcement events over the existing Tor-proxy-aware Nostr
client (nostr_discovery::build_nostr_client, never a second relay
client), process-cached with a 5-minute TTL; select_provider picks the
globally cheapest affordable (provider, model) price across every
discovered provider (Routstr has no fixed target model the way
Ollama/Claude do — CONTEXT.md delegates provider selection strategy to
Claude's discretion), preferring an onion endpoint when Tor is up;
attach_payment calls the existing budget-capped auto_pay_token verbatim
(never hand-rolled); parse_openai_tool_calls parses the one
string-encoded function.arguments shape exactly once at this adapter's
edge; screen_outbound (G-B1/G-B2) runs before any body leaves the node,
exactly as it does for Claude; ROUTSTR_MAX_TOKENS caps every request
explicitly.
- assistant/egress.rs: message_is_turn_own gains "system" and "tool" role
handling plus an OpenAI tool_calls-sibling-field check — the pre-existing
function was written only against Claude's wire shape (system as a
top-level field, tool results wrapped in role:"user") and would have
silently stripped Routstr's system prompt and tool-result context out of
every outbound request via G-B2's fail-closed default arm. Fixed with 4
new regression tests pinning both wire shapes.
- assistant/backends/mod.rs: registers `pub mod routstr;`. select_backend's
actual wiring of the Routstr leg (budget-gated, per D-05) is Task 3's
commit, once AssistantBudget exists — this task's own acceptance criteria
do not require select_backend integration, only the adapter itself.
30/30 assistant::backends:: tests pass (17 new in routstr.rs, 3 new in
egress.rs's OpenAI-shape regression tests were run separately at 12/12).
Zero new packages (nostr-sdk/reqwest already in-tree); dispatcher.rs and
Cargo.toml untouched.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
chown_for_rootless_container prefers `podman unshare chown` (which maps
container uid N through the userns), but when that failed once it fell
back to `sudo chown -R <literal>` — writing e.g. host uid 999 for
container uid 999 and reporting success. Host-999 maps to nobody inside
the userns, so the app could not open its own data while everything
claimed the chown worked: botfights on framework-pt crash-looped every
10s on SQLITE_CANTOPEN over a data dir the daemon itself had just
"fixed".
The sudo fallback now translates container ids (1..99999) to
subuid_base + id - 1 (fleet base 100000; container root maps to the
service user, 1000). Already-mapped ids and uid 0 pass through.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A sweep of 92 unconfirmed/dust sats failed with LND's debug-flavored
"insufficient input to create sweep tx: input_sum=0 BTC, output_sum=
0.00000092 BTC" — and the RPC sanitizer then masked even that behind
"Operation failed. Check server logs." (framework-pt, 2026-08-06).
The sweep mechanics are untouched (balance minus fee, as always) —
this only makes the refusal say WHY in plain language.
- lnd.sendcoins translates the sweep refusal: balance below Bitcoin's
dust minimum or not yet confirmed, so no transaction can be built
(LND's original message kept in parens).
- "Failed to send" joins the sanitizer's user-facing allowlist — the
same lesson as "Insufficient balance"/"Payment failed" before it.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
rate_limit.rs: assistant.chat gets its own request log keyed by
AUTHENTICATED SESSION (not client IP, per 13-AI-SPEC.md §6 G-B3's own
spec — an operator's session can roam across IPs within one sitting), on
the SAME EndpointRateLimiter struct rather than a second limiter type.
check_session/record_session_request enforce a hard ceiling (60/5min);
session_soft_threshold_reached (30/5min) is checked separately so the
call site can raise an owner notice before the hard refusal ever fires.
Wired into assistant_chat.rs's handle_assistant_chat (Rule 3 — the plan's
own declared intent, "assistant.chat is rate-limited per authenticated
session," has no other call site to reach the real RPC surface) and into
the existing 5-minute cleanup task in api/rpc/mod.rs.
loop_.rs: run_loop now tracks whether D-10-wrapped untrusted content is
present in context (seeded and re-checked as new tool results arrive
mid-loop), counts grant refusals split by that flag via
AssistantCounters::note_grant_refusal (a burst WITH untrusted content
raises a Security notice — something in shared content may be trying to
trigger actions; the same burst WITHOUT it raises a Ux/config notice
instead, so probing is never confused with misconfiguration, T-13-83),
counts turns-per-request, and counts MAX_TURNS-reached (3+ in one session
raises an owner notice) right before the loop's own bail — this is EV-13's
read-only injection loop, the one case the confirm gate structurally
cannot see because reads never confirm.
