progress+roadmap: sync with third-session work, mark stale items

PROGRESS.md:
- remove Kuma from 'Wired but needs deploy' (key wired in eda434f)
- remove cold-start unlock from 'Not built yet' (built in b0932a1+15fe7bb)
- add third-session block: cold-start unlock, conversation depth,
  routing+persona — with the cold-start test gap called out
- update gap #2: anaphora + cross-intent landed (05236ad)
- update gap #6: note download-embedder + query_min_score knob
- remove 'Personality prompt' from Future (landed in b7eb53a)
- add caveat: cold-start unlock tests missing (3 required cases absent)

ROADMAP.md:
- add Status line under every item header with commit SHAs + verdict
- summary table gains a Status column
- replace stale 'Recommended order' with 'Remaining work' priority list

PROGRESS.md

@@ -86,8 +86,6 @@ tests, `-race` in `make test`.
 
 - **`desk_active`** (strongest presence signal) — `scripts/desk-active.sh` runs
   on the **desk PC** (hypridle-gated systemd timer), posts over wg to mavweb.
-- **Kuma `service_down`** — needs an API key created in Kuma → Settings → API Keys,
-  passed to `mavpoll -kuma-key`.
 - **`mavwaked`** (always-on listening) — needs a systemd user unit on a client
   box (desk PC, pi, etc.) where the mic is attached. Connects to mavend over wg
   or local net via `-addr`. Deferred until a client box is wired with a mic.
@@ -107,6 +105,13 @@ Caveats / gotchas:
   -wg` flag exists (defaults `""`) and could later back the spec's "away override"
   by flipping the sign; as a presence-*here* signal it's inverted. desk_active +
   page_heartbeat cover home presence.
+- **Cold-start unlock tests are missing** — the key wrap/unwrap code
+  (`internal/webauthn/keywrap.go`) and locked-mode IPC gating (`cmd/mavend/main.go`)
+  are correct but have **zero test coverage**. The roadmap (item 2.1) required
+  three new test cases (wrap/unwrap round-trip, wrong-cred unwrap fails,
+  locked-mode IPC rejects non-unlock methods); none were written. `make test`
+  is green by omission. Write these before relying on the cold-start path with
+  real keys.
 
 ### Done since last revision (overnight-jul6, 2026-07-06)
 
@@ -125,6 +130,41 @@ Since then (**2026-07-06, second session**):
   `Makefile` `build-waked` target. Runs on client boxes (not docker/homesrv)
   via systemd user unit; connects to mavend over wg or local net.
 
+Since then (**2026-07-06, third session** — roadmap execution agent):
+
+- **Cold-start unlock (ROADMAP 2.1)** — the at-rest AES key is now wrapped
+  (HKDF-SHA256 + AES-256-GCM, stdlib-only — no `x/crypto` dep) with the passkey
+  credential's public key and persisted to disk. At boot, if a wrapped key file
+  exists AND no env key is set, mavend starts **locked**: the IPC server runs
+  but `srv.Check` rejects everything except `MethodAssertStepUp` +
+  `MethodUnlock`. A passkey assertion at `/auth/passkey` calls `MethodUnlock`
+  with the credential's public key → unwraps the blob → opens the store → wires
+  voice/loop/delivery → `srv.SetAPI` swaps the locked stub for the real
+  CoreAPI. mavweb's `RegisterFinish` wraps the env key on enrollment;
+  `AssertFinish` calls `Unlock` on assertion. Env-key fallback preserved
+  (dev/CI path unchanged). **Test gap:** the roadmap required three new test
+  cases (wrap/unwrap round-trip, wrong-cred unwrap fails, locked-mode IPC
+  rejects non-unlock methods) — none were written. The code is correct but
+  untested; `make test` is green by omission, not coverage.
+- **Conversation depth (ROADMAP 3.2)** — cross-intent anaphora + fact-by-key
+  lookup. `AnaphoraResolver` in `router/slots.go` detects RU pronouns
+  (это/он/она/оно/тот/мой + inflected forms). `followUpMerge` now handles
+  three cases: same-intent slot inheritance (existing), cross-intent anaphora
+  (Query/Fact/Reminder after a Fact with a pronoun inherits the prior key +
+  time), and query-after-fact (a query following a fact inherits the key for
+  fact-by-key lookup). `Session.History []Turn` added as the multi-turn
+  scaffold (capped at 4). 7 new test cases including the exact done-when
+  scenarios (anaphora query-after-fact, three-turn break, explicit-key-wins).
+- **Routing quality + persona (ROADMAP 4.1/4.4)** — `QueryMinScore` is now a
+  config knob (`voice.query_min_score`, default 0.55) instead of a hardcoded
+  const. `make download-embedder` fetches Xenova/paraphrase-multilingual-
+  MiniLM-L12-v2 (~90MB ONNX) + tokenizer; AGENTS.md documents the embedder +
+  libonnxruntime setup. `Persona` field in `VoiceConfig` prepends to every
+  LLM system prompt (nudge phrasing, note queries, general knowledge); empty
+  = current hardcoded feminine-gendered Russian persona. Also fixed two
+  pre-existing data races found by `-race`: `voice/server.go` wg.Add vs
+  wg.Wait (accept mutex), `mavweb/server.go` s.api field (atomic.Value).
+
 - **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
@@ -204,10 +244,7 @@ The overnight session (`SESSION-05-07-2026.md`, 25 tasks) closed the previous
 
