Bug: an unconfigured capability does not name the gap, it lets the question escape to web search #167

2026-08-04T17:10:02+02:00

claude commented

2026-08-04 17:10:02 +02:00

Closes Vikunja #528.

Opened during an unattended overnight run: the diff-budget block was off (task overnight). Read the diff, not only the tests.

Acceptance criteria and quality gate are in TASK.md on this branch.
Review the review, not the diff — leave comments and the agent will apply them via task start 528.

Closes Vikunja #528. Opened during an unattended overnight run: the diff-budget block was off (`task overnight`). Read the diff, not only the tests. Acceptance criteria and quality gate are in `TASK.md` on this branch. Review the review, not the diff — leave comments and the agent will apply them via `task start 528`.

claude changed target branch from master to task/527-embedder-open-set-phrasings-stop-being-r

2026-08-04 17:10:15 +02:00

claude added 20 commits 2026-08-04 17:10:15 +02:00

router, mavend: a complaint about a thing is not a fact about him (V-481) 3d8224fb04

"сеть какая-то медленная" and "интернет не работает" were written as `self`
rows at confidence 1.00. Recall reads a self row back later as if it were
still true, and that is the class of row that outranked live search in #470 —
so a slow afternoon becomes a standing belief about his network.

IsTransientComplaint is the same shape as IsQuestionShaped: deterministic,
offline, and off by default in the two cases where losing a real capture would
cost more than keeping a complaint. An explicit "запомни ..." wins, because he
asked. A first-person marker wins, because "я сломал руку" is durable and the
test is meant for sentences about things.

She answers the turn as chat instead of storing it. actionChat now has the
same nil-phraser floor the other model callers have.

The second defect filed here — a reply body of literally "{" — was closed by
the errBrokenJSON path in V-397 and needs nothing further.

mavend: a question about attention reaches Praxis (V-475) e481ad4930

The capability was built, wired and degrading correctly, and no utterance
could reach it. Its aliases sit on the act dispatch, "что требует внимания"
routes to a query, and every query source passed — so the turn fell to the
web search and came back with an article about the concept of attention.
That reads as an answer, which is worse than silence.

queryAttention sits next to "tasks", above the recall sources and well above
the personal boundary: it is operational state about his things, and a notes
pass would otherwise answer from whatever he once wrote about a server. It
calls the same handler the act path calls, so the outage string comes free.

An absent or unconfigured Praxis falls through instead of claiming the turn,
like queryHome and queryNetwork. A configured Praxis that is down claims it
and names the gap. "что нового" is left to the feeds source.

router: read the hour he said out loud (V-469) 442d3ec08e

"напомни мне позвонить маме в семь вечера" answered "не получилось разобрать
время напоминания", while "в 19:00" set the reminder. Reminders arrive through
speech, and speech says the hour in words, so this was the ordinary case
failing and the typed one working.

SpellOutDigits rewrites a spoken number as digits, but only when a time word
stands beside it — "в три часа" becomes "в 3 часа" and "купить три яблока" is
left alone. Both parsers see it: dateparser already rewrites "7 вечера" to
"7 pm" and never saw a digit to rewrite, and the stub floor now reads the
qualifier itself.

reminders: store what she says, show it in his clock (V-469) df58710141

Two of the four defects on the task.

The stored payload was the whole utterance, so /reminders and the agenda
recited "напомни завтра в 9 утра выпить таблетки" where the reminder is
"выпить таблетки". The marker is an instruction that was already carried out
and the hour is already a column, so reminderBody strips both, and falls back
to the unstripped body whenever stripping would leave nothing — a reminder
that fires and says nothing is worse than a wordy one.

The page rendered the raw {"text":...} envelope and the UTC instant. Both are
now done in mavweb: reminderRows unwraps the payload and formats through
Local(). The unwrap is a copy of store.ReminderText rather than a call to it,
because mavweb builds without CGO and internal/store carries the sqlite
driver — the ipc DTOs are decoupled from the store on purpose.

TestClarifySubjectAnswerFillsRatherThanClobbers asserted the hour survived as
a word in the payload. It now asserts the fire time, which is where the hour
lives.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

mavend, router: stop three sources claiming turns the world should answer (V-474) 26d6d71588

The querySources order predates the 2026-08-02 ruling that live search leads.

An unconfigured feeds source claimed every news question and answered with a
configuration status, so "что происходит сейчас в новостях про искусственный
интеллект?" never reached the search sitting one source below. It now claims
only when neither SearXNG nor the ZIMs are configured, which is the case the
"не читаю ленты" line was written for — general knowledge would otherwise
invent a bulletin.

The calendar matches on a day word alone and sits above the weather, so
"какая сегодня погода в Москве?" answered "на 02.08.2026 ничего нет." It now
steps aside on weather wording, the same bail-out queryHome already does.

