The review comment asked for basic DI. The answer is the idiom voice.go
already had for capabilities — a cohesive *Wiring struct — applied to a
group that is not a capability toggle, plus the decision written down so
it is a rule and not a habit.
recallWiring holds the embedder, the vector store, the personal boundary
and the two numbers that gate an answer. They sat in three places on
reactiveHandler, with the gate numbers a hundred lines from the store
they gate. Its zero value means no recall, so it is a value, not a
pointer like the optional-capability groups.
dataStore stays out of it. patterns.go, ecosystem_acts.go and confirm.go
use it, so it is not part of this cluster.
docs/handler-wiring.md records the choice, rejects a container or a
wire-style generator outright, defers narrow per-handler interfaces to
the package split that would justify them, and states the constraint the
task named: a wiring change does not ride a feature PR.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The swap itself already landed: deploy loads
models/embedder/multilingual-e5-small/model_quantized.onnx, and
onnxembedder.go grew EmbedQuery/EmbedPassage with the query:/passage:
prefixes the model was trained with. What was missing is the half of #371
that says "re-run make eval-recall and compare against the recorded numbers",
so nothing in the repo says whether it worked.
It worked, on every axis at once. recall@1 60.0% → 70.4%, recall@3 80.0% →
85.2%, answered after the gate 48.0% → 63.0%, false recall 1/5 → 0/5, and
latency p50 59ms → 23ms because the quantized file is 118MB against the 470MB
fp32 one the old config loaded. The guitar-chords note no longer beats the
docker-logs note.
One premise of the task did not come true and the new doc says so. #371
expected a better retriever to separate the score distributions and make
query_min_score tunable. It did not: right-first top-1 runs 0.791-0.890 and
must-stay-silent runs 0.795-0.835, still overlapping, just higher and
tighter. The margin separates them instead — 0.024 median against 0.002 — and
0.008 is the knee where all five silent cases are silenced at no cost. The
score gate is close to inert now; the margin is the live dial. Neither is
changed here, since #412 is where a sweep belongs.
docs/evals/2026-08-04-recall-e5-small.md is the dated measurement.
rearchitecture.md's "upgrade MiniLM → bge-m3 later" is now done and says so,
CLAUDE.md names the retriever and the prefix rule where it already promises
the embedder never leaves homesrv, and the Makefile comment points at this
eval instead of the one that asked for the swap.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The decision, not a behaviour change: ClarifyStore stays in memory, and she
does not announce the loss either.
The TTL and the attempt count measure a pause in one conversation. A restart
is a gap of unknown length, so a restored question is either dead already or
lying about its age, and the request behind it is one he has likely given up
on. Announcing it would mean storing a marker that outlives the thing it
describes, to say one sentence in the rare window where he speaks within 90s
of a restart. His next words route fresh, which is right either way.
Written down in docs/design.md, pinned at both ends by a comment, and held by
a test that builds a second handler over the same store.
#496 asked to skip the veto when the question and the hit are in
different scripts, so an English question stops losing a Russian note.
Measured first: the fixture has no cross-language case, and en-hard-024
is an English question against an English note. Both proposed fixes are
no-ops.
What the veto actually does on the fixture, with the real embedder: it
costs en-hard-024 and buys ru-silent-029. Pass count is 22/32 either
way; false recall is 0/5 with it and 1/5 without. The two cases are one
lexical class, so no rule cheap enough for RecallAllowed separates them.
Accepts the loss and pins both sides in a test.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The forwarded log named the cause in one line: the prompt cache limit
defaults to 8192 MiB. llama-server saves the full KV state of every idle
slot it evicts, 112 kiB per token, so RSS climbed about 170MB per
distinct prompt until the deployed server held 7.9GB for a 1.1GB model.
Measured on homesrv today, uncapped versus `--cache-ram 512`: RSS
plateaus at 932MB from the fourth distinct prompt instead of climbing.