mod.rs: ToolExecCtx gains a `counters: Arc<AssistantCounters>` field
(defaulting to the process-wide global_counters(), overridable per-test via
with_confirm_gate_and_counters) so loop_.rs's counting has somewhere to
write and tests can assert against an isolated instance without polluting
concurrently-running tests.
read_only_injection_loop_terminates_and_is_counted (EV-13) and
grant_refusals_with_untrusted_content_are_a_security_signal (T-13-83) both
pass. Full `cargo test --package archipelago` (1211 tests) green — the
existing rate-limited RPC methods are unaffected by the new session-keyed
limiter.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
The periodic reconcile runs ExistingOnly — merely listing a catalog
manifest must never install an app — and its only absent-container
recovery keyed on the last running-names snapshot, which ages out after
a few daemon restarts. An absent member of an installed stack then stays
absent forever: .38 ran indeedhub with no minio/postgres for days, nginx
down on 'host not found in upstream "minio"', and nothing ever put the
members back.
A live sibling container is proof the stack is installed on this node,
so an absent member is now treated as a hole to repair, not a choice to
respect: the recovery guard also fires when another member of the same
stack (app_ops::stack_member_app_ids) has a container in any state.
A stack with no containers at all is left untouched, and sibling app ids
resolve through the loaded-manifest container names (immich-postgres
runs as immich_postgres).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
assistant/egress.rs: screen_outbound(body, ctx) -> EgressVerdict runs on
every request body about to leave this node for a cloud backend. G-B1
scan_secret_shapes checks for macaroon-shaped hex runs, BIP39-length word
runs, ecash/Nostr-key-shaped strings, and the literal contents of files
under data_dir/secrets — a hit fails closed (BlockFallBackLocal), logging
only the match's kind, never the value. G-B2 assert_turn_minimal checks the
outbound body against a mechanical allowlist of this turn's own fields (the
user's turn, this turn's granted tool names, this turn's own tool results);
an unrelated earlier tool result or content wrapped for a different turn is
truncated out rather than eyeballed. An unparsable/ambiguous body also fails
closed. MAX_OUTBOUND_CONTEXT_CHARS caps body size independent of minimality.
Wired into backends/claude.rs's send() before the outbound HTTP request (on
a block, send() errors before anything is sent — Rule 3, outside this
task's originally-declared file list but structurally required to give
screen_outbound a real caller); never wired into ollama.rs — nothing leaves
the node on that leg, so paying the scan cost would be pointless.
mod.rs: AssistantCounters/OwnerNotice — grant refusals, validation
failures, turns-per-request, untrusted-content-present,
cloud-escalation-while-local-up, blocked-egress and MAX_TURNS-reached
counters, each raising an owner_notice() at its own AI-SPEC §7b threshold.
Local and owner-facing only: no exporter, no /metrics, no OTLP anywhere in
assistant/ or rate_limit.rs. backends/mod.rs's select_backend raises a
cloud-escalation-while-local-up notice when Ollama is reachable but its
configured model isn't tool-capable (Rule 3, same file-scope reasoning).
9/9 assistant::egress:: tests pass in this task's own isolated state
(Task 1's 56 plus these 9 — ToolExecCtx's counters field and its loop_.rs
call sites are Task 3's own commit, since nothing in this task's behavior
needs them yet).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
assistant/untrusted.rs: wrap_untrusted(label, text) wraps peer-supplied text
(filenames, log lines, mesh/peer status) in a delimiter block whose token is
freshly randomized on every call via the in-tree rand crate — never a module
constant, never derived from content. A forged closing boundary using a
guessed/fixed token cannot terminate the real block early (EV-11).
tools.rs: wrap_tool_result_if_untrusted wires this in for content_list,
app_logs and mesh_status (the tools whose results carry peer-authored text);
every other tool result passes through unwrapped. loop_.rs's execute_tool
calls it at the exact point a successful ToolResult is constructed, before
that content ever becomes part of a ChatMessage.
