Close a Vikunja task with done, and nothing else (V-641)

Owner's call, 07-08-2026. A completion summary written into the
description on the way out is lost anyway, and the durable record is the
commit messages and the merged PR.

Written during the V-641 session and left uncommitted; it rides this
branch rather than being dropped.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YMNNEkYx1mZFtHNrFk7uqb

CLAUDE.md

@@ -101,9 +101,15 @@ protocol; the config in `deploy/mavend.json` (with `${VAR}` env expansion from g
 Count against compose, not against the table. Four of the nine daemons are absent, and each
 absence has a different reason.
 
-`mavmaild` is commented out in compose, with the reason written beside it: it needs a mail
-account and this box has none. `mavcaldav` appears nowhere at all, and unlike the other
-three that is an oversight rather than a decision (V-644).
+`mavmaild` and `mavcaldav` are commented out in compose, each with the reason written
+beside it: the first needs a mail account, the second a CalDAV account, and this box has
+neither. `mavcaldav` used to appear nowhere at all, which was an oversight; it became a
+recorded decision on 07-08-2026 (V-644). Two things ride on that absence and the block
+names them. Agenda questions route to `IntentQuery` at stage 0 (V-498) and the `calendar`
+query source then reads a table nobody writes. And `loop.State.CalendarBusy` is fed by the
+same facts, so the gate's "do not nag mid-meeting" is permanently false. Its password is
+read from a file (`-pass-file`, and `-render-pass-file` for the render collection), never
+taken as a flag value, which is the rule `mavpoll` and `mavmaild` follow too.
 
 **`mavwaked` and `mavenclient` are absent by decision, not oversight** (Vikunja #463,
 `docs/plans/17-where-the-voice-loop-runs.md`).
@@ -454,8 +460,11 @@ start of a session rather than one lookup per first use:
 ToolSearch("select:mcp__vikunja__list_tasks,mcp__vikunja__get_task_details,mcp__vikunja__create_task,mcp__vikunja__update_task")
 ```
 
-`update_task` carrying a `description` resets `done` to false, so closing a task with a
-write-up takes two calls: the description, then `done: true`.
+**Close a finished task with `done: true` and nothing else** (owner's call, 07-08-2026).
+Do not write a completion summary into the description on the way out. It is lost anyway,
+and the durable record is the commit messages and the merged PR. Note that `update_task`
+carrying a `description` resets `done` to false, which is why a write-up ever took two
+calls.
 
 ## Session workflow
 

cmd/mavcaldav/main.go

@@ -50,10 +50,10 @@ func run(args []string) error {
 	socket := fs.String("socket", "", "core IPC socket path (required)")
 	url := fs.String("url", "", "CalDAV calendar URL, e.g. http://localhost:5232/kami/personal (required)")
 	user := fs.String("user", "", "CalDAV basic-auth username (required)")
-	pass := fs.String("pass", "", "CalDAV basic-auth password (required)")
+	passFile := fs.String("pass-file", "", "file holding the CalDAV basic-auth password (required — never passed as a flag value)")
 	renderURL := fs.String("render-url", "", "CalDAV collection maven publishes her own reminders to; empty disables rendering")
 	renderUser := fs.String("render-user", "", "basic-auth username for -render-url (defaults to -user)")
-	renderPass := fs.String("render-pass", "", "basic-auth password for -render-url (defaults to -pass)")
+	renderPassFile := fs.String("render-pass-file", "", "file holding the password for -render-url (defaults to -pass-file)")
 	renderDur := fs.Duration("render-duration", calendar.DefaultReminderDuration, "how long a rendered reminder occupies")
 	interval := fs.Duration("interval", 5*time.Minute, "poll cadence")
 	timeout := fs.Duration("timeout", 10*time.Second, "per-request HTTP timeout")
@@ -63,13 +63,22 @@ func run(args []string) error {
 	if *socket == "" {
 		return fmt.Errorf("-socket is required")
 	}
-	if *url == "" || *user == "" || *pass == "" {
-		return fmt.Errorf("-url, -user, -pass are required")
+	if *url == "" || *user == "" || *passFile == "" {
+		return fmt.Errorf("-url, -user, -pass-file are required")
 	}
 	if err := checkRenderTarget([]string{*url}, *renderURL); err != nil {
 		return err
 	}
 
+	// The password is read from a file, never taken as a flag value: an argv
+	// secret is visible in `ps` to every user on the box and lands in the compose
+	// file and the shell history. Same rule mavmaild and mavpoll follow. Read
+	// once at start, so a rotated password means a restart.