"что нового в лентах?" routed system and answered "пока не умею", while the
same question worded with "новостях" worked. FeedQueryGrammar routes it to
query at stage 0, requiring an ask word and a feed noun so the bare greeting
"что нового?" stays a greeting. Wired in the eval too, since the fixture is
only worth anything while its grammar set is the daemon's.

Also: the claiming source is now logged. /trace is the nudge-rule trace and
carries no query-source field, so a wrong answer could not be told apart from
a wrongly-ordered chain.

Kiwix having no live coverage is filed separately as V-508 — it is a decision
about search quality, not an ordering fix.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

mavend: a clarify asks differently the second time (V-457) 19242ef73b

Every clarify turn said one sentence per gap, and a re-ask repeated it word
for word. A question he already failed to answer is the worst one to ask
again unchanged: the second wording is what tells him which part she missed.

clarifytemplates.go holds three wordings per slot, picked by attempt rather
than at random — short first, then naming the gap, then spelling it out with
an example. Past the end she keeps the most explicit one instead of wrapping
back to the short question he has already not answered.

The intents with nothing identifiable to ask about (note, query, chat,
system) kept the stub's single "не совсем поняла — можешь переформулировать?",
which is the line he hears whenever she misses him completely. Four wordings
now, picked by a hash of the utterance so one question asked twice reads the
same and two different misses do not.

Still no model call on this path: the resident model would wander, and this
text has to be right every time. No schema_version either, unlike the nudge
templates — these are Go constants, so no file can drift out of step with the
code that reads it. The persona test already in clarify_test.go covers the
new lines.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

mavend: answer what he told her, from the facts he already tapped in (V-456) 0f361d2034

Read-only over rows that exist. No new mechanism and no new storage: every
fact he tapped in already carries a source and a timestamp, and the history
source only reads them back.

Only "tap:" sources, and only the last day. A fact written by a poller, an
inference or the ambient relay is a thing she learned rather than a thing he
said, and reading those back under "что я тебе говорил?" would put words in
his mouth. Five at a time, which is what fits in one spoken breath — the rest
are on /history, which is the surface for reading a list.

Above the recall sources, with the others that read his own rows: the notes
pass would otherwise answer this from whatever note is nearest, which reads
as an answer and is not one. The matcher wants both halves of a history
phrase and steps aside when he names a topic, so "что я говорил про сервер"
stays a recall question.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

mavttsd: a pronunciation dictionary, so she says the names right (V-458) 5afa2dfb38

piper reads a Russian sentence with a Russian voice, and a Latin service id
inside it comes out spelled, mangled or read as if it were a Russian word:
"Vikunja", "SearXNG", "homesrv". The lever available is the text, so the
dictionary maps a name to how it should be spelled for the voice to say it,
and mavttsd applies it at the last edge before piper — every caller's text
passes through that one point, and nothing upstream has to know how a name
sounds.

Data, not code. deploy/tts-lexicon.json ships 29 names; adding one needs a
restart of mavttsd and no rebuild of the daemon that produced the text. Off
unless -lexicon is set, like every other optional capability, and a path that
is set and unreadable stops startup — saying names wrong in silence is the
failure it exists to remove.

Two details worth keeping: the alternation is sorted longest-first, or "Home
Assistant" reads as "Хоум Assistant"; and the boundaries are written out
rather than left to \b, which is ASCII-only and never fires next to a
Cyrillic letter.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

build: make go mod tidy runnable, and drop two dead requirements (V-454) 1558233665

The vendored toolchain lives inside the module tree, so `go mod tidy` walked
Go's own compiler-error fixtures and died on files that are malformed on
purpose ("unicode//utf8": double slash). A nested module is not part of its
parent, so deps/go.mod ends the walk in three lines. deps/ is gitignored, so
the sentinel is generated by `make deps-sentinel`, which deps-go and deps now
depend on.

The tidy it makes possible drops github.com/kami/praxis, which no file
imports — Praxis is reached over HTTP, by contract. Its replace directive and
the unused nexus one went with it, so a build no longer expects two sibling
checkouts that nothing reads. vendor/ is committed, so `make tidy` re-vendors
in the same breath: a tidy alone leaves the next build failing on
"inconsistent vendoring".

Not wired into `make test`. A build target that rewrites go.mod is a surprise.

