progress: dialogue and memory now wired (tasks 6/7 follow-up)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

PROGRESS.md

@@ -126,13 +126,13 @@ This session was run through **opencode**, not Claude Code (co-author trailer).
   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.
+  TTL `SessionStore` + pure `InheritSlots`. **Now wired** (post-merge follow-up):
+  the voice handler carries slots across same-intent turns within a 2-min window
+  (`followUpMerge`, unit-tested) — bounded gap-filling, not full multi-turn 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).
+  + `InMemoryStore` (cosine). Wired into `IntentNote` (best-effort insert) and,
+  post-merge, into `IntentFact` (facts indexed) + `IntentQuery` (read-back after
+  notes-RAG misses). In-memory only — no persistent backend yet (gap #8).
 
 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
@@ -233,11 +233,13 @@ first — these define the category:
    Today it's a dictaphone with a brain, not something you talk to across the
    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?"). 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.
+2. **Conversation is thin, not absent.** The router still classifies one
+   utterance → one reply and there's no anaphora resolution or LLM-driven
+   dialogue. But `internal/dialogue` is now **wired** (jul6 task 6 + follow-up):
+   a 2-min session carries slots across turns, so a same-intent follow-up
+   («напомни завтра» → «…позвонить маме») inherits the earlier time. Bounded to
+   same-intent gap-filling — cross-intent anaphora and real multi-turn dialogue
+   are still future. 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.
@@ -258,11 +260,13 @@ Capability-class gaps — built but thin:
    "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) 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,
+8. **Long-term memory is in-memory only, not the spec's chroma.** `internal/
+   memory` (jul6 task 7 + follow-up) has a `Store` interface + in-memory cosine
+   impl; notes **and facts** are indexed on capture, and `IntentQuery` now reads
+   it back (after notes-RAG misses, before general-knowledge) — fact recall
+   («когда я пил воду?») is its distinct payoff. Still missing: a persistent/
+   external vector backend (the store is lost on restart) — the read seam is
+   there to swap onto one. 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