The task's leading guess was wrong. `-ngl 99` costs almost no RSS,
because RADV keeps device memory outside the process. Numbers and method
in docs/evals/2026-08-03-llama-prompt-cache.md.
`-c 4096` is untouched. The knob is `phraser.cache_ram_mib`, unset means
512, negative passes no flag for a llama-server too old to know it.
The deploy still runs the old image, so the box keeps its 8 GiB default
until mavend is rebuilt.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
"что я говорил про бэкапы?" is his data by definition, and nothing outside the
box has ever heard him say anything. The boundary matched possession words only,
so the question walked past it into SearXNG and came back answered out of a Habr
article about somebody else's backups.
A speech-verb marker class was written first and dropped. Russian gives every
verb a dozen surface forms and the "как я говорил, ..." preamble list has no end,
so each form the lexicon missed was one more question reaching the world, and a
missing verb looks exactly like no bug.
The boundary now embeds two frozen seed sets and scores the turn's own query
vector, already computed upstream, against both. Nearest side wins. The
possession markers stay as the offline floor for a handler with no embedder.
19/19 held-out utterances correct against multilingual-e5-small; see
docs/evals/2026-08-03-personal-boundary.md. The live probe on the deployed box is
not done.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Every write-path fix leaves the rows already stored wrong, and a box in that
state looks fine: recall answers with the wrong text and nothing logs an error.
That is how the original poison survived four restarts.
RepairFactVectors resolves each fact vector against the fact it names,
re-embeds the ones whose text is stale, and deletes the voided, superseded and
orphaned ones. Marker-guarded and idempotent, so it runs once per box and a run
that dies partway is simply redone.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The offload inventory grows a column, because "seven callers of the resident
model" stopped being the useful fact. Which of them is offloaded, and under
which half of the rule, is. Three are resident-only on purpose and the table
now says why rather than leaving it to be rediscovered.
The three-outcome table is the part that was not obvious from the rule as
written. A configured-and-asleep workstation names the gap; a box with no
workstation block does not, because naming a gap requires a gap.
Both fixtures, run from homesrv across the LAN with the proxy env stripped.
Routing: 84.4% full / 93.5% intent-only at p50 329ms through the cascade, against
72.7% / 77.9% at p50 0.80-1.04s for Qwen3-1.7B. Talk: 25/27 against 20/27, with
knowledge 9/9. Nudges 15/15. Settles #485's first assumption by measurement.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NJYcaBiuny9UGSpFweQVQ1
The remote model cannot be a llama-server that is simply left running: a
resident 7-14B holds 16GB against the CPT runs the card is for. So what
is always up on the workstation is a supervisor, and llama-server is
loaded while the card is free.
Still not a scheduler. It arbitrates nothing between callers, and Maven
never asks it to start anything.
483 is an umbrella and its children are the work, so what it owes them is
the shape they must all obey. docs/offload.md records it: the degradation
rule and where its line falls, admission control rather than a GPU
arbiter, the embedder staying on homesrv because it backs the classifier,
and the inventory of what runs a model on the box today.
CLAUDE.md gets a pointer, because an agent about to add a model caller or
touch a daemon seam needs to know this before it starts, not after.
morning_routines, feeds, crawl.on_demand and netscan.enabled in
deploy/mavend.json; -ambient-token on mavweb, interpolated from a gitignored
/.env. All verified on the box: the dispatcher builds the morning plan,
/api/ambient answers 401/201, the crawler reads a named page, netscan finds 3
devices, and /events fills with scan:lan and ambient:notif.
Filed 482 (ambient reads a notification's wall clock as UTC). Corrected 479:
both capabilities work once configured, so it is not a routing defect.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NJYcaBiuny9UGSpFweQVQ1
Ran sessions 1 and 2 on the live box.
Session 1 steps 1 and 3-6 pass. Steps 2 and 7-9 need a person at the box.
POST /api/chat is drivable with form encoding and a cookie jar, so the text
half needs no browser.