+	pass, err := readSecret(*passFile)
+	if err != nil {
+		return err
+	}
+
 	ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGINT, syscall.SIGTERM)
 	defer stop()
 
@@ -85,17 +94,20 @@ func run(args []string) error {
 		http: hc,
 		url:  strings.TrimRight(*url, "/"),
 		user: *user,
-		pass: *pass,
+		pass: pass,
 	}
 
 	var rend *renderer
 	if *renderURL != "" {
-		ru, rp := *renderUser, *renderPass
+		ru, rp := *renderUser, pass
 		if ru == "" {
 			ru = *user
 		}
-		if rp == "" {
-			rp = *pass
+		if *renderPassFile != "" {
+			rp, err = readSecret(*renderPassFile)
+			if err != nil {
+				return err
+			}
 		}
 		rend = newRenderer(core, hc, *renderURL, ru, rp, *renderDur)
 		log.Printf("mavcaldav: rendering reminders to %s", *renderURL)
@@ -131,6 +143,21 @@ func run(args []string) error {
 // It takes the whole read set, not one URL. The guarantee in the package
 // comment is about every calendar maven reads, and a second read target added
 // later must not quietly fall outside the check.
+// readSecret reads one credential from a file and refuses an empty one. An
+// empty file is a deployment mistake, not a password, and CalDAV basic auth
+// would send it and get a 401 every poll.
+func readSecret(path string) (string, error) {
+	raw, err := os.ReadFile(path)
+	if err != nil {
+		return "", fmt.Errorf("read password file: %w", err)
+	}
+	secret := strings.TrimSpace(string(raw))
+	if secret == "" {
+		return "", fmt.Errorf("password file %s is empty", path)
+	}
+	return secret, nil
+}
+
 func checkRenderTarget(readURLs []string, renderURL string) error {
 	if renderURL == "" {
 		return nil

cmd/mavcaldav/main_test.go

@@ -5,12 +5,38 @@ import (
 	"fmt"
 	"net/http"
 	"net/http/httptest"
+	"os"
+	"path/filepath"
 	"testing"
 	"time"
 
 	"github.com/kami/maven/internal/ipc"
 )
 
+// The password comes from a file so it never reaches argv. An empty or missing
+// file must fail at start rather than authenticate as "" against his calendar.
+func TestReadSecret(t *testing.T) {
+	dir := t.TempDir()
+	good := filepath.Join(dir, "ok")
+	if err := os.WriteFile(good, []byte("  hunter2\n"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if got, err := readSecret(good); err != nil || got != "hunter2" {
+		t.Fatalf("readSecret(good) = %q, %v; want \"hunter2\", nil", got, err)
+	}
+
+	empty := filepath.Join(dir, "empty")
+	if err := os.WriteFile(empty, []byte("\n \n"), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := readSecret(empty); err == nil {
+		t.Fatal("readSecret(empty) = nil error, want refusal")
+	}
+	if _, err := readSecret(filepath.Join(dir, "absent")); err == nil {
+		t.Fatal("readSecret(absent) = nil error, want refusal")
+	}
+}
+
 type fakeCore struct {
 	ipc.UnimplementedCoreAPI
 	facts    map[string]ipc.Fact // composite key "key|source" → Fact

docker-compose.yml

@@ -157,6 +157,44 @@ services:
   #     - maildata:/var/lib/mavmaild
   #     - ./deploy/imap.password:/run/secrets/imap.password:ro
 
+  # The calendar reader (Vikunja #644) is OFF and commented out: it needs a
+  # CalDAV account, and there is none on this box. It was built, listed in
+  # `make build`, and deployed nowhere, which is the worst of the three states —
+  # this block records the decision instead.