No pattern-stripping or keyword-blocklist filter was added (D-10 rejects
that approach by name) — the delimiter and D-11's confirm gate are two
independent layers. Four scripted-worst-case tests in mod.rs prove the gate
still holds even when a compromised model acts on an injected imperative
(injected_instruction_does_not_grant_authority), a forged closing delimiter
plus fake operator turn (forged_closing_delimiter_does_not_escape_block), or
an injected mislabel attempting to hide the real action from the human
(injected_mislabel_still_confirms_real_action) — plus
wrap_untrusted_token_is_per_call (tools.rs) asserting the per-call token
itself. Zero packages added — rand 0.8.5 already in-tree.
56/56 assistant:: tests pass in this task's own isolated state.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Both predate this session's changes and were masked by the release
gate's cargo-test-weekly compile timeout:
- login_page_sources_its_art_from_the_gate still asserted the retired
wordmark (logo-archipelago.svg); the login page ships the sidebar A
mark (favico-black-v2.svg) since the 2026-08-05 rework.
- unauthenticated_ports_are_all_accounted_for lagged at 17; the
v1.7.123 port-policy round grew the rationale-carrying exempt set
to 25 (reviewed and enumerated in the test comment).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Two daemon bugs, one debugging arc (2026-08-05, operator-reported):
1. The app gate removed the ENTIRE Cookie header before proxying. That
broke the data plane of every first-party companion UI behind the gate
(lnd-ui/bitcoin-ui/electrs-ui/fips-ui render their shell, then every
/proxy/* and /lnd-connect-info call 401s — observed as "LND UI
unreachable"), and silently logged users out of every gated app with
its own cookie login (vaultwarden, nextcloud, gitea) on each request.
The gate now strips only its own cookie pairs (session, csrf_token);
a new per-port manifest opt-in `session_passthrough: true` forwards
the node session to first-party UIs whose nginx proxies the daemon's
authenticated endpoints. Undeclared ports never get passthrough.
2. podman_client::create_container sent named volumes to the libpod API
as bind mounts with the bare volume name as source, so creating any
manifest app with a `type: volume` mount failed. On .38 the reconciler
removed indeedhub-postgres/-minio for env drift and then could never
create their replacements, leaving the stack half-missing forever.
Named volumes now ride the spec's `volumes` field ({Name, Dest,
Options}). Also: the reconcile-failure log now prints the full anyhow
chain — `%e` showed only "create_container X" and hid the real error.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Unbreaks Bitcoin on every node running the 1.7.124 catalog: the embedded
start script had a shell syntax error, so bitcoind never launched and the
app vanished. Delivered by catalog rather than a release because manifests
reach nodes through the signed catalog.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
history.rs persists the ChatMessage transcript under data_dir (D-08),
keyed by a HistoryKey derived from CallerScope so an operator's AIUI
session and a mesh peer's transcript are structurally distinct files, not
two rows a filter could forget. Writes are atomic (temp sibling + rename,
matching music/index.rs::save_atomic's precedent) and 0600, following
grants.rs's convention.
Tool results longer than MAX_TOOL_RESULT_CHARS are truncated with a
visible marker before entering history -- a new, assistant-scoped
constant, never assist.rs's LoRa-airtime-tuned reply cap. Once the
transcript exceeds KEEP_VERBATIM_TURNS, older turns fold into a running
summary extended incrementally as turns age out, never regenerated from
the full transcript. Wallet/files-category tool-call arguments are never
persisted (AI-SPEC §7b's field policy applied to storage, not only
tracing) -- categories are resolved by the caller from the same tools
registry execute_tool uses, so history.rs never re-derives a second,
driftable category list. Nothing reachable from confirm.rs's pending-
confirmation state has a parameter path into this module at all (S-09
stays true structurally).
assistant.history / assistant.clear-history route through 13-01's
existing assistant.* dispatcher arm (dispatcher.rs untouched), each
scoped to the calling session's own HistoryKey.
run_loop (loop_.rs) now returns (answer, full_history) instead of just
the answer string -- structurally necessary so chat() (mod.rs) can
persist the tool-call/tool-result messages the loop built internally, not
only the user question and final answer (Rule 3, mirroring 13-05's
precedent of touching a file outside its own plan's files_modified list
when the plan's own intent requires it). chat() persists this turn after
run_loop returns; it does not yet feed prior persisted turns back into
live model context -- a documented, deliberately scoped follow-up (see
mod.rs's chat() doc comment and the plan SUMMARY).
