MaxAttempts was 1, justified as "not a nag". Wrong reading: "not a nag" is about
interrupting unprompted, and a clarifying question is part of a conversation he
started. Now three, configurable via voice.clarify_max_attempts (default 3).
Three, because after that the likely problem is she misheard the whole request,
not one slot.
Answer used to keep the parked value, so "в три" then "нет, в пять" threw the
five away. Now a value the answer carries wins for the slot she asked about.
Only for the clarify answer — a correction in a fresh turn is followUpMerge.
The eight-field chained assertion in the Answer test is one DeepEqual now, so a
new field in Slots is covered without touching the test.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
The e5 embedder puts every cosine in one narrow band (0.79-0.89), so the
absolute query_min_score gate cannot tell a real hit from a made-up
question: any value under the band answers everything, any value above it
answers nothing. False recall was 5/5.
New gate asks whether one note is clearly the best instead: top1 - top2 >
delta. New query_min_margin config knob, default 0.008, read off the sweep
in the recall harness. The absolute floor stays as a second check.
On the recall fixture with e5: answered 72% -> 68%, false recall 5/5 -> 1/5.
Vikunja #359
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
The two things that made this unsafe are fixed: the router can now
refuse, and slot extraction runs on its decisions.
On the held-out fixture it gets 63.2% of intents right against the
classifier's 50.0%, with no route errors. It costs about a second a
turn instead of 30ms.
The flag is a pointer now, so leaving it out of the config means on
and only writing false turns it off.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
Chose an 8th enum value over a confidence number: the model already picks
one enum token, so it costs nothing in the grammar, while a score from a
0.8B model would be uncalibrated noise. A refusal returns "no decision"
with no error, which is the fall-through the caller already uses for a
bad parse, so the classifier and its clarify gate take the turn.
Reviewers: the prompt's counter-examples matter most — a small model will
over-use any easy escape hatch. The training workspace copy of the prompt
still needs the same edit (Vikunja #362).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
Wires cmd/mavend/voice.go to build the LLM router when the operator asks
for it. Default false, so nothing changes on the deploy box.
Look at pickLLMRouter: the flag on with no llama-server logs one line and
keeps the classifier, it never fails a turn.
The default stays off until the router can refuse (#359) and the extractor
runs on LLM decisions — both noted as TODOs in config.go.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
Backlog item #3 (20-07-2026-BACKLOG.md). A morning routine is a checklist for
a daily window: several items, each evidenced by a fact key, completed in any
order, checked once near the end of the window. Modelling it as four
independent reminder timers would stack into exactly the kind of noise Maven is
supposed not to produce, so the engine nags at most once per day per routine
and only for what is actually still missing.
internal/morning follows the established pure-engine pattern (loop, routine,
pattern): no store, no clock of its own. Evaluate answers "what's still
missing" at any point; Due decides whether to nag. The impurity — reading
facts under the store lock, holding the last-nudge map across ticks — stays in
the tick driver, which calls Due each tick exactly as it does for loop.Rule
and routine.Routine.
Completion evidence is a fact key's latest non-voided value timestamped inside
today's window, so manual ("выпил воды", voice-tapped) and inferred (another
daemon writing the same key) are indistinguishable and both count. Weekdays
scopes which days a routine applies to, so weekday/weekend variants are two
routine rows rather than a special case in the engine.
Exposed read-only: a MorningStatus RPC over ipc, and a /morning page in mavweb
built on the same server-rendered shape as /trace — no live-update loop, since
checklist state moves on the scale of minutes.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X5JApcrCRVGmqrxnhynSik
facts gain a Subject/EntityID/ResolutionState triple and an async
enrichment worker that resolves free-text subjects to canonical Nexus
entity_ids, mirroring Praxis's enrichment-worker pattern. Ambiguous or
unreachable Nexus never guesses an entity_id — the fact stays pending
or terminal-ambiguous instead.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018ghELqYhZNLub2TXGMazqA
Bring the Nexus/Praxis/Hexis integration in line with
MAVEN_ECOSYSTEM_ARCHITECTURE.md:
- Praxis over HTTP: drop the in-process praxis.db open (praxisstore/
praxistools) and call praxisd's /api/v1/tools/* API via a new praxisClient.
Honors the "no component reads another's DB" invariant (AC#12).