+  #
+  # What its absence costs, so the cost is visible from here:
+  #   - Agenda questions route correctly and answer from nothing. Stage 0 sends
+  #     "что у меня сегодня" to IntentQuery (V-498) and the `calendar` query
+  #     source reads facts(kind=env, source=caldav:*) that nobody writes.
+  #   - The nudge gate loses a suppressor. loop.State.CalendarBusy is fed by
+  #     those same facts, so "do not nag mid-meeting" is permanently false.
+  #
+  # Core never sees the CalDAV password: the reader polls the collection itself
+  # and hands core one fact per event over WriteFact. Nothing here can create a
+  # reminder, so a misread event cannot fire.
+  #
+  # The password is read from a FILE, so it never appears in `ps`, in this file,
+  # or in shell history — the same rule mavpoll and mavmaild follow.
+  #
+  # To enable: write the password to deploy/caldav.password (0600, gitignored),
+  # point -url at the collection, and uncomment this service. No mavend.json
+  # block is needed — events arrive over IPC as facts. -render-url is optional
+  # and OFF here: it publishes Maven's own reminders back as events, and it must
+  # not name the collection -url reads, or the poller reads its own writes back
+  # in (checkRenderTarget refuses that). It takes -render-pass-file, and falls
+  # back to this password when that is not given.
+  # mavcaldav:
+  #   <<: *image
+  #   command: ["mavcaldav", "-socket", "/run/maven/mavend.sock",
+  #             "-url", "http://localhost:5232/kami/personal",
+  #             "-user", "kami",
+  #             "-pass-file", "/run/secrets/caldav.password",
+  #             "-interval", "5m"]
+  #   depends_on: [mavend]
+  #   volumes:
+  #     - sockets:/run/maven
+  #     - ./deploy/caldav.password:/run/secrets/caldav.password:ro
+
 volumes:
   dbdata:
   sockets:

internal/rss/poller.go

@@ -89,8 +89,8 @@ type Poller struct {
 	ranker  Ranker
 	cfg     Config
 	nextDue map[string]time.Time
-	seen    map[string]map[string]bool // feed → item ID, for items with no date
-	polled  map[string]bool            // feed → polled at least once in THIS process
+	seen    map[string]*seenIDs // feed → item IDs, for items with no date
+	polled  map[string]bool     // feed → polled at least once in THIS process
 }
 
 // NewPoller wires a poller. Returns nil when there is nothing to poll — a
@@ -122,7 +122,7 @@ func NewPoller(feeds []FeedConfig, fetch Fetcher, notes Notes, marks Marks, embe
 		feeds: valid, fetch: fetch, notes: notes, marks: marks,
 		embed: embed, ranker: ranker, cfg: cfg,
 		nextDue: map[string]time.Time{},
-		seen:    map[string]map[string]bool{},
+		seen:    map[string]*seenIDs{},
 		polled:  map[string]bool{},
 	}
 }
@@ -283,6 +283,38 @@ func (p *Poller) mark(ctx context.Context, feed string, now time.Time) (time.Tim
 	return at, true
 }
 
+// maxSeenPerFeed bounds the undated-item set. It has to stay comfortably above
+// any one feed's front page, or an item still listed there would fall out of the
+// set and be written a second time. A few hundred entries covers the largest
+// page anyone publishes, and the set only has to span one poll window plus the
+// resync guard, not all of history.
+const maxSeenPerFeed = 512
+
+// seenIDs is a bounded insertion-ordered set. The map answers the lookup, the
+// slice remembers what to drop first, so an undated feed cannot grow the poller
+// for as long as mavend runs.
+type seenIDs struct {
+	ids   map[string]bool
+	order []string
+}
+
+// add records id and reports whether it was new.
+func (s *seenIDs) add(id string) bool {
+	if s.ids == nil {
+		s.ids = make(map[string]bool, maxSeenPerFeed)
+	}
+	if s.ids[id] {
+		return false
+	}
+	s.ids[id] = true
+	s.order = append(s.order, id)
+	if len(s.order) > maxSeenPerFeed {
+		delete(s.ids, s.order[0])
+		s.order = s.order[1:]
+	}
+	return true
+}
+
 // fresh — two dedup rules, because feeds are inconsistent about dates. A dated
 // item must be newer than the mark; an undated one is kept once per process by
 // ID.
