diff --git a/PROGRESS.md b/PROGRESS.md index d32cf65..e37ee74 100644 --- a/PROGRESS.md +++ b/PROGRESS.md @@ -1,13 +1,17 @@ -## Maven — current state (2026-07-05) +## Maven — current state (2026-07-06) Consolidated status. The reactive↔proactive core is closed and testable through the web PWA. The SPEC's open items 1–7 are landed (protocol doc, away-channel fallthrough, CalDAV poller, quiet-hours schedule, tools enable/disable, note RAG, passkey step-up); item 8 (multi-user) is deliberately deferred — see the tail. -The two big infra gaps from the last revision are now closed on `overnight-jul5`: +The two big infra gaps from the jul5 revision are closed on `overnight-jul5`: **at-rest encryption** (AES-256-GCM, tmpfs working copy — not sqlcipher, see `internal/store/crypt.go`) and **Docker deployment** (one image, six daemon -containers). ~14.6k LOC + ~8.1k test, 284 tests, `-race` in `make test`. +containers). The `overnight-jul6` session (now on `master`) closed the biggest +*query-surface* gaps — **calendar querying, general-knowledge answers, and +weather** — plus a populated homelab act allowlist and two pure scaffolds +(dialogue state, long-term-memory vector store). ~15.2k LOC + ~8.5k test, 303 +tests, `-race` in `make test`. ### Access model @@ -93,7 +97,49 @@ Caveats / gotchas: by flipping the sign; as a presence-*here* signal it's inverted. desk_active + page_heartbeat cover home presence. -### Done since last revision (overnight-jul5, 2026-07-05) +### Done since last revision (overnight-jul6, 2026-07-06) + +Seven tasks (`SESSION-06-07-2026.md`), one commit each, merged to `master`. +This session was run through **opencode**, not Claude Code (co-author trailer). + +- **Calendar querying (task 3)** — "что у меня завтра?" now answers from the + CalDAV facts the poller already writes. Added `store.CalendarEvents(from,to)`, + a RU date-scope parser («сегодня»/«завтра») in `router/slots.go`, and an + IPC `CalendarEvents` RPC (api/client/server/wire) feeding the `IntentQuery` + handler. Empty day → «на сегодня ничего нет». Previously calendar only *gated* + nudges; it's now queryable. +- **General-knowledge routing (task 4)** — when notes-RAG misses `queryMinScore`, + the query now falls through to the phraser with an anti-hallucination system + prompt (`router.KnowledgePrompt`, single tested source) instead of giving up. + Empty/errored/Stub phraser → «не знаю.», never a fabrication. +- **Weather (task 5)** — new `internal/weather/`: `Provider` interface, a stub + («погода не настроена»), and a real **keyless Open-Meteo** provider (geocode + + current_weather, injectable `*http.Client`, mocked in tests — no live network). + Wired into `IntentQuery` (keywords погода/градус/температура) with a ~5s + context timeout; selected by `voice.weather.provider` ("open-meteo" | "" → stub). +- **Homelab act allowlist (task 2)** — `voice.tools` seeded with read-only acts + (`systemctl status`, `docker ps`, `uptime`, `df`, `free`, `journalctl` reads) + as `destructive:false` and mutating ones (restart/stop/start/reboot, + docker-restart/stop) as `destructive:true`. Guardrail verified: no dangerous + verb is `destructive:false`. RU phrasings seeded in `act.txt`. +- **Embedder config validation (task 1)** — a partially-filled `voice.embedder` + block (some of model/tokenizer/lib paths missing) is now a load error instead + of a silent fall-through to the Hash floor; the floor fallback logs explicitly. +- **Dialogue state scaffold (task 6)** — `internal/dialogue/`: `Session` + + TTL `SessionStore` + pure `InheritSlots`. **Library only — not wired** into the + live path (wiring left as the plan's optional BLOCKED tail). This is the + substrate for future multi-turn (gap #2), not conversation itself yet. +- **Long-term memory interface (task 7)** — `internal/memory/`: `Store` interface + + `InMemoryStore` (cosine). Wired into `IntentNote`: after `WriteNote` the note + embedding is `Insert`ed best-effort (log-and-continue, never fails the write). + In-memory only — no external vector backend