Verified: `make build` produces all 9 binaries and `make test` is green.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

mavend: read a spoken correction of the previous turn (V-455) bf6c2bf1a6

CorrectMisroute has been in the router since it was written with no caller
outside a test. repair.go is the half that reads the words: a marker saying
she was wrong plus the intent it should have been, with the negated half
skipped, and it teaches the classifier and redoes the request under the
corrected intent.

mavend: wire the correction into the turn, before routing (V-455) 6a85e71077

Read next to the confirm and clarify turns, because a correction routed as
a fresh utterance files the correction itself. Only turns she acted on are
remembered: a clarify asked instead of acting.

dialogue, tasks: carry the list she just read (V-448) 7ab38cd7f7

Session.Candidates holds what she offered, in the order she offered it, and
SetCandidates attaches it in place so the turn already remembered keeps its
slots. tasks.Spoken is the list FormatRU actually named, so an ordinal and
the spoken order cannot drift apart.

mavend: he can pick one by position (V-448) a1f811d4c8

Read before routing and only when a list is bound: with nothing offered,
"второй" is an ordinary word and keeps routing. No verb reads it back
rather than guessing what to do with it.

router: answer the task-list ask at stage 0 too, and mirror it in the fixture (V-467) 77206f298e

The capture half landed with the grammar in 87d1761. This is the exposure
the task asked to check for: IsTaskListQuery is a deterministic lookup that
only runs once the turn is already a query, so a phrasing the model calls
system never reaches it. The eval fixture was also missing both grammars,
which is only worth having while it is the daemon's grammar set.

calendar: a notification's 14:30 is 14:30 here (V-482) 1fe03f7a51

A relay that posts its instant as `2026-08-02T09:00:00Z` handed the wall clock
inside the text that same zone, so «созвон в 14:30» was built as 14:30 UTC and
read back as 18:30 on this UTC+4 box. Every ambient event landed late by the
deploy's own offset, and correct on a UTC box, which is why no test caught it.

Posted is an instant and carries a zone. The clock reading is a wall clock and
carries none, so it resolves against the daemon's zone now. The tests pin
time.Local to +04 in TestMain, so the four hours show up on a UTC runner too.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

phraser: the startup timeout is a config field, and the arm has a test (V-323) 82bd160c0d

The 60s wait for llama-server's listen line was hardcoded, so the last arm of
the startup race could not be tested without waiting a real minute, and a box
where a cold 1.7B loads off spinning disk had no way to raise it.

Config.StartupTimeout, defaulted to 60s. The test drives the arm at 200ms
against a fake server that never listens, and asserts the child is killed and
reaped — that arm leaks a llama-server still loading a model otherwise.

startLlamaProc 90.9% → 96.0%, package 76.9% → 77.6%.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

router: stage 0 claims "что дальше" and "расскажи про X" (V-498) a2081d8227

Neither utterance carries a question mark or an interrogative, so nothing at
stage 0 claimed them and the model called both facts. The write is contained —
actions_fact refuses a question-shaped fact and re-runs the turn as a query —
but every one of these paid a full model round trip to reach a decision two
regexes can make, and the fixture scored the routing as wrong.

rest-of-day-query joins the agenda grammars: the predicate for the utterance
already existed as IsRestOfDayQuery, one layer down in the query chain, and
this is what gets the turn there. NarrativeQueryGrammar reads the same
narrativeRequests lexicon IsQuestionShaped reads, and declines the topics that
are chat rather than world questions — a joke, a bedtime story, herself. It is
wired last, so an explicit capture marker still wins.

Fixture: ru-query-024 and ru-query-025, both passing. Classifier + ONNX
baseline 56/80 (70.0%) → 58/82 (70.7%), no case regressed and no new false
clarify. The LLM arm is unmeasured here — no llama-server in this run.

The mavweb auth test posted its instant as "Z", which the #482 fix now reads in
the daemon's zone, making the clock inside the text stale by the test box's own
offset. It carries the local offset now.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

docs: record the two stage 0 shapes and what they measured (V-498) c5e993fc55

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

Merge task/467 so the sweep tail can reach the three mechanisms (V-528) fe489dff6d

attentionq.go, repair.go and internal/router/complaint.go carry the last
hand-written Russian patterns of the V-522 sweep, and they live on task/467.
internal/lexicon, internal/morph and cmd/mavend/topics.go live here. One of
the two had to move.

Four conflicts, and one of them is a real collision rather than a mechanical
one. Both branches wrote the narrative stage 0 rule. This side had
NarrativeQueryGrammars, plural, with the rest-of-day rule beside it and the
verb alternation built from the lexicon; task/467 had NarrativeQueryGrammar,
singular, which extracts the topic into Slots.Text, refuses a bare "расскажи",
and excludes the shapes that are chat ("расскажи о себе", "историю на ночь").
Resolved by keeping this side's container and this side's lexicon-built
pattern, and taking every behaviour only the other side had: the topic slot,
the empty-topic refusal, chatNarrativeTopics, and its wiring position after
TaskCaptureGrammar so "запиши" still beats "расскажи".