@@ -308,12 +340,11 @@ func (p *Poller) fresh(f FeedConfig, it Item, mark, now time.Time, resync bool)
 		id = it.Title
 	}
 	if p.seen[f.Name] == nil {
-		p.seen[f.Name] = map[string]bool{}
+		p.seen[f.Name] = &seenIDs{}
 	}
-	if p.seen[f.Name][id] {
+	if !p.seen[f.Name].add(id) {
 		return false
 	}
-	p.seen[f.Name][id] = true
 	return !resync
 }
 

internal/rss/poller_test.go

@@ -3,6 +3,7 @@ package rss
 import (
 	"context"
 	"errors"
+	"fmt"
 	"strings"
 	"testing"
 	"time"
@@ -208,3 +209,27 @@ func TestNoFeedsMeansNoPoller(t *testing.T) {
 		t.Fatal("a feed with no name or url is not a configuration")
 	}
 }
+
+// An undated feed used to grow p.seen for as long as mavend ran. The set is
+// bounded now, and the bound must not cost the dedupe an item still on the
+// front page — only ids far older than any page fall out.
+func TestSeenIDsBounded(t *testing.T) {
+	var s seenIDs
+	for i := 0; i < maxSeenPerFeed*3; i++ {
+		if !s.add(fmt.Sprintf("item-%d", i)) {
+			t.Fatalf("item-%d read as already seen", i)
+		}
+		if len(s.ids) > maxSeenPerFeed || len(s.order) > maxSeenPerFeed {
+			t.Fatalf("after %d inserts: ids=%d order=%d, cap is %d",
+				i+1, len(s.ids), len(s.order), maxSeenPerFeed)
+		}
+	}
+	// The newest insert is still deduped; the oldest was evicted.
+	last := fmt.Sprintf("item-%d", maxSeenPerFeed*3-1)
+	if s.add(last) {
+		t.Fatalf("%s read as new, so the most recent id was dropped", last)
+	}
+	if !s.add("item-0") {
+		t.Fatal("item-0 survived, so nothing was evicted")
+	}
+}

internal/store/memory.go

@@ -68,6 +68,13 @@ func (m *MemoryStore) Insert(ctx context.Context, id string, vec []float32, meta
 // Rows under memory.NonRecallPrefix are excluded in SQL. They are speaker
 // voiceprints sharing this table, and note recall must not rank them; see that
 // constant for why the previous arrangement only appeared to do this.
+//
+// Every row is still scored, because a full scan is what picks the winners.
+// What the scan does NOT do is pay for a row it is about to discard: the score
+// is read straight off the stored bytes without materializing a []float32, and
+// the meta blob is copied and unmarshalled only for a row that has entered the
+// topK. Losers cost one dot product and nothing else. Ranking is unchanged —
+// same scores, same order, same ties.
 func (m *MemoryStore) Search(ctx context.Context, vec []float32, topK int) ([]memory.Result, error) {
 	if topK <= 0 {
 		topK = 10
@@ -80,30 +87,127 @@ func (m *MemoryStore) Search(ctx context.Context, vec []float32, topK int) ([]me
 	}
 	defer rows.Close()
 
-	var out []memory.Result
+	// sql.RawBytes hands us the driver's own buffer, valid only until the next
+	// Next(). Nothing here outlives the row except what topK.offer copies on a
+	// survivor, so the three columns cost no allocation per row.