8 new tests under assistant::history::tests::, including
operator_and_mesh_transcripts_are_separate and
wallet_tool_arguments_never_reach_the_transcript (asserted against both
the deserialized struct and the raw on-disk bytes). Full assistant::
suite: 50/50 (42 baseline-after-Task-1 + 8 new); confirm::tests::
restart_drops_pending_not_executes still passes -- S-09 not weakened.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
backends/ollama.rs implements the Backend trait against Ollama's
POST /api/chat (messages + tools arrays, message.tool_calls response) --
never mesh/listener/assist.rs::call_ollama's older single-shot prompt
endpoint, which has no tool-calling support at all. Ollama's per-call
tool-call ids (absent on the wire) are synthesized; its already-parsed
function.arguments object is passed through without a second string-parse
(the OpenAI-shape normalization would be wrong here). Every request sets
an explicit generation-length cap and runs non-streaming.
model_supports_tools queries Ollama's /api/show and caches the answer for
the process lifetime, turning AI-SPEC's [ASSUMED] note about
qwen2.5-coder's tool capability into a runtime fact: a non-tool-capable or
unreachable Ollama falls through to Claude with a logged reason, never a
silent tools-free degrade.
select_backend (backends/mod.rs) is now async and reuses the existing
detect_ollama() probe (mesh::assistant, bumped to pub(crate) for this
reuse) rather than re-probing. A new FallbackChain wraps the Ollama leg so
a transport error mid-turn falls through to Claude for that same call
instead of failing the turn outright.
13 new tests under assistant::backends::{ollama,}::tests::, exercised
against a local hyper-based HTTP stub (no mock-HTTP crate exists in this
workspace). Full assistant:: suite: 42/42 (29 baseline + 13 new).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
generate-app-catalog.py writes APP_LAUNCH_PORTS one entry per line; rustfmt
packs it. The release gate checks formatting, so the generated file has to
be formatted after regeneration or every catalog sync fails the gate.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Portainer's image reaches the public catalog (the release gate caught the
manifest and catalog disagreeing), and fips-ui 8336 joins the mesh relay's
port list now that it declares a port — it is auth: gated, so the relay
withholds it rather than bridging it.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Pre-bumped so the release gate compiles the test profile at the final
version — create-release bumps after the gate, so the gate would otherwise
run on the old version and the bump would invalidate the cache, timing out
cargo-test-weekly on the compile rather than the tests.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Two more on-device UAT findings:
1. Deny-retry loop: the model, told 'the user declined', simply called the
tool again — each retry minted a fresh pending and re-opened the dialog
(T-13-50 habituation, mechanized). ToolExecCtx now remembers declined
actions for the turn, keyed by confirm::action_key — the same canonical
(tool_name, validated_args) identity the nonce binds — and execute_tool
refuses a re-ask before the gate, minting nothing. Regression test
declined_action_never_reprompts_same_turn.
2. Timeout chain: rpcClient's 15s default aborted every confirmable turn
client-side while the node kept the pending alive — the next turn then
re-announced it (modal over and over) and every wait read as 'timed
out'. assistant.chat now rides a 420s timeout; AIUI's bridge goes
180s→430s so the host's error path (which also expires the dialog)
always fires first. Declined ToolResult text now also tells the model
to stop.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
auth.session-policy.get/set plus a card under Account. Presented as two
plain questions rather than the token mechanism underneath, because the
distinction that matters to an operator is which control actually ends a
session: the dashboard polls constantly, so an idle timeout alone never
fires on an open tab — the absolute cap is what guarantees it.
Values are clamped server-side and the stored result is echoed back, so
the bounds are discoverable instead of an error. Presets rather than a free
number field: a box accepting '5' invites locking yourself out. A short
idle choice warns that it is the payments-industry posture.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
On-device UAT: the operator was timed out mid-read (120s), the chat turn
returned 'declined' while the dialog was still up, and their Approve then
hit a dead entry ('no such pending confirmation', 13:37:12 log). Nothing
executed — the gate failed safe — but the UX was a lie in both directions.
- CONFIRM_TIMEOUT 120s→300s: human-speed per T-13-51's own rubric.
- ContextBroker dispatches aiui:tool-confirm-expired when a pending action
vanishes node-side (poll) or the turn ends; Chat.vue closes the modal on
it. Same host-only CustomEvent discipline; iframe has no path to it.