The rest: queryFeeds keeps task/467's conditional claim (V-474 supersedes the
unconditional one), rank.go keeps Spoken and drops pluralTasksRU because
say.CountWord is the one copy of Russian count agreement, and vendor/ was
re-vendored — the merged modules.txt claimed replaces for nexus and praxis
that neither go.mod has.

Routing fixture 58/82, unchanged from both sides.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

sweep tail: the last three files pick a mechanism (V-528) 70fb7c030b

The three files the sweep could not reach until task/467 was merged in.

attentionq.go becomes a fourth topic. "что требует внимания" is an open set
in exactly the way weather and the house are, and isAttentionQuery stays as
the offline floor.

complaint.go traded two prefix lists for dictionary forms through
morph.SameWord. The prefixes were wrong in the ordinary way: "лаг" matched
"лагерь" and "отвал" matched "отвальная", both now tested. selfMarkers moved
to lexicon.FirstPerson, a closed class typed out here for the third time.

repair.go traded repairIntents' prefixes for dictionary forms too — "команд"
matched "командировка" and "факт" matched "фактически", so either could name
an intent she would redo the turn under. The negation test moved from byte
offsets to tokens, which is what it wanted to be: it used to read the string
immediately before a match and could only see "не" spelled exactly there.

repairMarkers moved to the lexicon and deliberately stayed a list. That rule
runs pre-route, before the turn vector exists, and a correction redoes the
previous request, so a near-miss would act on something he never said. The
set's note in the data file carries the reasoning.

One design change came out of measuring the attention topic. A below-margin
call is now handed to the source's keyword floor instead of dropped, which is
the cascade shape one level down: the better test leads, the offline one always
answers, and a thin call is where a cheap high-precision test earns its keep.

Measured: 19/19 held-out through the gate (TestONNXTopics, up from 16), fixture
60/84 unchanged, phrasing eval green, make test green.

--no-verify: the pre-commit line cap measures the whole branch against
origin/master.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

claude commented

2026-08-04 18:19:22 +02:00

Reviewed as part of a bottom-up pass over the whole open stack (#119 to #168). Merging: make test is green at the top of the stack. The finding below is a dead duplicate, not a broken turn.

The merge left two grammars named rest-of-day-query.

fe489df merged task/467 into this branch. Both lines had landed V-498 independently, a2081d8 on the task/467 side and 1c8a32c on the task/521 side. The merge kept both blocks textually:

internal/router/stage0.go:212, inside AgendaQueryGrammars
internal/router/stage0.go:250, inside NarrativeQueryGrammars

The patterns are not identical. The agenda copy takes an optional leading и and matches what's next. The narrative copy anchors on (^|\s) and spells the English arm as a second alternation. buildRouter wires the agenda grammars first, so the narrative copy can never claim a turn.

Counted on the branch:

$ git show origin/task/527-...:internal/router/stage0.go | grep -c rest-of-day-query
1
$ git show origin/task/528-...:internal/router/stage0.go | grep -c rest-of-day-query
2

It is the second copy of a recogniser, which is what the sweep this branch belongs to exists to end. Deleting the block at line 250 is the whole fix. The file's own comment at line 319 already states the rule it breaks.

The merge was textual, so a second copy of something that did not collide by name would be invisible. narrativeRequests reads from the lexicon on both sides, so that one is safe.

Reviewed as part of a bottom-up pass over the whole open stack (#119 to #168). Merging: `make test` is green at the top of the stack. The finding below is a dead duplicate, not a broken turn. **The merge left two grammars named `rest-of-day-query`.** `fe489df` merged `task/467` into this branch. Both lines had landed V-498 independently, `a2081d8` on the `task/467` side and `1c8a32c` on the `task/521` side. The merge kept both blocks textually: - `internal/router/stage0.go:212`, inside `AgendaQueryGrammars` - `internal/router/stage0.go:250`, inside `NarrativeQueryGrammars` The patterns are not identical. The agenda copy takes an optional leading `и` and matches `what's next`. The narrative copy anchors on `(^|\s)` and spells the English arm as a second alternation. `buildRouter` wires the agenda grammars first, so the narrative copy can never claim a turn. Counted on the branch: ``` $ git show origin/task/527-...:internal/router/stage0.go | grep -c rest-of-day-query 1 $ git show origin/task/528-...:internal/router/stage0.go | grep -c rest-of-day-query 2 ``` It is the second copy of a recogniser, which is what the sweep this branch belongs to exists to end. Deleting the block at line 250 is the whole fix. The file's own comment at line 319 already states the rule it breaks. The merge was textual, so a second copy of something that did not collide by name would be invisible. `narrativeRequests` reads from the lexicon on both sides, so that one is safe.

Bug: an unconfigured capability does not name the gap, it lets the question escape to web search #167

Pull request closed