Session 2 confirms the deploy matches the bench at 72.7% full accuracy, and
contradicts two recorded numbers. The classifier scores 68.8% at p50 16.6us,
not 36.8% at 31ms. Router latency measured under contention again.
Also: 319 item 2 point 2 closes on the recall margin sweep, CheckFeminine has
a false positive on second-person masculine verbs, and the wake path cannot be
checked because mavwaked and mavenclient are deployed nowhere.
The plan named 40 task numbers on 2026-08-01. Ten open QA tasks were missing
and two of the named ones had closed, so the 44-of-50 header was wrong twice
over.
- header is 42 of 50, and every open task now appears
- placed the ten unlisted QA tasks: 14, 248, 249, 250, 258, 283, 284, 285,
286, 323
- new Operations sitting for 249 and 250, and a Query sources sitting for
258 and 286
- 14 and 284 join housekeeping: both are gated on something unbuilt
- dropped the 317 and 354 rows, closed 01-08-2026, with one line saying what
landed
- 319's gate recalibration is done; what is left is re-deriving QueryMinMargin
- 323 is down to the 60s startup timeout arm after PR #90
- new "Not this repo" section for 358 (Hexis) and 362 (training workspace)
- router latency is ~27x, not 90x; the 2.7s p50 was contention, not the model
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NJYcaBiuny9UGSpFweQVQ1
Checked the doable, epic and infra tiers against the code, not just the two
tiers V-447 asked about. Ten entries are already built. The two the ranking
calls blockers for everything below are among them: sqlcipher at-rest ships as
Store.enc plus OpenEncrypted, and mavweb/mavcaldav have nine test files
between them where the ranking says zero coverage.
Also built and still ranked as work: rule trace, recurring reminders (cron +
RescheduleReminder), stale-reminder burst collapse (collapseReminders),
revert (VoidLatestFact), digest mode, testing infra, passkey persistence.
Recorded as a section at the top of the archived file so the tiers underneath
are read with the corrections in hand. No tasks created: V-447 scoped task
creation to the mandatory and easy tiers.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Xwomr2cT93KMSz9u3digX5
Checked the mandatory and easy tiers against the code instead of trusting the
2026-07-03 ranking. Two were already built and their tasks closed unstarted:
quiet hours (QuietHoursConfig + the care gate in internal/loop/loop.go:37) and
schema migrations (internal/store/migrations.go on PRAGMA user_version, 12+
steps shipped).
Three more were narrowed to what is actually missing. Destructive-confirm has
a mechanism and no policy: store.Tool.Destructive is one boolean, not a risk
tier. Bounded follow-up state has dialogue.Session with a TTL and slot
inheritance; what it lacks is Candidates, so "второй" resolves against nothing.
Clarify has a gate that can ask and one hardcoded sentence to ask with
(internal/voice/replier.go:56, which replier_llm.go hands straight through).
The other six were confirmed absent: list_items, capability model, go.mod
tidy, conversation repair, command history, pronunciation dictionary.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Xwomr2cT93KMSz9u3digX5
PROGRESS.md and 20-07-2026-BACKLOG.md were state snapshots that git log and
the Vikunja board already carry. Everything PROGRESS.md claimed as shipped is
a QA task. The backlog's only untracked item, bounded follow-up state, is now
V-448.
maven-feature-ranking.md moves to docs/archive/2026-07-03-feature-ranking.md
instead of dying. Its mandatory and easy tiers became V-449 through V-458; the
doable and epic tiers are reasoning about why things are not worth doing yet,
which no task captures.
Four code comments and the design.md ledger pointed at the deleted files.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Xwomr2cT93KMSz9u3digX5
Seventeen markdown files at the repo root, twelve of them dated one-shot
reports sitting next to CLAUDE.md. That is why stale docs read as
current: nothing in the path said which was which.
Root now keeps CLAUDE.md and AGENTS.md. Living docs move under docs/
and carry a Last verified line. Dated measurements move to docs/evals/
ISO-prefixed, and are never edited after the day, so a newer number is
a new file. The senior review moves to docs/archive/.