 ### Not built yet (ranked by ROI)
 
-1. **Cold-start unlock** — the at-rest key still comes from env/config; the
-   passkey→key L3 dance is a documented seam, not a feature. Until then the key
-   sits in the container env.
-2. **Multi-user (SPEC item 8)** — deliberately deferred, see the tail.
+1. **Multi-user (SPEC item 8)** — deliberately deferred, see the tail.
 
 Closed (jul6 follow-ups): `/api/revert` now sits behind the same passkey
 step-up as POST `/tools`; `go.mod` direct deps (`onnxruntime_go`,
@@ -260,13 +297,16 @@ first — these define the category:
    Hardware: the mic lives on a client box (desk PC, pi, etc.) — never the
    homesrv. Deploy action: systemd user unit on whichever box has the mic,
    connects to mavend over wg or local net.
-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.
+2. **Conversation is deeper now, still not full dialogue.** The router
+   classifies one utterance → one reply, but `internal/dialogue` carries
+   context across turns: a 2-min session inherits slots for same-intent
+   follow-ups («напомни завтра» → «…позвонить маме»), and cross-intent
+   anaphora («запиши что я пил воду» → «когда я это сделал?») now resolves
+   RU pronouns (это/он/она/оно/тот/мой + inflections) to the prior turn's
+   key for fact-by-key lookup. `Session.History []Turn` is the scaffold for
+   real multi-turn. Still missing: LLM-driven dialogue manager (decide
+   ask-vs-act), anaphora beyond RU pronouns, single-slot session (single-user
+   box). 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.
@@ -284,7 +324,9 @@ Capability-class gaps — built but thin:
    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".
+   "clarify". `make download-embedder` now fetches the multilingual MiniLM
+   model + AGENTS.md documents libonnxruntime setup; `voice.query_min_score`
+   is a config knob (default 0.55) so the floor can be tuned without recompile.
 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 is now persistent (store-backed), not the spec's chroma.**
@@ -297,8 +339,8 @@ Capability-class gaps — built but thin:
    `IntentQuery` reads it back (after notes-RAG misses, before general-knowledge)
    — fact recall («когда я пил воду?») is its distinct payoff. The in-memory
    impl remains the test/no-store floor. Remaining: an ANN/external index is
-   optional-scale, not a gap. Persona prompt and custom TTS voice (kami-picked,
-   replaces the irina floor — [[custom-voice-training]]) are still future items.
+   optional-scale, not a gap. Custom TTS voice (kami-picked, replaces the irina
+   floor — [[custom-voice-training]]) is still a future item.
 
 Ops footnote: voice-over-web verified 2026-07-06 — mavend binds 0.0.0.0:9100
 and mavweb reaches it cross-container at mavend:9100 (nc -z confirmed).
@@ -306,8 +348,8 @@ mavpoll uses network_mode=host to reach localhost services (netdata, kuma).
 
 ### Future / logged, not now
 
-Personality prompt; custom TTS voice training (kami-picked voice, replaces irina
-floor); listening modes 2–3 (meeting-record, ambient-derive).
+Custom TTS voice training (kami-picked voice, replaces irina floor); listening
+modes 2–3 (meeting-record, ambient-derive).
 
 ### Services & layout