yet (gap #8 remains). + +Follow-ups (Claude Code, post-merge): gofmt'd `handlers_test.go` (the jul6 +verification commit left it misaligned, so `gofmt -l` still flagged it despite the +"all gates green" claim); deduped the task-4 knowledge prompt to the single tested +`router.KnowledgePrompt()`. Tree is now genuinely green (gofmt/vet/303 tests). + +### Done since the jul5 revision (overnight-jul5, 2026-07-05) The overnight session (`SESSION-05-07-2026.md`, 25 tasks) closed the previous "not built yet" items 1–3 and added feature depth: @@ -177,7 +223,7 @@ Also fixed: semantic `query`. Earlier: notes/query recall, `/dash` monitoring, `wg_handshake` poller (NO-OP). -### Gaps — why "voice assistant" is still aspirational (2026-07-05) +### Gaps — why "voice assistant" is still aspirational (2026-07-06) What separates Maven today from the thing the spec describes. Dealbreakers first — these define the category: @@ -188,29 +234,36 @@ first — these define the category: kitchen. Highest-leverage gap — a wake word + speaker device changes what Maven *is*, not just how good it is. (Listening modes 2–3 in maven.md.) 2. **No conversation.** The router classifies one utterance → one reply. No - follow-ups, no anaphora ("а когда?"), no dialogue state beyond the 90s - destructive-confirm park. The sub-1B phraser only words replies; nothing - converses. + follow-ups, no anaphora ("а когда?"). A dialogue-state scaffold exists + (`internal/dialogue`, jul6 task 6 — session TTL + `InheritSlots`) but is + **not wired** into the live path; the only runtime multi-turn state is still + the 90s destructive-confirm park. The sub-1B phraser only words replies. 3. **Latency/shape of a turn.** Clip-based STT (record → upload → whisper → route → phrase → piper → play). No streaming either direction, no barge-in; every exchange is a full round trip. Capability-class gaps — built but thin: -4. **Act surface is a handful of argv allowlist entries.** propose→enable - works; until populated, "acts on your homelab" is mostly potential. -5. **Query answers cover notes + a few built-ins.** No weather, no calendar - *querying* (calendar only gates nudges), no general knowledge; the - cheatsheet promises more than the router delivers. +4. **Act surface is a small argv allowlist.** propose→enable works and the + allowlist now ships a homelab starter set (jul6 task 2 — status/ps/uptime/ + df/free/logs read-only, restart/stop/reboot gated). Still bounded to what's + seeded; broadening it is config, not code. +5. **Query answers now cover notes + calendar + weather + general knowledge** + (jul6 tasks 3/4/5). Calendar querying, keyless Open-Meteo weather, and a + phraser knowledge-fallback all landed; caveat — general-knowledge quality is + only as good as the sub-1B phraser, and weather needs `voice.weather.provider` + set. The cheatsheet and router are now roughly aligned. 6. **Routing quality depends on the ONNX embedder being configured** — the HashEmbedder floor makes RU recall lexical/weak; many commands fall to "clarify". 7. **Presence is effectively one signal** (page_heartbeat); desk_active is still an undeployed script — "voice when near" routing runs on a guess. -8. **Long-term memory per spec (obsidian → chroma) doesn't exist** — sqlite - brute-force cosine over notes is recall, not personalization. Persona - prompt and custom TTS voice (kami-picked, replaces the irina floor) are - still future items. +8. **Long-term memory per spec (obsidian → chroma) is still stubbed** — jul6 + task 7 added an `internal/memory` `Store` interface + an in-memory cosine + impl, and note writes now insert into it best-effort, but there's no + persistent/external vector backend and nothing reads it back yet. It's a + seam, not personalization. Persona prompt and custom TTS voice (kami-picked, + replaces the irina floor — [[custom-voice-training]]) are still future items. Ops footnote: in the Docker deploy, voice-over-web needs mavend to bind its voice server on 0.0.0.0:9100 — unverified on the target host; until then the