docs: record what the e5-small swap bought (V-371)

The swap itself already landed: deploy loads
models/embedder/multilingual-e5-small/model_quantized.onnx, and
onnxembedder.go grew EmbedQuery/EmbedPassage with the query:/passage:
prefixes the model was trained with. What was missing is the half of #371
that says "re-run make eval-recall and compare against the recorded numbers",
so nothing in the repo says whether it worked.

It worked, on every axis at once. recall@1 60.0% → 70.4%, recall@3 80.0% →
85.2%, answered after the gate 48.0% → 63.0%, false recall 1/5 → 0/5, and
latency p50 59ms → 23ms because the quantized file is 118MB against the 470MB
fp32 one the old config loaded. The guitar-chords note no longer beats the
docker-logs note.

One premise of the task did not come true and the new doc says so. #371
expected a better retriever to separate the score distributions and make
query_min_score tunable. It did not: right-first top-1 runs 0.791-0.890 and
must-stay-silent runs 0.795-0.835, still overlapping, just higher and
tighter. The margin separates them instead — 0.024 median against 0.002 — and
0.008 is the knee where all five silent cases are silenced at no cost. The
score gate is close to inert now; the margin is the live dial. Neither is
changed here, since #412 is where a sweep belongs.

docs/evals/2026-08-04-recall-e5-small.md is the dated measurement.
rearchitecture.md's "upgrade MiniLM → bge-m3 later" is now done and says so,
CLAUDE.md names the retriever and the prefix rule where it already promises
the embedder never leaves homesrv, and the Makefile comment points at this
eval instead of the one that asked for the swap.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

CLAUDE.md

@@ -32,7 +32,11 @@ See `docs/rearchitecture.md` for the target architecture, `docs/design.md` for t
 GPU and the workstation has 16GB of VRAM. So the resident model, STT and TTS become preferred
 remotes with a floor on homesrv. The workstation is never assumed up. Fall back silently when
 it would only do the job better. Name the gap when the 1.7B cannot do it at all. The embedder
-stays on homesrv permanently, because it backs that floor. Read `docs/offload.md` before
+stays on homesrv permanently, because it backs that floor. It is multilingual-e5-small,
+quantized and asymmetric — `EmbedQuery` and `EmbedPassage` apply the `query:`/`passage:`
+prefixes it was trained with, and calling plain `Embed` on a note is a bug. It replaced
+MiniLM and bought ten points of recall@1 and 2.5× the speed; see
+`docs/evals/2026-08-04-recall-e5-small.md`. Read `docs/offload.md` before
 touching a daemon seam or adding a model caller. Vikunja #483 is the umbrella, #484 to #487
 are the work.
 

Makefile

@@ -197,7 +197,7 @@ deps-piper:
 # multilingual-e5-small: an asymmetric retrieval model. It is trained to match
 # a short question against a longer passage, which is what note recall is.
 # The quantized file is the one we download, deploy and measure — see
-# docs/evals/2026-07-31-recall.md.
+# docs/evals/2026-08-04-recall-e5-small.md for what the swap bought.
 EMBEDDER_DIR := $(shell pwd)/models/embedder/multilingual-e5-small
 EMBEDDER_MODEL_URL := https://huggingface.co/Xenova/multilingual-e5-small/resolve/main/onnx/model_quantized.onnx
 EMBEDDER_TOKENIZER_URL := https://huggingface.co/Xenova/multilingual-e5-small/resolve/main/tokenizer.json