PraxisConfig.DBPath -> URL.
- Hexis confirmation gate: mutating capabilities (ReadOnly=false) now park a
bound pendingHexis confirmation and require a spoken "да" before executing;
read-only run immediately (AC#7, no auto attention->action).
- Capability safety: >1 verb match is ambiguous -> ask instead of firing the
first; ambiguous Nexus resolution asks for clarification (AC#2).
- Correlation IDs on Hexis execute, recorded in the cross-service trace.
- Bug: importance arrives as JSON float64 over HTTP, not int.
- Tests: confirm-gate, decline, read-only, and ambiguity paths.
Build: vendor/ bakes in the hexis client (replace-directed at a sibling repo
outside the Docker context); Dockerfile builds from vendor and no longer
`go mod download`s the unreachable replace paths.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
three bugs causing time queries to land on reminder or fact intent:
- seed collision: query.txt and system.txt shared identical time/date
seeds (который час, сколько времени), making system intent
indistinguishable from query intent in centroid space
- threshold (0.35) too low for ONNX embedder — cosine similarities
cluster 0.5-0.7 for related intents, so Clarify never fired
- reminder centroid contaminated by time-lexicon (every seed has a time
expression), pulling any time-word utterance toward reminder intent
fixes:
- remove 3 duplicate time/date seeds from query.txt (keep in system.txt)
- DefaultRouterThreshold 0.35 -> 0.55
- stage-0 grammar for напомни/remind me -> IntentReminder, bypasses
classifier (fixes 'напомни через час' being misrouted to fact)
- stage-0 grammars for time/date system queries (сколько времени,
который час, какой сегодня день) -> IntentSystem, with Build filter
to exclude elapsed/duration queries (сколько времени прошло)
- time parser fallback in applyAction for stage-0 reminder matches
(extractor doesn't run on stage-0 decisions)
- VoiceConfig: add QueryMinScore (default 0.55) + Persona config fields
- voice.go: remove queryMinScore const, wire from cfg.Voice.QueryMinScore
as reactiveHandler field
- llmphraser.go: add Persona to Config, prepend to system prompts in
chat and query paths (systemPrompt/querySystemPrompt methods)
- main.go: pass personaFromCfg into both phraser config blocks
- Makefile: add download-embedder target (Xenova/paraphrase-multilingual-
MiniLM-L12-v2, ~90MB ONNX)
- AGENTS.md: document embedder model download + libonnxruntime setup
- server.go: fix pre-existing wg.Add vs wg.Wait data race using accept
mutex. make test green, zero races across all 29 packages.
Two additive proactive/recall features.
Routines (internal/routine): a third proactive class beside reminders
(user-stated) and care rules (world-state) — operator-declared clockwork.
config.routines[] (cron + literal RU body + severity) fire through the
normal dispatcher on schedule. Bodies are literal, not LLM-phrased (can't
hallucinate); rule name routine:<name> keeps them out of the care
autotuner; a cold-start guard seeds on first sight so a restart never
replays a missed schedule. Pure routine.Due + config validation, unit-
tested; the tick driver holds the last-fired map and calls fireRoutines.
Persistent memory (internal/store/memory.go): store.MemoryStore backs the
memory.Store interface with the SAME encrypted sqlite db — survives
restarts and recall text inherits at-rest encryption (no plaintext
sidecar). float32-blob vectors, brute-force cosine (ANN is a later swap
behind the interface), upsert-by-id. The daemon wires st.VectorMemory()
into wireVoice; the in-memory impl stays the test/no-store floor. Closes
the "in-memory only, lost on restart" gap (PROGRESS #8).
Gate green: gofmt/vet clean, -race across routine/config/store/mavend.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01U2PNdwDj2Gt8YW294J7oSc
- Add CalendarEvents method to recordingAPI in auth_test.go
- Add CalendarEvents method to fakeCore in handlers_test.go
Co-Authored-By: opencode <opencode@anthropic.com>
- New internal/weather/ package: Provider interface, Weather struct, StubProvider
- OpenMeteoProvider with geocoding + current weather (keyless, free API)
- Config: WeatherConfig in VoiceConfig (provider, default_location)
- Wire in voice.go as weatherProvider on reactiveHandler
- Handle weather queries in IntentQuery (before notes RAG)
- Helper: isWeatherQuery / extractWeatherLocation
- Tests: mocked HTTP round-trip for OpenMeteo, stub ErrNotConfigured, config tests
- No real network calls in any test
Co-Authored-By: opencode <opencode@anthropic.com>
When enabled, eligible nudges (sev ≤ ceiling) are queued in memory
instead of sent immediately. Every 'window' duration (or when
'max_items' reached), the queue is flushed as a single digest
notification with concatenated bodies.