+	var id, blob, metaJSON sql.RawBytes
+	top := newTopK(topK)
 	for rows.Next() {
-		var id, metaJSON string
-		var blob []byte
 		if err := rows.Scan(&id, &blob, &metaJSON); err != nil {
 			return nil, fmt.Errorf("memory: row: %w", err)
 		}
-		meta := map[string]string{}
-		if err := json.Unmarshal([]byte(metaJSON), &meta); err != nil {
-			return nil, fmt.Errorf("memory: unmarshal meta for %q: %w", id, err)
-		}
-		out = append(out, memory.Result{ID: id, Score: dot(vec, decodeVec(blob)), Meta: meta})
+		top.offer(dotBlob(vec, blob), id, metaJSON)
 	}
 	if err := rows.Err(); err != nil {
 		return nil, fmt.Errorf("memory: rows: %w", err)
 	}
 
-	sort.Slice(out, func(i, j int) bool { return out[i].Score > out[j].Score })
-	if topK < len(out) {
-		out = out[:topK]
+	survivors := top.sorted()
+	out := make([]memory.Result, 0, len(survivors))
+	for _, c := range survivors {
+		meta := map[string]string{}
+		if err := json.Unmarshal(c.meta, &meta); err != nil {
+			return nil, fmt.Errorf("memory: unmarshal meta for %q: %w", c.id, err)
+		}
+		out = append(out, memory.Result{ID: c.id, Score: c.score, Meta: meta})
 	}
 	return out, nil
 }
 
+// candidate is one row that is currently in the topK: its score, its id, and
+// its meta blob copied out of the driver's buffer. The copy is the price of
+// surviving, and only survivors pay it.
+type candidate struct {
+	score float64
+	id    string
+	meta  []byte
+}
+
+// topK keeps the k highest-scoring candidates seen so far as a min-heap, so the
+// weakest survivor is always heap[0] and one comparison decides whether a new
+// row is worth copying. k is 10 in practice, so the heap is tiny and the whole
+// structure fits in cache.
+//
+// It is a plain slice with hand-written sift operations rather than
+// container/heap, because that interface boxes every element into an `any` on
+// Push and costs an allocation per surviving row.
+type topK struct {
+	k    int
+	heap []candidate
+}
+
+func newTopK(k int) *topK {
+	return &topK{k: k, heap: make([]candidate, 0, k)}
+}
+
+// offer admits a row if it beats the weakest survivor, or if the heap is not
+// full yet. id and meta are the driver's buffers and are copied here, never
+// retained.
+//
+// A row that only ties the weakest survivor does not displace it, so among
+// equal scores the earliest k rows are kept. The full sort this replaced used
+// sort.Slice, which is not stable, so it broke such a tie arbitrarily. That is
+// the ONE observable difference between the two, and it is deliberate:
+// deterministic beats arbitrary.
+//
+// It is not academic. Under the real embedder an exact tie means duplicate
+// vectors and nothing in the recall eval moved (V-643). Under the hash
+// embedder the eval's deterministic floor uses, ties are everywhere — it is
+// bag-of-words, so every note sharing no word with the query scores exactly 0
+// — and recall@3 on that run moved 74.1% to 81.5% purely because the zeros now
+// come out in a fixed order. Neither number measures retrieval. recall@1 and
+// false recall, which the eval actually asserts, are unchanged on both runs.
+func (t *topK) offer(score float64, id, meta []byte) {
+	if t.k == 0 {
+		return
+	}
+	if len(t.heap) < t.k {
+		t.heap = append(t.heap, candidate{score: score, id: string(id), meta: append([]byte(nil), meta...)})
+		t.up(len(t.heap) - 1)
+		return
+	}
+	if score <= t.heap[0].score {
+		return
+	}
+	t.heap[0] = candidate{score: score, id: string(id), meta: append([]byte(nil), meta...)}
+	t.down(0)
+}
+
+func (t *topK) up(i int) {
+	for i > 0 {
+		parent := (i - 1) / 2
+		if t.heap[parent].score <= t.heap[i].score {
+			return
+		}
+		t.heap[parent], t.heap[i] = t.heap[i], t.heap[parent]
+		i = parent
+	}
+}
+
+func (t *topK) down(i int) {
+	for {
+		l, r, small := 2*i+1, 2*i+2, i
+		if l < len(t.heap) && t.heap[l].score < t.heap[small].score {
+			small = l
+		}
+		if r < len(t.heap) && t.heap[r].score < t.heap[small].score {
+			small = r
+		}
+		if small == i {
+			return
+		}
+		t.heap[small], t.heap[i] = t.heap[i], t.heap[small]
+		i = small
+	}
+}
+
+// sorted drains the heap into descending score order — what Search returns.