docs/evals/2026-08-04-recall-e5-small.md

@@ -0,0 +1,88 @@
+# Note recall after the e5-small swap — 04-08-2026
+
+Closes Vikunja #371, which asked for the swap and for this re-measurement. The embedder is no
+longer paraphrase-multilingual-MiniLM-L12-v2. It is **multilingual-e5-small**, quantized, with the
+`query:` / `passage:` prefixes it was trained with (`internal/router/onnxembedder.go`,
+`EmbedQuery` / `EmbedPassage`). `deploy/mavend.json` loads
+`models/embedder/multilingual-e5-small/model_quantized.onnx`, which is the same file `make
+download-embedder` fetches and the same file this run measured.
+
+- Fixture + scorer: `internal/memory/recalleval/` — 32 cases now, not 30
+- Reproduce: `make eval-recall`
+- Commit: `b6abb19`
+- Gate as deployed: `query_min_score` 0.55, `query_min_margin` 0.008
+
+The fixture grew since 31-07, so the case counts are not comparable row for row. The percentages
+are.
+
+## Results
+
+| | 31-07 MiniLM (onnx) | 04-08 e5-small (onnx) |
+|---|---|---|
+| **recall@1** | 60.0% (15/25) | **70.4% (19/27)** |
+| recall@3 | 80.0% (20/25) | **85.2% (23/27)** |
+| **answered after the gate** | 48.0% (12/25) | **63.0% (17/27)** |
+| **false recall** | 1/5 (20%) | **0/5** |
+| wrong note on top / tie on top | 10 / 0 | 8 / 0 |
+| ranked first, then silenced by the gate | 3 | 2 |
+| `hard` cases passed | 2/11 | 5/12 |
+| RU / EN passed | 13/24 / 3/6 | 18/26 / 4/6 |
+| latency p50 / p95 / max | 59ms / 148ms / 194ms | **23ms / 41ms / 62ms** |
+
+The hash ratchet CI runs is unchanged in kind and still answers nothing after the gate: recall@1
+37.0%, recall@3 74.1%, 0/27 answered, 0/5 false. It is lexical and exists so CI has a deterministic
+floor. Never compare a hash number to an ONNX one.
+
+## Findings
+
+### 1. The swap paid on every axis at once, including latency
+
+Ten points of recall@1, fifteen points of *answered*, the one false recall gone, and it is 2.5×
+faster because the quantized e5-small is 118MB against the 470MB fp32 file the old config loaded.
+Finding 3 of the 31-07 eval predicted the recall half and said nothing about speed; the speed came
+from fixing the second half of that finding, which was that the deployed path loaded a different
+file than the download target.
+
+The concrete case that eval named is fixed. "из-за чего кончилось место" no longer returns the
+guitar-chords filler note. It now returns a homelab note, `n2` at 0.884, and the wanted note is
+still not in the top 3 — so the query moved from absurd to merely wrong. That is the shape of what
+is left.
+
+### 2. The score distributions still overlap. The margin is what separates them
+
+This is the part of #371's premise that did not come true. Right-note-first top-1 scores run
+0.791 / 0.857 / 0.890 (min / median / max). Must-stay-silent top-1 scores run 0.795 / 0.815 /
+0.835. The silent cases sit *inside* the answering range, so no value of `query_min_score` keeps
+every real recall and rejects every false one — the same verdict as 31-07, at a higher and tighter
+band of scores.
+
+What separates them is the second-place gap. Margin top1-top2 for a right first hit: median 0.024.
+For a must-be-silent case: median 0.002, max 0.019. A false recall is a note that beats its
+neighbours by nothing, because nothing in the store is about the question. The sweep:
+
+| margin | answered | false recall |
+|---|---|---|
+| 0.000 | 18/27 (67%) | 3/5 |
+| 0.005 | 17/27 (63%) | 1/5 |
+| **0.008 (deployed)** | **17/27 (63%)** | **0/5** |
+| 0.010 | 15/27 (56%) | 0/5 |
+| 0.015 | 12/27 (44%) | 0/5 |
+
+0.008 is the knee: it is the smallest margin that silences all five, and the next step up costs two
+real answers for nothing. The score gate contributes almost nothing on its own — every value from
+0.00 to 0.70 answers the same 18 and admits the same 3 — so `query_min_score` is now close to inert
+and the margin is the live dial. Leave both where they are; #412 is where a further sweep belongs.
+
+### 3. What is left is a retrieval problem, not a gate problem
+
+Eight cases put the wrong note on top, and the failures cluster: `hard` 5/12, `preference` 5/9,
+`homelab` 8/13. Four of the eight have the right note in the top 3, so a reranker would collect
+them; the other four do not, so nothing downstream can. Two more rank first and are silenced by the
+margin — `en-hard-024` at 0.826 with margin 0.023, and `ru-home-026` at 0.846 with margin 0.001,
+which is a genuine near-tie against a second note that is also plausible.
+
+Preference queries are the weakest class in a way that is not about the model. "когда запускать
+резервное копирование" and "как мне присылать оповещения" both return a fact, not the note that
+states the preference. Facts and notes are searched in one pass since #373, so a confidently-scored
+fact wins a question that a note answers better. That is a ranking policy question and it belongs
+in its own task, not in a threshold.

docs/rearchitecture.md

@@ -1,6 +1,6 @@
 # Maven — Re-architecture (Qwen3 resident model, revised 2026-07-18)
 
-*Last verified: 2026-08-02 @ 7079a24. Living doc: correct it in place, do not append.*
+*Last verified: 2026-08-04 @ b6abb19. Living doc: correct it in place, do not append.*
 
 > Supersedes the classifier-first routing model. Agreed in a design session
 > after diagnosing that homesrv deploys with a **stub phraser** (no LLM
@@ -40,8 +40,10 @@ utterance
   are deferred until the main feature set is complete.
 - **Embedder demoted from router to tool** — it now backs `memory.search`
   (RAG) and gives the router a cheap "similar past notes/intents" hint. The
-  router no longer depends on it clearing a threshold. Upgrade MiniLM → bge-m3
-  for better RU retrieval later (model swap, not architecture).
+  router no longer depends on it clearing a threshold. The MiniLM upgrade is
+  done: it is multilingual-e5-small, asymmetric, with the `query:`/`passage:`
+  prefixes (Vikunja #371, `docs/evals/2026-08-04-recall-e5-small.md`). A
+  further swap is a model swap, not architecture (Vikunja #412).
 
 ### Router output
 - Constrained structured JSON action `{tool, args, escalate}` — NOT free-form