Config:
digest:
enabled: true # default false
window: 30m # flush window (default 30m)
max_items: 5 # flush at this count (default 5)
severity_ceiling: 2 # max sev batched (default 2; sev3+ bypass)
Changes:
- config.go: add DigestConfig struct with defaults
- tick.go: QueuedNudge type, digest queue/flush in TickLoop,
shouldQueue/maybeFlush/flushDigest helpers
- main.go: pass cfg.Digest to newTickLoop
- tick_test.go: 6 new tests covering queue, flush, bypass, dedup
Add a 'scope' TEXT column (default 'homelab') to the tools table so tools
can be namespaced by scope (e.g. "homelab:restart", "datacenter:reboot").
Backward-compat: bare name defaults to "homelab" scope.
Changes:
- Migration #1: ALTER TABLE tools ADD COLUMN scope
- store.Tool: add Scope field, update all SQL and scanTool()
- ipc.Tool DTO and request types: add Scope field
- CoreAPI interface: pass scope in ProposeTool/EnableTool
- storeAPI adapters: forward scope
- cmd/mavend/voice: pass scope (empty → homelab)
- cmd/mavweb/tools: show scope column in UI tables, hidden fields
- All tests updated for scope field
- Migration test made dynamic (startVer = len(migrations))
Two spine infra items (feature-ranking #1, part of the migration prereq):
- migrations.go: PRAGMA user_version runner, empty (no-op) migration slice,
one tx per step, fail-closed. Mechanism in place before any real schema
change needs it.
- crypt.go: file-level at-rest encryption. On-disk file is always AES-256-GCM
ciphertext; decrypted to a tmpfs working copy modernc sqlite operates on;
re-encrypted atomically on Close, plaintext wiped, key zeroed. Pure stdlib,
CGO stays off. Fails closed on wrong key/tamper, never falls back to
plaintext. Key is a 32-byte seam (config db_key_b64/db_key_env today; the
passkey-derived L3 cold-start key plugs into the same seam later).
Chosen over cgo SQLCipher (would force libsqlcipher + CGO across the project)
and over the ncruces page-level VFS (swaps the driver project-wide); noted as
the upgrade path in a ponytail: comment. Threat model is disk-at-rest only.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Adds QuietHours config section (start/end as HH:MM local time). The loop's
gatherer checks the window each tick: if now falls within [start, end), the
State.QuietHours flag is set to true regardless of the config fact (which
the voice toggle writes independently). Both sources activate quiet —
schedule AND toggle.
Handles midnight-crossing windows (23:00-08:00). The gate already reads
State.QuietHours for care nudge suppression — no gate change needed.
piper_handler: close stdin/stdout pipes on Start() failure and on
WriteString error instead of leaking fds. Propagate WriteString error.
worker/client: log SetDeadline errors instead of discarding them.
voice/session: pushAudio marshals params inline and returns the marshal
error instead of swallowing it via mustParams (removed).
tool/matcher: log ListTools errors instead of silently returning an
empty allowlist that refuses every act.
config: applyDefaults now sets RouterThreshold and ToolTimeout defaults
so consumers self-contained defaults are belt-and-suspenders.
worker/server.go: dispatch now receives a per-connection context instead of
context.Background(), so handler cancellation propagates on conn close.
voice/server.go: same — per-conn context fed through safeDispatch into
HandlePushToTalk instead of context.Background().
store/reminders.go: propagate LastInsertId error.
store/nudges.go: propagate LastInsertId and RowsAffected errors.
store/tools.go: propagate RowsAffected error.
config/config.go: applyDefaults now respects StateDir when set, using it as
the base for empty DBPath/SocketPath instead of silently ignoring it.
phraser/llmphraser.go: close stderr pipe fd when cmd.Start() fails.
kami