Every reference was rewritten across markdown, Go comments, the Makefile
and the recall fixture. The touched Go packages still build.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Maven can now be told who someone is. She cannot yet tell who is speaking,
and this commit is careful to say so rather than pretend otherwise.
What works: profiles are enrolled from several deliberately recorded samples,
listed, and deleted. They live in the existing memory_vectors table under a
"speaker:" id prefix, so there is no migration; what that needed was a wider
interface than memory.Store, hence memory.Catalog with ByPrefix and Delete.
Delete is the load-bearing half — a voiceprint someone asked to be rid of has
to actually go, and a search-only store cannot do that. InMemoryStore.Insert
became an upsert by id to match what the persistent store already did.
What does not work, and why it is not faked: there is no speaker-embedding
model on this box. Sixteen ggufs in /mnt/hdd1/llms, all text; no ECAPA, no
x-vector, no titanet, no wespeaker, no .onnx anywhere under /mnt/hdd1. So
newSpeakerEmbedder returns nil, internal/speaker falls back to
speaker.Disabled, Identify answers ErrDisabled, and the daemon logs which
half is off at startup. The plan's "simple MFCC + GMM" floor is refused in
the package comment: MFCC cosine distance detects channel and loudness as
much as voice, and a biometric that is confidently wrong writes false claims
about named people into his memory. A bad floor is worse than none here.
Refused as well, and the reason is in enroll.go's doc comment: the plan asked
for unknown speakers to be enrolled on first interaction with a TTS "кто
это?". There is no request shape in the protocol that could express that.
Taking a biometric of whoever walks past the microphone does it to guests who
are not party to the exchange, and a synthesised question into a room is not
consent from whoever answers.
Authority: enrolment is AuthStepUp, because it is a deliberate sit-down act
that writes a biometric of a named person and never something done by voice
mid-conversation. Deletion is one rung lower at AuthWrite, deliberately
inverting the usual pattern — getting rid of a biometric must never be the
harder half. Listing is AuthRead and never returns the vectors themselves.
Off unless configured: no speaker block means the three methods answer
ErrUnknownMethod, so a default box has no wire path that takes a voiceprint.
make build and make test pass.
Vikunja #255
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TrVSBKe3RFDF4fGYKWYQnX
Maven can record a meeting when she is told to, transcribe it through the
STT she already has, and write a summary note. The audio lives in the blob
store #252 introduced, under the same retention loop.
Nothing here listens. Recorder.Append is the only way audio enters and it
refuses every frame unless someone explicitly started a session, so audio
arriving at an idle core is dropped rather than buffered. The plan document
asked for a keyword trigger ("maven record" heard in the room) and that is
refused: noticing a keyword means listening to the room, which is the one
behaviour this capability must not have.
Off unless configured twice over. No media block means nowhere to keep
audio, no capture block means no recorder, and in either case the four IPC
methods answer ErrUnknownMethod. On an unconfigured box there is no wire
path that begins a recording at all.
A forgotten session ends itself at max_minutes, checked on every append,
and the audio collected before the cap is kept. Stop with discard set is
what "забудь, не записывай" maps to and it leaves nothing behind. The
verbatim transcript is not saved unless save_transcript says so; the
summary is.
Long audio against n_ctx 4096 is handled by map-reduce over 3000-rune
windows rather than by truncation, because a truncated meeting summary
reads as complete and is not. Transcription is windowed at five minutes so
the whisper worker stays responsive to the voice path.
No second STT: internal/capture takes the stt.Transcriber the voice path
already holds. Capture with voice off is refused rather than degraded,
since hours of unreadable audio of other people is worse than no recording.
The three write methods are AuthWrite, not AuthStepUp: step-up needs a
passkey gesture the voice path cannot make, which would leave "запиши
встречу" impossible by voice. capture_status is AuthRead.
make build and make test both pass.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TrVSBKe3RFDF4fGYKWYQnX
Vision needs a second model this box does not have, so the shipped half is
the part that works without one: an image arrives, is sniffed, is stored
content-addressed, and is prepared for inference. The describing half is
written and tested against a fake server, and refuses any endpoint that is
not on this box.
internal/media is the intake all three senses share — hearing and speaker
recognition store their audio in the same place under the same retention.