- Two new tests; 21/21 green across toolConfirm + chatAiuiEmbed.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
austin-sapien (100.70.96.88) sat dead for over two hours after taking
v1.7.122 — 'server starting' in the UI, service inactive, exit status
0/SUCCESS. It did not crash: the in-process updater replaces the binary and
exits cleanly for systemd to restart it, and that node's unit still carried
Restart=on-failure from an older install. systemd read the clean exit as
success and left it stopped. Every node with the old unit has this waiting
for it on the next update.
self-update.sh does refresh units, but the in-process update path never
runs it, so nothing was repairing them. The daemon now checks its own unit
at boot and rewrites only the Restart= line, so a node that starts even
once ends up with a policy that survives the next update.
Also carries the session-policy wiring: validate() now honours the
configured idle and absolute limits and the per-device class, instead of
the single hard-coded 24h constant.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
On-device UAT hit an infinite politeness loop: 'every write requires a human
confirmation you cannot bypass' read to the model as 'collect consent in text
first', so it never called restart_app, the confirm gate never engaged, and
each stateless turn (history is 13-10) dropped the user's 'confirmed' into a
void. The preamble now states the intended contract: the node presents the
trusted dialog the moment the tool is called; a text pre-ask stalls the action
and trains rubber-stamping.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Mesh right panel: a >=2560px screen hid the tab bar and stacked all five
tool panels in fixed grid rows. On a real display that clipped the Bitcoin,
Dead Man and AI headings to a few pixels each, letterboxed the map, and
pushed Radio Settings into a scroll — more screen producing a worse view.
Very wide now uses the same tabbed column as every other desktop width,
with the selected panel filling the column and the map running edge to edge
(it is the one panel with nothing to scroll).
Session policy: idle timeout, absolute cap and a re-prompt-for-funds flag,
persisted and clamped. Two tokens already existed — a session token and a
30-day login token — so the knob changes how long a quiet tab stays usable
without putting a long-lived credential on every request. Kiosk screens are
exempt from the idle timeout (nobody is there to log a TV back in) but keep
the absolute cap so a stolen box does not stay authenticated forever. The
cap is not optional theatre: idle alone never fires on a polling dashboard.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Portainer: nodes have been running :latest — which is 2.39.1 — while the
manifest pinned 2.19.4 from two years ago. The port migration recreated the
container onto that old pin and Portainer refused to start: it migrates a
database forward, never backward, so an existing install died with 'schema
version does not align' and My Apps showed 'app is not responding'
(100.82.34.38). 2.39.1 published as an immutable tag and pinned forward, so
existing databases keep working and older ones migrate up.
Bitcoin: complements PR #131. That removes the code which kept writing a
datadir bitcoin.conf; -allowignoredconf=1 additionally makes an existing
one non-fatal, so a node already carrying the file recovers on restart
instead of crash-looping until something reinstalls it.
App gate login: rebuilt against the dashboard's own design — rotating
intro backgrounds served from the gate, the glass panel, the Archipelago
mark in its gradient ring, the app's icon as a My Apps tile, and the glass
button. Crucially it no longer sends X-Frame-Options: DENY, which made
every gated app render as unreachable inside My Apps' embedded frame;
frame-ancestors expresses 'only this node may frame me', which
X-Frame-Options cannot.
OTA origin: primary mirror is now source.archipelago-foundation.org over
TLS instead of a bare IP on plaintext. The IP stays as an automatic
fallback for nodes whose DNS or clock is broken — both break TLS, and the
signature, not the transport, is what establishes trust.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Root cause of the Bitcoin crash-loop on 100.82.34.38: since a597c1d9
bitcoind launches with -conf=/tmp/rpc.conf and never reads the datadir
bitcoin.conf, but write_bitcoin_conf / ensure_bitcoin_rpc_config /
run_bitcoin_rpc_repair kept writing one on every install and restart.
Bitcoin Core's own datadir-conflict check then refuses to start at all.
Conflict resolved in favour of the PR: HEAD still carried
write_bitcoin_conf, whose deletion is the fix.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Mint failures surfaced raw JSON ({"detail":"proofs already spent"}) to
the user; now the top-level message is actionable while the raw body stays
in logs via {:#}.
Executor stopped deliberately for a session restart (bypass-permissions relaunch).
