The serve tests waited for the socket file, then killed `loopd` and read its stderr, but the
socket is bound before its mode is set and before "serving on" and the broker notice are printed,
so a kill in between lost those lines (`pointers` failed once under load in M5c-1 task 15). The
broker notice now comes before the bind, so "serving on" is the last startup line, and the tests
wait for it (`tests/support/serving.rs`).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Found in the M5b device check on straylight: the self-test asked about
each of the 33 tags and each neutralised form, 66 requests, one
connection each, and inferproxy's token bucket (burst 10) refused the
ninth, so loopd would not start. Now it asks about all the tags at once,
one per line, and then all their neutralised forms: the answer to the
first must hold each tag's recorded token in order, the second none of
them. Each tag is a special token, split out before anything else, so
the lines between cannot change it; and a neutralised form is only
dangerous as a tag's own token, so that is what the second answer must
not hold. The errors name a tag by its id, as before.
The fake tokenizer reads text with several tags in it; the tests cover
each tag as ordinary tokens, as another listed or unlisted token, a
duplicated token in the middle and at the end, a form holding each tag,
and both requests failing. Spec section 8 and the runbook entry follow.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Text from outside the model (the user's message, every tool result, and the
memory block) is neutralised the moment it is first logged, so every later
request replays the same bytes and a tag in that text cannot reach the model as
one of its own control tokens. The model's own output, replay, and the system
prompt are left byte-for-byte.
Co-Authored-By: ornith-1.5-35b-a3b <agent@wntrmute.dev>
Done the way the owner asked and the spike mapped: the crate and the
manifests renamed, then what the build reported fixed. Layers: 138
"proto unresolved" errors across 169 files; cargo fmt reordering
imports; six fixture paths built as strings in brokerd's and bxctl's
tests, which the compiler cannot see, and comments naming
crates/proto/; the crate-dependency check and its self-test. One more
the spike did not reach: a `\nproto =` key inside a printf format in
the self-test, which a word-boundary replacement skips because `n` and
`p` are both word characters.
make gate: gate: ok, 944 tests; no new entry in /tmp.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
About 10,000 test leftovers had built up in titan's /tmp. loopd's Home
and FakeServer, its fake broker's socket, bxctl's temp sockets, fake
loopd and command homes, inferproxy's socket, and a few brokerd and
toolkit tests created uniquely named directories or sockets and never
removed them, or removed them by hand at the end, which a failing test
skips. Each is now a guard removed on drop (bxctl gains
tests/support/temp.rs). Two races also left gatewayd homes behind: the
test Running only signalled its server to stop, and two Stage structs
declared the home first, so it was removed while the server could still
write into it. Running's drop now waits for the thread (with a 5-second
limit), and every home is declared last.
Checked: make gate twice, then the gate and three rounds of gatewayd and
loopd tests; no new entry in /tmp; 944 tests pass.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The session did the task and stopped on make verify-device. The cause
was not the server: run-plan.sh and the device tests both read
BOXMAKER_MODEL, and the run's value (OpenCode's provider-prefixed id)
reached llama-server as the model name. With it unset, verify-device
passes 6 of 6. The copied files are identical to the plan's, and the
gate prints gate: ok, 936 tests.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
loopd's self-test caught the change (context per slot 131072 -> 262144,
slots 2 -> 4). The device tests keep the expectation in one constant, and
the M3a script matches it; verify-device passes 6 of 6 and the M3a device
check passes. The inference contract notes which M0 findings rest on the old
layout and need re-measuring.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
M3a review finding 8. The wait was expires plus the timeout with no bound,
and the "expiry too far away" guard could not fire, so a far expiry (which
brokerd produces when now + ttl_ms does not fit) parked a turn for ever.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
M3a review finding 7, for the other three roles. loopd keeps its config path
as a path; bxctl and inferproxy take text arguments and answer one that is
not UTF-8 with their usage.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
macOS refuses every socket option with EINVAL once the peer has closed
(XNU sosetoptlock, bsd/kern/uipc_socket.c), even with unread data still
buffered. loopd set a read timeout before each read, so on macOS every
frame or response that arrived just before the peer closed was lost:
BrokerPort reported the broker unavailable with "os error 22", and the
llama client failed the same way. Twelve loopd test binaries failed on
macOS; Linux never refuses, so the gate on Talos did not see it.
Both places now go through socket::set_read_timeout, which on Apple
targets takes that one refusal as success: a socket shut in both
directions returns its data or the end at once and cannot block. A
zero timeout is still an error.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Implemented SlotGate (one request in flight per server slot, FIFO queue,
bounded) and chat_with_retry (retry only server-gone errors, jittered
backoff within a window and attempt budget). chat acquires the gate and
maps GateFull to Busy; Client gained a gate field.
Implemented-By: OpenCode session (model recorded in docs/implementer-log.md)
kyleandornith-1.5-35b-a3b