Blobs stay out of the sqlite store; only the derived text becomes a note,
and only when the caller asks. Retention is enforced by an hourly prune
loop rather than by a comment.
The plan's RemoteProvider step is refused: no cloud model, inference stays
on the box, and vision.NewLocal validates that at construction.
The network fallback behind the local sources, off unless configured.
internal/crawl is pure: a stdlib robots.txt parser (group specificity,
wildcards, Crawl-delay, cached per host), HTML-to-plaintext extraction, and a
watcher that notes a watched page only when its text changed. It has no store
access and no net/http; cmd/mavend/crawls.go is the impure half.
Every limit is code and tested: the guarded fetcher from #258 enforces the host
allowlist/denylist, refuses private addresses in the dialer Control hook (so DNS
rebinding and each redirect hop are covered), caps size and redirects, times out,
and spaces requests per host. A robots.txt Disallow is refused with no override.
On demand, reading is a query source placed last in the chain, after his memory,
his notes, and the local Kiwix ZIMs once those are wired: no URL in the
utterance means no fetch, and only the URL ever leaves the box. Scheduled
watches write notes and announce nothing.
The vendored tree has no x/net/html, goquery or temoto/robotstxt, so the parsers
are stdlib. No new dependency.
internal/rss parses RSS 2.0 and Atom, and polls each configured feed on its own
interval; internal/webfetch is the one door either of them uses to touch the
network. The poller writes items as notes with source "rss:<feed>" and nothing
else: the answer path reads them back when he asks "что нового в лентах?", and
nothing is announced on arrival. A feed that dispatched would be a nag, which is
why the plan's breaking-news rule was left out rather than built.
webfetch is where the limits live, as code rather than a paragraph: http(s)
only, an allowlist (the configured feeds' hosts) and a denylist, a 2 MiB body
cap, a 3-redirect cap, one request per host per second, and a refusal to connect
to any private address — checked in the dialer's Control hook so it holds for
every resolved address and every redirect hop, not just for a literal IP.
Off unless configured: no "feeds" block, no poller, no outbound request. How far
a feed was read is a config fact (rss:latest:<name>), so a restart does not
re-note yesterday's headlines.
Behavioural memory, narrowed on purpose. internal/memory/behavior.go builds a
profile out of self-facts — distinct days per weekday, median time of day — and
reads it back in RU; router.ParseHabitQuery finds the weekday deterministically;
a `habits` query source answers the question.
Three things the plan doc asks for are deliberately absent, and the doc now
records why:
- The profile is COUNTED, not LLM-generated. A 1.7B asked to summarise a year of
habits writes fluent claims about the owner's life that no row supports, and a
wrong claim about him is the most expensive kind of wrong maven can be.
- No cached profile fact, so no "update on fact write" machinery. It is
recomputed on the question; a cache that can disagree with its own rows is two
truths.
- No proactive daily plan nudge. A dispatcher proposal at 08:00 every day is the
definition of a nag. The path from "she noticed a pattern" to "she acts on it"
already exists in internal/pattern with the proposal queue on /routines, and it
goes through him.
A one-off is not a habit: an activity needs two distinct days before she will
call it usual, and until then she says she does not know yet. Only self-facts
count — env rows are the world, config rows are her own tuning state. The typical
time is a median so one 03:00 outlier cannot move a morning habit into the night.
An unrecognised fact key is read back verbatim rather than glossed into something
she made up.
The source sits before "calendar" in querySources, and its matcher requires a
habit marker, so "что я делаю в среду?" still reaches the calendar — answering a
question about this coming Wednesday with a statistical average would be
answering a different question.
Verified: make build and make test both exit 0.