Executor's final report: 'cargo test assistant confirm-gate suite 28/28 green,
individual nonce test passes; committing Task 1 next — first verify the
tools.rs/grants.rs/backends diffs are formatting-only.'
Task 1 (D-07/D-11 confirm gate, backend) is implemented and test-green but this
checkpoint is verbatim-uncommitted-state, NOT the reviewed atomic Task 1 commit:
continuation executor should verify diffs, then reset --soft or commit-on-top
into proper feat(13-08) task commits. Task 2 (ToolConfirmModal.vue trusted
chrome, Chat.vue + contextBroker.ts wiring) is partially built, tests written.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
A rebuilt image never reached a running companion. ensure_image_present
rebuilds in place under the same tag, so the quadlet body is identical,
write_if_changed reports no change, and enable_now is a no-op on a running
service — the container keeps the old layers indefinitely.
That is precisely how archi-dev-box kept serving the LND, FIPS, Electrs and
Guardian screens on 0.0.0.0 after v1.7.123 rebuilt every one of those images
to bind loopback: correct images on disk, three-day-old containers still
running. Closing those ports needed a manual 'podman rm -f' per container,
which no other node would ever get. Compare the running container's image ID
against the built one and restart when they diverge.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Scanning archi-dev-box from OUTSIDE found five ports serving their screens
with no login — lnd-ui 18083, bitcoin-ui 8334, fips-ui 8336, electrs-ui
50002 and the Fedimint Guardian 8175 — none of which appeared in the gate's
unprotected list. They are host-networked, so Podman publishes nothing to
pin and their manifests declared 'ports: []'; the gate builds its map from
declared ports, so it neither protected them nor reported them. An audit
that reports success while five screens are open is worse than no audit.
Their nginx now listens on 127.0.0.1 instead of 0.0.0.0, and each port is
declared 'auth: gated' so the daemon owns the outside. 'bind:' on a
host-networked app is a statement of where the container listens, not a
publish instruction — quadlet already skips PublishPort in host mode.
Guardian 8175 is declared on the fedimint app because its companion has no
manifest, and the gate keys on port, not container.
Credential paths were NOT exposed and are verified so: /lnd-connect-info,
the /proxy/lnd/ passthrough, container logs and every RPC method through
these screens all return 401 unauthenticated. What leaked was the page
shell.
Also fixes the delivery gap that would have made this unshippable: only
bitcoin-ui, lnd-ui and electrs-ui were ever rsynced to
/opt/archipelago/docker, so edits to fips-ui and fedimint-ui reached nodes
through no path at all. All five now sync; the two whose rebuilds the
daemon owns are synced without being handed to container-specs.
Every remaining undeclared port is now declared with a stated reason —
gated: botfights 9100, router 8084, pine 10380; exempt with rationale:
fedimint consensus 8173/8174, gateway 8176/9737, netbird 8086/8087 (TLS +
own auth, and enrolled devices cannot hold a session), pine TLS 10381,
lightning-stack REST 8091 (macaroon, mirrors lnd). Zero undeclared ports
remain across all 56 manifests.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- confirm.rs: ConfirmGate/PendingConfirmation/Confirmed/PendingSnapshot/
ResolveRefusal API skeleton (request/resolve/mint_nonce/build_description
still todo!()) plus the five named confirm tests: S-02 nonce binding,
S-03 no-model-text, S-08 distinct resources, S-09 restart drops pending,
timeout declines, and the no-shared-lock-across-the-wait case
- mod.rs: ToolExecCtx gains the confirm gate (global by default, injectable
for tests) and the S-01 destructive_tool_requires_confirm test with a
seeded installed-app snapshot
- verified RED: 7 new tests fail (todo! cores + unfilled destructive branch)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Mint HTTP failures (swap/melt/mint-quote) were surfacing raw JSON bodies
like {"detail":"proofs already spent","code":11001} straight to the
user. Add a translator for the NUT-02/03/04/05 transaction-validation
error codes (10001-11017, 12001-12003; see
https://github.com/cashubtc/nuts/blob/main/error_codes.md) and layer it
onto the mint_client bail sites via anyhow context, so the top-level
message is actionable while the raw status/body stays available via
{:#} for logs. receive_token now surfaces the real reason (e.g. "This
ecash has already been redeemed") instead of a generic "Failed to
receive any proofs from token" when every mint in a token fails.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Leads with what changes for the operator: app screens now require the node
password across LAN, Tailscale, mesh and Tor; the wallet/protocol ports that
must stay open stayed open; the mesh leak found during on-node verification;
nodes repairing their own legacy containers; and the signing-key rotation.