+func (t *topK) sorted() []candidate {
+	out := t.heap
+	sort.Slice(out, func(i, j int) bool { return out[i].score > out[j].score })
+	return out
+}
+
 // ByPrefix returns every row whose id starts with prefix, vectors included.
 //
 // This is not a similarity query and deliberately does not score anything:
@@ -240,6 +344,26 @@ func decodeVec(b []byte) []float32 {
 	return v
 }
 
+// dotBlob is dot against a vector still in its stored encoding, so scoring a
+// row the query is about to discard does not allocate the []float32 that
+// decodeVec would build. Same arithmetic, same order of operations, so it
+// returns bit-identical scores to dot(a, decodeVec(b)).
+//
+// A blob whose length isn't a multiple of 4 is truncated to the whole-element
+// prefix, matching decodeVec, and a length mismatch is 0, matching dot.
+func dotBlob(a []float32, b []byte) float64 {
+	n := len(b) / 4
+	if len(a) != n || n == 0 {
+		return 0
+	}
+	var sum float64
+	for i := 0; i < n; i++ {
+		f := math.Float32frombits(binary.LittleEndian.Uint32(b[4*i:]))
+		sum += float64(a[i]) * float64(f)
+	}
+	return sum
+}
+
 // dot is the cosine similarity for L2-normalized vectors (mismatched lengths ⇒
 // 0, matching internal/memory's cosine).
 func dot(a, b []float32) float64 {

internal/store/memory_bench_test.go

@@ -0,0 +1,77 @@
+package store
+
+import (
+	"context"
+	"fmt"
+	"math"
+	"math/rand"
+	"path/filepath"
+	"testing"
+)
+
+// benchDim is the resident embedder's width (multilingual-e5-small, 384), so
+// the per-row decode cost the benchmark measures is the real one.
+const benchDim = 384
+
+// seedMemVectors fills a fresh store with n L2-normalized rows carrying a meta
+// blob the size recall actually stores — the note text plus its type — because
+// the cost this benchmark exists to measure is unmarshalling that blob for
+// every row when only topK survivors need it.
+func seedMemVectors(tb testing.TB, n int) *MemoryStore {
+	tb.Helper()
+	path := filepath.Join(tb.TempDir(), "mem_bench.db")
+	st, err := Open(context.Background(), path)
+	if err != nil {
+		tb.Fatalf("Open: %v", err)
+	}
+	tb.Cleanup(func() { _ = st.Close() })
+	m := st.VectorMemory()
+
+	rng := rand.New(rand.NewSource(1))
+	ctx := context.Background()
+	for i := 0; i < n; i++ {
+		if err := m.Insert(ctx, fmt.Sprintf("note:%d", i), randUnitVec(rng, benchDim), map[string]string{
+			"type": "note",
+			"text": fmt.Sprintf("заметка номер %d о том, что надо не забыть сделать на неделе", i),
+		}); err != nil {
+			tb.Fatalf("Insert %d: %v", i, err)
+		}
+	}
+	return m
+}
+
+func randUnitVec(rng *rand.Rand, dim int) []float32 {
+	v := make([]float32, dim)
+	var norm float64
+	for i := range v {
+		f := rng.NormFloat64()
+		v[i] = float32(f)
+		norm += f * f
+	}
+	norm = math.Sqrt(norm)
+	for i := range v {
+		v[i] = float32(float64(v[i]) / norm)
+	}
+	return v
+}
+
+// BenchmarkMemoryStoreSearch measures one recall query against a store of n
+// rows. Row counts bracket the documented scale: 1000 is a plausible today,
+// 10000 is the "thousands, not millions" ceiling the type doc claims a full
+// scan is fine at.