Ships the real, local, testable part of the memory-evaluation plan
(docs/plans/03-memory-evaluation.md): Maven reads back her own recent
memory on a slow ticker, asks the resident model what it notices, and
records the confident answers as notes.
internal/memeval — not internal/memory/eval.go as the plan says, because
internal/store imports internal/memory for the vector backend and an
evaluator has to read store.Fact/Note/Nudge, which would close the
cycle. Evaluate() gathers RecentFacts/RecentNotes/RecentNudges, prompts
under a GBNF grammar bounded to three {observation, confidence,
suggested_action} objects, drops anything under min_confidence,
deduplicates against what earlier runs wrote, and writes the rest as
notes with source infer:memory-eval. /dash already renders notes with
their source, so the output is visible with no UI change.
cmd/mavend/memoryeval.go drives it on its own goroutine and ticker, not
on the 60s tick: an evaluation is a multi-second round-trip on the same
llama-server that answers voice turns, and it runs hourly at most. The
memory_eval config block is absent by default and absence means the
goroutine does not exist. No llama-server phraser also means no loop —
there is no template fallback, because a "memory evaluation" assembled
from templates is a fixed sentence pretending to be an observation.
What it deliberately cannot do, since this is the feature most likely to
turn Maven into a nag:
- It cannot speak. No dispatcher reference, no channel, no nudge. An
observation is a thought she wrote down and he reads on /dash.
Announcing them is a separate decision with its own opt-in.
- It cannot act. suggested_action is recorded as text and interpreted
by nobody — no reminder, routine or fact is created from it.
- It says nothing about an empty store: no memory means no LLM call,
so there are no observations invented out of two facts.
- Its own notes are excluded from the next evaluation's input, and are
written with a nil embedding so they stay out of the recall pool.
The plan's remaining items (dispatching observations, an /eval IPC
method and trace view, RecentEvents) and the fact that output quality is
entirely unmeasured are written up at the bottom of the plan doc.
Add a read-only /ecosystem page that consumes the sibling services'
JSON APIs (Nexus entities, Praxis attention, Hexis capabilities),
fetched concurrently with honest per-panel error states. Siblings stay
headless — mavweb is their human surface (arch §16). Wired via mavweb
-nexus/-praxis/-hexis flags; mavweb joins the ecosystem compose network.
Fix mobile horizontal overflow across all pages: .content is a flex
child with default min-width:auto, so it refused to shrink below the
tables' intrinsic width. min-width:0 lets wide tables pan inside .scroll
instead of dragging the page sideways. Verified via CDP geometry check
(scrollWidth === clientWidth at 430px).
Also includes in-progress Ethos UI redesign, ecosystem deploy compose,
and planning docs.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Route contract is now a JSON array of action objects (one per ask) so
compound utterances route all their intents, not just the first. Grammar
root emits `[{intent...},...]`; parseActions tolerates a bare object.
Cascade still returns one Decision — full N-action dispatch lands with the
engine turn-on (marked in-code).
Router prompt rewritten shorter + decision-ordered (prompt-guy feedback),
fact redefined as "implicit update" not "trackable state", kept in Russian
to match the CPT base + phraser. "интент" → "намерение".
CLAUDE.md: routing-architecture section + refreshed open items.
docs/plans: route-data generation plan.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017GMrVfuYN3nE4L1vEiFYC9
Daemon side of Decision B: parse {"response","mood"} across the 4 consumers
(replier, nudges, reminders, chat), fall back to legacy formats. Drop the
LLM router — the classifier handles routing; replier/phraser share one
llm.Client (timeout 20s->60s). llm.Client reads reasoning_content when
content is empty (thinking models).
Docs: TTS piper-student plan (OmniVoice teacher -> piper student, from
scratch, phoneme-first). CLAUDE.md training guide.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Add reactive_notes_test.go: tests for context-aware reactive nudge
generation using LLM phraser with dialogue history.
- Add docs/plans/2026-07-10-router-lfm-foundation.md: architecture research
on replacing classifier cascade with LFM-based router.
claude
kami