Known gaps disclosed, including the eleven still-undeclared ports and that
non-browser clients will now meet the login page.
The new block uses <strong> rather than the literal ** markers in earlier
entries, which render as asterisks in the modal.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
DO NOT MERGE INTO A RELEASE SIGNED WITH THE NEW KEY. See below.
The previous release root (z6Mkkid…q7ur, pinned 2026-07-02) was exposed
in a chat transcript and is treated as compromised. It signs both OTA
manifests and the app catalog, so anyone holding it could sign updates
the fleet would install.
Pins the new key in trust::anchor and moves EXPECTED_DID in all three
signing/publishing scripts.
ORDERING IS CRITICAL — nodes pin the OLD key:
* The release CARRYING this commit must be signed with the OLD key.
That is the only signature a node running the previous binary will
accept, and it is what installs the binary pinning the new key.
* Only the release AFTER that may be signed with the new key.
* Signing this release with the new key makes every node reject it,
ending OTA fleet-wide and requiring hands-on recovery per node.
sign-catalog.sh moves in the same commit, so the app catalog must also be
re-signed with the new key once this ships, or nodes accept the binary
and reject the catalog.
Key verified before pinning: the hex and the did:key are the same
keypair, checked with a base58 decoder round-tripped against the previous
known-good pair. An earlier candidate hex (cb830e13…) was rejected
because it decoded to a different DID than the one supplied — pinning it
would have made every node reject every future update.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
- api/rpc/music.rs: handle_music prefix sub-dispatcher (assistant_chat.rs
shape) with list-albums / list-artists / list-tracks / status / reindex
- one guarded dispatcher.rs arm for the whole music. prefix, adjacent to
the content.* block; the only registration point for the surface
- list-tracks: optional album_id filter, limit/offset pagination, limit
clamped to [1,500] (default 100) — out-of-range degrades, never errors
(T-13-41)
- reindex spawns the scan and returns immediately; second call while one
runs reports already-running with the last stats; optional
incremental:true routes to refresh_incremental so a changed library is
reflected without a full re-extraction
- newer-schema index served as an empty library, never overwritten or
reinterpreted by readers (13-MUSIC-MODEL.md downgrade contract)
- nothing music.* in UNAUTHENTICATED_METHODS — the surface rides the
session/CSRF/RBAC gate; asserted by music_methods_require_session
(T-13-40)
- 7 tests, one per Task 2 behavior bullet plus the incremental mode
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Caught verifying the gate fixes on archi-dev-box: [fips0-ULA]:32838
answered HTTP 200 straight from nbxplorer with no credential. The
catalog declares that port auth: local — host-local by intent, pinned to
loopback, the gate deliberately keeps its hands off — but the mesh relay
bridges a STATIC port list to 127.0.0.1, so it republished it to the
whole mesh. Same bug class as the Tor onion gap: a transport that
converges on the app loopback without consulting the declaration.
PortMap now records declared-local ports and the relay withholds them
(tearing down an existing bridge if a catalog refresh newly declares
one), alongside the declared-gated withhold. Undeclared ports keep
todays behaviour — silence is not an instruction in either direction.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Dev-box verification of the Tor/FIPS fixes caught a pre-existing split
brain: the orchestrator publishes containers from the signed catalog's
embedded manifests (origin-wins), but the gate classified ports from the
stale disk manifests — so it externally bound nbxplorer 32838, a port
the catalog declares auth: local and pins to loopback. Reachable behind
a login, but reachable where it deliberately was not.
- build_port_map now consults the catalog overlay first, via the same
parse/validate/image-only filter the orchestrator uses (moved to
app_catalog::catalog_manifest_overlay so the two cannot diverge again).
- GatedPort carries . The gated set still includes undeclared
Session-default ports for challenge/audit, but every action that
REDIRECTS traffic — the torrc 127.0.0.2 repoint, the FIPS relay
stand-down, the Tor-upstream bind — now keys on the declaration.
- The sweep releases held claims whose port left the gated set, so a
catalog refresh that withdraws a port (gated → local/none) takes
effect without a daemon restart.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