+func BenchmarkMemoryStoreSearch(b *testing.B) {
+	for _, n := range []int{1000, 10000} {
+		b.Run(fmt.Sprintf("rows=%d", n), func(b *testing.B) {
+			m := seedMemVectors(b, n)
+			q := randUnitVec(rand.New(rand.NewSource(2)), benchDim)
+			ctx := context.Background()
+			b.ReportAllocs()
+			b.ResetTimer()
+			for i := 0; i < b.N; i++ {
+				if _, err := m.Search(ctx, q, 10); err != nil {
+					b.Fatal(err)
+				}
+			}
+		})
+	}
+}

internal/store/memory_search_test.go

@@ -0,0 +1,107 @@
+package store
+
+import (
+	"context"
+	"fmt"
+	"math/rand"
+	"sort"
+	"testing"
+
+	"github.com/kami/maven/internal/memory"
+)
+
+// naiveSearch is the implementation Search replaced: score every row into a
+// slice, sort the whole slice, truncate. It stays in the test file as the
+// reference the bounded-heap version is judged against, because "recall must
+// not change" is a claim about output, not about the code that produces it.
+func naiveSearch(t *testing.T, m *MemoryStore, vec []float32, topK int) []memory.Result {
+	t.Helper()
+	rows, err := m.db.QueryContext(context.Background(),
+		`SELECT id, vec FROM memory_vectors WHERE id NOT LIKE ? ESCAPE '\'`,
+		escapeLike(memory.NonRecallPrefix)+"%")
+	if err != nil {
+		t.Fatalf("naive scan: %v", err)
+	}
+	defer rows.Close()
+	var out []memory.Result
+	for rows.Next() {
+		var id string
+		var blob []byte
+		if err := rows.Scan(&id, &blob); err != nil {
+			t.Fatalf("naive row: %v", err)
+		}
+		out = append(out, memory.Result{ID: id, Score: dot(vec, decodeVec(blob))})
+	}
+	if err := rows.Err(); err != nil {
+		t.Fatalf("naive rows: %v", err)
+	}
+	sort.Slice(out, func(i, j int) bool { return out[i].Score > out[j].Score })
+	if topK < len(out) {
+		out = out[:topK]
+	}
+	return out
+}
+
+// TestMemoryStoreSearchMatchesNaive is the constraint on V-643: the bounded
+// heap must return exactly what a full scan and sort returned. Distinct random
+// vectors, so no two scores tie and the ranking is total — a mismatch here is
+// arithmetic or heap logic, not a tie-break difference.
+func TestMemoryStoreSearchMatchesNaive(t *testing.T) {
+	ctx := context.Background()
+	m := newMemTestStore(t).VectorMemory()
+
+	rng := rand.New(rand.NewSource(7))
+	const rows, dim = 500, 64
+	for i := 0; i < rows; i++ {
+		if err := m.Insert(ctx, fmt.Sprintf("n%d", i), randUnitVec(rng, dim), map[string]string{
+			"text": fmt.Sprintf("note %d", i),
+		}); err != nil {
+			t.Fatalf("Insert %d: %v", i, err)
+		}
+	}
+
+	for _, topK := range []int{1, 3, 10, 50, rows, rows + 100} {
+		q := randUnitVec(rng, dim)
+		got, err := m.Search(ctx, q, topK)
+		if err != nil {
+			t.Fatalf("Search topK=%d: %v", topK, err)
+		}
+		want := naiveSearch(t, m, q, topK)
+		if len(got) != len(want) {
+			t.Fatalf("topK=%d: got %d results, naive returned %d", topK, len(got), len(want))
+		}
+		for i := range want {
+			if got[i].ID != want[i].ID {
+				t.Errorf("topK=%d rank %d: got %q, naive says %q", topK, i, got[i].ID, want[i].ID)
+			}
+			if got[i].Score != want[i].Score {
+				t.Errorf("topK=%d rank %d (%s): score %v, naive says %v",
+					topK, i, got[i].ID, got[i].Score, want[i].Score)
+			}
+		}
+		if len(got) > 0 && got[0].Meta["text"] == "" {
+			t.Errorf("topK=%d: survivor %s has no meta — it was never unmarshalled", topK, got[0].ID)
+		}
+	}
+}
+
+// TestDotBlobMatchesDot pins the claim in dotBlob's doc comment: reading the
+// vector out of its stored bytes is bit-identical to decoding it first. Scores
+// feed a gate with a 0.008 margin, so "close enough" is not the bar.
+func TestDotBlobMatchesDot(t *testing.T) {
+	rng := rand.New(rand.NewSource(11))
+	for i := 0; i < 200; i++ {
+		a := randUnitVec(rng, 384)
+		b := randUnitVec(rng, 384)
+		if got, want := dotBlob(a, encodeVec(b)), dot(a, b); got != want {
+			t.Fatalf("dotBlob = %v, dot = %v", got, want)
+		}
+	}
+	// Length mismatch is 0 in both, and so is an empty vector.
+	if got := dotBlob([]float32{1, 0}, encodeVec([]float32{1, 0, 0})); got != 0 {
+		t.Errorf("mismatched lengths scored %v, want 0", got)
+	}
+	if got := dotBlob(nil, nil); got != 0 {
+		t.Errorf("empty scored %v, want 0", got)
+	}
+}

internal/webfetch/webfetch.go

@@ -295,6 +295,27 @@ func (f *Fetcher) checkURL(u *url.URL) error {
 	return nil
 }
 
+// pruneHostsAbove is when pruneLocked bothers to walk the map. Below it the
+// walk costs more than the entries do, and `crawl.on_demand` means the host set
+// is whatever he names out loud, so it grows slowly.
+const pruneHostsAbove = 64
+
+// pruneLocked drops hosts whose last dial is further back than HostInterval.
+// Such an entry cannot delay anything — waitTurn would let the next request
+// through immediately — so keeping it only holds memory for the life of the
+// process. Caller holds f.mu.
+func (f *Fetcher) pruneLocked(now time.Time) {
+	if len(f.last) <= pruneHostsAbove {
+		return
+	}
+	cutoff := now.Add(-f.cfg.HostInterval)
+	for h, at := range f.last {
+		if at.Before(cutoff) {
+			delete(f.last, h)
+		}
+	}
+}
+
 // waitTurn blocks until this host's rate-limit interval has elapsed. It holds
 // no lock while sleeping, so two hosts never wait on each other.
 func (f *Fetcher) waitTurn(ctx context.Context, host string) error {
@@ -304,6 +325,7 @@ func (f *Fetcher) waitTurn(ctx context.Context, host string) error {
 		earliest := f.last[host].Add(f.cfg.HostInterval)
 		if !now.Before(earliest) {
 			f.last[host] = now
+			f.pruneLocked(now)
 			f.mu.Unlock()
 			return nil
 		}

internal/webfetch/webfetch_test.go

@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"context"
 	"errors"
+	"fmt"
 	"io"
 	"net"
 	"net/http"
@@ -318,3 +319,37 @@ func TestPostObeysDenylist(t *testing.T) {
 		t.Fatalf("error = %v, want ErrBlocked", err)
 	}
 }
+
+// f.last used to hold one entry per host ever dialed, for the life of the
+// process. A host whose last dial is older than HostInterval cannot delay
+// anything, so it is dropped once the map is worth walking.
+func TestHostRateMapIsPruned(t *testing.T) {
+	f := New(Config{HostInterval: time.Minute, AllowPrivate: true})
+	stale := time.Now().Add(-time.Hour)
+	for i := 0; i < pruneHostsAbove*2; i++ {
+		f.last[fmt.Sprintf("h%d.example", i)] = stale
+	}
+
+	// One real turn is what triggers the sweep.
+	if err := f.waitTurn(context.Background(), "fresh.example"); err != nil {
+		t.Fatal(err)
+	}
+	if len(f.last) != 1 {
+		t.Fatalf("len(f.last) = %d after the sweep, want 1 (only the host just dialed)", len(f.last))
+	}
+	if _, ok := f.last["fresh.example"]; !ok {
+		t.Fatal("the host just dialed was pruned, so its own rate limit is lost")
+	}
+
+	// A host inside the interval is kept: pruning must not hand out a free turn.
+	f.last["recent.example"] = time.Now()
+	for i := 0; i < pruneHostsAbove*2; i++ {
+		f.last[fmt.Sprintf("g%d.example", i)] = stale
+	}
+	if err := f.waitTurn(context.Background(), "other.example"); err != nil {
+		t.Fatal(err)
+	}
+	if _, ok := f.last["recent.example"]; !ok {
+		t.Fatal("a host dialed inside HostInterval was pruned")
+	}
+}